WO2023144690A1

WO2023144690A1 - Method and system for facilitating user conversations with agents using online promotions

Info

Publication number: WO2023144690A1
Application number: PCT/IB2023/050576
Authority: WO
Inventors: Nitin Gupta; Abhishek Ghose
Original assignee: [24]7.ai, Inc.
Priority date: 2022-01-25
Filing date: 2023-01-24
Publication date: 2023-08-03

Abstract

A method and system for facilitating user conversation with agents using online promotions to improve user experiences is disclosed. The method implemented by a system includes accessing user behavior data of a user from a database associated with the system. Further, the method includes accessing one or more promotional content based, at least in part, on the user behavior data. Further, the method includes determining a need for a conversational promotion based, at least in part, on user behavior data. The conversational promotion enables an interaction between the user and an agent of an enterprise. Upon determining the need for a conversational promotion, the method includes configuring the conversational promotion based, at least in part, on the one or more promotional content. Further, the method includes facilitating a display of the conversational promotion on an electronic device of the user.

Description

METHOD AND SYSTEM FOR FACILITATING USER CONVERSATIONS WITH AGENTS USING ONLINE PROMOTIONS

Cross-reference to related applications

This application claims priority from Indian provisional patent application 202241004309, filed on 25th January 2022, which is incorporated herein in its entirety by this reference thereto.

The present technology generally relates to improving user experiences and more particularly to facilitating user conversation with agents using online Advertisements to improve user experiences.

Background

Enterprises routinely use promotions such as Advertisements (Ads) to promote their brands, to market new product/service offerings, to announce important messages, and in general to reach out to the target audience. The enterprises may opt for a mix of digital print media promotions such as Ads in newspapers, multimedia channel content advertisements such as Ad commercials displayed in-between TV channel content, and/or Ads displayed on third-party websites. Such promotions may be displayed on third-party websites and are referred to herein as ‘online promotions’, ‘online Advertisements’, or ‘online Ads’. In an illustrative example, an online Ad may showcase a product or a service related to an enterprise to visitors visiting a third-party website (i.e. a website not associated with the enterprise associated with the online Ad) and the online Ad is configured to direct the visitors to an enterprise website subsequent to the selection of the online Ad via touch or a click input.

Currently, the online Ads are configured to be static in form, i.e. each online Ad provides limited information to lure an interested visitor into clicking the Ad so that the visitor may be directed to enterprise online channels, such as the enterprise website, where more information and/or engagement channels are available to the visitor. For example, if the visitor needs additional information after being redirected to the enterprise website, the user may fill out a form, chat with an agent or call a customer support number provided on the enterprise website. From clicking on the Ad to selecting an option to engage with an enterprise agent, is an additional cognitive step, which most users do not feel comfortable with, and as a result, even though a visitor is redirected to the enterprise channel, the enterprise is unable to convert such visitors into customers.

Accordingly, there is a need to improve promotions such as online Ads and cause the Ads to perform a function larger than merely redirecting a visitor to an enterprise channel. Further, it would be advantageous to provide a potential customer with all support upfront without requiring the potential customer to perform additional steps in seeking the desired information.

A computer-implemented method is disclosed. The method implemented by a system includes accessing user behavior data of a user from a database associated with the system. Further, the method includes accessing one or more promotional content based, at least in part, on the user behavior data. Further, the method includes determining a need for a conversational promotion based, at least in part, on user behavior data. The conversational promotion enables an interaction between the user and an agent of an enterprise. Upon determining the need for a conversational promotion, the method includes configuring the conversational promotion based, at least in part, on the one or more promotional content. Further, the method includes facilitating a display of the conversational promotion on an electronic device of the user.

A system including at least one processor and a memory having stored therein machine executable instructions is disclosed. The machine executable instructions are executed by the at least one processor, causing the system to access user behavior data of a user from a database associated with the system. Further, the system is caused to access one or more promotional content based, at least in part, on the user behavior data. Further, the system is caused to determine a need for a conversational promotion based, at least in part, on user behavior data. The conversational promotion enables an interaction between the user and an agent of an enterprise. Upon determining the need for a conversational promotion, the system is caused to configure the conversational promotion based, at least in part, on the one or more promotional content. Further, the system is caused to facilitate a display of the conversational promotion on an electronic device of the user.

A non-transitory computer-readable storage medium is disclosed. The non-transitory computer-readable storage medium includes computer-executable instructions that, when executed by at least a processor of a system, cause the system to perform a method. The method includes accessing one or more promotional content based, at least in part, on the user behavior data. Further, the method includes determining a need for a conversational promotion based, at least in part, on user behavior data. The conversational promotion enables an interaction between the user and an agent of an enterprise. Upon determining the need for a conversational promotion, the method includes configuring the conversational promotion based, at least in part, on the one or more promotional content. Further, the method includes facilitating a display of the conversational promotion on an electronic device of the user.

The advantages and features of the invention will become better understood with reference to the detailed description taken in conjunction with the accompanying drawings, wherein like elements are identified with like symbols, and in which:

Fig.1

shows an example representation of an environment in which various embodiments of the present invention may be practiced.

Fig.2

is a block diagram of a system configured to facilitate user conversations with agents using online Ads, in accordance with an embodiment of the invention.

Fig.3

shows an example representation of a conversational Ad displayed to a user on an off-domain website, in accordance with an embodiment of the invention.

Fig.4

depicts an example representation of a conversational Ad facilitating user conversation with an agent being executed on an off-domain website, in accordance with an embodiment of the invention.

Fig.5

shows a sequence flow diagram for illustrating a process flow for facilitating user conversation with an agent using conversational Ads, in accordance with an embodiment of the invention.

Fig.6

depicts a block diagram of an Advertisement network connecting enterprises to prospective customers, in accordance with an embodiment of the invention.

Fig.7

is a flow diagram of a method for facilitating user conversations with agents using conversational Ads, in accordance with an embodiment of the invention.

The drawings referred to in this description are not to be understood as being drawn to scale except if specifically noted, and such drawings are only exemplary in nature.

Detailed Description

The best and other modes for carrying out the present invention are presented in terms of the embodiments, herein depicted in FIGS. 1 to 7. The embodiments are described herein for illustrative purposes and are subject to many variations. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient but are intended to cover the application or implementation without departing from the spirit or scope of the present technology. Further, it is to be understood that the phraseology and terminology employed herein are for the purpose of the description and should not be regarded as limiting. Any heading utilized within this description is for convenience only and has no legal or limiting effect. It is noted that for the purposes of explanation, advertisements have been considered as promotions throughout the present disclosure. However, it is understood that the use of the same does not limit the scope of the present disclosure and other suitable forms of promotions can also be used to implement the various embodiments described herein.

The terms “a” and “an” herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced items.

The term ‘conversion’ as used herein primarily refers to an action of a user that may be counted when the user interacts with an advertisement (i.e., online advertisement). For example, when the user performs an action on a displayed advertisement (i.e., clicks a text advertisement or views a video advertisement) and then takes an action that is valuable to an enterprise or business, such as an online purchase, an inquiry, a chat with an agent, and the like is referred to as conversion.

shows an example representation of an environment 100 in which various embodiments of the present invention may be practiced. The environment 100 depicts the user 102 accessing a website 104 using an electronic device 106 embodied as a desktop computer. Users, such as the user 102, may access a website such as, the website 104 for a variety of reasons, such as for example, to obtain information, purchase products/services, access entertainment content, and the like. It shall be noted that the website 104 is depicted as an informational website for illustration purposes and the website 104 may correspond to a website offered by an e-commerce entity, a retailer, a news Website, or any other Website offered by a private or a public enterprise. Further, it is noted that a user may use any electronic device, such as but not limited to, a smartphone, a tablet computer, a mobile phone, a laptop computer, a personal digital assistant, a web-enabled wearable device, and the like, for accessing the website 104.

The electronic device 106 may include necessary applications, such as for example, a Web browser application to enable the user 102 to access the website 104. The website 104 may be hosted on a remote web server and the web browser application may be configured to retrieve one or more web pages associated with the website 104 via a communication network 110. Some examples of the communication network 110 may include wired networks, wireless networks, or a combination thereof. Examples of wired networks may include Ethernet, local area networks (LANs), fiber-optic cable networks, and the like. Examples of wireless networks may include cellular networks like GSM/3G/4G/CDMA based networks, wireless LANs, Bluetooth or Zigbee networks, and the like. An example of a combination of wired and wireless networks may include the Internet.

The environment 100 further includes a Promotion server 112 configured to manage and run online advertising campaigns. More specifically, enterprises employ advertising agencies for developing advertising content that is creative and appealing for prospective users, and such advertising content is stored in the Promotion server 112 and is distributed into appropriate advertising slots in at least one webpage of a website such as the website 104. To that effect, the Promotion server 112 is configured to receive online user behavior such as but not limited to, device identifier, IP address, geo-location information, browser information (e.g., cookie data, MAID), time of the day, and so forth. Additionally, the promotion server 112 may also include rich online user behavior such as access credentials (e.g., name, age, gender, nationality, e-mail identifier, registered user name, contact number, and the like), cart information, URLs, transaction information such as, payment history, call logs, chat logs and the like. The online user behavior related to user 102 may be used by the promotion server 112 to select an online Ad related to an enterprise among a plurality of online Ads. For example, the online user behavior may indicate that the user 102 has been viewing websites of different enterprises (for example, an e-commerce website and websites of enterprises manufacturing smartphones) and exploring device specifications of smartphones. As such, an online Ad presented to the user 102 may be related to a smartphone offered by an enterprise.

In many scenarios, the promotion server 112 selects an online Ad 108 based on the online user behavior and embeds the online Ad 108 in at least a part of a web page associated with the website 104. The online Ad 108 may be used for creating brand awareness, enhancing sales and purchases, and generating leads. Accordingly, online promotions such as the online Ad 108 are placed in high-visibility locations such as the top portion or side portions of a webpage. The online Ad 108 may be associated with an enterprise. The term ‘enterprise’ as used herein may refer to a corporation, an institution, a small/medium-sized company, or even a brick-and-mortar entity. For example, the enterprise may be a banking enterprise, an educational institution, a financial trading enterprise, an aviation company, a retail outlet, an e-commerce entity, or any such public or private sector enterprise. It is understood that many users may use products, services, and/or information offered by the enterprise. The existing and/or potential users of the enterprise offerings are referred to herein as ‘users’ or ‘consumers’ or ‘online users’ or ‘customers’. The environment 100 is depicted to display only one user for illustration purposes and it is understood that the promotion server 112 may be associated with a large number of users.

In , the online Ad 108 corresponds to an off-domain Ad or more specifically, the online Ad 108 is related to an offering from an enterprise ‘Kidtoonz’ is displayed on a web domain other than the web domain corresponding to the enterprise ‘Kidtoonz’. In this example representation, the online Ad 108 related to an offering from enterprise ‘Kidtoonz’ is displayed on a web domain, for example, ‘www. enterprise-earlylearning&childhood.com’. It is noted that the term ‘web domain’ and ‘website’ are used interchangeably herein. Further, it is noted that online Ads, such as the online Ad 108 may also be displayed on the websites related to the enterprise (i.e., enterprise associated with the displayed Ad). For example, the online Ad 108 may be displayed on the website of the enterprise ‘Kidtoonz’, such as for example ‘www.enterprise-kidtoonz.com’, in a similar or a different form than that depicted in the representation 100 in .

In an example scenario, a user viewing the online Ad 108 may have several questions in response to the content displayed in the online Ad 108. For example, the user 102 may wish to know what color options are available for the advertised smartphone. In another illustrative example, the user 102 may wish to know if the smartphone has a memory card slot to expand storage capacity of the smartphone. Even though the user 102 may be interested in purchasing the advertised smartphone or at least in learning more about the smartphone, the user 102 may choose to ignore the online Ad 108 due to their static nature. More specifically, such online Ads provide limited information to lure an interested user into clicking the Ad so that the user 102 may be directed to enterprise online channels, such as the enterprise website related to the Ad, where more information and/or engagement channels are available to the user 102. Moreover, if the user 102 needs additional information after being redirected to the enterprise website, the user 102 may have to fill out a form, chat with an agent or call a customer support number provided on the website, which is an additional cognitive step that may result in drop-offs reducing user conversion rates.

Various embodiments of the present technology provide a method and system that are capable of overcoming these and other obstacles and providing additional benefits. More specifically, various embodiments of the present technology disclosed herein suggest the provisioning of online promotions such as Ads that are capable of facilitating user conversation with agents related to the enterprise. More specifically, the online promotions are configured in such a manner that the user may click on the online promotion and connect to an agent to have his/her queries answered or receive additional information related to a product or service being promoted, almost instantly. As a result, the user may be more inclined to click on the promotions and in many cases purchase the promoted offering, thereby improving a user’s interaction experience as well as increasing the revenues of the enterprises. Further, the user will be able to receive product-related information and solve their queries without performing any extra steps directly from the promotion itself, thereby saving his or her time.

In an embodiment, the system 150 is configured to facilitate user conversation with agents using online promotions. In particular, the system 150 is configured to provision online promotions such as Ads to several other users so as to effectively promote an enterprise and also enhance user experience whilst providing desired assistance in a similar manner. Further, the system 150 is configured to predict the need for a bi-directional chat interaction process within an existing website through the use of one or more Artificial Intelligence (AI) or machine learning (ML) based models by analyzing user behavior data. In particular, a conversational promotion need parameter is determined via the model based, at least in part, on the user behavior data. It is noted that the conversational promotion need parameter may include one or more parameters that indicate towards a user’s need for conversational promotion.

Various embodiments of the present disclosure when implemented via the system 150 improve the effectiveness of promotions such as online Ads 108 by providing all information that the user 102 requires within the website 104 itself. Further, the queries that the user 102 has, can also be addressed without the need to redirect the user 102 to an external website such as, the enterprise website, thereby saving their time. To that effect, the system 150 provides the user 102 with a real-time dynamic chat interaction experience within the website 104. A system for facilitating user conversation with agents using online Ads is explained with reference to .

Furthermore, the environment 100 depicts that the system 150 is associated with a database 144. In an embodiment, the database 122 may be embodied within the system 150 or communicably coupled to the system 150. In another embodiment, the database 122 stores the one or more AI or ML based models. In some embodiments, the database 122 provides a storage location to the conversational content, promotional content, online Ads, user interaction data, metadata, JSON structural content, dynamic HTML, and any other data associated with the system 150.

is a block diagram of a system 150 configured to facilitate user conversations with agents using online Ads, in accordance with an embodiment of the invention.

The term ‘online promotions’ or ‘online Ad’ as used herein interchangeably primarily refers to a messaging platform, or chat platform that provision options for a prospective or existing customer to converse using natural language with an agent (i.e., an automated agent (such as Chatbots, IVRs and the like) or a human agent). The messaging or chat platform may support text and/or voice messaging. More specifically, the online Ads provide an engaging and/or interactive platform that encourages the conversion of a prospective user after meaningful interaction with the agent and is also referred to as a ‘conversational promotion’, ‘conversational Advertisement’, or ‘conversational Ad’ hereinafter. In one illustrative example, the conversational Ad may display graphic content related to a service/product provided by an enterprise along with a chat widget that enables interaction of the user with the agent.

Further, the term ‘agent’, in at least one example embodiment may refer to a customer service representative, such as a human agent, a virtual agent, chatbots, and the like trained to interact with the users for providing information, selling to them, answering their queries, addressing their concerns, and/or resolving their issues.

In an embodiment, the system 150 may be a standalone component in a remote machine connected to a communication network (for example, the network 110 explained with reference to ). In at least one embodiment, the system 150 may be embodied within a promotion server such as the promotion server 112. In some embodiments, the system 150 may be disposed of external to the promotion server and configured to be in operative communication with the promotion server. The system 150 includes at least one processor, such as a processing module 152 and a memory module 154. It is noted that although the system 150 is depicted to include only one processor, the system 150 may include more number of processors therein. In an embodiment, the memory module 154 is capable of storing machine-executable instructions. Further, the processing module 152 is capable of executing the stored machine-executable instructions. In an embodiment, the processing module 152 may be embodied as a multi-core processor, a single-core processor, or a combination of one or more multi-core processors and one or more single-core processors. For example, the processing module 152 may be embodied as one or more of various processing devices, such as a coprocessor, a microprocessor, a controller, a Digital Signal Processor (DSP), a graphics processing unit (GPU), a processing circuitry with or without an accompanying DSP, or various other processing devices including integrated circuits such as, for example, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Microcontroller Unit (MCU), a hardware accelerator, a special-purpose computer chip, or the like. In an embodiment, the processing module 152 may be configured to execute hard-coded functionality. In an embodiment, the processing module 152 is embodied as an executor of software instructions, wherein the instructions may specifically configure the processing module 152 to perform the algorithms and/or operations described herein when the instructions are executed.

The memory module 154 may be embodied as one or more volatile memory devices, one or more non-volatile memory devices, and/or a combination of one or more volatile memory devices and non-volatile memory devices. For example, the memory module 154 may be embodied as magnetic storage devices (such as hard disk drives, floppy disks, magnetic tapes, etc.), optical magnetic storage devices (e.g. magneto-optical disks), compact disc read-only memory (CD-ROM), Compact Disc Recordable (CD-R), Compact Disc Rewritable (CD-R/W), Digital Versatile Disc (DVD), Blu-ray® Disc (BD), and semiconductor memories (such as mask ROM, PROM (programmable ROM), Erasable PROM (EPROM), flash ROM, Random Access Memory (RAM), etc.). In some example embodiments, the memory module 154 may also store one or more machine learning models for predicting the likelihood of the user conversion on presenting a conversational promotion or conversational Ad.

The system 150 also includes an input/output module 156 (hereinafter referred to as ‘I/O module 156’) and a communication module 158. The I/O module 156 is configured to facilitate the provisioning of an output to a user of the system 150. The I/O module 156 may also include mechanisms configured to receive inputs from a user of the system 150. The I/O module 156 is configured to be in communication with the processing module 152 and the memory module 154. Examples of the I/O module 156 include, but are not limited to, an input interface and/or an output interface. Examples of the input interface may include but are not limited to, a keyboard, a mouse, a joystick, a keypad, a touch screen, soft keys, a microphone, and the like. Examples of the output interface may include, but are not limited to, a display such as a light-emitting diode display, a Thin-Film Transistor (TFT) display, a liquid crystal display, an Active-Matrix Organic Light-Emitting Diode (AMOLED) display, a microphone, a speaker, a ringer, a vibrator, and the like.

In an example embodiment, the processing module 152 may include I/O circuitry configured to control at least some functions of one or more elements of the I/O module 156, such as, for example, a speaker, a microphone, a display, and/or the like. The processing module 152 and/or the I/O circuitry may be configured to control one or more functions of the one or more elements of the I/O module 156 through computer program instructions, for example, software and/or firmware, stored on a memory, for example, the memory module 154, and/or the like, accessible to the processing module 152.

The communication module 158 may include several channel interfaces to receive information from a plurality of on-domain and off-domain interaction channels. It is noted that for an enterprise for which the ads are to be provisioned to the customers, the interaction channels related to the enterprise are referred to herein as ‘on-domain’ enterprise interaction channels. Some non-exhaustive examples of such interaction channels may include a Web channel (i.e. an enterprise Website), a voice channel (i.e. voice-based customer support offered by the enterprise), a chat channel (i.e. chat support offered by the enterprise), a native mobile application channel, and the like. For example, if an ad of an enterprise ABC is displayed on a Website ‘www.enterprise-abc.com’ associated with the enterprise, then the website corresponds to an ‘on-domain website’ (i.e., an on-domain enterprise interaction channel) and the Ad corresponds to an on-domain Ad. Similarly, for an enterprise for which the Ads are to be provisioned to the customers, the websites not related to the enterprise are referred to herein as ‘off-domain websites’. For example, if an Ad of a telecom-enterprise XYZ is displayed on an e-commerce website ‘www.ecommerce-enterprise.com’, then the website corresponds to an off-domain website or off-domain enterprise interaction channel and the Ad corresponds to an off-domain Ad.

As explained above, the communication module 158 may include several channel interfaces to receive information from a plurality of on-domain and off-domain interaction channels. Each interaction channel interface of the communication module 158 may be associated with a respective communication circuitry such as for example, a transceiver circuitry including antenna and other communication media interfaces to connect to a wired and/or wireless communication network. The communication circuitry associated with each channel interface may, in at least some example embodiments, enable transmission of data signals and/or reception of signals from remote network entities, such as Web servers hosting enterprise and non-enterprise Websites, promotion servers configured to display promotions on Websites, servers associated with promotion platforms configured to generate a conversational promotion or conversational Ad or even servers deployed at enterprise customer support and service centers configured to manage real-time interactions between customers and customer support representatives (also referred to as agents).

In at least some embodiments, the communication module 158 may include relevant Application Programming Interfaces (APIs) to communicate with various customer touch points, such as electronic devices associated with the customers, Websites visited by the customers, devices used by customer support representatives (for example, voice agents, chat agents, IVR systems, in-store agents, and the like) engaged by the customers and the like.

The system 150 is further depicted to include a storage module 160. The storage module 160 is any computer-operated hardware suitable for storing and/or retrieving data. In one embodiment, the storage module 160 is configured to store user activity information based on tracking user activity on a plurality of websites (such as enterprise websites), (e.g., transaction history, transaction status, cart information, payment information, etc.), information of a plurality of interaction channels (e.g., websites, mobile applications, social media, etc.) and a plurality of devices. The storage module 160 may include multiple storage units such as hard drives and/or solid-state drives in a redundant array of inexpensive disks (RAID) configuration. In some embodiments, the storage module 160 may include a storage area network (SAN) and/or a network-attached storage (NAS) system. In one embodiment, the storage module 160 may correspond to a distributed storage system, wherein individual databases are configured to store custom information, such as consumer data logs, consumer preferences, etc. It is noted that the storage module 160 in some embodiments may be embodied as a database identical to database 114 of . To that end, the database 114 may store the same data as the storage module 160

In some embodiments, the processing module 152 and/or other components of the processing module 152 may access the storage module 166 using a storage interface (not shown in ). The storage interface may include, for example, an Advanced Technology Attachment (ATA) adapter, a Serial ATA (SATA) adapter, a Small Computer System Interface (SCSI) adapter, a RAID controller, a SAN adapter, a network adapter, and/or any component providing the processing module 152 and/or the modules of the processing module 152 with access to the storage module 166.

In an embodiment, various components of the system 150, such as the processing module 152, the memory module 154, the I/O module 156, the communication module 158 and the storage module 160 are configured to communicate with each other via or through a centralized circuit system 162. The centralized circuit system 162 may be various devices configured to, among other things, provide or enable communication between the components (152 - 160) of the system 150. In certain embodiments, the centralized circuit system 162 may be a central printed circuit board (PCB) such as a motherboard, a main board, a system board, or a logic board. The centralized circuit system 162 may also, or alternatively, include other printed circuit assemblies (PCAs) or communication channel media.

It is understood that the system 150 as illustrated and hereinafter described is merely illustrative of a system that could benefit from embodiments of the invention and, therefore, should not be taken to limit the scope of the invention. It is noted that the system 150 may include fewer or more components than those depicted in . In an embodiment, the system 150 may be implemented as a platform including a mix of existing open systems, proprietary systems, and third-party systems. In another embodiment, the system 150 may be implemented completely as a platform including a set of software layers on top of existing hardware systems. In an embodiment, one or more components of the system 150 may be deployed in a web server. In another embodiment, the system 150 may be a standalone component in a remote machine connected to a communication network (such as the network 110 explained with reference to ) and capable of executing a set of instructions (sequential and/or otherwise) so as to predict the need for a concurrent digital channel to serve the user better. Moreover, the system 150 may be implemented as a centralized system, or, alternatively, the various components of the system 150 may be deployed in a distributed manner while being operatively coupled with each other. In an embodiment, one or more functionalities of the system 150 may also be embodied as a client within devices, such as users’ devices. In another embodiment, the system 150 may be a central system that is shared by or accessible to each of such devices.

The provisioning of conversational promotions by the system 150 to facilitate user conversation with an agent is hereinafter explained with reference to the provisioning of a conversational promotion to one user, for example, the user 102 explained with reference to . The term ‘conversational promotion’ and ‘conversational Ad’ are used interchangeably hereinafter. It is noted that the system 150 may be caused to serve, or more specifically, provision conversational Ads to several other users so as to effectively promote an enterprise and also enhance user experience whilst providing desired assistance in a similar manner.

In at least one example embodiment, the communication module 158 is configured to enable the system 150 to communicate with other entities, such as for example, web servers hosting and managing third-party websites, remote data gathering servers logging user activity information on various interaction channels, the promotion server 112, and the like. Communication with other entities may be realized over various types of wired or wireless networks. In at least some embodiments, the communication module 158 may include relevant application programming interfaces (APIs) to communicate with the other entities. In an example scenario, the communication module 158 may receive online user behavior related to the user 102 from remote data gathering servers tracking user activity information based on tracking user activity on a plurality of enterprise websites, a plurality of interaction channels (for example, websites, native mobile applications, social media, etc.) and a plurality of devices. Additionally, the system 150 may also receive information such as device identifier, Internet Protocol (IP) address, geo-location information, browser information, time of the day, chat logs, device identifiers, user profiles, messaging platforms, social media interactions, user device information such as, IP address of the user, location co-ordinates, device type, device operating system (OS), device browser, browser cookies, and phone number related to past user activity, and the like.

The user 102 may access a website for several reasons as described in . As already explained, the system 150 is configured to receive user activity information (i.e., online user behavior) via the communication module 158. For example, the online user behavior captured by remote data gathering servers may include information such as web pages visited, time spent on each web page, menu options accessed, drop-down options selected or clicked, mouse movements, hypertext mark-up language (HTML) links those which are clicked and those which are not clicked, focus events (for example, events during which the user has focused on a link/webpage for a more than a predetermined amount of time), non-focus events (for example, choices the user did not make from the information presented to the user (for examples, products not selected) or non-viewed content derived from scroll history of the user), touch events (for example, events involving a touch gesture on a touch-sensitive device such as a tablet), non-touch events and the like. In at least one example embodiment, the communication module 158 may be configured to receive such information from a plurality of web servers hosting the web pages associated with the website and logging information related to the user activity information on the website. In one embodiment, the online user behavior may be stored as a data or dataset (also referred to as user behavior data) corresponding to a user profile or a tracker associated with the electronic device 106 of the user 102. The system 150 can access user behavior data from the database 114 or storage module 160 associated with the system 150.

The communication module 158 is configured to forward the online user behavior to the processing module 152. In at least one example embodiment, the processing module 152 is configured to, with the content of the memory module 154, cause the system 150 to (1) determine an advertisement content (also referred to as promotional content) for the user 102, (2) predict a need for a conversational Ad (i.e., predict the likelihood of the user conversion) for the user 102 via an AI or ML model, i.e., a conversational promotion need parameter is determined based on the user behavior data via the AI or ML model (3) facilitate the display of the conversational Ad for the user, and (4) facilitate interaction between the user and an agent using the conversational Ad.

In at least some embodiments, the processing module 152 is configured to deploy machine learning models for determining the promotional content for the user 102 based on online user behavior. More specifically, products and/or services related to enterprises that may interest the user are determined based on the user's activity. To that effect, the processing module 152 may utilize sophisticated algorithms, such as for example at least one algorithm based at least on Logistic regression, Linear Regression, Naïve Bayes, Rule Engines, neural networks, Linear Discriminant Analysis, decision trees, support vector machines, k-nearest neighbor, K-means and the like, for predicting user interests and preferences. In one illustrative example, user activity information may indicate that the user 102 frequently browses smartphones on e-commerce websites, explores new models, and reads about the architecture of the new models and online user 102 may also have enquired about additional features not mentioned in the specification with an agent of the e-commerce platform. Accordingly, the machine learning model may identify the user 102 to be interested in smartphones and as such, the processing module 152 may identify one or more enterprises dealing with smartphones. It shall be noted that the one or more enterprises dealing with smartphones may have individually designed and developed advertisement contents and such advertisement contents may be stored in a promotion server such as the promotion server 112.

In some embodiments, the machine learning model is configured to monitor one or more platforms associated with one or more accounts corresponding to the user 102 to determine user activity information. The engine is then configured to generate the user interaction data based, at least in part, on the determined user activity information. In an example, the one or more platforms may include social media platforms associated with the user 102, enterprise accounts associated with the user 102, online shopping accounts associated with the user 102, and the like. Further, the machine learning models may use web scraping to determine user activity information (such as purchase history, returns, replacements, refunds, reviews, ratings, and the like). Based on the user activity information, the machine learning model may access the user interaction data. In another embodiment, user activity information is generated by tracking user activity through cookies and trackers associated with the electronic device 106 (in particular, the MAC address of the electronic device 106) of the user 102.

The provisioning of the chat interaction experience within the website 104 by the system 150 is hereinafter explained with reference to one user, such as the user 102 explained with reference to . It is noted that the system 150 may be caused to serve, or more specifically, send conversational promotions providing chat interaction experience to several other users to effectively promote an enterprise and enhance customer experience whilst providing desired assistance to the users.

Moreover, the processing module 152 has suitable logic and/or interfaces for provisioning an interface to facilitate the chat interaction experience between the user 102 and the agent (e.g., virtual agent, chatbot, human agent, etc.) within the body of the website 104 via the chat widget. The chat interaction experience is facilitated based, at least in part, on the conversational content. In an example, the user 102 can interact or chat with the agent (e.g., chatbot) regarding the offering (i.e., product or service) described in the conversational promotion. In an example, the user 102 may ask questions related to the product offered by the enterprise. In another example, the user 102 may ask additional questions related to the products or services offered by the promotion. In one non-limiting example, An AI or a ML based chatbot (i.e., automated agent) is invoked once the user 102 clicks on the chat widget and the same may interact with the user 102 to address their issues.

In one embodiment, the interface provided by the processing module 152 is configured to receive a user query in the chat widget from the electronic device 106 of the user 102. The user query is received in one or more communication formats. The one or more communication formats include text, audio, video, animation, gif, and the like.

In at least one example embodiment, the system 150 may send a request for relevant advertisement content for the user 102 to the promotion server 112 via the network 110 (shown in ). On receiving the request, the promotion server 112 is configured to serve an appropriate advertisement content to the system 150. For example, the request from the system 150 may include preferences (for example, specifications or requirements) of the user as determined from the online user behavior and the promotion server 112 may select an advertisement content among a plurality of advertisement contents (i.e., related to a plurality of enterprises) that matches with the user preferences. The plurality of advertisement contents may correspond to one or more enterprises offering products/services that may interest the user 102. The promotion server 112 may also customize the advertisement content based on the preference of the user 102.

Typically, the advertisement content may include at least a graphical content such as, for example, depicting the product/service and/or the enterprise information and promotional information related to the product/service. In some example embodiments, components of the Ads (i.e., the graphical display or the textual portion) may be customized based on user preferences. For example, insights derived from the user activity information (i.e., the online user behavior) may also indicate that the user is interested in online gaming, and as such, the graphical portion and the textual portion may be customized to amplify the gaming features in the smartphone.

In one embodiment, the ‘advertisement content’ (also referred to as the ‘conversational content’) refers to a plurality of utterances that are typically exchanged during a chat conversation between an enterprise agent (e.g., virtual agent, chatbot, human agent, etc.) and a customer (e.g., the user 102) of the enterprise. The plurality of utterances may include introductory messages, common queries, quick responses, detailed answers to queries, default messages (for example, utterances displaying options to connect with enterprise via alternate channels), promotional messages (such as sales, discounts, offers, coupons, etc.), and any related content such as URLs, videos, animated images that may supplement a response.

An example utterance provided by a customer of an enterprise selling car insurance policies during a chat interaction may be ‘What is the coverage offered by XYZ car insurance policy?’. A response provided by a chat agent (hereinafter referred to as a chatbot) to such a query may be an utterance, such as ‘We provide coverage for all damages due to accidental or non-collision damage’. Similarly, the user 102 may ask ‘What is the payment cycle for this insurance policy?’ and the chatbot may respond with an utterance ‘You may pay for this policy either on a quarterly or yearly basis’.

Simultaneously, the processing module 152 is also configured to, with the content of the memory module 154, cause the system 150 to predict a need for a conversational Ad for the user 102 based at least in part on the online user behavior. In particular, a conversational promotion need parameter based, at least in part, on the user behavior data via an AI or ML model. In at least some embodiments, the machine learning model stored in the memory module 154 may be deployed to predict the likelihood of a user conversion on being presented with the conversational Ad. More specifically, the machine learning model generates a probability score indicating a likelihood of the user conversion based at least in part on the online user behavior related to the user 102. It is understood that if the probability score is higher than a predefined threshold, then it is determined that there exists a need for the conversational Ad. In one illustrative example, user activity information (i.e., the online user behavior) may indicate that the user 102 is keen to study a Master’s degree abroad and as part of preparation may have reviewed consultant websites and interacted with two different consultant enterprises that assist students to procure a Study Visa via respective enterprise websites. In addition, the user 102 may also have accessed the ‘Help’ Section provided on the immigration country website and read the frequently asked questions (FAQ) for learning the process to procure the Study Visa. In such a scenario, the processing module 152 predicts that the user 102 is likely to convert, for example, interact with the agent and/or take the assistance of the services provided by the consultancy enterprise for immigration services.

On successfully predicting the need for the conversational Ad, the processing module 152 is configured to generate a conversational Ad for the user 102. In particular, upon determining that the conversational promotion need parameter is greater than a need threshold, the processing module 152 is configured to generate a conversational Ad for the user 102. In a non-limiting example, the need threshold may be predefined or configured by an administrator of the enterprise (not shown). More specifically, the graphical content may be integrated with an interaction section such as a chat widget to generate the conversational Ad. Prospective customers visiting the Web domains may be more inclined to click on such off-domain Ads as their queries may be instantly answered, thereby increasing the efficacy of the online Ads and improving the online experience of the customers. More specifically, the conversational Ad provisions an option for the user 102 to directly interact with an agent related to the enterprise advertising the offering without having to waste time in navigating to an enterprise website related to the conversational advertisement and again exploring myriad options presented by the enterprise website.

It shall be noted that the system 150 may display one or more conversational Ads on the same web page. For example, a conversational Ad related to a car brand (i.e., an enterprise that manufactures and sells cars) may be displayed in a right corner portion of the screen and a conversational Ad related to a streaming web series/movie may be displayed on a top portion of an off-domain website that the user 302 visits. However, the user 102 may choose a conversational Ad based on his/her preference and interest. An example of a conversational Ad presented on an off-domain website for the user is shown and explained next with reference to

shows an example representation of a conversational Ad 310 displayed for a user 302 on an off-domain website 308 (also referred to as ‘an enterprise website 308’), in accordance with an embodiment of the invention. More specifically, the example representation 300 depicts the user 302 using a web browser application 306 on a personal device 304 (exemplarily depicted to be a personal computer) of the user 302 to access one or more web pages of the enterprise website 308. It is understood that the enterprise website 308 (hereinafter referred to as ‘website 308’) may be hosted on a remote web server and the web browser application 306 may be configured to retrieve one or more web pages associated with the website 308 from the remote web server over a network such as the network 110.

As an illustrative example, a web page of the website 308 retrieved from a remote web server over the network is displayed on the display screen of the personal device 304 in the example representation 300. As can be seen, the website 308 is depicted to be a website configured to assist users with air travel reservations. In an illustrative example, the user 302 may be checking flight charges for a select few destinations for planning a trip. As explained with reference to , the communication module 158 is configured to receive online user behavior related to the user 302. In an illustrative example, the online user behavior of the user 302 may reflect that the user 302 has been browsing about various holiday destinations and as such, the user 302 may have accessed ‘travel’ websites, ‘flight booking’ websites, and ‘information’ websites (for example, providing information on places of interest in a destination). Additionally, the online user behavior may also include other information such as but not limited to, device identifier, IP address, geo-location, browser information, and the like. Further, the online user behavior may also indicate that the user 302 is a frequent traveler who has accessed travel-related content in the past sessions. Such tracking of user activity information (i.e., online user behavior) may be used to determine the advertisement content and predict a need for provisioning the advertisement content as the conversational Ad 308 for the user 302. In particular, upon determining that the conversational promotion need parameter is greater than a need threshold, the processing module 152 is configured to generate a conversational Ad for the user 102. In a non-limiting example, the need threshold may be predefined or configured by an administrator of the enterprise (not shown).

As already explained, the promotion server 112 receives a request for the advertisement content from the system 150. Accordingly, the promotion server 112 is configured to determine the advertisement content based on the online user behavior related to the user 302. In one illustrative example, the online user behavior may indicate that the user is an avid traveler and is currently planning a holiday. As such, based on destinations he has visited in the past and destinations he is exploring right now, the promotion server 112 may identify advertisement content relating to travel agencies, hotels, or booking applications in a preferred destination of the user 302. The advertisement content is forwarded to the system 150.

In an embodiment, the processing module 152 is configured to predict a need for a conversational Ad for the user 302 accessing the website 308. In general, the likelihood of the user conversion is predicted. Such prediction enables the processing module 152 to decide whether a static banner Ad or a conversational Ad has to be shown to the user 302. In particular, the processing module 152 determines conversational promotion need parameter based at least in part on the user behavior data. Further, upon determining that the conversational promotion need parameter is greater than a need threshold, the processing module 152 is configured to generate a conversational Ad for the user 102. In one illustrative example, the online user behavior related to the user 302 may indicate that the user 302 usually interacts with enterprises providing products/services before making a purchase (for example, booking a flight). As such, this indicates that the likelihood of the user conversion is high on interacting with a customer service representative (i.e., an agent) related to the enterprise displaying the advertisement. In such a scenario, the processing module 152 is configured to integrate an interaction section (for example, a chat widget) along with the advertisement content to generate the conversational Ad 310 on the off-domain website 308. In other words, the system 150 via a machine learning model, determines the conversational promotion need parameter based, at least in part, on the user behavior data. Further, upon determining that the conversational promotion need parameter is greater than a need threshold, the conversational promotion for the user is configured based, at least in part, on the one or more promotional content

The conversational Ad 310 embeds the advertisement content in form of a graphic content 312 related to the product/service offered by the advertising enterprise (i.e., the enterprise displaying the conversational Ad 310) along with an interaction section 314 (i.e., a chat widget). In this example representation, the graphic content 312 depicts a name of a resort associated with text ‘SPRING VIEW’ along with an image of a person relaxing. Further, the conversational Ad 310 also includes the text ‘DISCOVER A FABULOUS GETAWAY’. The interaction section 314 is a rolling feature displayed in at least a portion of the conversational Ad 310 that facilitates interaction with an agent (not shown in ). The interaction section 314 may be used by the user 302 for interacting with an agent related to the enterprise (i.e., the resort, Spring View) on the website 308 (i.e., an off-domain website) itself. It is noted that the conversational Ad 310 displaying the graphic content 312 of the resort along with the corresponding text is shown herein only for illustration purposes. The conversational Ad 310 may similarly include content related to several other hotels, homestays, and/or promotional content related to services (such as rental cabs, restaurants, travel services, etc.).

It shall be noted that, in some example embodiments, more than one conversational Ad may be presented to the user on the same website 308, for example, a conversational Ad related to apparel on a right side and a conversational Ad related to an electronic good on a left side of the website 308. Moreover, the same conversational Ad or different conversational Ad may be presented on each webpage for the user 302. For example, if the user 302 does not interact with a conversational Ad displayed on a web page, the system 150 may be configured to determine an alternate conversational Ad based at least on the online user behavior for the user 302.

Referring now to , in at least one example embodiment, the processing module 152 is configured to, with the content of the memory module 154, cause the system 150 to receive a selection input provided by a user in relation to the conversational Ad 310 displayed to the user 302. For example, the user 302 may provide a touch or a click input on the conversational Ad 310 shown in . In some embodiments, the selection input may be provided specifically on the portion offering assistance, such as for example, on the interaction section 314 of the conversational Ad 310 or on the conversational Ad 310.

In at least some embodiments, all components on the Web domain including the conversational Ad 310 may be associated with tags, such as JavaScript or Hypertext Markup Language (HTML) tags. The selection input on the conversational Ad 310 or the interaction section 314 may be recorded using the tags, which may be configured to generate an application programming interface (API) call. The communication module 158 of the system 300 may be configured to receive the API call indicative of the selection input provided by the user 302. The communication module 158 may be configured to communicate the receipt of the selection input to the processing module 152.

In response to the selection input provided by the user 302, in at least one example embodiment, the processing module 152 is configured to, with the content of the memory module 154, cause the system 150 to facilitate a user conversation with an agent associated with an enterprise related to the conversational Ad 310. The user conversation may be configured to provide the assistance required by the user 302. The type of engagement may be in form of a chat interaction with a human agent, a voice conversation with a human agent, a chat interaction with a virtual (i.e., automated) agent, and the like.

In some embodiments, the communication module 158 is in operative communication with servers associated with customer support centers, so as to facilitate connecting a customer to a server at a customer support center of an enterprise. The server at the customer support center may be capable of routing the customer to an appropriate human/virtual agent.

Thereafter, the user interaction may be conducted on the website 308 itself. Such instant initiation of interaction between the user 302 and the agent related to the enterprise offering the conversational Ad 310 precludes redirection to the enterprise website (i.e., website associated with the enterprise displaying the conversational Ad 310) the and results in significant time savings and sparing the hassles of navigating through myriad options presented to the user 302 on the enterprise website. An example scenario depicting the user 302 interacting with an agent via the interaction section 314 on the conversational Ad 310 is explained next with reference to .

depicts an example representation 400 of the conversational Ad 310 facilitating user conversation with an agent being executed on the off-domain website 308, in accordance with an embodiment of the invention.

As already explained, the online user behavior of the user 102 may be used to predict the need for the conversational Ad 310 (i.e., a likelihood of the user conversion on being presented a conversational Ad). Further, upon determining a high likelihood of user conversion, the conversational Ad 310 (shown in ) may be presented to the user on the website 308 and the user 302, may click on the conversational Ad 310 or the interaction section 314 (i.e., the chat widget) to request an interaction with an agent associated with the enterprise website (i.e. enterprise displaying the conversational Ad 310). For example, contents of the conversational Ad 310 (for example, graphical content depicting promotional offers, enterprise name, schemes or services) may interest the user and as such, the user 302 would prefer to know more about the products/services offered by the advertising enterprise related to the conversational Ad 310. Initiating of user interaction with an agent related to the advertising enterprise on a different enterprise medium, such as the off-domain website 308, enables the user 302 to interact with the advertising enterprise without having to waste time and effort in navigating to the advertising enterprise website and accessing options facilitated for initiating a conversation with an agent (i.e., on the advertising enterprise website) or browsing products/services. Moreover, facilitating user interaction on the off-domain website 308 provides continued access to the user 302 to the content accessed on the website 308. Further, the conversational Ad 310 also increases the advertising enterprise’s brand awareness by provisioning an option for conversion of the user.

As explained with reference to , the communication module 158 may receive the request for interaction from the user 302, in real-time. For example, when the user 302 provides a touch/click input on the conversational Ad 310 or the interaction section 314 (shown in ), the agent will initiate the interaction with the user 302 in real-time on the conversation Ad 310 itself. The agent may correspond to an automated agent and/or a human agent. In an example scenario, the user 302 may also choose to post a query for the agent related to the services offered by the enterprise related to the conversational ad 310. For example, the user 302 may enquire the agent about facilities offered in each room type and charges for each room type as shown by the conversation in . The user 302 may use natural language to converse with the agents.

Referring now to , in at least one example embodiment, the processing module 152 is also configured to, with the content of the memory module 154, cause the system 150 to predict an intent from the user interaction and utilize the predicted intent along with information such as user presence/attention information, location information, query timing information, etc., to determine the most appropriate response to the user query in the conversational Ad 310. Further, the automated agent may be caused to provide the most appropriate response to the user query on the conversational Ad 310 itself.

In some example embodiments, the processing module 152 is configured to predict a persona type of the user 302 on a selected business metric. To that effect, a number of customer persona classification frameworks or taxonomies capable of facilitating segregation of customers based on customer personas types may be stored in the memory module 154. The predicted persona type is further associated with a value trait, characteristic of the most appropriate set of attributes that a persona type is most likely to value or appreciate. These value traits may be collated from surveys, behavioral studies, design of experiments, explicitly mentioned by customers in their interactions, inferred or predicted from interaction history. An example of a persona type may be a “convenience customer” which corresponds to a group of customers characterized by the behavioral trait that they are focused and are looking for expeditious delivery of service. Such a persona type would value attributes like knowledge, focus & speed, or terseness from an agent (for example, a customer care representative or human agent), they are interacting with, in order to accomplish their goal. Therefore, an association is made with a value trait “knowledge, focus & speed” of agents to determine a matching persona type. The association of a value trait may further be made from customer surveys, agent surveys, association mining, predictive models on structured and unstructured chat data, design of experiments, etc.

In at least one example embodiment, the processing module 152 is configured to, with the content of the memory module 154, cause the system 150 to route a chat conversation to an agent with the best matching persona type. More specifically, upon receiving a user request to initiate an interaction with an agent, the processing module 152 facilitates connecting the user 302 with an agent that matches the persona type of the user 302 such that they aid in accomplishment of the goal of the persona and are suited to satisfy the value trait that the persona is associated with.

As shown in , the agent related to the conversational Ad 310 may initiate the interaction by asking the user 302 if the user 302 intends to book a room between 13th June and 15th June at Spring View, California. Such a personalized experience provisioned to the user 302 improves a user browsing experience. The user 302 may then respond in affirmative and request additional information on available room types and tariffs. As already explained, the processing module 152 may be configured to predict the next best action for the user 302 based on the predicted intent, and accordingly, the agent provisions a response with a brochure depicting tariffs and inclusions for different room types available in the hotel. In some example embodiments, if the query is more specific or unclear to the automated agent, the user interaction may be transferred to a human agent.

shows a sequence flow diagram for illustrating a process flow 500 associated with facilitating user conversation with an agent using online Advertisements, in accordance with an embodiment of the invention. The process flow 500 starts at 502.

At 510 of the process flow 500, a user 502 browses a website (also referred to herein as an off-domain website) using an electronic device 504. In an illustrative example, the user 502 may be accessing news-related content on the website for collecting information on current political affairs of the world.

At 512 of the process flow 500, a remote data gathering server 506 is configured to track online user behavior related to the user 502.

At 514 of the process flow 500, the remote data gathering server 506 forwards the online user behavior to a system such as, the system 150 explained with reference to FIGS. 1 to 4.

At 516 of the process flow 500, the system 150 is configured to send a request for advertisement content to a promotion server 508. The request includes online user behavior related to the user 502.

At 518 of the process flow 500, the promotion server 508 selects a relevant Ad content for the user based on the online user behavior. In one illustrative example, the promotion server 508 may determine that the user 502 may be interested in fortnight magazines that provide more information on political affairs. In another illustrative example, the promotion server 508 may identify that books on international politics, for example, political ideologies, and policy making may kindle the interest of the user 502 and accordingly select, Ad contents related to one or more bookstores that deal with books on international politics.

At 520 of the process flow 500, the promotion server 508 sends the advertisement content to the system 150.

At 522 of the process flow 500, the system 150 is configured to predict a need for a conversational Ad based at least in part on the online user behavior. In particular, the system 150 determines conversational promotion need parameter based at least in part on the user behavior data. More specifically, the system 150 determines the likelihood of conversion of the user 502 (for example, the user interacting with an enterprise) when the conversational Ad is presented to the user 502. In an illustrative example, the online user behavior related to the user 502 indicates that the user 502 is interested in online gaming and usually gathers information related to an online game, for example, the nature of the game, number of players, number of levels, hardware requirements, software compatibility, monetary benefits (i.e., prize money), and the like, before subscribing for an online gaming platform. Moreover, the online user behavior may also indicate that the user 502 has interacted with agents prior to past purchases. As such, the system 150 interprets that the user 502 is usually a potential user for conversion and accordingly, the system 150 may predict a conversational Ad, for example, an Ad that includes an option for the user to interact with an agent related to an online gaming platform. In at least one example embodiment, a machine learning model may be deployed for predicting the likelihood of user conversion on being presented with the conversational Ad.

At 524 of the process flow 500, the system 150 is configured to generate a conversational Ad based on the successful outcome of the prediction. In particular, upon determining that the conversational promotion need parameter is greater than a need threshold, the system 150 is configured to generate a conversational Ad for the user 102.More specifically, an interaction section is integrated along with the advertisement content to generate the conversational Ad. An example of generating the conversational Ad is shown and explained with reference to .

At 526 of the process flow 500, the system 150 is configured to facilitate display of the conversational Ad on the off-domain website being viewed on the electronic device 504.

At 528 of the process flow 500, the user 502 may initiate an interaction on the conversational Ad. For example, if the user 502 finds the conversational Ad to be interesting and/or aligned with the user's preference, he may initiate the interaction (for example, provide a touch/click input on the interaction section or the conversational Ad) with an agent (i.e., a customer service representative providing support services) related to the advertising enterprise for resolving queries or answering inquiries about products/services via the conversational Ad. For example, the user 502 may enquire the agent about various subscription plans related to the gaming platform. An example of the conversational Ad is shown and explained with reference to FIGS. 3 and 4. Thus, the conversational Ad facilitates an interaction section between the user 102 and an agent.

At 530 of the process flow 500, the system 150 manages the conversation between the user 502 and the agent. The process flow 500 ends at 530.

It should be noted that in one embodiment, the determination of the conversational promotion is performed by generating a probability score indicating a chance for conversion with the user based, at least in part, on the user behavior data and predicting the need for the conversational promotion based on the probability score is higher than a predefined threshold. In particular, the conversational promotion need parameter is determined based, at least in part, on the probability score being higher than a predefined threshold.

depicts a block diagram of an Advertisement network 600 connecting enterprises to prospective customers, in accordance with an embodiment. The Advertisement network 600 includes an Ad exchange 602 (hereinafter referred to as Ad exchange 602) including a demand side platform (DSP) 604 and a supply side platform (SSP) 606. The DSP 604 is configured to be in communication with a plurality of advertising agencies, such as an advertising agency 608, to receive bids for Ads on behalf of advertisers (i.e. enterprises), such as the advertiser 610. The advertisers along with advertising agencies and the DSP 604 configure a buy side component of the Advertisement network 600.

It is understood that enterprises wishing to engage with prospective customers may wish to advertise using both on-domain advertising and off-domain advertising. Accordingly, the enterprises (also interchangeably referred to herein as advertisers) may contract advertising agencies to generate creative advertisement content. In one illustrative example, 2-3 different advertisement contents may be generated for an enterprise to cater to different customers. Such creative advertisement content is stored in the Advertisement server 612 or Ad server 612 (similar to the promotion server explained earlier in the present disclosure). The Advertisement agencies also referred to herein as ‘Ad agencies’ may scout for possible options for placing the creative Ads and select the most optimal options, such as for example available Ad space on popular web domains, such as those related to web search engine service providing Websites, e-commerce Websites, popular blogs, popular news sites etc. Typically, many advertisers seek to place Ads on limited available Ad space on such domains.

The SSP 606 of the Ad exchange 602 is further configured to be in communication with the Advertisement server 612, which in turn is configured to display the Ads on publisher Websites, such as the Web search engine service providing Websites, e-commerce Websites, popular blogs, popular new sites, etc. so as to be viewed by prospective customers visiting these Websites. The publisher Websites and the prospective customers are exemplarily depicted using a representative publisher Website 614 and a representative customer 616 in . The Ad server 612 along with publisher Website 614, the customer 616 and the SSP 606 configures a sell side component of the Advertisement network 600.

The Advertisement network 600 further includes the system 150 explained with reference to . The system 150 is configured to be in communication with the third-party data gathering servers 652 tracking user activity (i.e., user online behavior) to generate user activity information, existing and potential customers, such as the customer 616, the advertising agencies, such as the advertising agency 608, the Ad server 612 and the Ad exchange 602. The system 150 includes a plurality of channel interfaces in the communication module 158 (not shown in ), which facilitates communication with such remote entities over a communication network, such as the network 110 explained with reference to . The system 150 is configured to predict the need for a conversational Ad based on the online user behavior by determining a conversational promotion need parameter based, at least in part, on the user behavior data. For example, if the online user behavior related to the customer 616 indicates that the customer 616 usually interacts with automated agents on enterprise websites for assistance before purchasing a product, there is a high likelihood that the customer 616 may be convinced to make a purchase when he/she interacts with the agent.

In at least one example embodiment, based on the prediction, the system 150 is configured to facilitate display of a conversational Ad that facilitates user conversations with agents. In particular, upon determining that the conversational promotion need parameter is greater than a need threshold. More specifically, the system 150 is configured to integrate a chat widget, such as the interaction section 314 in the conversational Ad 310 shown in . Prospective customers viewing such conversational Ads may be more inclined to click on such conversational Ads as their queries may be instantly answered, thereby increasing the efficacy of the Ads and improving the online experience of the customers. In some example embodiments, the system 150 is configured to identify a persona type of the user and connect the user with an agent based on a matching persona type. The provisioning of Ads is further explained with reference to an illustrative example below.

In an example scenario, a prospective customer wishing to purchase a digital camera may visit an e-commerce website to explore different models and further individually look up different enterprise websites to learn about specifications (for example, megapixel range, image quality, zoom capability, etc.). Based on user activity information generated by tracking user activity over multiple sessions and other information collated, such as device type, operating system type, geography, and other third-party data, the system 150 may predict the need for a conversational Ad. On successfully predicting the need for the conversational Ad, the system 150 is configured to integrate the advertisement content received from the Ad server 612 with a chat widget to configure the conversational Ad for the customer 616. The customer 616 is shown the conversational Ad on the appropriate ad slot by the system 150. The customer 616 clicks on the conversational Ad and the customer 616 is connected with an agent. Further, a persona type (for example, a discount seeker) of the customer 616 may be determined to connect with a matching agent (i.e., automated agent or human agent). The agent is trained to answer customer queries related to cameras and the agent is further configured to help the customer 616 complete the purchase transaction.

A method for provisioning of online Ads to customer for facilitating user conversation is explained with reference to . It should be noted that the conversational Ad and conversational promotion are interchangeably used, and similarly, the advertisement content and promotional content are interchangeably used in .

is a flow diagram of an example method 700 for facilitating user conversations with agents using online Ads, in accordance with an embodiment of the invention. The method 700 depicted in the flow diagram may be executed by, for example, the system 150 explained with reference to FIGS. 1 to 6. Operations of the flowchart, and combinations of operation in the flowchart, may be implemented by, for example, hardware, firmware, a processor, circuitry, and/or a different device associated with the execution of software that includes one or more computer program instructions. The operations of the method 700 are described herein with help of the system 150. It is noted that, the operations of the method 700 can be described and/or practiced by using a system other than the system 150. The method 700 starts at operation 702.

At operation 702, the method 700 includes accessing, by a system, user behavior data of a user from a database associated with the system. In other words, the online user behavior (also referred as user behavior data) related to a user 102 is accessed from database 114 by a system such as the system 150 explained with reference to FIGS. 1 to 6. As explained with reference to , the user may be browsing content online and the online user behavior may be tracked and collected by remote data gathering servers logging user activity, and web servers hosting and managing third-party websites.

At operation 704 of the method 700 includes accessing, by the system, one or more promotional content based, at least in part, on the user behavior data. In particular, the one or more promotional content is accessed from a promotion server such as the promotion server 112. For example, if the user is browsing entertainment content related to a regional language, the system may identify an Ad related to an OTT platform that provides entertainment content in the regional language of the user. Accordingly, the system may also customize the Ad content based on the online user behavior, for example, the advertisement content may include promotional offers on subscription plans based on the spending behavior of user (i.e., determined from historical data).

At operation 706, the method 700 includes, determining, by the system, , a need for a conversational promotion based, at least in part, on the user behavior data. Herein, the conversational promotion enables an interaction between the user and an agent of an enterprise. In other words, the system 150 determines a need for a conversational Ad based, at least in part, on the online user behavior. More specifically, the probability of a user conversion when presented with the conversational ad is determined. In at least one example embodiment, an AI or ML model may be deployed for predicting the likelihood of user conversion on being presented with the conversational promotion.

At operation 708, the method 700 includes, upon determining the need for the conversational promotion, configuring, by the system, the conversational promotion based, at least in part, on the one or more promotional content. In a non-limiting example, the need threshold is configured by an administrator of the enterprise. In other words, a conversational Ad is configured for the user upon successfully determining the need for the conversational Ad. More specifically, the system 150 integrates an interaction section (i.e., a chat widget) with the relevant advertisement content (received from the Ad server) to generate the conversational Ad. The chat widget is capable of facilitating a chat interaction with an agent of the enterprise promoting products/services via the conversational Ad.

At operation 710, the method 700 includes facilitating, by the system, a display of the conversational promotion on an electronic device of the user. In some scenarios, a display of the conversational Ad is facilitated on at least a portion of an off-domain website on the electronic device 106 of the user 102. The conversational Ad is an interactive online Ad and the user, such as the user 102 may click on the chat widget or the conversational Ad to request an interaction with an agent (i.e. request an interaction with the advertising enterprise). Further, the user may request information, make inquiries, or request suggestions or recommendations regarding products/services offered by the advertising enterprise using natural language. For example, the user may request charges per month for viewing regional content. The system 150 determines that the user’s intent is to understand different subscription plans for subscribing to streaming content and accordingly, provides sufficient information (i.e., various subscription plans, promotional offers, and contents offered by each subscription plan) for the user. The facilitation of the conversational Ad for the user, using prediction techniques (employing information such as the online user behavior), precludes the need for the user to be redirected or navigated to the advertising enterprises’ website, thereby saving time and improving a quality of interaction experience for the user.

Various embodiments disclosed herein provide numerous advantages. More specifically, the embodiments disclosed herein suggest techniques for providing users with a chat interaction experience within the website. Such seamless interaction within the website increases the effectiveness of promotional content by providing all information that a user 102 requires within the website itself. Further, the user 102 may address any queries that they have without the need to redirect to an external website, such as the enterprise website, thus reducing drop-offs and enhancing user experience. Moreover, such chat interactions provided within the website result in significant time savings by saving the user from the hassle of navigating through a myriad of options that may be presented to a customer on the enterprise website and in turn increase the engagement level of the users.

Although the present invention has been described with reference to specific exemplary embodiments, it is noted that various modifications and changes may be made to these embodiments without departing from the broad spirit and scope of the present invention. For example, the various operations, blocks, etc., of the system 150 described herein may be enabled and operated using hardware circuitry (for example, Complementary Metal Oxide Semiconductor (CMOS) based logic circuitry), firmware, software, and/or any combination of hardware, firmware, and/or software (for example, embodied in a machine-readable medium). For example, the systems and methods may be embodied using transistors, logic gates, and electrical circuits (for example, Application Specific Integrated Circuit (ASIC) circuitry and/or in Digital Signal Processor (DSP) circuitry).

Particularly, the system 150 and its various components such as the processing module 152, the memory module 154, the I/O module 156, and the communication module 158 may be enabled using software and/or using transistors, logic gates, and electrical circuits (for example, integrated circuit circuitry such as ASIC circuitry). Various embodiments of the present invention may include one or more computer programs stored or otherwise embodied on a computer-readable medium, wherein the computer programs are configured to cause a processor or the computer to perform one or more operations or methods (for example, the method explained herein with reference to ). A computer-readable medium storing, embodying, or encoded with a computer program, or similar language, may be embodied as a tangible data storage device storing one or more software programs that are configured to cause a processor or the computer to perform one or more operations. In some embodiments, the computer programs may be provided to a computer using any type of transitory computer-readable media. Examples of transitory computer-readable media include electric signals, optical signals, and the like. Transitory computer-readable media can provide the program to a computer via a wired communication line (e.g., electric wires, and optical fibers) or a wireless communication line.

The foregoing descriptions of specific embodiments of the present technology have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present technology to the precise forms disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to best explain the principles of the present technology and its practical application, thereby enabling others skilled in the art to best utilize the present technology and various embodiments with various modifications as are suited to the particular use contemplated.

Claims

A computer-implemented method, comprising:
accessing, by a system, user behavior data of a user from a database associated with the system;
accessing, by the system, one or more promotional content based, at least in part, on the user behavior data;
determining, by the system, a need for a conversational promotion based, at least in part, on the user behavior data, wherein the conversational promotion enables an interaction between the user and an agent of an enterprise;
upon determining the need for the conversational promotion, configuring, by the system, the conversational promotion based, at least in part, on the one or more promotional content; and
facilitating, by the system, a display of the conversational promotion on an electronic device of the user.
The computer-implemented method of claim 1, wherein the user behavior data includes user activity information of the user on a plurality of websites, information of a plurality of interaction channels and a plurality of devices, the user behavior data comprising at least a device identifier, Internet Protocol (IP) address, geo-location information, browser information, time of the day, chat logs, user profiles, messaging platforms, social media interactions, and user device information.
The computer-implemented method of claim 1, wherein accessing the one or more promotional content, further comprises:
determining, by the system, a user preference of the user based, at least in part, on the user behavior data;
requesting, by the system, the one or more promotional content from a promotion server based, at least in part, on the user preference; and
receiving, by the system, the one or more promotional content from the promotion server.
The computer-implemented method of claim 1, wherein determining the need for the conversational promotion, comprises:
determining, by the system via a machine learning model, a probability score based, at least in part, on the user behavior data, the probability score indicating a likelihood of the conversational promotion being required by the user; and
determining, by the system, the need for the conversational promotion based, at least in part, on the probability score being higher than a predefined threshold.
The computer-implemented method of claim 1, comprising:
receiving, by the system, a user request to initiate in interaction with the agent;
determining, by the system via a machine learning model, a persona type of the user based, at least in part, on the user behavior data; and
selecting, by the system, the agent based, at least in part, on the persona type of the user.
The computer-implemented method of claim 5, wherein the machine learning model comprises at least one algorithm based at least on, logistic regression, linear regression, Naïve Bayes, rule engines, neural networks, linear discriminant analysis, decision trees, support vector machines, k-nearest neighbor and K-means.
The computer-implemented method of claim 1, wherein configuring the conversational promotion, comprises:
generating, by the system, graphical content based, at least in part, on the one or more promotional content;
integrating, by the system, an interaction section with the graphical content, the interaction section being configured to enable the interaction between the user and the agent; and
facilitating, by the system, an option in the interaction section for the user to interact with the agent.
The computer-implemented method of claim 7, wherein the interaction section is a chat widget.
The computer-implemented method of claim 1, wherein the agent comprises at least one of a human agent and an automated agent.
A system, the system comprising:
at least one processor; and
a memory having stored therein machine executable instructions, that when executed by the at least one processor, cause the system, at least in part, to:
access user behavior data of a user from a database associated with the system;
access one or more promotional content based, at least in part, on the user behavior data;
determine a need for a conversational promotion based, at least in part, on the user behavior data, wherein the conversational promotion enables an interaction between the user and an agent of an enterprise;
upon determining the need for the conversational promotion, configure the conversational promotion based, at least in part, on the one or more promotional content; and
facilitate a display of the conversational promotion on an electronic device of the user.
The system of claim 10, wherein the user behavior data includes user activity information of the user on a plurality of websites, information of a plurality of interaction channels and a plurality of devices, the user behavior data comprising at least a device identifier, Internet Protocol (IP) address, geo-location information, browser information, time of the day, chat logs, user profiles, messaging platforms, social media interactions, and user device information.
The system of claim 10, wherein for accessing the one or more promotional content, the system is further caused to:
determine a user preference of the user based, at least in part, on the user behavior data;
request the one or more promotional content from a promotion server based, at least in part, on the user preference; and
receive the one or more promotional content from the promotion server.
The system of claim 10, wherein for determining the need for the conversational promotion, further causes the system to:
determine via a machine learning model, a probability score based, at least in part, on the user behavior data, the probability score indicating a likelihood of the conversational promotion being required by the user; and
determine the need for the conversational promotion based, at least in part, on the probability score being higher than a predefined threshold.
The system of claim 10, wherein the system is further caused to:
receive a user request to initiate an interaction with the agent;
determine via a machine learning model, a persona type of the user based, at least in part, on the user behavior data; and
select the agent based, at least in part, on the persona type of the user.
The system of claim 14, wherein the machine learning model comprises at least one algorithm based at least on, logistic regression, linear regression, Naïve Bayes, rule engines, neural networks, linear discriminant analysis, decision trees, support vector machines, k-nearest neighbor and K-means.
The system of claim 10, wherein for configuring the conversational promotion, the system is further caused to:
generate graphical content based, at least in part, on the one or more promotional content;
integrate an interaction section with the graphical content, the interaction section being configured to enable the interaction between the user and the agent; and
facilitate an option in the interaction section for the user to interact with the agent.
The system of claim 16, wherein the interaction section is a chat widget.
The system of claim 10, wherein the agent comprises at least one of a human agent and an automated agent.
A non-transitory computer-readable storage medium comprising computer-executable instructions that, when executed by at least a processor of a system, cause the system to perform a method comprising:
accessing, by the system, user behavior data of a user from a database associated with the system;
accessing, by the system, one or more promotional content based, at least in part, on the user behavior data;
determining, by the system, a need for a conversational promotion based, at least in part, on the user behavior data, wherein the conversational promotion enables an interaction between the user and an agent of an enterprise;
upon determining the need for the conversational promotion, configuring, by the system, the conversational promotion based, at least in part, on the one or more promotional content; and
facilitating, by the system, a display of the conversational promotion on an electronic device of the user.
The non-transitory computer-readable storage medium as claimed in claim 19, wherein the user behavior data includes user activity information of the user on a plurality of websites, information of a plurality of interaction channels and a plurality of devices, the user behavior data comprising at least a device identifier, Internet Protocol (IP) address, geo-location information, browser information, time of the day, chat logs, user profiles, messaging platforms, social media interactions, and user device information.