Handwriting recognition (HWR) is the ability of computers to recognize handwritten texts on any medium such as paper, photographs, documents etc. This is also often referred to as Handwriting Text Recognition(HTR). Optical Character Recognition(OCR) is the electronic conversion of handwritten of typed texts whether from scanned documents or photographs. HWR is a new research field of OCR, which many researchers and tech giants are trying to address. According to reports published by marketsandmarkets in 2021 , the global market size of OCR handwriting recognition was estimated to be USD 1,039.3 Million in 2016. It has an expected CAGR of 15.7% from 2017 to 2025. HWR market is expected to grow along with it and also show tremendous improvements on the current accuracy levels.
Handwriting recognition has a large number of industrial use cases from health care industry and pharmaceuticals to banking and insurance. HWR technologies can be employed for various reasons like – reducing labor costs, saving time invested on manually digitizing handwritten records, enhancing the user experience of customers, etc. HWR may also lead to automation of various labor intensive processes.
The varied handwriting style, lighting of an image, separation of text in cursive handwriting have made handwriting recognition a difficult problem to achieve good accuracy. However, the ongoing research which deploys state of art deep learning architectures have made considerable strides in improving accuracy. These prove to be far superior than earlier used machine learning algorithms where features to train the machine learning model were human defined.
Current Status and Future Predictions According to a new market research report published by Credence Research “Handwriting Recognition (HWR) Market (By Type – Online and Offline; By Application: Automotive; Education and Literature; Enterprise and Field Services; Healthcare and Others) – Growth, Future Prospects, Competitive Analysis and Forecast 2017 – 2025”, the global handwriting recognition (HWR) market was valued at US$ 1,039.3 Mn in 2016 and is expected to grow at a CAGR of 15.7% during 2017 to 2025.
HWR technologies can be classfied into two types – online and offline methods. Online methods correspond to extracting machine readable texts from strokes on touch screens. Offline methods refer to extracting machine readable text from paper, journals etc.
Fig. Global Handwriting Recognition Market Revenue by type
The major players of this market face high competition. The key for surviving in this market is better efforts towards service enhancement so as to address the changing regulations and economic conditions in the global market. Along with it improving accuracy of HWR software is also necessary. The key players of handwriting recognition (HWR) system market include MyScript, Nuance Communications, Inc., SELVAS AI, Inc., Hanwang Technology Co., Ltd., Paragon Software Group, PhatWare Corporation, SinoVoice (Beijing Jietong Huasheng Technology Co. Ltd.), and Sciometrics, LLC.
A ton of apps for mobile, tablet and web platforms are also available for online methods. The table below is summarizing some of most popular handwriting recognition apps.
Table 1. Software for handwriting recognition
Major cloud services like AWS (Amazon Textract), Google Cloud (Google Vision) and Azure (Microsoft Azure Vision) also provide APIs for handwriting recognition.
Handwriting Recognition Use Cases
We have all heard jokes about doctors’ unrecognizable handwriting and also faced this issue first hand. Jokes apart, according to July 2006 report from the National Academies of Science’s Institute of Medicine (IOM) found doctors’ s unrecognizable handwriting kills more than 7,000 people annually. Using a HWR technology could easily save people’s time, money and lives. A lot of healthcare institutes and hospitals are implementing data strategies to combat loss of life arsing from illegible script. These include Electronic Health Records(EHR) which have been adopted by 71% physicians as claimed by a 2013 survey.
These technologies also help mitigate issues such as dependence on paper, regulatory violations, compliance issues, forgeries and frauds. HWR technologies can be further used to digitize patient entry forms and handwritten records. Digitizing will also give access to huge amount of data which can be used for data analytics to gain meaningful insights.
There is an ongoing effort to introduce children and educators to computing devices early on. Google for educators is one such campaign which focused on schools to embrace technology. With the increasing use of tablets in schools and colleges HWR technology is bound to grow in education sector. This is a powerful tool which can enhance students learning experience. As an example student can make handwritten notes on their iPad which helps in better understanding. These notes can also be converted to computer readable text using handwriting recognition techniques. This technologies have been augmented in various note taking apps, apps to deal with complex mathematical sums and also on music apps. For example mathematical apps can convert handwritten questions and equations into neat computer readable digits and text which can be used to crunch desired answers. Other uses include turning scrawled diagrams into digital documents, music composition and even streamlining the process of adding references to research papers by including highlight and search capabilities. Thus, handwriting recognition technologies can benefit the educator, and students at all levels be it a kindergartner or a senior year college student.
Fig. Application of handwriting recognition in Banking Applications
Currently cheques deposited to banks are manually analyzed and then entered on the computer. Bank employees also have to manually verify the signature and date of the cheques. This takes time and manual effort also delays reflecting of balance on the benefited bank account. Handwriting recognition technologies can be used to read these cheques and other bank documents such as forms, demand drafts etc at a much faster pace.
A large number of historical books and journals have been digitized to make it accessible to entire world. However, most of these efforts are restricted to photos or scans of books. This effort can become even more useful if the text on these historical books could be parsed and queried and indexed by web crawlers. Handwriting recognition plays a key role in bringing alive the medieval and 20th century documents, postcards, research studies etc.
There has been an increasing demand for OCR and related technologies by consumers. This has fueled the adoption of such technologies in tablets and smartphones. The demand has surged owing to increase in number of devices to capitalize on. OCR technologies including handwriting recognition have been around for a decade. However the wide spread reach of touchscreen mobile devices have increased the adoption of such technologies in day to day life. HWR technologies might provide a viable alternative to use of digital keyboards in near future. Whether it is within mobile applications, leveraged in your smart watch, included as an alternative to your smartphone keyboard, or integrated within the dashboard of your car, HWR technology is gaining momentum.
Handwriting text recognition can be categorized in two categories – offline method and online method.
1. Online method – Online method involves touch screen devices, light pen, stylus etc. This method has access to information such as stroke and direction. They also don’t face the issue of noisy backgrounds. They can be recognized with pretty high accuracy as compared to offline methods.
2. Offline method – This method refers to text written down on a non digital media such as a paper.
In this, information such as stroke, directions are not available like in case of online methods. Apart from this method might also have issues of noisy background.
The ongoing efforts are more concentrated towards handwriting recognition in offline method which still has a long way to go before it achieves a respectable accuracy. Also offline method does not require extra devices such as light pens and stylus.
Early attempts at handwriting recognition utilized machine learning algorithms such as Hidden Markov Models(HMM), Support Vector Machines (SVM) etc. These techniques involved input of per-processed text, feature interaction to identify key elements such as loops, aspect ratio and inflection points. These generated features are then fed into machine learning algorithms such as HMM and SVM. Such methods had limited accuracy due to need of identifying features by humans. Also, this method is not scale-able as it cannot cover different languages.
Deep Learning solves this issue with use of state of art technologies together such as – Convolution Neural Networks (CNN), Recurrent Neural Networks (RNN) and Connectionist Temporal Classification .
Convolution Neural Networks are used for feature extraction from input images. The convolution layers contains three main operations – use of convolution (filter kernel) to the input image, a non-linear ReLU function, and finally a pooling layer to downsize the output of CNN. Recurrent Neural Network (RNN) is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. LSTM implementation of RNN is used as it facilitates long term propagation of information, thus making the trained model better. Finally Connectionist Temporal Classification (CTC) layer is used to classify the images. The CTC is given the RNN output matrix and the ground truth text as input using which it computes the loss value. The CTC gives the final text as output.
Fig. Overview of Neural Network Architecture for handwriting recognition
One of the main struggles of HWR technologies is accuracy. A lot of HWR technologies cannot predict many handwriting making them unreliable to use in real life scenarios. They also require huge datasets and huge computing power to train models. As a result of this implementing HWR on industry level might be quite expensive. Apart from this, the recognizing capability of the model depends a lot on the data used for training the model.
The future of HWR is hopeful, with recent strides in accuracy level, mass adoption of mobile devices and a push for paperless operations. A ton of softwares are available for handwriting recognition with varied accuracies and price points.
Some popular handwriting recognition softwares are –
- Amazon Textract
- Microsoft Azure Vision
- Google Cloud Vision API
While utilizing handwriting recognition software for business, you should ponder on factors such as – character recognition accuracy, word recognition accuracy, computation speed in case results need to be delivered real-time, continuous learning capabilities, user-friendliness of the interface if the interface will be used by humans and the price point carefully.
HWR technologies will play are huge role in the upcoming years. So, is your company ready to reap its benefits?
Need help with Emotion recognition and detection software?
If you want to utilize Handwriting recognition technologies and need help, advice, or developers, feel free to contact us at firstname.lastname@example.org or on our LinkedIn page or visit our company website, www.quantiantech.com
-  https://www.credenceresearch.com/press/global-handwriting-recognition-hwr-market
-  https://www.itbusinessedge.com/mobile/five-industries-benefitting-from-handwriting-recognition-technology/
-  https://towardsdatascience.com/build-a-handwritten-text-recognition-system-using-tensorflow-2326a3487cd5
At the peak of COVID-19 pandemic, government launched a chatbot called MyGov Corona Helpdesk (for whatsapp) to provide constant updates and eradicate fake news about Novel Coronavirus. People could converse with the chatbot on platforms like Facebook’s messenger, Whatsapp and Telegram. About 17 million people used it within 10 days of its launch. This chatbot is an example of “rule based chatbot”. However this chatbot can only handle pre-defined inputs. Conversational bots are a level up from these rule based or FAQs chatbots which can recognize context in a conversation.
MyGov Corona Helpdesk Whatsapp chatbot
What are conversational bots and how do they differ from FAQ chatbots?
A massive improvement over rule based chatbots are conversational bots. If you think about how human converse, context matters. What the user said before, how, when and where should influence how the conversation goes. Conversational bots powered with AI can understand the context. Understanding the context also means that the bot are capable of answering new and unexpected inputs from user. These conversational bots consider the context of what has been said before, gracefully handle unexpected dialogue turns, drive the conversation when the user drifts from the regular conversation path and improve over time.
Apollo Hospitals launched an app with a conversational bot called Apollo247 which analyses dialogue with its user to tell whether they need to visit a hospital for COVID 19 related symptoms or not. The app has a bot which asks the user gender, his/her age, what ailments one is suffering from and advises whether to visit a hospital or not. However, it states that the bot’s analysis “should not be taken as a medical advice”. It can also tell whether one should get a scan done or not .
Apollo247 conversational bot
How conversational bots can help your business?
As per survey published by Statistia in 2019 , about 78% has leveraged conversational bots powered by AI in simple self-service scenarios. 77% enterprises have reported to be using bots to try and assist with a query before passing it onto a customer care personnel. Another 70% companies, reportedly use bots to retrieve information and offer recommendations and answer to queries quicker. According to Statistia, conversational AI bots are most used in customer service. The second most common area where conversational bots are used are Customer Relationship Management (CRM) .
Most common areas for conversational bot implementation in organizations worldwide
A user can be dissuaded from using a certain online service/product if they find the site hard to navigate, or cannot get answers to simple queries, or find it too hard to get basic services. These hurdles can be overcame by conversational chatbots which are fast, intuitive and convenient. AI chatbots offer a way to increase customer engagement by providing a personalized experience. They can retrieve high value content from customers.
Listed below are 10 key areas where business can take advantage of conversational AI bots:
Chatbots provided customers with a sense “immediate response”. They always want their queries “now” service within five minutes of making contact online. Conversational chatbots enables a similar kind of response and behavior akin to talking to customer care personnel.
Drive More Revenue
Intelligent chatbots acts as a guide for customers and take them on a buying journey. This makes sales conversion and revenue. Advanced chatbots can remember “context” and thus provide customers with preferences and provide advice, tips and help, while gently providing recommendations that results in upselling of products.
According to reports use of virtual assistants cut need for queries handled by human agent by 40%, and often deliver first call resolution (FCR) rates far in excess of live agents. Chatbots will reduce costs by handling more customers at a time.
Maximize Staff Skills
Conversational bots can be used to automate a portion of call, email, SMS etc, that would have required human involvement. This gives time to employees to engage in higher-value customer engagements.
Reach New Channels
Chatbots provide personalized customer experience and try to solve customer’s query before initiating a human involvement. These bots can be simultaneously deployed on various platforms like social media, calls, SMS etc. This reduces the overhead required to deploy a support to team on each new channel or network.
Conversational bots can increase brand loyalty as well as customer retention. This happens due to fast and frictionless answering of customer queries. Use of conversational AI reduces the cost overheads of the company as well as increases customer retention.
Customer want service 24/7 and 365 days. Delivering this kind of support by human agents seems impossible. However, conversational bots can be available all the time. The customers can get their queries solved using conversational bots anytime and even on holidays.
Customers tend to spend 60% more per purchase and also report an increased frequency of purchase. As customers start to favor online methods of communication, chatbots provide an opportunity to reignite the customer experience with increased engagement, personalized customer service and improved customer satisfaction.
Understand the Customer Better
Apart from providing customers with quick query solving, these bots can also provide meaningful insights into the company’s customers. They can be used to understand trends and better interpret customer sentiment, providing invaluable insight that informs product and service development.
Furthermore, this data can be accessed by for a single product or for multitude of products.
Conversational bots can be a key factor for customers choosing your company over your competitors. These bots can deliver frictionlesss user experience that derives higher customer brand loyalty and higher customer retention.
Use cases of Conversational Bots
Chatbots are being used by multiple industries to provide seamless experience to their customers. Some of these are covered here.
Banking, Insurance and Financial Services
These chatbots can guide customers to perform a variety of financial operations without making it feel like they have to fill too many forms. The information shared with these chatbots are completely safe. From checking an account, reporting lost cards or making payments, to renewing a policy or managing a refund, the customer can manage simple tasks autonomously. These chatbots can provide immediate support to a customers. These can also be used to train customer care personnel.
These chatbots can take information from humans and then accordingly recommend car for the customers according to their needs and wants. They intake various needs of customers such as the features they want to have, their budget etc. These feel lie human-like interaction and is bound to drive the conversion rate upwards. Apart from recommending cars these chatbots prompt to schedule a test drive at the nearest car dealer.
Retail & Ecommerce
Adding conversational bots to your existing retail channels increases customer engagement as they can answer clients queries and requests instantaneously. These also provide various updates on shipping details, discount etc. in a human-like fashion. They can also help customer navigate the website to pages where they can find the product they are looking for. The data collected by chatbots can further be analyses by the marketing team understand customer behavior and make strategies to increase customer engagement and retention.
Here conversational bots are used to provide self-help FAQ and knowledge forums to find a customer’s answer to any technical issues they might be facing. Customers can also use these bots to find best deals for them, and even change their personal information such as address just by chatting to bots! Further, chatbots can come up with personalized plans for customers. At the same time, chatbots can assist potential customers in choosing the right product for their needs. This will also allow customer care employees to only address the complex issues rather than getting involved in trivial issues.
Smart Homes & IOT devcies
These conversational bots enable customers to access various functionality of smart homes via every day human speech. They can also be used as guide in smart cars to tell directions, set desired temperatures etc.
Chatbots in healthcare industry can avoid unnecessary visits to hospital. This technology seems very useful especial during pandemic when there is massive stress on hospitals and doctors alike. Further, they can also be used to schedule appointments and scans for the patients.
When bots were launched first time into the market, their were predictions that these bots will replace customer care employee requirements totally. However, this did not happen as the current state of bots have its own limitations. One of the biggest limitations of conversational bots are they fail to understand complex queries. Secondly, bots can only handle the situations fr which they have been trained. On failing to recognize an incoming message they generate messages like – “Sorry I could not understand your question” which might lead to the customer becoming frustrated. If the bot is supposed to handle high volume queries, the cost of building and deploying such a bot might be higher. The chatbot may make the conversation feel repetitive which might again frustrate the customers.
Developers understand the above limitation and thus are careful while developing bots. There are a lot of tools available to build bots for commercial purposes such as Keras, TensorFlow, and PyTorch. Apart from this various frameworks like Google’s diagflow and RASA can also be used to develop effective conversational bots which can handle context. These chatbots can act as first point of contact and reduce the overhead of backend office by solving simple queries and requests of customers. A lot of companies have already integrated chatbots to their websites, apps or other channels to drive customer engagement higher. So are your ready to step up your customer experience with these conversational bots capable of recognizing contexts?
Need help with Conversational Bot?
If you want to build Conversational bot or integrate to your existing products and need help, advice, or developers, feel free to contact us at email@example.com or on our LinkedIn page or visit our company website, www.quantiantech.com
References https://gadgets.ndtv.com/apps/news/coronavirus-mygov-corona-helpdesk-chatbot-whatsapp-indian-government-total-users-haptik-2204458  https://yourstory.com/2020/03/apollo-hospitals-launches-24-7-ai-free-app-coronavirus  https://www.statista.com/statistics/966909/worldwide-conversational-bot-implementation/
Artificial Intelligence in Emotion Recognition
Emotions serve as a source of information to perceive how a person is reacting to a particular scenario. Recognizing emotions can help us take actions for getting desired outcomes. Humans use a variety of indicators such as facial expression, voice modularity, speech content, body language, and historical context to gauge the emotions of others.
Emotion recognition using AI is a relatively new field. It refers to identifying human emotions using technology. Generally, this technology works best if it uses multiple modalities to make predictions. To date, most work has been conducted on automating the recognition of facial expressions from video, spoken expressions from audio, written expressions from the text, and physiology as measured by wearable devices.
As per the reports by marketsandmarkets  published in February 2020 the global Emotion Detection and Recognition Market is expected to grow from USD 21.6 Billion to a staggering USD 56 Billion by 2024. Many technology companies like Amazon, Microsoft have already launched emotion detection tools for predicting emotions with varying accuracy. So, are you ready to utilize this upcoming technology to your business advantage?
This article will take a look at use cases of such technologies, an overview of how it is achieved, and concerns related to this technology.
Emotion Detection and Recognition Market
The ongoing pandemic has led to many day-to-day activities being carried out in online mode. These include online classes, hiring processes, work from home scenarios, etc. This online adoption has led to an increase in the demand for emotion detection and recognition software. The market size for software related to this technology is expected to grow at a Compound Annual Growth Rate (CAGR) of 21.0% till 2024. Factors such as the rising need for socially intelligent artificial agents, increasing demand for speech-based biometric systems to enable multifactor authentication, technological advancements across the globe, and growing need for high operational excellence are expected to work in favor of the market in the near future. Also, the pandemic situation has reinforced the need for such a technology.
The advancement in technologies such as Deep Learning and NLP (Natural Language Processing) have further accelerated the development and adoption of emotion recognition software. Deep Learning uses neural networks to classify images into several classes. For instance, neural networks can be applied on the face to detect whether their expression denotes sad, happy, shock, anger, etc.
Applications Of Emotion Detection and Recognition Technologies
FER (Facial Expression Recognition) software can be used in focus groups, beta-testing for product marketing, and other market research activities to find how the customers feel about certain products. Here, the participants have already consented to the use of FER software on them, thus having no legal ramifications. FER technologies have become quite infamous for using data by stealth. This application of FER does not involve any such malpractices.
Another novel experiment in marketing was back in 2015 by M&C Saathchi where advertisement changed based on their people’s facial expressions while passing an AI-Powered poster.
The ongoing coronavirus pandemic has led to the shifting of most in-person interviews to video call interviews. The emotion detection software can analyze expressions such as fear, shock, happiness, neutral, etc. However, this remains a controversial use case of Emotion recognition software as it has the following caveats –
• The AI model used for it might have a racial bias. For example, black men are usually classified as having an “angry” facial expression
• It is not legal to use such technologies in the EU and few other nations
• This usage will be subjected to further regulations.
Deepfakes are AI-generated fake videos from real videos.  It takes as input a video of a specific individual (’target’) and outputs another video with the target’s faces replaced with those of another individual (’source’). 2020 US election saw a surge in such videos, with politically motivated videos. A research was conducted by Computer Vision Foundation and in partnership with UC Berkley, DARPA and Google which used facial expression recognition to detect deep fakes.
Medical Research in Autism
People who have Autism often find it difficult to make appropriate facial expressions at right time. As far as  39 studies have concluded the same. Most autism-affected people usually remain expressionless or produce facial expressions that are difficult to interpret. Machine Learning can be applied for the early detection of Autism spectrum disorder (ASD), where people who are diagnosed with this disorder have long-term difficulties in evaluating facial expressions.
There are a number of Machine Learning projects and research that were conducted to help people on Autism Spectrum.  Stanford university’s Autism Glass project leveraged Haar Cascade for face detection in images. Google’s face worn computing system was then applied to these images to predict emotions. This project aimed at helping autism-affected people by suggesting them appropriate social cues. Another project used an app for screening subject’s facial expressions in a movie to identify how their expression compared with non-autistic people. The project utilized Tensorflow, PyTorch, and AWS (Amazon Web Services).
There are much more applications of emotion detection technologies that can help people suffering from autism.
Virtual Learning Environment
A number of studies have been conducted using emotion detection technologies to determine how well students understand and perceive what is being thought in an online class.
One of the research based on the same applies neural networks to classify emotions in six kinds of emotional categories . For this, they have used the Haar Cascades method to detect the face on the input image. Using face as the basis, they extract eyes and mouth through Sobel edge detection to obtain characteristic value. Neural networks are then used to classify facial expression in one of the six emotion classes.
How does Emotion Recognition Works?
Emotion Recognition using images
In most emotion recognition software, emotions are usually classified in one of these 7 classes – neutral, happy, sad, surprise, fear, disgust, anger. The first step to any facial expression classifier is to detect faces present in an image or video feed.
The next step is to input the detected faces into the emotion classification model. The classification models usually employ CNNs (Constitutional Neural Networks) to detect various classes of facial expression on the training dataset. Essentially, a CNN is able to apply various filters to generate a feature map of an image which can then be applied to ANNs (Artificial Neural Networks) or any other machine learning algorithm for further classification.
Detecting emotions in audio clips
In emotion recognition from audio, different prosody features can be used to capture emotion-specific properties of the speech signal . The features such as pitch, energy, speaking rate, word duration are applied to suitable machine learning models to detect possible emotion.
Another method to detect emotion in audio clips is using Mel-frequency cepstral coefficients (MFCCs)  on audio clips and then applying CNN to the input generated using MFCCs. This is so far one of the most famous techniques in emoticon recognition using audio.
Putting it to use to analyze video
Emotion recognition using images and audio is combined using complex mathematical or machine learning models to produce accurate results.
Limitations of Emotion Recognition Technologies
Emotion recognition shares a lot of challenges with detecting moving objects in the video: identifying an object, continuous detection, incomplete or unpredictable actions, etc. It might also suffer from lack of context of the conversation, lighting issues for images, and disturbances in form of noise for audio inputs.
Depending on the datasets used, the Machine Learning models for emotion recognition can have an inherent bias. Even google photos suffered from racial bias, where google photos could not identify dark-skinned people. Emotion recognition often suffers from biases such as classifying black men as angry etc. Thus it is very important to use diverse datasets for emotion detection and recognition software.
Political and Public Scrutiny
Facial recognition and systems built on this technology have often drawn criticism from politicians and people alike. These are usually privacy concerns, and the use of data without a person’s knowledge. European Union (EU) has already banned Facial recognition-based software. More regulations are expected to follow for emotion recognition technologies.
Emotion detection and recognition systems are under constant political scrutiny. In spite of this, the market for these systems are expected to have a compound growth rate of 21%. It is also expected to have a revenue of USD 56 Billion by year 2024. Apart from the outstanding economic projections for emotion detection and recognition software, the use cases of this technology are rather compelling. If hurdles like privacy, laws regulations, racial bias can be overcome this technology can be integrated in various products to enhance the user experience.
Need help with Emotion recognition and detection software?
If you want to build Emotion recognition and detection and need help, advice, or developers, feel free to contact us at firstname.lastname@example.org or on our LinkedIn page or visit our company website, www.quantiantech.com
References “Emotion Detection and Recognition Market,” Market Research Firm. [Online]. Available: https://www.marketsandmarkets.com/Market-Reports/emotion-detection-recognition-market-23376176.html. [Accessed: 02-Mar-2021]  Sackett Catalogue of Bias Collaboration, E. A. Spencer, K. Mahtani. “Hawthorne bias.” Catalogue Of Bias, 2017  Li, Y., & Lyu, S. (2018). Exposing deepfake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656.  Trevisan, D. A., Hoskyn, M., & Birmingham, E. (2018). Facial expression production in autism: A meta‐analysis. Autism Research, 11(12), 1586-1601.  Google Glass may help kids with autism – Stanford Children’s Health. [Online]. Available: https://www.stanfordchildrens.org/en/service/brain-and-behavior/google-glass. [Accessed: 02-Mar-2021]  W. I. R. E. D. Insider, “Researchers Are Using Machine Learning to Screen for Autism in Children,” Wired, 23-Oct-2019. [Online]. Available: https://www.wired.com/brandlab/2019/05/researchers-using-machine-learning-screen-autism-children/#:~:text=Studying%20ASD%20at%20an%20Unprecedented,children%20in%20a%20single%20study. [Accessed: 02-Mar-2021]  Yang, D., Alsadoon, A., Prasad, P. C., Singh, A. K., & Elchouemi, A. (2018). An emotion recognition model based on facial recognition in virtual learning environment. Procedia Computer Science, 125, 2-10.  Štruc, V., Dobrišek, S., Žibert, J., Mihelič, F., & Pavešić, N. (2009, September). Combining audio and video for detection of spontaneous emotions. In European Workshop on Biometrics and Identity Management (pp. 114-121). Springer, Berlin, Heidelberg.  R. Chu, “Speech Emotion Recognition with Convolution Neural Network,” Medium, 01-Jun-2019. [Online]. Available: https://towardsdatascience.com/speech-emotion-recognition-with-convolution-neural-network-1e6bb7130ce3. [Accessed: 02-Mar-2021]
We are living in an era of instant noodles. People prefer experience before commitment. The same is playing out the app markets. Google introduced feature called ‘Instant App’ on google store and Apple has recently followed with its version of IOS clips on apple store.
So what are instant apps?
Google Play Instant enables native apps and games to launch on devices running Android 5.0 or higher without being installed. By allowing users to run an instant app or instant game, known as providing an instant experience, developers can improve app or game’s discovery, which helps drive more active users or installations.
More recently, at its worldwide developer conference (WWDC 2020, held in full virtual mode because of the coronavirus outbreak), Apple unveiled the next version of iOS. One of its innovations is App Clips, mini apps that can begin running on the device without having to be installed.
This is akin to sample tasting in grocery stores. Instead of making a purchase decision based on advertising or a promotional sample that’s later opened at home, you can try the product on the spot, and if you like it, buy it.
One common use of Instant Apps is to demo ultralight versions of games. In the form of an instant app, the user is offered, say, one level of the game. The main attraction is not having to install anything — you can play right there and then. And if you’d like to play the next level, you can download the full version.
E-commerce businesses can greatly benefit from Instant Apps. They provide their users with instant experience of their products. It means that users don’t need to search for an app on a company’s website or in Google search, which significantly increases brand awareness and quick demo encourages users to download the app.
How does it work?
With Google Play Instant, users can tap on a button in the Play Store, Google Play app, or a website banner to use an app or game without installing it first. There are two options:
- Try now – This type of experience is typically a smaller trial version of an app. For example, developers may want to build the first level of their app as an instant experience and then prompt users to install the full app.
- Instant Play – The “Instant play” app are full experience , not trial versions. Users tap on the Instant play button to use the full app without installing it first
On the iOS side, app clips can be found Clips in Safari, Maps, and Messages, or in the real world in the following ways
- App Clip Code or QR code: Scan the code using the iPhone camera or Code Scanner in Control Center.
- NFC-integrated App Clip Code or NFC tag: Hold iPhone near the NFC tag.
- Safari or Messages: Tap the App Clip link.
- Maps: Tap the App Clip link on the information card
In this blog, we will look particularly at Android’s instant apps.
How does this help my business?
Businesses can derive great benefits by using instant apps. Instant apps enhance user experience due to fast speed and on demand functionality. When users click on an instant app’s URL, they instantly receive the desired content. These apps are easy-to-use, highly responsive, and user-friendly.
Enhance online visibility
Instant apps make it possible to access your app content without downloading it. It will become more discoverable on search engines. People will be able to search your app like websites on the internet resulting in increased traffic. Instant mobile apps enhance traffic and access to more users.
Easy user acquisition
A key advantage of using instant apps is that these apps allow users to complete the desired tasks without forcing them to download and install the application to their devices. With this feature, you can attract users to your app. Since instant apps are built on Google Play Services, a simple app link is enough for users to access lots of features. So, apps can reach millions of users who can simply tap to run the app. The app can also be used via NFC or QR code.
Improve user retention
Instant apps allow users to use the app again and again anytime without installing it. Often users struggle with two main options – mobile web and native apps. Users can install an app for specific features, but when they need free space on their device, unimportant apps are removed first. If your app has poorly optimized ads, it will slow down the app and kill the user experience. Instant apps help you build trust among users as they offer a great experience. Users will be tempted to use your app due to easy-to-use options, fast-speed, and better user experience in your app. So, more users will stick around your service.
Sounds good! Is there a catch?
Well there are some restrictions and dependencies on the use of instant features.
- Each app module shouldn’t exceed the size of 15MB so that the users can download them quickly. The size puts a certain level of limitations on Instant App software development. For example, developers can’t add diverse multimedia elements into the app’s samples, like inserting heavy 3D games or full HD videos, at least for now.
- The instant app must not consume more than 150 MB of storage space on the device.
- Another Instant App-specific is to prevent malicious use of these apps by third parties, Instant App developers restrict them from supporting background services. This ensures that an Instant App won’t send any push notifications, access to external storage, or change device settings without a user’s awareness.
- Android Instant Apps are compatible with any Android devices that have Android 5.0 and above
- Android Instant Apps works for apps built using native code in Java or C++. But apps built with Cordova, PhoneGap, Titanium, and other “build once, deploy everywhere” tools will not work with Instant Apps. Google requires that you make Instant Apps with Android Studio.
Great! How do I build these?
Although Instant Apps is a new feature in the mobile app world, its development process doesn’t differ much from building a traditional app. All the software developers need to do is to modularize their apps so that they allow access to a particular code section. It means that users don’t need to download the whole app but only the part that developers decide to share with them.
Moreover, if software developers already have their apps being in use, they don’t need to build a new Instant App to meet the market demand. As they can customize the existing applications by restructuring the app code.
I already have a full fledged app. Can I make it instant?
Upgrading an existing Android app to an instant app is a pretty easy process. For a seasoned developer, it will take about a couple of days to update an existing medium-size project to support Android Instant Apps functionality.
Developers need not create a new separate app, but they can utilize the existing app code, API, and project to build a new instant app. However, the efforts that you need to put into updating the app rely on the structure of the app. The following are the steps to update an existing app to the instant app.
Step 1: Install SDK and set up the environment
Step 2: Move code to feature module
Step 3: Build module
Step 4: Create an instant app module
Step 5: Define app links
One of the requisites for Instant Apps it’s that they need to be published using the App bundle format which already has a significant advantage over the old apk format.
Are Instant Apps secure?
One challenge for instant apps is the increased perception of inadequate security. After all they are installed ad-hoc. Fortunately, Google has been working on security in Instant Apps for many years. Google Play is central to the success of Instant Apps, and Google is dramatically improving the tools in Google Play to analyze new and existing apps for malicious code. Only apps published on the Google Play App Store will support Instant Apps.
This is big news for security. There are many independent Android app stores, most of which do not have security measures that come even close to those used by Google. By using Instant Apps you assure the source of the app (Google Play) and a prescribed level of security. That’s one less problem you need to tackle.
Instant Apps represent a tech breakthrough in the world of mobile apps. They allow their users to utilize their functionality in one click. This feature creates new opportunities for businesses to advertise and present their products, placing them at users’ fingertips.
If you decide to build your own business app or have an existing app, you should also consider making it instant. This way you’ll make your product easier to reach for potential buyers while improving their customer experience. We at Quantian technologies can help you with both! In case of any questions or to discuss further reach us at email@example.com
The history of chatbots dates to Joseph Weizenbaum’s ELIZA program, which was released in 1966. Weizenbaum, a professor at the Massachusetts Institute of Technology (MIT), named the program after Eliza, a character in Pygmalion, a play about a Cockney girl who learns to speak and think like an upper-class lady. Weizenbaum’s computer program convinced many users that they were talking to a human being and not a machine at all.
In the half century since ELIZA was released, chatbots have come a long way. The introduction of machine learning capabilities in bots has vastly improved the human-like experience in their conversations. Most bots, though, still behave like machines over short interactions.
Interacting with the earliest versions of chatbots was frustrating and time-consuming process. These bots would often respond to very specific request and could not answer anything beyond a fixed script. It was essentially the text equivalent of calling a customer service call center. As a result, communicating with a bot was an irritating (if not painful) option most consumers than speaking with a human customer service agent. Artificial intelligence has changed this.
AI-powered Natural Language Processing, or NLP, enables chatbots to mimic human conversation. They can identify the underlying sentiment and intention behind the communication, then deliver a response that is similar to what a human would have done. In addition, chatbots with NLP can now learn from past conversations and improve their ability to provide appropriate responses and solutions.
How are these different from regular chatbots?
AI bots Use Contextual Information
Chatbots that aren’t powered by artificial intelligence essentially deliver a one-size-fits-all experience to all of the users. They begin with a generic greeting, offer a standard list of menu options, and can only to deliver a fixed list of issues and questions.
AI bots can however use information around the content users access and read on your company’s site. If a user visits several pages focused on a specific service you offer, for example, the AI Bot understands that this user is primarily interested in that service. Then, it can begin the conversation around that service.
2. They do lot of pre-work for human interaction
A chatbot doesn’t have to hold an entire conversation with a customer from start to finish. They can initiate conversation, then ask for the details a support agent would need to assist the user. These details might include the user’s account number, order number, payment details, and contact information. This way, when a support agent steps in, they’ll already have the background information they need to assist the customer — and they won’t need to spend any additional time asking those basic questions.
Al, more advanced bots can even tell when it’s time to escalate a conversation. As technology advisor Bernard Marr explains, “AI-powered chatbots, can raise an alert when they detect, for example, a customer becoming irate – thanks to sentiment analytics – prompting a human operator to take over the chat or call.”
3. They can Route Inquiries intelligently
For large support teams, routing each ticket to the right person can be challenging time-consuming. AI-powered chatbots can help. AI chatbot can determine the need behind a user’s request. It can “understand” what that user is looking for, and what information they’ll need before their issue can be resolved. Then, it can intelligently determine which agent to assign your ticket.
If a user’s query is relatively simple the chatbot might opt to assign it to a newer member of your support team. If the inquiry is more complex and will require a subject matter expert, on the other hand, the bot would likely assign it to an agent with experience in that particular area. Plus, if the bot has access to each agent’s list of tickets, it can also take workload into account, and route inquiries to manage capacity efficiently.
This way, each customer will be directed to the person most qualified to resolve their issue — and to deliver that resolution in the least amount of time.
4. They can understand change in conversation
Conversational chatbot solutions powered by AI also support multi-turn dialogue. This is the ability to switch between various user questions within a single conversation. This is what sets apart a human-like AI versus building chatbots. An AI-powered virtual agent responds without getting confused if a person pivots the conversation. For instance, a person can ask about the price of checking a bag in the midst of checking flight status. In conclusion, AI can also understand more short-form and slang than chatbots.
5. Voice recognition
Voice recognition enables faster, hands-free interactions for users, making AI bots even more convenient. Examples of voice recognition can be found in a number of personal assistants, including Google Assistant, Siri and Alexa. Companies, including WestJet, are also launching skills on voice platforms to provide yet even more choice with how customers receive support.
Qualifying leads: A significant portion of leads to car dealers come from online channels. Therefore conversion optimization is crucial for automotive companies. As a result, automotive companies are using chatbots like Kia’s Kian which can answer customers’ complex questions and dramatically increase conversions.
Chatbots can add a new layer of interactivity to e-commerce, allowing customers to interact beyond menus and buttons. Major use cases are:
- Set price alerts: Bots that give price alerts notify when there is a change by observing the change of prices on different websites. Settings can be made according to the person and give alarm in desired situations.
- Order physical goods like clothes with conversational commerce unlock more options
- Buy gifts: Similar patterns in the users’ behavior can be analyzed and the product they are looking for can be recommended by chatbots. this facilitates the search for gifts.
- Track orders: Order tracking, which is one of the most common features of e-commerce platforms, can be done quickly via chatbots. Tars provides a chatbot solution for payment and order tracking by integrating on e-commerce websites.
Travel & Hospitality
All the way from booking travel to solving travel-related problems, chatbots have the potential to help.
Vacation planning: While most parts of travel bookings are already self-service, it is time-consuming to plan a vacation. Travelers need to discover the sights and experiences they would be interested in, plan an itinerary, pick hotels to stay in based on numerous criteria from kid-friendliness to location. While these tasks are frustrating for travelers, clever chatbots can make them much more pleasant experiences.
- 2Reservations & handling menu related questions: Chatobook aims to become OpenTable of chatbots. Beyond reservations, it can share menus and promotions, collecting feedback.
- Queries & complaints: In the long run, it is not good for business to make complaints more difficult to make. It frustrates customers and deteriorates a company’s reputation. Chatbots can service most queries and complaints fast, improving the satisfaction of your most dissatisfied customers.
- Information service: Most banks chatbots are capable of informing users about their balances, recent transactions, credit card payment dates, limits and so on.
- Credit applications: Just as robo-advisor chatbots are taking over investment advisors, chatbots are also capable of collecting necessary data for credit decisions
- Money transfer: Chatbots can easily handle money transfers via SMS, Facebook messenger or other popular chat platforms. Western Union has a money transfer bot that enables money transfer requests through Facebook Messenger.
- Bill payments: BillHero is an example of a bank-agnostic mobile application and it brings bill-paying capabilities via chatbots on Facebook Messenger.
- Handling healthcare & insurance coverage related inquiries: Applications such as HealthJoy, HealthTap and Your.MD help customers navigate the complex healthcare landscape in the US.
- Diagnosis: MedWhat and Ada Health are AI-powered chatbots that can serve as a medical assistant by gathering information via conversation with the patients. It seems chatbots are on the way of becoming the first contact point on diagnostic healthcare. After the SARS CoV-2 outbreak, people have become more aware of the dangers of infection. Diagnostic bots, like telemedicine, facilitate remote diagnostics, reducing potential infections.
- Therapy: Since therapy is almost completely text-based, it is a great area for chatbots to work in. Woebot is one of the leading chatbots, providing cognitive-behavioral therapy in the treatment of depression.
23- Agent inquiry handling: Allstate developed Allstate Business Insurance expert (ABIe) to handle questions from 12K agents. Agents inquire ABIe about policy details sales quotes.
24- Customer inqury handling: Allstate’s Allstate Business Insurance expert (ABIe) was expanded to serve end users as well.
Lead qualification: Qualifying leads take significant time in real estate. Chatbots such as Apartment Ocean greet potential clients and understand their level of interest, helping human agents prioritize who they will serve. Roof.AI is a chatbot platform that helps to create communication between real estate businesses and their customers via social media.
These are just a few samples. Some more success stories can be viewed here – Top 30 successful chatbots of 2021 & Reasons for their success (aimultiple.com)
As brands find new ways to incorporate artificial intelligence into their daily operations, it’s certain to establish an increasingly large presence in the business world. But for now, chatbots are an excellent way to become an early adopter of this technology and start delivering better customer experiences than ever before.
Interested in learning more about artificial intelligence and chatbot technology? We’d love to discuss how we can help provide you a powerful AI customer service platform which in turn provides a conversational experience your customers expect. Let’s chat! Or if you prefer to write then reach us at firstname.lastname@example.org
Progressive Web Apps
The number of web and cloud apps is growing every day. Today, there are 2 billion websites in the world and among them, 400 million are active. Mobile apps are growing at an even faster pace. There are close to 4.2 billion mobile apps in the world consumed by 4 billion mobile internet users. If you look at the global mobile app market, it is captured by two companies, Google, and Apple. The global mobile operating system market is dominated by Google’s Android with a 74% share and Apple’s iOS is 23%. Native apps are not confined to mobile. Windows has always had a rich native application eco-system. Windows applications are typically written in C#, C++, or even C. Other platforms, like Linux, cannot be excluded. We can classify these as desktop or workstation-based applications.
Whats is PWA?
In simple terms, Progressive Web Apps give you the feel of a native application while you are browsing the web on your mobile, without actually installing the application on your mobile phone.
These Apps use features of web browsers and progressive enhancement strategy to bring a traditional App-like user experience to web applications. Progressive web applications have the same speed, responsiveness and comprehensive capabilities of websites with database access and automatic data. They are capable, reliable and installable, and can reach anyone, anywhere and on any device with a single codebase.
- Progressive & Responsive
Progressive web Apps should work on any web browser and progressively enhance themselves for browsers with more features. Once you build a PWA, you don’t need to worry about what browsers or devices users use.
You can install a PWA to your desktop or mobile device. The PWA will appear in your Start menu, desktop or applications, with a minimum of fuss and without much change to the code.
- App-like Look and Feel
The App-like appearance is essential for user experience and functionality. A PWA is added to the home screen in the same way as a native App, and offers many of the same features like offline mode and push notifications. Due to the responsive nature of progressive web applications, they are more user friendly and attractive.
- Better Performance
PWAs cache and serve text, images and other content in a specific, efficient manner, allowing them to operate like websites which significantly improves the running speed. Better performance has a huge impact on user experience and conversion rates, and as a result, a progressive web App can improve customer retention and customer loyalty.
- Fast Installation
The usage threshold is low as no new App needs to be downloaded from an App distribution service. There is no need to search, download and update a PWA as with a native App; rather, users can download the App quickly and directly to their device. This presents a significant advantage, as it streamlines the process and reduces customer abandonment.
- Offline Operation
One reason to prefer building a native mobile App over a progressive web App has historically been that a mobile App can work (to some extent) without an Internet connection, using cached data. Whereas websites can only work whilst an Internet connection is present. However, Service Workers have allowed for web Apps to compete with mobile Apps, providing a solution to accessing certain web pages when offline.
- No Dependence on App Distribution Services
App Distribution Services like the App Store, Google Play or Microsoft Store have high requirements for what kinds of Apps can feature. Designing a PWA avoids meeting any complicated procedures that may be unnecessarily time and effort consuming.
At first glance, this appears to be a disadvantage. However, upon closer inspection, a progressive web App provides great user experience and is great for SEO. That’s certainly worth considering! As progressive web Apps are websites, they are discoverable in search engines. Plus, their safety, fast loading time and relevant and unique content put them ahead of native Apps.
- Push Notifications
Progressive web Apps seek to improve engagement with your users using push notifications (just like the ones you get on your iOS or Android phone). For progressive web Apps, this is achieved using two different technologies in combination: Push and Notifications.
Push notifications are very short messages (a bit like text messages) that appear on your progressive web App users’ device when sent from your server. Users must permit your progressive web App to display the Push Notifications before they see them, so they are not a guaranteed method of communication. Use push notifications in your progressive web App design to encourage engagement with your App, and remind users to use your App more frequently.
- Automatic Updates
Progressive web applications automatically update when the user visits them, making it unnecessary to download and install any batch changes. So, without bothering the user with a permission request for updates, you can reserve any push notifications for engaging and re-engaging users with your App.
Progressive web applications must be hosted over HTTPS to ensure the secure delivery of data. Therefore, content and interactions are as safe as they can be with as on a secure website.
- Low maintenance
A lot of companies ignore the maintenance cost of an application. Whereas, before building any application you should always consider both the development and maintenance cost of the application.
In general, the maintenance of an app includes the following:
App Hosting charges
Resolving bugs and releasing new updates
The annual cost of any third-party plugins or so
Tracking performance and marketing
For any type of application (mobile or web), the fee for maintenance will be approximately 20% of the development cost. Because the cost of building progressive web apps is less than native apps, so will be the maintenance cost.
How do PWA’s work?
PWAs use a quirky architecture consisting of four pillars, which work in tandem to provide the native app-like user experience. These four are:
Service Worker: When you visit a PWA powered website for the first time, the Service Worker shifts gears, downloading all the content in the background. With the content already cached on the device, the site loads much faster. Service Workers also enable websites to send you push notifications.
Web Manifest: The web app manifest gives you information about the application(name, author, icon, and description) in a JSON text file. The web manifest makes the installation of web applications to the home screen possible, meaning faster access and a better UX.
HTTPS: One of the prerequisites of a Service Worker is that they make websites available over Https, meaning the connection is secure.
Icon: The display end of the PWA that the user will be able to see once he installs the application.
Limitations of Progressive Web Apps
The idea of PWAs sounds amazing. So, why isn’t every mobile app a PWA then? Here are some of the PWA’s limitations.
PWA is not native. Some app developers and users just love native. Native user interfaces are often changed when a new operating system is launched. Most of the native functionality is backward compatible.
PWA needs and runs in a browser. It is still a Web application and you need to be a Web developer to write PWAs.
Progressive web apps restrict the developers from accessing the hardware resources required to run the application. These hardware resources are platform-specific APIs and are required in a rare case.So, if your application requires access to any of this hardware, then you must stick to native or cross-platform frameworks.
When to choose building a PWA
Not sure whether to opt for a progressive web app or not? Lets see some of the reasons for switching to progressive web apps.
- Targeting a Developing Country
There are still a lot of countries around the globe that still don’t have access to 3G or 4G networks. So, if your app is heavy most of the users won’t be able to access it. In this case, using a progressive web app is definitely an advantage.
- Target Users are Coming from Mobile Devices
Let’s assume that your business already has a web application and most of the users are coming from a mobile device. In this case, using the push notification, offline functionality and native app-like features make the life of your users easy.
- High User Engagement and Conversion
A lot of companies like Flipkart, Uber, Twitter, Pinterest, etc, have seen a massive increase in the number of users and engagement with a progressive web app. So, if your native app isn’t performing well, you should consider migrating to a progressive app.
Do you relate to any of the above reasons? If yes, then you must consider building a progressive web app for your business.
PWA success stories
A lot of companies have switched over to PWA to enhance user engagement, including:
Twitter: Twitter launched Twitter Lite, a PWA in 2017, which helped them connect with mobile users more deeply while consuming fewer data. The PWA relies on cached data and optimized images, and the Twitter lite PWA is just 600KB, compared to the 23.5 MB size of the native app available on the Play store.
Tinder: The now-infamous dating app also launched their PWA in 2017, and found that there was a higher user interaction with the PWA over the native app, with users spending more time messaging on the web application compared to the native app, along with increased session lengths and purchases in par with the native Tinder app.
Trivago: The German-based hotel search engine, one of the largest in the business, wanted to be at the forefront when it came to their mobile website and implemented a PWA in a phased manner to make use of the speed and use of lesser resources. Today, Trivago’s PWA powered website is available in 33 languages, across 55 countries, and the company has seen. User Engagement increased by more than 150%
Uber: Uber uses PWA technology for ride-share booking for low-speed, 2G networks. This PWA allows users to access Uber’s services on low-end devices that are not compatible with their native app.
Starbucks: Starbucks built a PWA for their web ordering system to provide offline ordering that is similar to their native app. Starbucks’ PWA allows you to browse the menu and customize an order without internet.
Spotify: Spotify is powered by PWA-technology to overcome the limitations of working with Apple. Spotify’s PWA app utilized the adaptive UI to changes the background as you progress through the app.
The need for progressive web apps is growing each day. This article touched on the basics of PWA and why a business should look into adding PWA to its product strategy. Not only is PWA a need today, with its offline abilities, local caching, and push notifications offerings, but it also builds one code base to target both desktop and mobile devices, making it more attractive to any business that is not dependent on native mobile apps and wants to save money and resources.
Need help with a PWA?
If you want to build a progressive web app and need help, advice, or developers, feel free to contact us at email@example.com or on our LinkedIn page or visit our company website, www.quantiantech.com
Accelerated mobile pages
Mobile traffic has surpassed desktop traffic in overall reach. While conversions remain a sore spot for mobile commerce, they are increasing over time. For example, mobile conversions increased by 47% year-on-year during Cyber Week and amounted to 39% of all conversions in 2020. From this, it’s clear that mobile commerce is here to stay.
However, users are changing how they make mobile purchases. App usage is declining, with 53% of worldwide shoppers using a retailer’s mobile website rather than their app. Consumers want the most engaging experience on mobile, directly from their browser, Speed of page load is a major reason for this preference.
According to data collected by Google, 40% of consumers leave a page that takes longer than three seconds to load.
That’s all the time you have to keep the attention of a user who liked your ad and clicked it. And if your webpage fails to load in that time, you created the ad, regardless of how compelling it was, in vain. The bad news is the fact that according to data, most retail mobile sites take around 7 seconds to load, that’s more than double the amount of time 40% of users wait before abandoning the page. That’s not all, users will not only abandon the page, but, research suggests 60% of users won’t come back once they’ve had a slow experience on a webpage.
What is AMP?
Google launched the Accelerated Mobile Pages open-source project to ensure that mobile webpages operate at optimal speed. The AMP project allows developers to create web pages and ads that are consistently fast and high-performing across devices, and distribution platforms.
More than 1.5 billion AMP pages have been created to date.
When you create mobile pages on the AMP format you get:
- Higher performance and engagement: Pages created in the AMP open-source project load almost instantly, giving users a smooth, more engaging experience on both their mobiles and desktop.
- Flexibility and results: Businesses have the opportunity to decide how to present their content and what technology vendors to use, while maintaining and improving KPIs.
Google reports that AMP pages served in Google search typically load in less than one second and use ten times less data than the equivalent non-AMP pages. CNBC reported a 75% decrease in mobile page load time for AMP Pages over non-AMP pages, while Gizmodo reported that AMP pages loaded three times faster than non-AMP pages.
How does AMP work?
AMP pages are built with the following three core components:
The AMP HTML is essentially HTML just with some restrictions for reliable performance.
Most tags in AMP HTML are regular HTML tags, however, some HTML tags are replaced with AMP-specific tags. These custom tags are called AMP HTML components and they make common tag patterns easy to implement in a performant way. AMP pages are discovered by search engines and other platforms by the HTML tag. You can choose to have a non-AMP version and an AMP version of your page, or just an AMP version.
The AMP JS library ensures the fast rendering of AMP HTML pages. The JS library implements all the AMP’s best performance practices such as inline CSS and font triggering, this manages resource loading and gives you the custom HTML tags to ensure a fast page rendering. The AMP JS makes everything from the external resources asynchronous so that nothing on the page can block anything from rendering.
The Google AMP Cache is used to serve cached AMP HTML pages. The AMP Cache is a proxy-based content delivery network used for delivering all valid AMP documents. The Cache fetches AMP HTML pages, caches them, and improves page performance automatically.
The three core components of AMP work in unison to make it possible for pages to load quickly.
The next section will highlight some optimization techniques that combine to make AMP pages so fast.
- All resources are sized statically
All external resources such as images, iframes, and ads have to state their HTML size so AMP can determine each element’s size and position before the page resources are downloaded. AMP loads the layout of the page without waiting for any resources to download.
- CSS must be inline and size-bound
CSS blocks rendering, it also blocks all page load, and it has the tendency to cause bloating. AMP HTML only allows inline styles, this removes 1 or mostly multiple HTTP requests from the critical rendering path to most web pages.
- Font triggering is efficient
Web font optimization is critical for fast loading as web fonts are typically large in size. On a typical page that includes a few sync scripts and a couple of external style sheets, the browser waits to download the fonts until all scripts are loaded.
- Resource loading is prioritized
AMP controls all resource loading, it prioritizes resource loading and it loads only what’s needed and pre-fetches all lazy-loaded resources.
When AMP downloads resources, it optimizes the downloads so the most important resources are downloaded first. All images and ads are only downloaded if they are likely to be seen by the user, if they are above the fold, or if the visitor is likely to scroll them.
AMP also has the ability to pre-fetch lazy-loaded resources, these resources are loaded as late as possible, but are pre-fetched as early as possible. This way things load very fast, but the CPU is only used when resources are shown to users.
- Pre-rendering pages
The new AMP pre-connect API is used heavily to ensure that HTTP requests are as fast as possible as soon as they are made. Because of this, the page is rendered before the user explicitly states they would like to navigate to it, the page may be available by the time the user actually sees it, making the page load instantly.
Significant business benefits
Increased mobile browser visibility for content marketers: Google has started displaying AMP results in organic listings. You can identify these results by the AMP symbols, in green. These green AMP symbols will definitely lead to an improved click-through-rate because these mobile search engine results stand out from the rest.
Mobile search engine users will then begin to look specifically for AMP plugin pages since these pages load up quicker than the typical mobile pages.
Improved mobile search engine rankings
Since sites that are mobile-friendly are rewarded with higher rankings in organic mobile search results, pages developed with AMP will most likely rank higher than non-AMP pages, in the mobile results pages (MRPs).
Improved Advertisement visibility
Most people started a website or blog in order to make money. But the websites currently seem to have too many distractions. E.g. header image, navigational menu, sidebar, social share buttons, forms, popups, and other unnecessary elements.
But, with AMP, you can get rid of distractions on your mobile browser pages. When displaying ads from a third party on your Accelerated Mobile Pages, you deliver ads that load quickly but also grab the user’s attention.
User tracking made simple
Tracking users and site performance is pretty easy on AMP because there are analytical tools in place, where you can study your AMP versions in greater detail.
Publishers can utilize tag manager analytics to choose from two tags. These tags help to automatically track essential data, such as clicks/conversions, video and link tracking, visitor counts, new vs. returning visitors and more.
Technology companies, such as WordPress, Parse.ly, Chartbeat, LinkedIn, Adobe Analytics, Pinterest and, of course, Twitter, are also already supporting AMP.
AMP is truly powerful. As an upgrade to mobile-friendly pages, it helps you meet user’s expectations for speed and simplicity along with publisher’s expectations of reader engagement and monetization. To understand this further or discuss feel free to contact Quantian Technologies at firstname.lastname@example.org