System and method for generating interactive response for computing device

Abstract

To provide a system and method for generating one or more interactive responses for a computing device [220].SOLUTION: A system comprises at least one processing unit [202] connected to a memory [208]. The method comprises the steps of: generating one or more prompts to be displayed at a computing device [220]; thereafter, receiving in real time one or more input queries from the at least one computing device [220]; and identifying one or more interactive attributes based on the one or more input queries and the one or more prompts. Lastly, one or more responses are generated to the one or more input queries and displayed at a display unit [224] of the at least one computing device [220].SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The invention of this disclosure relates to the field of interactive user engagement on computing devices, and more particularly to generating interactive responses for computing devices such as living room devices. [Background technology]

[0002] The following discussion of related art is intended to provide background information related to the field of the present disclosure. This section may include some aspects of the art that may be related to various features of the present disclosure. However, it should be understood that this section is not intended as an admission of prior art, but rather is intended solely to enhance the reader's understanding of the general field of the present invention.

[0003] Recent advances in generative artificial intelligence (AI) techniques have paved the way for the introduction of AI into many areas of consumer electronics, such as mobile phones, exploration and learning, automated workflows, etc. However, current media devices of the prior art have yet to take advantage of the integration of AI with other user engagement technologies to create active and interactive forms of content consumption.

[0004] Interactive television (ITV) refers to technologies that engage viewers with television content and provide two-way communication between viewers and their TVs. ITV also offers a variety of additional features, including the ability to participate in polls, access video-on-demand services, and utilize electronic program guides. ITV is based on artificial intelligence (AI) technology and represents a breakthrough in the field of television entertainment. Traditional television is a one-way communication medium in which viewers passively consume content without active participation. However, the integration of AI technology into television platforms provides viewers with a more interactive and engaging experience.

[0005] For example, television, currently one of the most popular and commonly used devices for media consumption, only offers passive forms of user interaction with on-screen content. This interaction can be related to basic actions such as liking or disliking content available on a media platform, or the ability to view viewing metrics or other trends related to a piece of content. Despite advances in ITV, its current state is unable to provide viewers with an engaging, two-way conversational experience. Although many types of ITV are available on the market, viewers still cannot effectively interact with TV content because ITV systems are unable to properly understand and respond to the diverse queries and comments provided by viewers in real time. Furthermore, currently available ITV systems are also unable to handle dynamic and unpredictable conversational scenarios. Furthermore, content presented on ITV is diverse and constantly changing in nature, ranging from news updates to sporting events to scripted dramas. As a result, currently available ITV systems also struggle to keep up with the rapid flow of information and coordinate their responses, resulting in disjointed and unsatisfying interactions for viewers. One key challenge facing ITV is ensuring effective communication across multiple languages. As television audiences become increasingly diverse, accommodating different languages ​​and dialects becomes crucial to providing an inclusive and accessible experience for all viewers.

[0006] Some conventional solutions to the problem of lack of user engagement and interactivity with content involve integrating basic chatbots or assistants into media devices. However, these solutions are limited by their own set of drawbacks. For example, these capabilities are often only available in a limited set of languages ​​and may therefore not be accessible to a diverse range of individuals. Furthermore, the functionality of these chatbots or assistants is limited to IoT control of connected appliances or automating the most basic tasks, such as play, pause, and volume control, which are often unrelated to the actual on-screen content itself. Furthermore, currently available ITV systems often overlook the crucial aspect of multilingual support when addressing user inquiries. This oversight leads to various instances of misinterpretation or misunderstanding, which is particularly evident when users with diverse accents attempt to engage with the ITV platform. The lack of accent support poses a significant challenge, as speech recognition struggles to accurately decipher commands or queries expressed in nonstandard accents, causing user frustration and reduced usability. This gap in multilingual support not only hinders ITV's outreach but also undermines overall user satisfaction and engagement levels.

[0007] Therefore, there is a need in the art for systems and methods that may be able to leverage technological advances in the context of user engagement technologies to facilitate active interaction between users of media devices and on-screen content. Summary of the Invention [Problem to be solved by the invention]

[0008] This section is provided to introduce in a simplified form some aspects of the disclosure that are further described below in the Detailed Description. This Summary is not intended to identify key features or scope of the claimed subject matter.

[0009] In order to overcome at least some of the problems of the known solutions provided in the previous section, it is an object of the present disclosure to significantly reduce the limitations and / or drawbacks of the prior art described herein above.

[0010] Another object of the present disclosure is to increase user engagement and interactivity with on-screen content on media devices.

[0011] It is yet another object of the present disclosure to increase accessibility to content on media devices through real-time multilingual translation and captioning support.

[0012] It is yet another object of the present invention to provide a system and method for maintaining contextual language preference based engagement with an audience and providing contextual conversational interactivity.

[0013] It is yet another object of the present disclosure to provide systems and methods that incorporate one or more artificial intelligence (AI)-based assistant features that improve user engagement and cater to individual user interests.

[0014] It is yet another object of the present invention to provide a system and method that integrates one or more advanced AI models to enhance engagement with content, thereby transforming the experience from passive viewing to active engagement. [Means for solving the problem]

[0015] This section is provided to introduce in a simplified form some aspects of the disclosure that are further described below in the Detailed Description. This Summary is not intended to identify key features or scope of the claimed subject matter.

[0016] One aspect of the present disclosure relates to a method for generating one or more interactive responses for at least one computing device. The method includes generating, by a processing unit, one or more prompts for the at least one computing device. The method further includes displaying, by the processing unit, the one or more prompts on a display unit of the at least one computing device. Thereafter, the method includes receiving, by the processing unit, one or more input queries in real time from the at least one computing device. The method further includes identifying, by the processing unit, one or more interactivity attributes based on one of the one or more input queries and the one or more prompts, and then dynamically generating, by the processing unit, one or more responses to the one or more input queries based on the one or more attributes. Thereafter, the method includes displaying, by the processing unit, the one or more responses on the display unit of the at least one computing device.

[0017] In an exemplary aspect of the present disclosure, the method further includes displaying one or more prompts in one or more languages ​​on a display unit of the at least one computing device.

[0018] In an exemplary aspect of the present disclosure, the method further includes generating one or more prompts based on at least one of user preferences and one or more pieces of content being presented on a display unit of the at least one computing device.

[0019] In an exemplary aspect of the present disclosure, the method further includes receiving, at the processing unit, from the at least one computing device, a selection from one or more prompts displayed on a display unit of the at least one computing device, wherein the one or more attributes are identified based on an analysis of the received selection for the one or more prompts.

[0020] In an example aspect of the present disclosure, the one or more interactivity attributes may include language, accent, and one or more tasks associated with one or more input queries.

[0021] In an exemplary aspect of the present disclosure, the method further includes transmitting, by the processing unit, the one or more interactivity attributes to an intelligent dialogue unit connected with the multilingual repository, wherein the intelligent dialogue unit generates one or more responses.

[0022] Another aspect of the present disclosure relates to a system for generating interactive responses for at least one computing device, the system comprising: a processing unit configured to generate one or more prompts for the at least one computing device and display the one or more prompts on a display unit of the at least one computing device. The processing unit is further configured to receive one or more input queries from the at least one computing device. The processing unit is further configured to identify one or more interactivity attributes based on one of the one or more input queries and the one or more prompts, and then dynamically generate one or more responses to the one or more input queries based on the one or more attributes. Additionally, the processing unit is further configured to display the one or more responses on the display unit of the at least one computing device.

[0023] Yet another aspect of the present disclosure may relate to a non-transitory computer-readable storage medium storing instructions for generating interactive responses for at least one computing device, the instructions including executable code that, when executed by one or more units of a system, causes a processing unit of the system to generate one or more prompts for the at least one computing device and display the one or more prompts on a display unit of the at least one computing device. The instructions, when executed by the system, further cause the processing unit of the system to receive one or more input queries from the at least one computing device. The instructions, when executed by the system, further cause the processing unit of the system to identify one or more interactivity attributes based on one of the one or more input queries and the one or more prompts, and then dynamically generate one or more responses to the one or more input queries based on the one or more attributes. Additionally, the instructions, when executed by the system, further cause the processing unit of the system to display the one or more responses on the display unit of the at least one computing device.

[0024] The accompanying drawings, which are incorporated herein and constitute a part of this disclosure, depict exemplary embodiments of the disclosed method and system, in which like reference numerals refer to the same parts throughout the different drawings. The components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Additionally, the embodiments shown in the figures should not be construed as limiting the present disclosure, and possible variations of the method and system according to the present disclosure are shown herein to highlight the benefits of the present disclosure. It will be appreciated by those skilled in the art that the disclosure of such drawings includes disclosure of electrical components or circuits commonly used to implement such components. [Brief explanation of the drawings]

[0025] [Figure 1] FIG. 1 illustrates a method for generating one or more interactive responses for at least one computing device, according to an exemplary implementation of the present disclosure. [Figure 2] FIG. 1 is a high-level functional block diagram of a system for generating one or more interactive responses, according to an example implementation of the present disclosure. [Figure 3] FIG. 1 is a high-level block diagram for processing one or more input queries in an intelligent dialogue unit for generating one or more interactive responses, according to an example implementation of the present disclosure. [Figure 4A] FIG. 10 illustrates the display of one or more prompts overlaid on a portion of content being displayed on a user's computing device, according to an exemplary implementation of the present disclosure. [Figure 4B] FIG. 1 illustrates a conversational interaction between a user and an intelligent dialogue service based on selecting one or more prompts, receiving one or more input queries, and generating one or more responses, in accordance with an exemplary implementation of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0026] In the following description, for purposes of explanation, various specific details are set forth to provide a thorough understanding of embodiments of the present disclosure. However, it will be apparent that embodiments of the present disclosure may be practiced without these specific details. Some features described below may each be used independently of each other or with any combination of other features. Individual features may not address any of the problems discussed above, or may address only some of the problems discussed above.

[0027] The following description provides exemplary embodiments only and is not intended to limit the scope, applicability, or configuration of the present disclosure. Rather, the following description of exemplary embodiments provides those skilled in the art with an enabling description for implementing the exemplary embodiments. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the present disclosure as described.

[0028] Also, it should be noted that particular embodiments may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. While a flowchart may describe operations as a sequential process, many of the operations may be performed in parallel or simultaneously. Additionally, the order of operations may be rearranged. A process is terminated when its operations are completed, but may have additional steps not included in the diagram.

[0029] The words "exemplary" and / or "illustrative" are used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. Additionally, any aspect or design described herein as "exemplary" and / or "illustrative" should not necessarily be construed as preferred or advantageous over other aspects or designs, nor is it intended to exclude equivalent exemplary structures and techniques known to those skilled in the art. Furthermore, to the extent that the terms "includes," "has," "contains," and other similar terms are used in either the detailed description or the claims, such terms are intended to be inclusive, similar to the open transitional term "comprising," without excluding any additional or other elements.

[0030] The presently disclosed invention relates to a solution for generating interactive responses for at least one computing device to enhance a user's engagement and interactivity with on-screen content. The solution intelligently incorporates an intelligent technique for dynamically generating one or more interactive responses in real time to interact with a user by identifying one or more attributes associated with the user to personalize the user's interaction with on-screen content. The solution further incorporates a dynamic prompt generation mechanism that measures user preferences while making enhanced user engagement and interactivity features available in a multilingual format that takes native accents into account to increase the accessibility of one or more pieces of content for diverse users. The solution further incorporates an artificial intelligence-supported mechanism that integrates advanced assistant-based capabilities into a user's content consumption experience to enable personalized content-based interactions, thereby elevating the traditionally passive experience of interacting with content on a computing device to an active and interactive experience.

[0031] 1 of the present disclosure illustrates a method for generating one or more interactive responses for at least one computing device (hereinafter referred to as a “computing device”) according to an exemplary implementation of the present disclosure. As shown, the method for generating one or more interactive responses for at least one computing device begins at step 102.

[0032] Thereafter, in step

[0104] , the method includes generating, by the processing unit, one or more prompts for the computing device, where the one or more prompts, as used herein, may include, but are not limited to, one or more of a question, a suggestion, an action, and / or an invocation of an interactive element.

[0033] In one implementation, the generation of the one or more prompts may be based on at least one of user preferences and one or more pieces of content being presented on a display unit of the computing device. Additionally, in another implementation, the one or more prompts may be further based on one or more related pieces of content previously viewed by the user.

[0034] As used herein, user preferences may include a set of parameters that may be stored in a storage unit of a computing device, any or each of which may be generated and stored based on the user's previous interactions with one or more pieces of content stored, viewed, hosted, streamed, or downloaded on the computing device. Additionally, in one implementation, the user preferences may further include one or more previous interactions of the user via the computing device with one or more prompts that may have been generated and presented to the user in a previous instance. Thus, the set of parameters stored as user preferences may include, but is not limited to, language preferences for audio or captions associated with one or more pieces of content the user is viewing, the genre of the content, the typical length of the content, usage patterns of one or more services enabled by the computing device, content viewing patterns, etc.

[0035] Furthermore, the one or more pieces of content displayed on the display unit of the computing device may include different media, including, but not limited to, movies, pictures, documents, web pages, blogs, applications, and / or text. In addition, in one implementation, the one or more pieces of content may further include audio, such as music or recordings, that may be complemented by one or more visual cues on the display unit of the computing device. Such visual cues may include graphical visualizations, cover art, music videos, dynamic display of captions corresponding to the audio, etc.

[0036] In one implementation, generating one or more prompts may include analyzing one or more pieces of content as described above to extract one or more features associated with the content being displayed on the computing device. For example, in the case of a movie, at least a portion of the audio associated with the content may be processed using a speech-to-text model to generate a text background for a currently ongoing portion of the movie-based content, and then specific features and / or events may be identified from the converted text that may be relevant to the user at a particular instance when one or more prompts may be generated. The extracted features may then be processed along with one or more user preferences stored on the computing device, which may be used to perform at least one of the following: generate additional prompts to be presented to the user, refine one or more prompts already generated, and / or remove at least one prompt from one or more prompts that may not match the stored user preferences.

[0037] Thereafter, in step

[0106] , the method includes displaying, by the processing unit, one or more prompts on a display unit of the computing device. Further, in one implementation, displaying the one or more prompts may include displaying the one or more prompts in multiple languages. Each of the multiple languages ​​in which the one or more prompts may be displayed may be determined in step

[0104] based on the stored user preferences.

[0038] Additionally, in one implementation, one or more prompts may be displayed as an overlay that may be superimposed in real time on a portion of one or more pieces of content being displayed on the computing device. Alternatively, one or more prompts may be displayed in the form of a pop-up or notification over the content. The above examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure, and thus it may be understood that one or more prompts may be displayed in any other manner known to one of ordinary skill in the art.

[0039] For ease of understanding, the above steps may be understood as an example in which a user, Mr. X, is watching a documentary, AW, about aquatic wildlife on a television unit, i.e., a computing device. In one instance in which the documentary discusses endemic species of fish, generating one or more prompts may include understanding the on-screen content, i.e., the discussion of fish species, and retrieving Mr. X's stored preferences to generate prompts in Mr. X's preferred languages, e.g., English, Hindi, and Spanish. Here, the one or more prompts may reflect one or more questions that may lead to the discovery of a new set of information associated with the fish species that is the focus of the ongoing portion of the on-screen content. By way of example, a prompt may be a question such as, "Can you tell me about the migration pattern of fish species Y?" After the one or more prompts are generated, these prompts may be displayed on Mr. X's television in three different languages: English, Hindi, and Spanish.

[0040] Then, in step

[0108] , the method

[0100] includes receiving, by the processing unit, one or more input queries in real time from at least one computing device. As used herein, the one or more input queries may be provided via the computing device based on one or more user inputs. The one or more inputs may include, but are not limited to, a selection of one or more prompts, a request to perform an action, and one or more questions.

[0041] It will be understood by those skilled in the art that, although the one or more input queries may include a selection of one or more prompts displayed in step 0106, the scope of the input queries in this disclosure is not limited to only such selections, and thus the one or more input queries may also include inputs independent of and in addition to the input queries corresponding to the selection of one or more prompts. For example, in one scenario, a user may choose not to engage with one or more prompts displayed in step 0106 and instead provide an input query that may not be covered by the one or more prompts.

[0042] In addition to the process of generating one or more interactive responses, the one or more input queries may additionally be used to determine and store one or more user preferences.

[0043] Continuing with the previous example, Mr. X may select a prompt in English due to his interest in the migration patterns of fish species. Alternatively, Mr. X may also wish to learn about the origin of the fish species he is interested in, and therefore Mr. X may further provide an additional input query in English. Furthermore, the selection of one or more prompts in English from among the available options may be used as an indicator of Mr. X's preferences.

[0044] Then, in step

[0110] , the method

[0100] includes identifying, by the processing unit, one or more interactivity attributes from the received query and one or more prompts. In one implementation, the identification of the one or more interactivity attributes may be based on an analysis of one or more prompts selected by a user via a computing device. Alternatively, in another implementation, the one or more interactivity attributes may be further identified from an analysis of one or more independent input queries, which may differ from the selection of the one or more prompts.

[0045] As used herein, one or more interactivity attributes may include, but are not limited to, one or more distinctive features of an input query that may indicate requirements for the performance of one or more underlying tasks associated with the one or more input queries. The interactivity attributes may define a mode of interaction requested by a user via a computing device. Additionally, in one implementation, the one or more interactivity attributes may further include one or more distinctive features of an input query that may indicate one or more preferences of a user, for example, the user's linguistic preferences, including language and accent.

[0046] For example, when a user selects one or more prompts displayed on the screen in step 0108, the user is indicating a desire to interact through performing a task associated with the selected prompt, such as receiving a response to a query related to the on-screen content. Similarly, a separate input query requesting a list of content available for purchase within a predefined price range may include multiple interactivity attributes, such as a lookup request for a desired set of content, a filtering request to derive content within a desired price range, etc.

[0047] Additionally, identifying interaction attributes may include associating user preferences with likely desired outcomes for the user. Continuing with the ongoing example to illustrate, Mr. X selected, "Can you tell me about the migration patterns of species Y?" Additionally, Mr. X also provided an independent query, i.e., "Can you recommend some good books for studying species Y and related aquatic wildlife?" in addition to the selected prompt. Here, identifying interaction attributes may include identifying Mr. X's preference for English through his selection of the prompt. This identification may further include identifying attributes related to data about the migration patterns of species Y and resource materials for studying related topics.

[0048] Then, in step

[0112] , the method includes dynamically generating, by the processing unit, one or more responses to the one or more input queries based on the one or more attributes. As used herein, the one or more responses may be interactive responses that may include multiple actions associated with the received one or more input queries. In one implementation, multiple identified interactivity attributes may be combined to generate a single interactive response. In application, the one or more responses may include, but are not limited to, changing the playback language, generating real-time multilingual captions based on user preferences, navigating one or more sets of data to generate a query response, performing one or more assistive interface actions, and redirecting the user to a second set of content.

[0049] Furthermore, in one implementation, generating the one or more responses may be performed by the processing unit via an intelligent dialogue unit. The intelligent dialogue unit may include one or more artificial intelligence (AI) models for generating the one or more responses. In another implementation, the method may include the intelligent dialogue unit retrieving one or more sets of data from a connected data repository for generating the one or more interactive responses. The same will be discussed in more detail later in relation to FIG. 3. The method includes sending, by the processing unit, one or more interactive attributes to an intelligent dialogue unit connected with the multilingual repository, where the intelligent dialogue unit generates the one or more responses.

[0050] In yet another implementation, the method may further include updating the intelligent dialogue unit based on the generation of the one or more responses. Parallel updating of the intelligent dialogue unit may be used to provide a user with a highly personalized experience in subsequent interactions based on the implemented adaptation parameters. This may include training one or more artificial intelligence (AI) models associated with the intelligent dialogue module to create a constant adaptation loop. The update action may further include updating a data repository associated with the intelligent dialogue unit with the latest available set of data.

[0051] Thereafter, in step

[0114] , the method includes displaying, by the processing unit, the one or more responses on a display unit of the at least one computing device. Thereafter, the method

[0100] ends in step

[0116] .

[0052] FIG. 2 shows a high-level functional block diagram of a system

[0200] for generating one or more interactive responses for at least one computing device. As shown in FIG. 2, the system

[0200] includes at least one of the following elements: a processing unit

[0202] , an intelligent dialogue unit

[0204] , a data repository

[0206] , a memory

[0208] , and a storage unit

[0210] . While it may be noted that the illustration of FIG. 2 shows one instance of each unit in an implementation of the system

[0200] , it may be understood that this is for illustrative purposes only and does not limit the scope of the present disclosure. Thus, the system

[0200] may include two or more instances of each unit in its possible implementation. As shown, the system

[0200] may be connected to at least one computing device

[0220] (hereinafter referred to as a "computing device").

[0053] Furthermore, in one implementation, the system

[0200] may reside on a server that may be connected to and in communication with the computing devices

[0220] . The server may be connected to the computing devices

[0220] via a remote connection using one or more wireless communication technologies known by those skilled in the art. For example, the system

[0200] residing on a server may communicate with the computing devices via a wide area network (WAN) such as the Internet, and at least one computing device may be configured to connect via one or more technologies for WAN implementation, such as Wi-Fi, Li-Fi, 5G, 4G, etc. Alternatively, in one implementation, the computing devices may be connected to the system

[0200] via a local area network (LAN).

[0054] In another implementation, the connection between the system

[0200] residing on the server and the computing device may be facilitated via one or more wired connection technologies known by those skilled in the art. For example, the connection may be based on the use of Ethernet technology. Alternatively, in one implementation, the system

[0200] may be implemented natively on the computing device itself.

[0055] As used herein, a computing device may be any electronic device equipped with at least one processor

[0222] and at least one display unit

[0224] that may be used by a user to view one or more pieces of content. For example, a computing device may include, but is not limited to, a television, a personal computer such as a laptop, a tablet, a monitor, a smartwatch, etc. Additionally, a computing device may be configured to take input, including, but not limited to, text input, auditory / voice-based input, gestures, through the use of multiple media and / or one or more input devices, such as a keyboard or joystick. Each of the inputs received by the computing device

[0220] may be transmitted to the system

[0200] in the form of an input query.

[0056] During operation, the system 0200 may be configured to generate one or more prompts for the computing device 0220 via the processing unit 0202. The one or more prompts generated by the system 0200 may include, but are not limited to, one or more of a question, a suggestion, an action, and / or an invocation of an interactive element.

[0057] In one implementation, the generation of the one or more prompts may be based on at least one of user preferences and one or more pieces of content being presented on the display unit

[0224] of the computing device

[0220] . Additionally, the one or more prompts may be further based on one or more related pieces of content previously viewed by the user.

[0058] As used herein, user preferences may include a set of parameters stored in the storage unit of the system, any or each of which may be generated and stored based on the user's prior interactions with one or more pieces of content stored, viewed, hosted, streamed, or downloaded on the computing device. User preferences may also include one or more prior interactions of the user, via the computing device, with previous instances of one or more prompts generated by the system.

[0059] In another implementation, the system

[0200] may be further configured to generate one or more prompts in multiple languages.

[0060] The system may then be configured to display one or more prompts on a display unit of the computing device, in one implementation, the generated prompts may be displayed in multiple languages, and the user may be free to select a prompt in one of the multiple languages ​​based on their preference.

[0061] The system 0200 may be further configured to receive one or more input queries from the computing device 0220. The input queries may be user input provided via the computing device 0220, and the input queries may be associated with the user's selection input for one or more prompts, or with independent and / or additional input that may be provided by the user apart from the selection of one or more prompts.

[0062] The system may be further configured to identify one or more interactivity attributes upon receipt of one or more input queries and one or more prompts. In one implementation, the identification of the one or more interactivity attributes may be based on an analysis of one or more input queries associated with the selection of one or more prompts selected by the user. Alternatively, in one implementation, the identification of the one or more interactivity outputs may be based on both the input queries associated with the selection of one or more prompts by the user and the one or more input queries, which may be independent of or in addition to the selection of one or more prompts.

[0063] In one implementation, the one or more interactivity attributes may include one or more distinctive features of the input query that may indicate one or more preferences of the user, for example, the user's linguistic preferences, including language and accent. Additionally, in another implementation, the one or more interactivity attributes may further include one or more distinctive features of the input query that may indicate requirements for performing one or more underlying tasks associated with the one or more input queries.

[0064] The system

[0200] may then be configured to dynamically generate, by the processing unit

[0202] , one or more responses to one or more input queries based on one or more attributes, and then display the generated responses on the display unit

[0224] of the computing device

[0220] .

[0065] In one implementation, the one or more responses may be generated by the processing unit 0202 via the intelligent dialogue unit 0204. Furthermore, the intelligent dialogue unit 0204 may include one or more artificial intelligence (AI) models for generating the one or more responses.

[0066] In another implementation, the intelligent dialogue unit

[0204] may be connected to a data repository

[0206] , and the intelligent dialogue unit

[0204] may be configured to retrieve one or more sets of data from the connected data repository

[0206] for generating one or more interactive responses.

[0067] Another implementation of the system may include updating the intelligent dialogue unit in real time based on the generation of one or more responses. This may include training one or more artificial intelligence (AI) models associated with the intelligent dialogue module to create a constant adaptive loop. The update action may further include updating a data repository associated with the intelligent dialogue unit with the latest available set of data.

[0068] 3 shows a high-level schematic block diagram of the intelligent dialogue unit

[0204] for generating one or more responses. As shown, in step

[0302] , the intelligent dialogue unit

[0204] processes one or more interactivity attributes identified by the system

[0200] , each of which may be associated with an input query. The identified interactivity attributes may be based on an input query related to the selection of one or more prompts generated by the system

[0200] and / or one or more input queries that may be independent of the selection of a prompt, such as an input query provided by a user for the implementation of one or more interactive assistant-based functions, such as a request to display weather information for a local area or a request for the meaning of a word or phrase from on-screen content.

[0069] Then, in step

[0304] , the intelligent dialogue unit

[0204] separates the one or more input queries into two categories, namely, domain-specific queries and non-domain-specific queries, based on processing of the associated one or more interactivity attributes. As used herein, a domain-specific query may include an input query whose one or more interactivity attributes may require access to subject or request specific domain knowledge.

[0070] For example, in one implementation, when a user requests a list of products associated with a particular domain, such as the recent records of a favorite sportsperson, one or more interactivity attributes of such an input query may include characteristic features of an underlying task for presenting a set of data to the user. Thus, a domain-specific input query may require fetching and processing one or more sets of data from one or more external sources.

[0071] On the other hand, non-domain-specific input queries may include input queries for which a response can be natively generated by the intelligent dialogue unit

[0204] . For example, in one implementation, if the user's preferred language is determined to be a language other than the current playback language of the content on the computing device's display, the system

[0200] may change the language to the preferred language of playback for the user. Alternatively, if one or more input queries are associated with a language preference that may not be available, the system

[0200] may generate real-time translated captions in the preferred language for the user via the intelligent dialogue unit

[0204] . The generation of such responses may be performed natively via one or more AI models associated with the intelligent dialogue unit

[0204] , such as a large-scale language model (LLM), thereby not requiring a domain-specific query to generate the response.

[0072] During operation, upon separation of the input query into domain-specific queries, in step

[0304] , the intelligent dialogue unit

[0204] may fetch one or more relevant sets of data from a data repository

[0206] connected to the intelligent dialogue unit

[0204] via a context fetch service.

[0073] For example, in one implementation, an input query may correspond to a request to purchase a T-shirt associated with a user's preferred brand. In this scenario, the intelligent dialogue unit

[0204] may determine a context and domain associated with the request to fetch a set of data from a data repository

[0206] that includes a list of T-shirt items from the user's preferred brand on popular websites.

[0074] The data repository may include a vector database that may be linked to multiple sources of data, each of which may be further associated with one or more domains. Additionally, the data repository may be configured to fetch one or more updated sets of data from the multiple sources at a preconfigured threshold duration.

[0075] In one implementation, the multiple sources may include, but are not limited to, websites, product catalogs, broadcasts, and proprietary databases associated with one or more domains. The data repository

[0206] may intelligently fetch one or more sets of data from such multiple sources based on user preferences and previous input queries to maintain an updated database for providing a personalized interaction experience to the user. In another implementation, in the event that it is determined that the data repository

[0206] does not have the required set of data associated with a domain-specific query, the data repository

[0206] may be configured to fetch one or more updated sets of data from the multiple sources in real time.

[0076] Additionally, the data repository

[0206] may be a dynamic database and may determine, via the intelligent dialogue unit

[0204] , the relevance of existing sets of data in the repository. Thus, the data repository

[0206] may update or overwrite one or more redundant sets of data with updated sets of data in real time.

[0077] Then, in step

[0306] , the intelligent dialogue unit

[0204] may process one or more sets of data fetched from the data repository

[0206] using one or more artificial intelligence (AI) models associated with the intelligent dialogue unit

[0204] to generate one or more responses.

[0078] In step

[0308] , one or more responses may be presented to the user on the display unit of the computing device via an interactive assistant service built into the intelligent dialogue unit

[0204] .

[0079] Alternatively, if in step

[0302] it is determined that the input query is a non-domain-specific query, step

[0302] may be followed by step

[0310] . As shown, in step

[0310] , the non-domain-specific query may be processed directly by the intelligent dialogue unit

[0204] using the associated AI model. Continuing with the above example to illustrate, in one implementation, the intelligent dialogue unit

[0204] may perform a real-time speech-to-text conversion operation on language audio associated with content displayed on the user's computing device

[0220] . One or more large-scale language models (LLMs) may then be used to generate a real-time translation of the text in the user's preferred language. It may be noted that the above functions are exemplary in nature and are not intended to limit the scope of operations that may be performed in step

[0310] . Thus, it may be understood by those skilled in the art that the intelligent dialogue unit

[0204] may perform other functions based on one or more input queries, as needed.

[0080] Then, in step

[0312] , one or more responses generated from processing the non-domain-specific query may be presented to the user on the user's computing device

[0220] via the intelligent dialogue service of the intelligent dialogue unit

[0204] .

[0081] As used herein, an intelligent dialogue service may include an intelligent conversational interface between a system and a computing device that may be used to display one or more prompts and one or more responses to a user. In addition, the intelligent dialogue service may also include an interface for registering an input query provided by a user via the computing device.

[0082] In one implementation, the intelligent interactive service may be an intelligent chatbot, hi another implementation, the service may be implemented as a multi-input interactive service configured to interact with a user using multiple media, such as a GUI, text, and voice.

[0083] Referring now to FIG. 4A, an exemplary implementation of displaying one or more prompts on a display unit of a computing device is shown. FIG. 4A illustrates a screen with one or more prompts, preferably contextual prompts, that invite a user to explore one or more internal screens and discover engaging content. As further shown, the one or more prompts may be displayed in two or more languages ​​to enable identification of the user's language preferences to provide personally curated content. Upon capturing the user preferences, the user preferences are utilized to shape the overall user flow. Content is delivered in the user's preferred language, and one or more internal screens are dynamically adapted, including one or more adjustments to audio output to match the selected preferences.

[0084] Additionally, as shown, using context, one or more prompts encourage the user to engage with the content by presenting the user with one or more questions related to the on-screen content. In one implementation, when the user selects one or more prompts, one or more responses may be generated and displayed to the user.

[0085] In one exemplary implementation, a condensed summary highlighting key points may be generated for the user to quickly skim through. If the user desires more information, the user is allowed to ask one or more questions related to the summary and receive detailed answers, as illustrated in Figure 4B. In another exemplary implementation, any questions that are out of context may be ignored.

[0086] Referring now to FIG. 4B , an exemplary diagram of one or more responses according to an exemplary implementation is shown. As shown, the one or more responses may be displayed in a summary format. Furthermore, the generation of the one or more responses may be multilingual in nature. For example, as shown, the summary-formatted content is displayed in English as a result of a user preference determined by the selection of one or more prompts in English. Alternatively, based on the user preference, one or more responses may be generated in multiple languages, thereby increasing the accessibility of the content and providing a rich user interaction experience. Furthermore, based on user engagement, if the user may be interested in further interaction after the display of one or more responses, the user may be prompted to provide one or more additional input queries to trigger the user's interactive conversation experience.

[0087] The technical solution of the present disclosure proposes a novel method and system for providing an interactive content experience on at least one computing device. The technical solution of the present disclosure also provides a technical advance over currently known solutions. The solution can revolutionize the way television content, encompassing images, videos, documents, and audio, is interacted with. By utilizing one or more advanced AI models deployed either on the server side or the client end, the solution enhances the interactivity of traditional TV content. The present disclosure also has several technical advantages, such as the generation of one or more context-aware prompts for initiating conversations that can additionally serve to measure user preferences. This feature improves the discoverability and ease of interaction within the viewing experience of one or more pieces of content on a computing device. Unlike conventional approaches that are often integrated with specific programs or applications, the system and method of the present disclosure seamlessly integrate with any content that may be viewed by a user. For example, during a program, the system provides timely prompts related to the topic, engaging conversations that are sparked among viewers, facilitating real-time two-way conversations while ensuring compliance with TV constraints.

[0088] Furthermore, unlike conventional solutions in the prior art, the solution of the present disclosure dramatically improves user accessibility through the integration of multilingual dialogue and real-time translation.

[0089] Additionally, by focusing on real-time prompt generation, the present disclosure enhances the immediacy and relevance of the dialogue, thereby enriching the overall viewing experience. Furthermore, the present disclosure introduces one or more prompts (i.e., one or more contextual prompts) tailored to the on-screen content in various languages. The one or more prompts are not only interactive elements but also serve as a tool for measuring user language preferences, promoting a more personalized viewing experience. When the user engages with the prompt, the system uses this interaction to refine future content and ensure it matches their language preferences. Furthermore, the present solution allows the user to engage in contextual conversations through voice or text input, with responses provided in the user's preferred language, both as text and in a native language accent. This aspect of the solution ensures a personalized and linguistically tailored interactive experience. Furthermore, the present solution introduces an AI assistant unit that acts as a personal assistant and responds to user queries with knowledge derived from LLM and RAG implementations of live information to make responses more accurate.

[0090] Furthermore, the disclosed solution is more technically advanced than existing solutions in the scope of one or more responses. Unlike prior solutions that are limited to basic tasks and automation within a limited set of languages, the present solution enables the generation of a broad set of responses, including intelligent assistant-based functionality, on-screen content awareness, content personalization, multi-language support and translation, caption generation, context determination, navigating websites and databases to assist users with one or more input queries, and the like.

[0091] Although considerable emphasis has been placed herein on preferred embodiments, it will be appreciated that many embodiments may be made and that many changes may be made in the preferred embodiments without departing from the principles of the present disclosure. These and other changes in the preferred embodiments of the present disclosure will be apparent to those skilled in the art from the present disclosure herein, and it is thereby clearly understood that the foregoing description is intended to be illustrative of the present disclosure and not limiting. [Explanation of symbols]

[0092] 100 ways 200 systems 202 Processing Unit 204 Intelligent Dialogue Unit 206 Data Repository 208 memory 210 Storage Unit 220 Computing Devices 222 processors 224 Display Unit

Claims

1. 1. A method for generating one or more interactive responses for at least one computing device [220], comprising: - by a processing unit [202], said at least one computing device generating one or more prompts for [220]; - by the processing unit [202], a display unit of the at least one computing device [220] displaying said one or more prompts on [224]; - receiving, by said processing unit [202], one or more input queries in real time from said at least one computing device [220]; - identifying, by the processing unit [202], one or more interactivity attributes based on one of the one or more input queries and the one or more prompts; - dynamically generating, by the processing unit [202], one or more responses to the one or more input queries based on the one or more interactivity attributes; - displaying, by the processing unit [202], the one or more responses on the display unit [224] of the at least one computing device [220]; A method comprising:

2. The method further comprises: displaying a display unit of the at least one computing device [220]; 2. The method of claim 1, further comprising displaying the one or more prompts in one or more languages ​​on [224].

3. 10. The method of claim 1, wherein the one or more prompts are generated based on at least one of user preferences and one or more pieces of content presented on the display unit [224] of the at least one computing device [220].

4. 2. The method of claim 1, further comprising receiving, at the processing unit [202], from the at least one computing device [220], a selection from the one or more prompts displayed on the display unit [224] of the at least one computing device [220], wherein the one or more attributes are identified based on an analysis of the received selection.

5. The method of claim 1 , wherein the one or more interactivity attributes include one of a language, an accent, and one or more tasks associated with the one or more input queries.

6. 2. The method of claim 1, further comprising the step of transmitting, by the processing unit [202], the one or more interactivity attributes to an intelligent dialogue unit [204] connected to a multilingual repository [206], wherein the intelligent dialogue unit generates the one or more responses.

7. 1. A system for generating one or more interactive responses for at least one computing device [220], the system comprising a processing unit [202] connected to a memory [208], the processing unit [202] comprising: - generating one or more prompts for the at least one computing device [220]; - a display unit of said at least one computing device [220] [224] displaying said one or more prompts on - receiving one or more input queries from the at least one computing device [220]; - identifying one or more interactivity attributes based on one of the one or more input queries and the one or more prompts; - dynamically generating one or more responses to the one or more input queries based on the one or more attributes; - displaying the one or more responses on the display unit [224] of the at least one computing device [220]; A system configured to:

8. The system [200] displays the display unit of the at least one computing device [220].

8. The system of claim 7, further configured to display the one or more prompts in one or more languages ​​on [224].

9. 8. The system of claim 7, wherein the processing unit [202] is further configured to generate the one or more prompts based on at least one of user preferences and one or more contents presented on the display unit [224] of the at least one computing device [220].

10. 8. The system of claim 7, wherein the processing unit [202] is further configured to receive from the at least one computing device [220] a selection from the one or more prompts displayed on the display unit [224] of the at least one computing device [220], and wherein the one or more attributes are identified based on an analysis of the received selection.

11. The system of claim 7 , wherein the one or more interactivity attributes include one of a language, an accent, and one or more tasks associated with the one or more input queries.

12. The system includes an intelligent dialogue unit connected to a multilingual repository [206]. The system of claim 7, further comprising: [204], wherein the intelligent dialogue unit is configured to receive the one or more interactivity attributes from the processing unit [202] and generate the one or more responses.

Images