“ Delivering customer engagement in silos can significantly damage the customer experience,” said Gene Phifer, vice president and distinguished analyst at Gartner. 

Customer engagement and marketing are one of the most important operations of any business and it has been predicted that poor performance in these two areas will be one of the top three reasons for failure of enterprises in the coming years.  

In general most of the enterprises are used to delivering its products and services in silos. Although this makes it easier for easily managing & running the enterprise, the risk of customers being dissatisfied because of poor customer engagement is very high. Poor customer engagement has a lot of ill effects on business ranging from minimizing their spending, turning to a competitor of yours to leaving negative feedback on social media which can significantly affect your brand and it’s revenues on the long run. 

Retaining customers and their loyalty is the ultimate goal that will help any business reach its revenue goals over both short and long term. And the best way to keep their loyalty is by providing them with a seamless customer engagement experience. While there are a million ways you can try to keep your customers with you, here are the top three ways you can use :




Nothing matches a good old fashioned one on one customer service that will make your customers feel special every time they call your company. Providing relevant and reliable contact information in a place where your customers can easily find it most important. The next thing you must do is to have a team that responds to your customer queries in the most sensible manner. 

At Voicy we provide automated Customer Engagement at a personal level that will respond to all your customer queries instantly, saving you time and assuring that you won’t lose any revenue in this space.

Another place where businesses, especially enterprises lose customers is the time they take to respond to their customer queries. Having a fixed time to close a customer query always helps. Usually closing a query within 30 days is considered best.




Letting your customers know of anything that is about to happen with your organisation is the best example for proactively communicating with your customers. Everybody wants to know what is coming next from your company. Be it a new feature update, a new product that is to be launched or a new product idea that you might want to work on, communicating that to your customers in advance always keeps their interest levels high. This also helps in anticipating your customer’s future needs and understanding their expectations in terms of products and services.

Ideally this move shows that your company cares about your customers and is investing time in giving them what they actually want. The most common practices for proactive communication are sending mails, opt in messages, etc. 

At Voicy we provide you a Two Way SMS platform that will not only help you keep your customers updated with your progress but also give them the chance to respond to your updates with their queries, thereby ensuring greater communication and stronger customer bonds.




If you are an enterprise, it means that you have worked really hard to build a successful brand. You know you have customers using them but do you know how many you have and how they are feeling using the products/services provided by your brand ??

It is also important that your customers also don’t feel that they are the only ones using your product/service. Building a community that will encourage them to share their experiences and read other stories will create a sense of oneness that will in turn strengthen loyalty for you. Listening to their feedback here will also be a good place for you to know what your customers want and this will help you in future product/service developments.


Having loyal customers means getting stable revenues and having a positive word of mouth that will eventually grow goodwill in the long run.

When you are an enterprise, there are a large no.of customers and giving them individual attention can be a very hard thing. Investing on the right kind of marketing and customer engagement programs means everything. However this is also the place where most of the company budget goes making it very expensive to afford solutions that can actually make a difference in this space.

This is where latest technologies like Artificial Intelligence (AI) and Natural Language Processing (NLP) step in providing easy and affordable solutions. At Voicy we use AI technology to provide seamless Marketing and Customer Engagement solutions that save a ton of time and money to all sizes of businesses – Small, Medium and Enterprise.

For Enterprise, check out our latest integration with Microsoft Azure at – 

Check out or other integrations at – 

Check out our Conversational self service Two way SMS application with a 14 day free trial : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :

Get the most out of this Valentine’s Day-2021 using Two Way SMS Marketing

Curate a Special Menu/Service/offering for Valentine’s Day:

Create a special menu if you are a restaurant/bakery etc or a section of your store that is dedicated to gifting loved ones and spread messages with the details or link of your offerings.

You can also take advantage of a two-way text marketing solution and create keywords that are dedicated for the Valentine weekend and provide more information to your customers.

Provide Coupon codes for loyal and new customers:

Coupon codes for special days have proven to create a lot of impact on consumer buying behavior and helped in making the purchase decision. Create unique coupon codes associated with valentine’s day and promote them with the help of SMS text messages.

Your promotions not only show how much appreciate their business but also it is a great way to promote and generate more revenues, walk-ins and increase loyalty for Valentine’s Day using a two-way conversational SMS marketing solution. 

Contact us now at discounts, annual plans,  multiple store requirements, and custom development.

For more information on product and pricing check out the links below :

Check out our Conversational self service Two way SMS application with a 14 day free trial : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :


Upsell with our “Sell Now’ Feature

No Matter how good your restaurant does in business, there is always a desire to improve sales. Many times restaurants try to come up with innovative ideas to capture their market and retain their customers. Amongst others the most common ones are rewards and upselling strategies. The rewards or referral programs are more direct. Convincing your customers to buy more or even convincing them to buy when they didn’t plan doing so needs some skill.

Having well trained table staff is one key requirement for this because they are the ones in direct contact with your customers at their tables and they must be able to build a good rapport with your customers in order to convince them to try out a new dish, a restaurant special or an add on at a discounted price. But all this can only happen when there are customers at your table. The recent shift in things has reduced this scenario of people wanting to visit a restaurant. Improving sales while people stay at home and order take outs is rather challenging than persuading them face to face.

This is where modern technologies of marketing step in. Cutting edge technologies like Artificial Intelligence, Natural Language Processing, Ect. have been taking over the market of digital marketing, proving that a shift in the older methods are inevitable. Although these names sound complicated they can come up with super simple solutions for your marketing needs. Chatbots are one such example.

Research shows that 80% of all the companies across the world are planning on implementing chatbots into their business in 2021. They are expected to reduce customer engagement costs by 30% and business costs by 8 billion by 2022. Chatbots are influencing the market so much that User Experience (UX) is now being called Chatbot User Experience (CUX).
For more information on the latest trends in Digital Marketing click here.

Although chatbots can perform a variety of tasks ranging from running campaigns, answering customer queries, personalizing communication, automating repetitive tasks and so many other complicated things, they can also be used to automate simple tasks like SMS marketing. This automation comes in handy especially for small and medium sized businesses (SMB).

Voicy.AI is a company that has been helping SMB’s with marketing and customer engagement with its two way SMS marketing app. The app is a conversational platform (Chatbot) that enables a dialogue between your business and your customers. The platform has been helping businesses with marketing and customer engagement. It lets you run a marketing campaign, lets your customers respond to it, generates orders directly when downloaded from your Point Of Sale system (POS) and more.

Amongst all the other features of the app one of the most interesting feature one is the ‘Sell Now’ feature. Let us talk in detail about what this feature does

Say you own a restaurant that wants to promote a special offer for the weekend. Since it is a rainy day you don’t have a lot of customers to dine in and so you decided to run a marketing campaign instead to generate some take out orders.

You open the Voicy Two Way SMS app and send your marketing message about your special offer to all your customers.Here, in the message you include a line that says ‘ Respond with YES if you want to place an order ’. Since our app already has access to your customer list you can simply run the campaign with one click. Your customers receive the message within minutes.

Being a Two Way SMS Platform, the app lets your customers chat with your business. Since the offer you are running tonight is an irresistible one, most of your customers decided to respond with a ‘YES’ to your message, thereby generating orders immediately in your POS. Some may even chat with the app to get more menu items and place an order for more, thereby helping you upsell.

For more information on product and pricing check out the links below :

Check out our Conversational self service Two way SMS application with a 14 day free trial : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :


New Year Marketing for SMB’s

All though New Years mean the end of the holiday season, they also symbolize hope of a fresh start. The year 2020 will always be remembered in history as the year of Covid – 19. So many businesses were shut down. However, a right marketing strategy is all you might need to jumpstart all the things that were lost.

All the larger conglomerates have probably already started their marketing around the new year. In reality marketing is not about the money one can invest, it is about the ideas that can get the attention of your consumers for your product/service. 

Ex. Instead of uploading a 200 page catalogue on their own website IKEA transitioned a printable version of it in Pinterest. It also included a product questionnaire with the shoppable version of the catalogue which helped them with understanding the user’s interests and purchase patterns. .

This is just one example of how budget friendly marketing ideas can change the game for you.

If you are constrained on your marketing budget, there are a few simple steps that you can follow to extract effective results that can ensure you good ROI

For first and foremost thing that needs to be done for any marketing to be done is to come up with a marketing plan. Design a marketing plan that will clearly help you understand your target market, the best way to reach them and the best way to persuade them to buy your product. Make sure you develop a year long plan that gives you an idea on what must be done for the entire year.

Create your own website. Having a website has become one of the most important criterias for a business to be considered as legitimate in recent times. Although as an SMB you can’t hire a professional agency to this for you, there are a lot of user-friendly websites like WIX and WordPress that help you build a basic website on your own.

Make sure your website is mobile friendly and has been optimized for SEO. If the technicalities of this task freak you out, then getting some help from a local agency can help you resolve the issue with minimal expenditure.

Adapt newer marketing techniques. Technologies like Machine learning, Natural Language Processing, Artificial Intelligence are the next generation of marketing. If you are worried about the expensiveness, then Voicy.AI can provide you readily available affordable chatbots that can help you with marketing and customer engagement. 

For more information on Modern Marketing Technologies click here.

 The next thing that comes in line is your social media presence. Improve your social media presence. Have a year long social advertising plan. If you don’t have one, then start making one. Get a social scheduling tool that will line up your marketing content in a pre-planned manner with quality matter. Some of the best social scheduling tools are Social Pilot, SEMrush, and others

Increase your followers on your social platforms. Keep your social channel platforms up to date. Having a presence on Linkedin will certainly improve the value of your business and dismiss any doubts of genuinity that the users might have.

You could get in touch with local media outlets like TV, Radio and others. The reporters and producers are in constant search for “Experts” in many fields. Offer yourself as an expert in the area. If you can get through then it can be free advertising for you.

Soliciting your online reviews has become an increasingly important practice in recent times. Work on a plan that will help you reuse these reviews that your customers leave you. This practice will eventually help you with better positioning with your search engines. 

Whether you chose to do all of these or just pick and choose the ones that work best for you, adopting a practice and working on a year round plan for your marketing will always yield the best of results.

Check out our Conversational self service Two way SMS application with a 14 day free trial : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :



Digital Marketing Trends of the Millennium

Digital Marketing Trends of the Millennium

As the digital analyst, speaker and author Brian Solis puts it :

Each business is a victim of Digital Darwinism, the evolution of consumer behavior when society and technology evolve faster than the ability to exploit it. Digital Darwinism does not discriminate. Every business is threatened.

In a world where consumer interests and consumer behaviours are unpredictable, it is important to keep up with the trends in marketing if you really intend to stay in the market in the longer run. Technologies that were once considered impossible – Chatbots, Artificial Intelligence, Voice Powered Assistants, Data Driven Marketing, are now the technologies all the businesses are thinking about exploring. 

Artificial Intelligence (AI)

The textbook definition for AI is the study of ‘Intelligent Agents’. Agents are machines that demonstrate intelligence by mimicking the cognitive functions of human beings like learning, problem solving, ect. 

How does Artificial Intelligence help with marketing ?

AI can be a game changer for the marketing industry as it leverages the use of customer purchase history data to predict their buying interests. It uses some latest concepts of machine learning to even predict the customer’s next move. Most people and businesses have already been exposed to the power of AI in marketing in the year of 2020 and we can only predict that it can get better.

For Example – If you are a car company and you are planning on launching the next version of your car which is going to be eco friendly – an electric car. Now for you to be sure if this is a right decision you need to know that your target market is really interested in such a product. Here is where AI comes in handy. With AI software and data spanning a few decades will help you understand your consumer buying personas and future trends in this kind of technology. Within a short span of time, you will have all the information you need to validate your decision of launching a new product line. 

This is just one example of what AI can do. There are so many areas AI is making a difference in today’s world. 

5 ways to boost your digital marketing experience with AI

The primary goal of any marketer is to improve sales and make profits. This involves a lot of hard work, but why do all the hard work while you have smarter ways to achieve what you want. Let’s see how AI can help you with this

  1. Customer behaviour prediction 

Knowing what your customers is the key to a successful business. No business exists without customers. So understanding your customer’s purchase behaviours and where the business trends are headed based on the tons of data that is already available is one of the best ways AI can help the marketing sector.

Some major examples are eCommerce companies like Amazon, eBay.

  1. Sentiment analysis

This is something that has been used by most of the businesses to understand their product/service is being perceived by its users. This can also be applied for specific ad campaigns that can help change the campaign immediately based on the customer’s interest in it. This can in turn be helpful in understanding the products that are loved by the customer and those that need to be improvised according to the user’s interest

  1. Targeted ads

If you have the right set of data that can help you talk to your customers about their needs and trigger a personal conversation to help them with it, you will be making huge profits with your business. For example if you are a hospitality industry, having the right set of data can help you reach out to those people who are planning on a vacation and you can start a conversation with them to help out with their trip while booking their stay with you. 

  1. Recommendation system

If you are a company that serves thousands of products to your customers, then AI can help you in a very huge way. Going through all the products you offer may be a tedious process for your customers. With the appropriate AI you can recommend the appropriate products they want dispensing on their previous purchase patterns or by asking questions. 

See how Voicy.AI can help you make personalized recommendations to your users –

  1. Personalization 

A chat bot is a classic example for personalization with AI. Whether you are an SMB or a corporate giant or an eCommerce platform, chatbots can help personalize your customer’s shopping experience. They can help you with your marketing campaigns, collecting customer feedback, responding to your customer queries and so many other things.

Voicy.AI has been using the chatbot technology to help businesses with marketing and customer engagement solutions for a while now. Sending a marketing campaign and generating orders in your POS, responding to customer queries even during off hours and holidays can all be automated with our simple AI software.

The ability to respond to your customers on a personal level can not only improve your sales but it can also improve brand loyalty, ROI and reduce churn. Our chatbot solution can also help personalize your customer engagement conversation at just 1/10th of the cost you would spend on recruiting personnel. 

The best way to keep your business afloat in these difficult times is by adapting one of these digitized marketing techniques.

Check out our Conversational self service Two way SMS application with a 14 day free trial : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :


Will there be additional discounts this Black Friday ??

Will there be additional discounts this Black Friday ?? 

This is a question that is popping up in everybody’s mind. COVID 19 has changed everything for us and it has certainly changed the tradition of lining up in front of the big box stores creating the Black Friday Frenzy.

As far as prices are concerned, shoppers are going to experience the lowest ranges as usual. However, it looks like this year the sale is not going to be just for one day. Most of the big box stores like Target, Walmart, Best Buy, Kohl’s and others will remain closed on Thanksgiving day.

This year all these stores will be taking a lead from Home Depot. Instead of one day or a week, this year’s Thanksgiving is going to give its shoppers offers and deals for a month or more so people can shop at their convenience.

Although surveys say there are still some percentage of shoppers who want to shop in store for their favourite doorbusters, most of them have surveyed to feel safer shopping online or doing a curbside pickup in case they don’t get free shipping

Whatever may be the case, the main idea is to be successful this season and the key to it is a right marketing strategy. 

Although there are many ways to market your product SMS marketing remains one of the most effective until now. Survey says that  two way SMS marketing has about 98% of open rate and 45x ROI. A two way SMS will not only let you market your product but also lets your customers interact with your business and respond back to your marketing campaigns that can instantly convert your leads to revenue


At Voicy we offer you the best SMS marketing packages that will help you with both your marketing and customer engagement services. Here is what you can do:

Get new customers

Build loyalty with your existing customers

Make personalized conversations with your customers at scale

Instantly convert Leads to revenue

Be available to your customers even during off business hours and holidays

And much more.


Check out our Conversational self service Two way SMS application : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :

How are you selling your treats this halloween ?

Halloween has its roots from the Celtic culture in Ireland. Originally Halloween’s night was considered an evil night when devils and spirits roamed the streets of villages. Superstition or not Halloween is now celebrated with costumes, candies, parties and dancing.

But, are you trick or treating this year ??

Will there be costumes and parties this year ?? We will know the answers to that in time.

Encouraging kids to go around knocking on people’s doors and accept non-descript treats is probably a no-go this year. Covid has created a new normal which means planning for a safe and contact less Halloween this year is very important. 

Out of all the things that have changed the most important changes are the ones affecting the retail industry. Seasonal marketing play a very big role for any industry and the usual ‘It’s a the most wonderful time of the year to spend time with your family’ is not going to work this time since most of them would have either lost family or would have gotten sick of hanging out too much with them during the lockdown or they will not be able to meet family because of the lockdown.  

So what is it that you could do to seasonally promote your product/service/brand ?? 

The first thing that you must not do is not to use your company’s work if you are not doing any pandemic related services. Instead, focus on things like affordability of the product, its accessibility, contact less delivery and all other things that show you follow the protocol to prevent the spread of Covid while delivering your product.

It is sad that people can’t meet each other but the ability to talk to them over phone and video calls is still a boon. Use something like this for your marketing. Use lines that say ‘ Let us give your best wishes to your loved ones this Christmas on your behalf through our contact less delivery ‘  and a lot more like this. 

If you are promoting products that can be enjoyed solo,  then use messages that emphasize usage of your products alone. Try promoting and making the idea of temporary isolation look good. 

Whatever the angle you choose to promote, make sure that it looks real and personal. Make sure you use the right platform to market it. 

Online marketing and chatbots are a proven trend for promoting your products now. Two way SMS marketing is yet another way where you let your customers talk to your business just like you talk to a friend and let them buy your products. Two way SMS marketing will not only help you with campaigning but also with your customer engagement process.

Check out our Conversational self service Two way SMS application : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :


Improve your Sales on this Labor Day Weekend using Two Way SMS Marketing

Labor Day in the United States is an annual holiday to celebrate the achievements of workers. It has its origins from the labor union moment, specifically form the eight hour day moment, which has advocated eight hours of work, eight hours of recreation, and eight hours of rest.

Believe it or not, Labor day is right around the corner. As summer comes to a close and people are getting used to the Pandemic and shoppers are coming out to fulfill their needs, or just want to take advantage of the offers and savings on their favorite products.

Businesses need to be more prepared for labor day than ever before due to the disrupted market after the COVID breakout across the globe. Offers and Promotions are a good way to attract consumers but without proper communication and customer service.

Using Conversational Text Messages, you will be more prepared to join the conversations with your consumers this Labor Day. Target audience right on their mobile devices using SMS Marketing.

Are you aware that text messages have an open rate of more than 98% and most of them read within 3 minutes.

Here are some tips and tricks when sending Text Messages during the Labor Day weekend.

Voicy.AI is offering a limited 14-day free trial on their two way conversational SMS Marketing application along with features like order generation, automatic replies, appointment scheduling, and much more.Write to us now at to get your free trial.

Plan your campaigns early:

Consumers need to educated early about your offers and especially with the ongoing pandemic they need to be prepared to encounter your offer or brand before their purchase decision.

Build Consumer Relation: 

When a consumer comes in contact with your brand, a call to action like instant order generation, video link, weblinks, etc can help your business in creating more engagement and showcasing your offers. 

Using the order generation feature from Voicy.AI, consumers can directly respond to their messages and generate an order. 

Take advantage of Geographic Elements:

If you are a local business and want to attract your neighborhood consumers using digital events, sidewalk sales, and community events. Text messages are the perfect way to notify them and increase your interaction.

Labor Day is the perfect weekend to get rid of your excess inventory and sell your summer inventory that you don’t want to store through the winter.

At Voicy.AI, we are celebrating Labor Day by proving a 14-day free trial for all new sign-ups. If you are ready to try out Conversational text marketing with your business and empower the benefits and results of SMS, write to us at 

Check out our Conversational self service Two way SMS application : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :



Voicy.AI Virtual Telephone Agent for Telemedicine/Telehealth

Telemedicine or Telehealth:

Telehealth is a distribution of health-related services and information via electronic information and telecommunication technologies. It allows providing clinical services to patients without an in-person visit.The global telemedicine market is estimated at USD 41.1 billion, expanding at a CAGR of 15.1% over the forecast period. The unprecedented outbreak of COVID-19 across the globe has resulted into increased demand for telemedicine solutions.

“The Telemedicine market is worth $155.1 Billion by 2027, CAGR 15.1%”

Voicy.AI is a pioneer in delivering virtual telephone agent services for various use cases, is working on delivering a telemedicine solution, which can be easily set up and enabled within in a very short time.How Voicy.AI Telemedicine solution is simple and easy to setup:

  • Easy to setup.
  • Customizable for all use cases.
  • No Technical help required.
  • Integration between Virtual Telephone Agent and Conversational SMS.
  • Appointments Scheduling.

You can utilize Voicy.AI’s Telemedicine to start taking consultations virtually and connect patients with doctors over call for consultations and feedback with the ability to understand human natural language and without the need for IVR systems.

Here’s what you need to get started:

  • Voicy.AI Virtual Telephone Agent Account.
  • Personalized Virtual Agent Number.
  • Customize the Flow.

Once the agent is set up, patients can call to your personalized virtual agent and get their consultations, connect with doctors, schedule appointments, and much more without the need of a physical person. Voicy can handle any number of calls at the same time and fulfill patients’ needs.We are offering a free trial for our Telemedicine, write to us at to get your free trial.

Call Flow for Voicy.AI Telemedicine:

Once the Call flow is set up and ready, patients can call the agent and get their consultations, connect to the concerned doctor, set up an appointment. Once an appointment scheduling is requested update will be received to them via SMS. It makes it easier with our existing and upcoming integrations with many CRM’s, POS systems, and medical software.


The need for Telemedicine is important and much needed for sustaining the market. Hospitals, clinics, and wellness centers should adapt to this technology to keep up with their patient’s needs and automate their calling experience.

This is just one simple example of flow, and you can customize and create more advanced flows based on your requirements. Contact us now at to get a consultation and a free trial of our solutions. 

Check out our Conversational self service Two way SMS application : 

Sign-Up with Google:

Install from QuickBooks app store :

Install from Clover  app market :

Install from Yext app Directory :

Install from Weebly app center :

Install from Hubspot app marketplace :

Install from constant contact app store :

Digital Clone technology for devices – Thoughts from 2018

Image recognition using popular algorithms such as Imagenet have bettered the human analysis. Word Vectors composed from text corpus have increased Natural Language understanding capability for software systems. End to End Deep Learning has improved Speech Recognition and has achieved parity with humans. We can apply theses advancements, to redefine customer interactions with businesses and customers on devices.

Users carry mobile devices all the time. The phone captures all the information about the user’s favorite applications, search queries, and the places he visits. Despite the rich user information, the current generation of software and hardware is still not able to recommend content to the users, the user wants to see. The user still needs to go to a search engine or a portal to get the information and/or content. The user still needs to learn how to interact with each application, as there is no universal interface that can help the user. Switching context to Augmented Reality (AR) applications, the user needs to painfully drag objects into the real world to see how the virtual object looks in the real world. The current generation of AR applications have limited support for Natural Language Interaction. The user has to painstakingly move virtual things using hands.

In this invention disclosure, we will describe how smarter hardware and software leveraging Natural Language, Image, and User Behavior analysis can help users and businesses with their experiences. We will discuss the personalized behavior model of the user to simulate his thinking process. The personalized behavior model takes in aggregated user behavior and application context captured by pixels on the screen that the user is looking for and helps with generating actions and content recommendations.

It is to be noted that this is unlike, a virtual agent from Apple, Google, and Amazon, which are triggered by hot keywords from the user’s speech and don’t use the visual, previous context about the user to generate content recommendations.

Behavior processor:

The current generation of devices knows everything about the user. They can capture where the user was, what the user is seeing currently, has seen and read in the past, whom did he talk to, what messages he sent to the friends, etc. Deep Learning and ReInforcement learning techniques have improved Image Understanding, Text extraction, Natural Language Understanding capabilities.

Despite the rich information and technology progress, we have seen that is available to the user, the current generation of devices are still not able to predict the content that the user likes. The user still has to go to a search engine and painfully type the search query on a small keyboard to find the information he wants. The user still has to go to the browser and type, to read up the news articles. The user can’t interact with the applications on the devices, even though the machines now can read, understand what the user is reading and answer questions in Natural Language.

In this invention, we will describe a hardware and software component called behavior analyzer which can be embedded int devices. The behavior analyzer running on the device can use the application context by modeling what the user is looking at and using aggregated information about the user to generate content that the user will like and execute actions on behalf of the users.

In an embodiment, to figure out what the user is reading and viewing on phone, the behavior processor is going to have a Location Analyzer, Vision Analyzer, Text Analyzer, Application Context Analyzer, a Memory component, Controller component and a Model Manager in the behavior processor. The behavior processor will form a hypothesis on the activity of the user, continuously learn from user interactions with content on the mobile phone and try to generate appropriate content or response in a timely manner, using above components

In an embodiment, we can use a combination of multiple architectures as will be discussed in the disclosure below to generate content and action recommendations based on the context.

Behavior processor to recommend content:

Let us say, a user is taking pictures of his family in a new year. If a user is generally active on Social Network and posts his pictures on the social network after taking pictures then there is a high probability that he will share the new year pictures on Facebook. In the current experiences, the user has to go to a social network, choose pictures taken from the camera, and then post his pictures on Facebook.

Switching context to another experience, would it not be easy for the user to show search results before the user decides to go to a search engine such as and type a search query in the search engine.

Experiences like above can be improved substantially using behavior processor. The behavior processor can run as an offline process, whenever the user starts an application or as a process that executes every ‘x’ minutes or so. The number ‘x’ can be a configurable parameter. The application context analyzer component, can take the pixels on the device that the user is looking, process it against a text recognition component, to extract text embedding. The pixels can be fed to object detection DNN to get image embeddings in the application.  In an embodiment of this, we can train a general model for the behavior processor based on the user cluster associated with the device. In embodiments the users can be clustered using a K-Means clustering algorithm.

The generalized model for the user cluster can be trained using a Neural Network on anonymous training data on the users in the cluster. We will use techniques borrowed from the provisional document 62543400 with title Techniques to improve Content Presentation Experiences for businesses to build a general model. In an embodiment, the generalized model for predicting a sequence of actions for the user can be done by training a Recurrent Neural Net or Sequence to Sequence Algorithm with attention on the user activity.

The generalized model can be built by using a Deep Neural Network by feeding the training data from Location Analyzer, Vision Analyzer, Application Context Analyzer, and Memory component and application actions, content follow-ups within the user cluster. The DNN will be learned to predict application actions such as entering search engine queries, sharing with social networks, sending an SMS message to a friend, calling a merchant, etc and content generation such as pro-actively showing interesting news items and an update from the social network.

The trained general model for the user cluster can then be pushed to the device. In an embodiment, the model manager component will initialize the general model either during the device setup or as part of the booting process.

The general model, can then be further retrained and personalized for the user. In an embodiment, this can be done by using Reinforcement Learning methods. We can model content and action recommendation as an MDP process. The aggregated user behavior updates from social networks, news articles can be the state for the user. The possible action space can be to show content recommendation, display an application action, or don’t do anything. A reward function can be correctly predicting the action at time t. We can then use Policy Leaning or Value Iteration approaches to figure out an action. To start with, a general Reinforcement Learning model can be learned offline on the user cluster, using the generalized model. The general model can then be personalized to the user by adjusting the Reinforcement Learning model to maximize explicit user interaction. The personalized user behavior model can then be persisted on a remote server using the internet. The personalized model can be used on other user devices and internet ecosystems.

In another embodiment, an End to End Neural Network using an architecture consisting of Policy Gradient Deep Reinforcement Learning on top of a Deep Neural Network (DNN). The DNN with attention can generate user behavior embeddings on the offline user cluster behavior data. The generic model than can be personalized for the user by adjusting the loss function in the Policy Gradient Deep Reinforcement Learning to predict the user actions.

In yet another embodiment, we can train a general model to do imitation learning for user clusters on the behavior sequence data. We can then apply techniques from One-Shot Learning to fine-tune user behavior.

It is to be noted that, we are proposing a different architecture for personalization and simulating user behavior from the current generation of ML models. Most of the current systems are built on the premise of a single global model for all groups of users. Personalization is done in a single global model by adding user features as an additional input to the mode. A single model for all users substantially simplifies the validation and debugging. The architecture in this disclosure builds out a single model for a user. A single model for a user gives the model more freedom to choose parameters that are applicable for that specific user. The single model can also be made complex to mimic the complex behavior and action of that user. We will remove the additional complexity of optimizing the burden on the model to optimize on all groups of users.

Behavior processor as a virtual agent for an application:

Patent Application US 15/356,512, talks about a Virtual Agent for an application/website which can talk in Natural Language based on using external API integration.  The behavior processor can also act as a virtual agent which can interact in Natural Language/Natural Speech for an application, without the application manually adding an external API service.

The behavior processor has got the application context of what the user is seeing, what the user is looking at the application, who the user is, the buttons and text in the application. The behavior process will also have access to external intelligence added by manual rules and/or derived by crawling the application. The behavior processor can also use information about the user aggregated from multiple ecosystems.

In an embodiment, the behavior processor can use the information identified in the above paragraph to answer questions about the service in the application and do actions in the application.

In an embodiment, the behavior processor can use Imitation Learning and one-shot learning approaches to execute actions in the application on behalf of the user. The behavior processor can learn from other user interactions that happen on the cloud

Behavior processor to help with Augmented Reality application:

Companies such as Flipkart, Amazon, and Walmart sell furniture, dresses, shoes and other merchandising in their Mobile eCommerce Apps. Before purchasing merchandise, the user wants to see how the furniture fits in their living room. He also wants to check, how the dress fits on him, before purchasing.

The eCommerce companies use experiences from augmented reality to increase user engagement with merchandising in their Mobile Applications. For instance, a user can choose a TV stand from the furniture category, point the camera on their Mobile Phone at their living room, move the chosen TV stand to get a physical sense of how the TV looks in the living room.

This painful experience of moving virtual object such as furniture in the Mobile App to the physical world can be improved by adding a software Virtual Agent which can interact in Natural Language to the flow. This virtual agent can be embedded within the app or can be triggered through a general voice agent on the phone such as SIRI on iPhone or Google Assistant on Google. The virtual agent can be embedded in the app using a third-party library code or be part of the application. The behavior processor described above can also act as a virtual agent for the eCommerce application.

The virtual agent can take the voice input, convert the voice to text optionally, and figure out the intent of the user. The entities associated with the user utterance can be figured out using slot filling algorithms. The bitmap of physical visual images captured by the physical camera, a textual description of the image, and the image of the object in shopping can be provided as additional context to the virtual agent. The virtual agent can use this additional context in figuring out intents and entities.

In an embodiment, the virtual agent can use Neural Module Networks to understand the Virtual Image in the application, the title, and category of the image, the Physical Context, and the Natural Language utterance. In an implementation, the Neural Module Networks can be dynamically assembled by parsing the Natural Language utterance. In another embodiment, we can train an end to end model using Reinforcement learning.

After understanding the intent using Neural Modules, we need to complete the action. An action can move the virtual object on the site to the physical environment of the user. Another example of action, can take a fish on Google Images and put it into a physical aquarium to see how the virtual fish looks in an aquarium at home.

Action sequences for the intent such as moving an object from one location to another can be configured manually for a Natural Language Intent. A Deep Neural Network can also be used to train actions from training data consisting of actions, Natural Language utterances, and scene input. In an embodiment, we can use the Deep Reinforcement Learning approach on top of Neural Modules for Natural Language Understanding, Object Detection, and Scene Understanding to execute actions.

In another embodiment, we can use Imitation Learning techniques to execute action sequences. We can use techniques borrowed from search engine rewrite to gather training data for imitation learning. For instance, let us say a user says, I want to see how an “I want to see how Guppy fish looks in my aquarium” pointing the Augmented Reality Device to his aquarium.

Let us say the behavior processor does not recognize the utterance in the context of the visual scene and says “Sorry, I can’t help you”. The user will then go to an Image Search Engine such as and search for Guppy Fish and then move Guppy Fish to the aquarium.

The behavior processor can learn from this interaction for the user cluster and apply it for future iterations down the line. This can be done by applying one-shot learning techniques on the general model, that we trained for AR applications.

Unified Model for different application scenarios:

In this disclosure, we talked about how a Behavior Processor can use application and user context to simplify user interactions.

We proposed different use cases for Behavior Processor. We also note that we proposed different DNN architectures for the Behavior processor for different use cases. We can use a Unified software component by combining different use cases. In an embodiment, we can run a simple Deep Learning classifier on the application and user context to decide which model to run. In another embodiment, we can train an end to end Neural Network on all the use cases and build a unified model to help the user in different application contexts.


In this disclosure, we propose a behavior processor on the user’s devices. The behavior processor simulates user behavior by leveraging application and user context and helps the user with different use cases using Natural Language and Vision techniques.