Determining user intent from chat robot interaction

Abstract

Systems and methods for determining user intent and providing targeted advertisements using chat robot interactions are disclosed. The system receives user cues during a chat session with the chat robot and generates a response using a large language model. User intent is extracted by analyzing chat conversations using natural language processing and machine learning techniques. The extracted user intent including weighted keywords and concepts is used to create a user intent profile. Targeted advertising content is generated based on the user intent profile, and the targeted advertising content is provided to the user during subsequent platform interactions. The large language model is continuously retrained using the user participation data to improve intent modeling accuracy. User privacy is maintained by limiting context extraction to chat robot conversations. The system enables personalized and related advertising by inferring user intent via dialog interactions.

Description

[0001] Priority claim

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 440,785, filed on January 24, 2023, which is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates generally to interactive platforms and, more particularly, to providing a user interface to a user of an interactive platform. Background Art

[0004] Users like to visit the interactive platform to share content with other users of the interactive platform. In addition, users often use the various features of the interactive platform to access useful information. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] In the drawings, which are not necessarily drawn to scale, the same reference numerals may describe similar components in different views. To easily identify the discussion of any particular element or action, the highest digit or digits in the reference numeral refer to the figure in which the element is first introduced. Some non-limiting examples are shown in the accompanying drawings, in which:

[0006] Figure 1 is a diagrammatic representation of a networked environment in which the present disclosure may be deployed, according to some examples.

[0007] Figure 2 is a diagrammatic representation of a messaging system having both client-side and server-side functionality, according to some examples.

[0008] Figure 3A is an illustration of an interactive session by a user with a chatbot system, according to some examples.

[0009] Figure 3B is a block diagram of a chatbot system according to some examples.

[0010] Figure 3C is a process flow diagram of the chatting and advertising process of the chatbot system according to some examples.

[0011] Figure 3D is a process flow diagram of an advertisement creation process according to some examples.

[0012] Figure 4A is a block diagram of a technique according to some examples.

[0013] Figure 4B is an activity diagram of a method for a chatbot system according to some examples.

[0014] Figure 5A and Figure 5B is an illustration of a user interface according to some examples.

[0015] Figure 6 A machine learning pipeline according to some examples is shown.

[0016] Figure 7 The training and use of a machine learning program according to some examples is shown.

[0017] Figure 8 is a diagrammatic representation of data structures as maintained in a database, according to some examples.

[0018] Figure 9 is a diagrammatic representation of messages according to some examples.

[0019] Figure 10 is a flow chart of an access restriction process according to some examples.

[0020] Figure 11 is a diagrammatic representation of a machine in the form of a computer system, according to some examples, within which a set of instructions may be executed, causing the machine to perform any one or more of the methodologies discussed herein.

[0021] Figure 12 is a block diagram illustrating a software architecture in which examples may be implemented. DETAILED DESCRIPTION

[0022] Interactive platforms (e.g., social platforms, social media platforms, AR platforms, applications, messaging platforms, AR applications, operating systems, gaming systems or applications, systems that users interact with, etc.) can provide users with ways to interact with other users with similar interests. Since interactive platforms may not charge for access to such platforms, the owners of interactive platforms can decide to provide advertising content to users based on the interests of users. Both users and owners of interactive platforms expect to see advertisements ("ads") that are more relevant to the user's intent, which can make the advertisements more engaging and less disruptive to the user experience. In addition, advertisers expect to easily provide attractive advertising content.

[0023] Various examples provide improved user intent detection during conversations with chatbots on interactive platforms. In some examples, chatbots are software applications designed to simulate human conversations through voice commands or text chat. Chatbots can employ natural language processing (NLP) and machine learning (ML) / artificial intelligence (AI) methods to understand and interpret user input and generate responses.

[0024] In some examples, improved user intent detection allows advertisers to bid and target their ads to specific user segments based on user intent and interests, which can increase the chances that users will engage with the ads. By providing targeted keywords, advertisers can have a faster time to market. In addition, advertisers can benefit from automatic creative generation based on matching user intent with the advertiser's targeted user intent.

[0025] In some examples, the chatbot system provides user intent detection, which improves targeting and optimization capabilities over time by analyzing data about user intent and conversions. This enhances the user experience and improves the relevance and performance of ads. Furthermore, the interactive platform uses the extracted user intent to enhance the user experience across other parts of the interactive platformized site, making them more personalized and relevant to the user community. In some examples, the interactive platform enhances display advertising by targeting users based on their true intent, determined in whole or in part through interactions with the chatbot. By extracting high-intent and timely relevant keywords and concepts from conversations with the chatbot, the interactive platform can improve user intent profiles.

[0026] In some examples, advertisers target and bid on specific keywords or expanded concepts, which enables them to reach highly targeted groups of users.

[0027] Some platforms currently rely on conventional methods of ad targeting, such as demographic information and browsing and engagement history, which are limited in targeting users based on their immediate and recent intent. With recent changes in privacy regulations, obtaining user intent information through third-party channels has also become increasingly difficult. Examples of the present disclosure address these limitations by leveraging large language models (LLMs) or AI systems and context extraction from conversations with chatbots to target users with relevant ads. By using the context of conversations with chatbots, interactive platforms can provide a more accurate and up-to-date representation of user intent and enable more effective ad targeting without compromising the user's privacy.

[0028] In some examples, users can interact with chatbots in several different ways. Users can chat directly with chatbots, in which case the entire conversation is used to establish user intent. This also allows the chatbot system to extract accurate information about user intent because users will express their interests and needs directly to the chatbot. In some examples, users can have a 1:1 chat with a friend and add a chatbot to the conversation using a tag such as @mention. In this case, the prompt after @mention can be used for user intent, or the entire conversation can be used after the chatbot is added to the user intent extraction. In this way, the platform can extract information about user intent from the context of the conversation and not just the prompt. In group chats, users can add chatbots to conversations. And the data extraction scenario can be similar to a 1:1 chat.

[0029] In some examples, the intent extraction pipeline maps conversations into an intent vector of important and intentional keywords and expanded concepts. This intent vector is a dynamic representation of the user's intent, updated in near real-time as the user engages in a conversation with the chatbot. Thus, the user's intent is defined by a combination of demographics, engagement embeddings in the system, and keyword and concept vectors.

[0030] In some examples, the intent vector is a rich representation of the user's intent, and the similarity of two vectors shows how closely the intents of the two users match. This can be used for "look-a-like" targeting and audience expansion, allowing interactive platforms to quickly identify and target users similar to users who have already engaged with an ad.

[0031] In some examples, the textual components of an ad are used to fine-tune responses to the LLM, which in turn modulates responses to the large language model. This improves recommendations made by the chatbot system and increases user engagement.

[0032] In some examples, advertisers can use concept vectors to select the target audience for their ads. Advertisers can bid on specific keywords and expanded concepts, which allows advertisers to target users who may be interested in their products or services. Newer and smaller advertisers can also find relevant audiences by specifying a few key keywords, and the chatbot system will match them with a broader group of users.

[0033] In some examples, the chatbot system has detailed control over the context extracted from the conversation, so it can curate and adjust the list of possible keywords and concepts as the platform evolves. The chatbot system can also learn new concepts every day and can adjust and curate the list of acceptable expansion concepts to ensure that they are relevant and appropriate for the platform. Overall, the platform uses representations of user intent to provide users with a more personalized and engaging experience and provide advertisers with more targeting options. Intent vectors can be used for many purposes, such as audience expansion, similar population targeting, and fast cold-start ramp-up.

[0034] In some examples, the chatbot system can be used in conjunction with many organic experiences such as content, search, augmented reality, and engagement with mapping applications. This enables the interactive platform as a whole to target the right audience more efficiently and improve the performance of advertising and organic experiences.

[0035] In some examples, the chatbot system protects user privacy because the chatbot system only uses the conversation when the chatbot is opted in to join the conversation and the expanded concepts are from a curated list of potential bid concepts.

[0036] In some examples, a chatbot system receives a prompt from a user during a first interactive session. The chatbot system uses the prompt and a large language model to generate a response. The chatbot system delivers the response to the user during the first interactive session. The chatbot system determines user intent based on the user prompt and the response. The chatbot system determines advertising content based on the user intent. The chatbot system delivers the advertising content to the user during a second interactive session.

[0037] In some examples, the first interactive session is a chat session between the user and the chatbot system, and the second interactive session is not a chat session between the user and the chatbot system.

[0038] In some examples, the chatbot system generates an original response based on a prompt, generates an adjusted prompt based on filtering the original response, and generates a final response using the adjusted prompt.

[0039] In some examples, the chatbot system generates potential responses, selects a response from the potential responses, and determines user intent based on the potential responses.

[0040] In some examples, the chatbot system determines user intent based on a user profile, which may include social network data.

[0041] In some examples, the chatbot system is a component of an interactive platform, a social platform, a social media platform, a social network, an AR platform, an application, a messaging application, an AR application, an operating system, a gaming system or application, or any other system, medium, or application with which a user can interact.

[0042] Networked computing environment

[0043] Figure 1 1 is a block diagram illustrating an example interactive system 100 of an interactive platform for facilitating interactions over a network (e.g., exchanging text messages, conducting text, audio, and video calls, or playing games). The interactive system 100 includes a plurality of client systems 102, each of which hosts a plurality of applications including an interactive client 104 and other applications 106. Each interactive client 104 is communicatively coupled to other instances of the interactive client 104 (e.g., hosted on respective other client systems 102), an interactive server system 110, and third-party servers 112 via one or more communication networks including a network 108 (e.g., the Internet). The interactive client 104 can also communicate with the locally hosted application 106 using an application programming interface (API).

[0044] Each client system 102 may include multiple user devices, such as a mobile device 114 , a head mounted device 116 , and a computer client device 118 , which are communicatively connected to exchange data and messages.

[0045] The interactive clients 104 interact with other interactive clients 104 and with the interactive server system 110 via the network 108. The data exchanged between the interactive clients 104 (e.g., interaction 120) and between the interactive clients 104 and the interactive server system 110 includes functions (e.g., commands for activating functions) and payload data (e.g., text, audio, video, or other multimedia data).

[0046] The interactive server system 110 provides server-side functionality to the interactive clients 104 via the network 108. Although certain functions of the interactive system 100 are described herein as being performed by either the interactive clients 104 or the interactive server system 110, whether certain functions are located within the interactive clients 104 or within the interactive server system 110 may be a design choice. For example, it may be technically preferable to initially deploy certain technologies and functions within the interactive server system 110, but later migrate the technologies and functions to the interactive clients 104 where the client system 102 has sufficient processing power.

[0047] The interactive server system 110 supports various services and operations provided to the interactive clients 104. Such operations include sending data to the interactive clients 104, receiving data from the interactive clients 104, and processing data generated by the interactive clients 104. The data may include message content, client device information, geolocation information, media enhancements and overlays, message content persistence conditions, interactive platform information, and live event information. The data exchange within the interactive system 100 is activated and controlled by functions available through the user interface (UI) of the interactive client 104.

[0048] Turning now specifically to the interaction server system 110, an API server 122 is coupled to and provides a programming interface for the interaction server 124, making the functionality of the interaction server 124 accessible to the interaction clients 104, other applications 106, and third-party servers 112. The interaction server 124 is communicatively coupled to a database server 126, thereby facilitating access to a database 128 that stores data associated with interactions processed by the interaction server 124. Similarly, a web server 130 is coupled to the interaction server 124 and provides a web-based interface to the interaction server 124. To this end, the web server 130 handles incoming network requests via the Hypertext Transfer Protocol (HTTP) and several other related protocols.

[0049] The API server 122 receives and sends interaction data (e.g., commands and message payloads) between the interaction server 124 and the client system 102 (and, for example, the interaction clients 104 and other applications 106), as well as the third-party servers 112. Specifically, the API server 122 provides a set of interfaces (e.g., routines and protocols) that the interaction clients 104 and other applications 106 can call or query to activate functionality of the interaction server 124. The API server 122 exposes various functions supported by the interaction server 124, including account registration; login functionality; sending interaction data from a particular interaction client 104 to another interaction client 104 via the interaction server 124; transferring media files (e.g., images or videos) from an interaction client 104 to the interaction server 124; setting up media data collections (e.g., stories); retrieving a friend list of a user of the client system 102; retrieving information and content; adding and removing entities (e.g., friends) from an entity graph (e.g., a social graph); locating friends within a social graph; and opening application events (e.g., related to the interaction client 104).

[0050] Interactive server 124 hosts multiple systems and subsystems, see below Figure 2 Provide a description.

[0051] Linked Applications

[0052] Returning to the interactive client 104, the features and functionality of an external resource (e.g., a linked application 106 or applet) are made available to the user via the interface of the interactive client 104. In this context, "external" refers to the fact that the application 106 or applet is external to the interactive client 104. External resources are typically provided by a third party, but may also be provided by the creator or provider of the interactive client 104. The interactive client 104 receives a user selection of an option to launch or access features of such an external resource. The external resource can be an application 106 installed on the client system 102 (e.g., a "local app"), or a small-scale version of an application (e.g., a "mini-program") hosted on the client system 102 or located remotely from the client system 102 (e.g., on a third-party server 112). The small-scale version of an application includes a subset of the features and functionality of the application (e.g., a full-scale local version of the application) and is implemented using a markup language document. In some examples, the small-scale version of an application (e.g., a "mini-program") is a web-based markup language version of the application and is embedded in the interactive client 104. In addition to using markup language documents (eg, .*ml files), applet may include scripting languages ​​(eg, .*js files or .json files) and style sheets (eg, .*ss files).

[0053] In response to receiving a user selection of an option to launch or access a feature of an external resource, the interactive client 104 determines whether the selected external resource is a web-based external resource or a locally installed application 106. In some cases, an application 106 installed locally on the client system 102 can be independent of and launched separately from the interactive client 104, for example, by selecting an icon corresponding to the application 106 on a home screen of the client system 102. A small-scale version of such an application can be launched or accessed via the interactive client 104, and in some examples, no portion of the small-scale application can be accessed outside of the interactive client 104 or only a limited portion of the small-scale application can be accessed outside of the interactive client 104. The small-scale application can be launched by the interactive client 104 receiving, for example, a markup language document associated with the small-scale application from the third-party server 112 and processing such a document.

[0054] In response to determining that the external resource is a locally installed application 106, the interactive client 104 instructs the client system 102 to launch the external resource by executing locally stored code corresponding to the external resource. In response to determining that the external resource is a web-based resource, the interactive client 104 communicates with the third-party server 112 (for example) to obtain a markup language document corresponding to the selected external resource. The interactive client 104 then processes the obtained markup language document to present the web-based external resource within the user interface of the interactive client 104.

[0055] The interactive client 104 can notify the user of the client system 102 or other users associated with such user (e.g., "friends") about activities occurring in one or more external resources. For example, the interactive client 104 can provide participants in a conversation (e.g., a chat session) within the interactive client 104 with notifications about external resources currently or recently used by one or more members of a group of users. One or more users can be invited to join an active external resource or a recently used but currently inactive external resource (in the group of friends) can be launched. The external resource can provide participants in the conversation, each using a corresponding interactive client 104, with the ability to share items, conditions, states, or locations in the external resource with one or more members of the group of users in the chat session. The shared items can be interactive chat cards that members of the chat can interact with to, for example, launch the corresponding external resource, view specific information within the external resource, or be taken to a specific location or state within the external resource. Within a given external resource, a response message can be sent to the user on the interactive client 104. Based on the current context of the external resource, the external resource can selectively include different media items in the response.

[0056] The interactive client 104 can present a list of available external resources (e.g., applications 106 or applets) to the user to launch or access a given external resource. The list can be presented in the form of a context-sensitive menu. For example, the icons representing different applications (or applets) of the application 106 (or applets) can change based on how the user launches the menu (e.g., from a conversational interface or from a non-conversational interface).

[0057] System Architecture

[0058] Figure 2 1 is a block diagram illustrating additional details regarding the interactive system 100 according to some examples. Specifically, the interactive system 100 is shown as including an interactive client 104 and an interactive server 124. The interactive system 100 includes a plurality of subsystems that are supported on the client side by the interactive client 104 and on the server side by the interactive server 124. Example subsystems are discussed below.

[0059] Image processing system 202 provides various functions that enable a user to capture and enhance (eg, enhance or otherwise modify or edit) media content associated with a message.

[0060] The camera system 204 includes control software (e.g., in a camera application) that interacts with and controls the hardware camera hardware of the client system 102 (e.g., directly or via operating system control) to modify and enhance the real-time images captured and displayed via the interactive client 104.

[0061] The enhancement system 206 provides functionality related to the generation and distribution of enhancements (e.g., media overlays) for images captured in real time by the camera of the client system 102 or retrieved from the memory of the client system 102. For example, the enhancement system 206 is operable to select, present, and display media overlays (e.g., image filters or image lenses) for the interactive client 104 for enhancing the real-time imagery received via the camera system 204 or the stored imagery retrieved from the memory of the client system 102. These enhancements are selected and presented to the user of the interactive client 104 by the enhancement system 206 based on a number of inputs and data (e.g., the geographic location of the client system 102, interactive platform information of the user of the client system 102, etc.).

[0062] Enhancement can include audio and visual content and visual effects. Examples of audio and visual content include pictures, text, logos, animations, and sound effects. Examples of visual effects include color overlays. Audio and visual content or visual effects can be applied to media content items (e.g., photos or videos) at client system 102 for transmission in a message, or applied to video content such as a video content stream or feed sent from interactive client 104. Therefore, image processing system 202 can interact with and support various subsystems of communication system 208, such as messaging system 210 and video communication system 212.

[0063] Media overlays can include text or image data that can be overlaid on a photo taken by client system 102 or a video stream produced by client system 102. In some examples, the media overlay can be a location overlay (e.g., Venice Beach), the name of a live event, or a business name overlay (e.g., Beach Cafe). In other examples, image processing system 202 uses the geographic location of client system 102 to identify a media overlay that includes the name of a business at the geographic location of client system 102. The media overlay may include other tags associated with the business. The media overlay may be stored in database 128 and accessed by database server 126.

[0064] Image processing system 202 provides a user-based publishing platform that enables users to select a geographic location on a map and upload content associated with the selected geographic location. Users can also specify situations in which specific media overlays should be provided to other users. Image processing system 202 generates a media overlay that includes the uploaded content and associates it with the selected geographic location.

[0065] The augmented creation system 214 supports the augmented reality developer platform and includes applications for content creators (e.g., artists and developers) to create and publish augmentations (e.g., augmented reality experiences) for the interactive clients 104. The augmented creation system 214 provides content creators with a library of built-in features and tools, including, for example, custom shaders, tracking techniques, and templates.

[0066] In some examples, the enhancement creation system 214 provides a merchant-based publishing platform that enables merchants to select specific enhancements associated with a geolocation via a bidding process. For example, the enhancement creation system 214 associates the highest bidding merchant's media overlay with the corresponding geolocation for a predefined amount of time.

[0067] The communication system 208 is responsible for enabling and processing various forms of communication and interaction within the interactive system 100 and includes a messaging system 210, a chatbot system 232, an audio communication system 216, and a video communication system 212. The messaging system 210 is responsible for enforcing temporary or time-limited access to content by the interactive clients 104. The messaging system 210 includes multiple timers within a transient timer system (not shown) that selectively enable access (e.g., for presentation and display) of messages and associated content via the interactive clients 104 based on duration and display parameters associated with a message or collection of messages (e.g., a story). Additional details regarding the operation of the transient timer system are provided below. The audio communication system 216 enables and supports audio communication (e.g., real-time audio chat) between multiple interactive clients 104. Similarly, the video communication system 212 enables and supports video communication (e.g., real-time video chat) between multiple interactive clients 104. The chatbot system 232 is responsible for generating and communicating responses to prompts received from users.

[0068] The user management system 218 is operationally responsible for managing user data and profiles and includes an interactive platform 220 that maintains interactive platform information regarding relationships between users of the interactive system 100 .

[0069] The collection management system 222 is operationally responsible for managing groups or collections of media (e.g., collections of text, images, video, and audio data). Collections of content (e.g., messages, including images, video, text, and audio) can be organized into "event galleries" or "event stories." Such collections can be made available for a specified time period (e.g., the duration of the event to which the content relates). For example, content related to a concert can be made available as a "story" for the duration of the concert. The collection management system 222 is also responsible for publishing an icon to the user interface of the interactive client 104 that provides notification of a particular collection. The collection management system 222 includes curation functionality that enables collection managers to manage and curate specific content collections. For example, a curation interface enables event organizers to curate a collection of content related to a specific event (e.g., removing inappropriate content or redundant messages). In addition, the collection management system 222 employs machine vision (or image recognition technology) and content rules to automatically curate content collections. In some examples, users can be compensated for including user-generated content in a collection. In such cases, the collection management system 222 operates to automatically pay such users for use of their content.

[0070] The mapping system 224 provides various geolocation functions and supports the presentation of map-based media content and messages by the interactive client 104. For example, the mapping system 224 enables the display of user icons or avatars (e.g., stored in the profile data 802) on a map to indicate the current or past locations of the user's "friends" within the context of the map, as well as media content generated by such friends (e.g., a collection of messages including photos and videos). For example, on the map interface of the interactive client 104, messages posted by the user to the interactive system 100 from a particular geographic location can be displayed to the "friends" of the particular user within the context of that particular location on the map. The user can also share his or her location and status information with other users of the interactive system 100 via the interactive client 104 (e.g., using an appropriate status avatar), where the location and status information is similarly displayed to the selected user within the context of the map interface of the interactive client 104.

[0071] The gaming system 226 provides various gaming functions within the context of the interactive client 104. The interactive client 104 provides a gaming interface that provides a list of available games that can be launched by a user within the context of the interactive client 104 and played with other users of the interactive system 100. The interactive system 100 also enables a particular user to invite other users to play a particular game by sending invitations to such other users from the interactive client 104. The interactive client 104 also supports audio, video, and text messaging (e.g., chatting) within the context of game play, provides leaderboards for games, and also supports the provision of in-game rewards (e.g., game coins and items).

[0072] The external resource system 228 provides an interface for the interactive client 104 to communicate with a remote server (e.g., a third-party server 112) to launch or access external resources (i.e., applications or applets). Each third-party server 112 hosts, for example, an application or a small-scale version of an application (e.g., a game application, a utility application, a payment application, or a ride-sharing application) based on a markup language (e.g., HTML5). The interactive client 104 can launch a web-based resource (e.g., an application) by accessing an HTML5 file from a third-party server 112 associated with the web-based resource. The applications hosted by the third-party server 112 are programmed in JavaScript using a software development kit (SDK) provided by the interactive server 124. The SDK includes an application programming interface (API) with functions that can be called or activated by a web-based application. The interactive server 124 hosts a JavaScript library that provides access to a given external resource for specific user data of the interactive client 104. HTML5 is an example of a technology used to program games, but applications and resources programmed based on other technologies can be used.

[0073] To integrate the SDK's functionality into a web-based resource, the third-party server 112 downloads the SDK from the interaction server 124, or the third-party server 112 receives the SDK in some other manner. Once downloaded or received, the SDK is included as part of the application code of the web-based external resource. The code of the web-based resource can then call or activate certain functions of the SDK to integrate the features of the interaction client 104 into the web-based resource.

[0074] The SDK stored on the interactive server system 110 effectively provides a bridge between external resources (e.g., applications 106 or applets) and the interactive client 104. This gives users a seamless experience of communicating with other users on the interactive client 104 while also preserving the appearance of the interactive client 104. In order to bridge the communication between the external resources and the interactive client 104, the SDK facilitates communication between the third-party server 112 and the interactive client 104. The WebViewJavaScriptBridge running on the client system 102 establishes two one-way communication channels between the external resources and the interactive client 104. Messages are sent asynchronously between the external resources and the interactive client 104 via these communication channels. Each SDK function activation is sent as a message and a callback. Each SDK function is implemented by constructing a unique callback identifier and sending a message with the callback identifier.

[0075] By using the SDK, not all information from the interactive client 104 is shared with the third-party server 112. The SDK limits which information is shared based on the needs of the external resource. Each third-party server 112 provides an HTML5 file corresponding to the web-based external resource to the interactive server 124. The interactive server 124 can add a visual representation of the web-based external resource (e.g., a box design or other graphics) in the interactive client 104. Once the user selects the visual representation or instructs the interactive client 104 to access a feature of the web-based external resource through the GUI of the interactive client 104, the interactive client 104 obtains the HTML5 file and instantiates the resource for accessing the feature of the web-based external resource.

[0076] The interactive client 104 presents a graphical user interface (e.g., a login page or title screen) for the external resource. During, before, or after presenting the login page or title screen, the interactive client 104 determines whether the launched external resource has previously been authorized to access the user data of the interactive client 104. In response to determining that the launched external resource has previously been authorized to access the user data of the interactive client 104, the interactive client 104 presents another graphical user interface of the external resource including the functions and features of the external resource. In response to determining that the launched external resource has not previously been authorized to access the user data of the interactive client 104, after displaying the login page or title screen of the external resource for a threshold period of time (e.g., 3 seconds), the interactive client 104 slides up a menu (e.g., animating the menu to emerge from the bottom of the screen to the middle or other portion of the screen) for authorizing the external resource to access the user data. The menu identifies the type of user data that the external resource is authorized to use. In response to receiving a user selection of the accept option, the interactive client 104 adds the external resource to the list of authorized external resources and allows the external resource to access the user data from the interactive client 104. External resources are authorized by the interactive client 104 to access user data under the OAuth 2 framework.

[0077] The interaction client 104 controls the type of user data shared with the external resource based on the type of external resource that is authorized. For example, an external resource comprising a full-scale application (e.g., application 106) is provided with access to a first type of user data (e.g., a two-dimensional avatar of the user with or without different avatar characteristics). As another example, an external resource comprising a small-scale version of an application (e.g., a web-based version of the application) is provided with access to a second type of user data (e.g., payment information, a two-dimensional avatar of the user, a three-dimensional avatar of the user, and an avatar with various avatar characteristics). Avatar characteristics include different ways to customize the appearance of an avatar (e.g., different poses, facial features, clothing, etc.).

[0078] The advertising system 230 operatively enables third parties to purchase advertisements for presentation to end users via the interactive clients 104 and also handles the delivery and presentation of these advertisements.

[0079] Chatbot system

[0080] According to some examples, Figure 3A is a diagram of an interactive session between a user and a chatbot system, Figure 3B is an illustration of a block diagram of a chatbot system, and Figure 3Cis an illustration of a process flow diagram of a chat and advertising process of a chatbot system. The chatbot system 300 uses the chat and advertising process to conduct a chat session with a user during a (first) interactive session and to provide advertising content to the user in a later (second) interactive session.

[0081] In some examples, the chatbot system 300 is a software application designed to simulate human conversation through voice commands or text chat. It can use natural language processing (NLP) and machine learning (ML) / artificial intelligence technology to understand and interpret user input and generate responses.

[0082] In some examples, the chatbot architecture includes a natural language understanding (NLU) component and a dialog management component. The NLU component is responsible for understanding the user's intent and extracting relevant information from the user's input. This is achieved by analyzing the user's input and mapping it to the intent. The NLU component can use various techniques, such as rule-based systems, statistical models, and neural networks, to understand the user's input. Meanwhile, the dialog management component generates responses to the user's input. The appropriate response is determined using the intent and any information extracted from the NLU component. This can be accomplished using rule-based systems, decision trees, or machine learning models, among others.

[0083] In some examples, the chatbot system 300 can use generative AI models such as the Large Language Model (LLM) 338 to improve its natural language understanding (NLU) and dialogue management capabilities. Figure 6 and Figure 7 Describes LLM 338 more fully.

[0084] In some examples, the chatbot system 300 can use LLM 338 to analyze user input and extract relevant information, such as the user's intent and entities. LLM 338 can also be used to identify and extract important information from unstructured text, such as the user's question or request. This can be accomplished using techniques such as named entity recognition, part-of-speech tagging, sentiment analysis, and the like.

[0085] When the NLU component has extracted relevant information from the user's input, the dialog management module can generate an appropriate response using LLM 338. LLM 338 can be used to generate responses in a human-like manner by using techniques such as text generation, machine learning models, etc.

[0086] In some examples, the knowledge base of the chatbot system 300 includes a set of information that the chatbot can use to understand and respond to the user's input. This includes a predefined set of intents, entities, and responses, as well as external information sources such as databases or application programming interfaces (APIs). In some examples, the intent information of one or more friends of the user can be used to understand, inform, and / or respond to the user's intent.

[0087] In some examples, the chatbot system 300 can be integrated into various platforms such as websites, messaging applications, and mobile applications, enabling users to interact with the chatbot system through text or voice commands.

[0088] In operation 302 of the chatbot method 374, the chatbot system 300 receives a prompt 328 from a user from a client system 336 during a first interactive session. For example, the user uses the client system 336 to access an interactive server hosting the chatbot system 300. The user enters a prompt, such as prompt 328, into the client system 336, and the client system transmits the prompt 328 to the chatbot system 300. In some examples, the prompt 328 may include other types of data in addition to text, such as, but not limited to, image data, video data, audio data, electronic documents, links to data stored on the Internet or on the client system 336, and the like. Regardless of the data type of the prompt 328, keyword attributes and expansions may be used to automatically generate clusters of keywords or attributes associated with the received prompt 328. For example, image recognition may be deployed to identify objects and locations associated with the image data and generate keyword clusters or clouds that are then associated with the image-based prompt.

[0089] Furthermore, prompts may be received through any number of interfaces and I / O components (e.g., I / O component 1108) of client system 102. These include gesture-based input obtained from biometric components and input received via a brain-computer interface (BCI).

[0090] In operation 304, the chatbot system 300 generates a response 370 based on the LLM 338 (LLM) through one or more processors. For example, the chatbot system 300 receives the prompt 328. The chatbot system 300 generates the response 370 using the LLM 338.

[0091] The chatbot system 300 generates an original response 362 based on the user's prompt, generates an adjusted input prompt 368 based on filtering the original response 362, and generates a new response based on the adjusted input prompt 368. The response filter component 340 uses a set of filtering criteria to eliminate specific content from the user feedback 360, such as offensive words or concepts, or content that some people may consider harmful. The chatbot system 300 generates the adjusted input prompt 368, which is transmitted to the LLM 338 as the prompt 328.

[0092] In some examples, LLM 338 is hosted by the same system that hosts the other components of chatbot system 300. In some examples, LLM 338 is hosted by a server system separate from the system that hosts chatbot system 300, and chatbot system 300 communicates with LLM 338 over a network. For example, chatbot system 300 receives a user prompt and transmits the user prompt to LLM 338, which resides on a separate system. LLM 338 receives prompt 328 and generates a raw response 362. LLM 338 then transmits raw response 362 to chatbot system 300. Chatbot system 300 receives raw response 362 for subsequent processing.

[0093] In some examples, the chatbot system 300 generates a set of potential responses and selects a response from the set of potential responses. In some examples, the chatbot system 300 transmits the potential responses to the client system 336, and the client system 336 displays them to the user, who then selects the response that best applies to the user's prompt.

[0094] In some examples, as part of response 370, the chatbot system 300 generates a set of chatbot system prompts that are displayed by the client system 336 to the user and prompt the user to interact with the chatbot system 300. The chatbot system prompts generated by the chatbot system 300 can include context-sensitive material, instructions to the user, possible conversation topics, and the like. In some examples, the chatbot system 300 uses the chatbot system prompts to suggest conversation topics to the user or to guide the user through the conversation, such as providing instructional material on various topics. In some examples, the chatbot system prompts include suggestions for conversations or questions intended to solicit user input for the user prompts. In such examples, the suggested conversations are intended to help the user obtain the information they need, but have the helpful side effect of generating additional user interaction with the chatbot system 300, from which intent can be inferred.

[0095] In operation 306, the chatbot system 300 determines user intent 366 based on the user prompt 328 and the response 370. For example, the logging component 350 receives the prompt 328, the potential response 364 and the response 370, and any subsequent messages, and transmits them to the intent processing component 348, which includes a parallel intent processing pipeline. The pipeline uses natural language processing (NLP) methods to map grouped conversations to a set of intended keywords and concepts. In addition to the keywords used in the original prompt, stem keywords and expanded concepts are generated. The platform also assigns weights to each concept based on the importance of those concepts in the conversation and their commercial weight. These keywords and concepts are aggregated and mapped to the user as part of an intent profile or intent vector with keywords and concepts weighted based on the importance of those keywords in the conversation.

[0096] In some examples, the chatbot system 300 collects a set of prompts during an interactive session, as illustrated by prompt 328, additional prompt 372, and additional prompt 330. The chatbot system 300 maps the set of prompts to a set of keywords and / or concepts comprising a user intent vector, as illustrated by keyword 332 and concept 334. The chatbot system 300 assigns weights to keywords in the set of keywords and / or concepts based on their importance scores to the conversation, and determines user intent based on the user intent vector comprising the weighted keywords and / or concepts.

[0097] In some examples, the chatbot system 300 stores the conversation state in the user profile database 354 for a series of interactive sessions so that the chatbot system 300 can have the context of the conversation that occurred over multiple interactive sessions.

[0098] Any conversation data collected by the chatbot system 300 is captured and cached only with user approval and is deleted upon user request. Furthermore, such conversation data may be used for very limited purposes, such as generating responses by the chatbot system 300. To ensure the restricted and authorized use of conversation data and other PII, access to this data is limited to authorized personnel (if any). Any use of conversation data may be strictly limited to chatbot purposes, and the conversation data will not be shared or sold to any third party without the user's explicit consent. Furthermore, appropriate technical and organizational measures are implemented to ensure the security and confidentiality of this sensitive information.

[0099] In some examples, the chatbot system 300 determines the personality or tone of responses generated by the chatbot system 300. For example, the chatbot system 300 stores the user's conversational state as part of the user's profile stored in the user profile database 354. The chatbot system 300 uses the conversational state and demographic or other information about the user to determine the user's personality or tone, for example by adopting a formal tone for older users and a more informal tone for younger users. The user may also have the ability to specifically change the "persona" of their interaction with the chatbot system by specifically requesting the chatbot system 300 to respond or act in a particular way (e.g., "more interesting," "answer in a riddle," etc.). In addition to modifying the personality or tone of responses, the visual interface presented by the chatbot system 300 may also be changed to reflect the particular "persona" of the chatbot system 300. In some examples, a sliding toggle may be presented to enable the user to select between a menu of persona traits (e.g., "cheeky," "wry," "cute," etc.).

[0100] In some examples, the chatbot system 300 associates a time factor with a keyword or concept, where the time factor decays over time. For example, the chatbot system 300 attaches a time factor to keywords and concepts that indicates how fresh the concept should be for targeting and bidding. For example, "hotels in Cancun for a spring break" and "planning a wedding next year" would have two different decay factors. In some examples, the chatbot system 300 applies the time factor to the conversation state.

[0101] In some examples, overall user intent is established using various signals or data, such as user demographics, location, device, engagement with the interactive platform's organic surface or interactive platform applications' characteristics and consumption patterns, and overall friend graph proximity carrier signals or data discernible from the user's connection to the interactive platform.

[0102] In some examples, the intent vector is an additional dimension that will be used to refresh and update the intent profiles stored in the user profile database 354.

[0103] In some examples, the chatbot system 300 uses the user profile 376 from the user profile database 354 that includes interactive platform data for the user.

[0104] In some examples, the chatbot system 300 generates the advertising content 358 using a user's interaction with previously provided advertising content, where the interaction was captured during the second interactive session. For example, the chatbot system 300 is a component of an interactive platform system that provides advertising content 358 to the user in the context of the user's interaction with the interactive platform system, outside of the user's interaction with the chatbot system itself. The chatbot system 300 receives data about the user's interaction with the advertising content 358 in the advertising analytics database 344 and uses the data about the user's interaction to determine how effective the intent processing component 348 is in determining the user's intent.

[0105] In some examples, the intent processing component 348 uses artificial intelligence methods including machine learning (ML) models to generate user intent 366. The chatbot system 300 uses data about user intent and conversation context to improve its targeting and optimization capabilities over time by ingesting feedback. The chatbot system 300 collects user engagement on advertisements, organic surfaces, or features of the interactive platform system, and also responds to the chatbot system 232 itself and feeds it into the intent processing component 348. Thus, the chatbot system 300 can fine-tune or further pre-train the ML model of the intent processing component 348 to not only consider user intent, but also use subsequent actions to fine-tune the user intent inference model.

[0106] In operation 308, the chatbot system 300 determines the advertising content 358 based on the user intent 366 and the response 370, as shown in FIG. Figure 3D More fully described.

[0107] In operation 310, the chatbot system 300 transmits advertising content 358 to the client system 336 during the second interactive session. Figure 1 The user interacts with the interactive system 100 and accesses some additional features of the interactive platform. When the user interacts with the interactive system 100, the interactive system 100 provides advertising content 358 outside the initial interactive session in which the prompt is received and the response is generated.

[0108] In some examples, the system hosting the chatbot system 300 may not be a component of the interactive platform, but rather another interactive system that provides services and information to a user group, such as, but not limited to, a platform that provides enterprise-wide connectivity to user groups such as employees of a company, clients of a business providing professional services, educational institutions, etc. In some of these examples, the content provided to users may not be advertisements, but may be other types of useful information, such as company policies, status messages for projects, newsworthy events, etc.

[0109] In some examples, end-to-end encryption is used to protect communications, ensuring that only the sender and intended recipient can read the messages being exchanged. By implementing end-to-end encryption, the chatbot system 300 can provide users with a secure and private messaging experience while still extracting intent for ad experience enhancement. In the context of user intent extraction, this means that once the conversation is end-to-end encrypted, the chatbot system 300, as one end of the conversation, can decrypt the messages and pass them to the intent extraction pipeline of the intent processing component 348.

[0110] In some examples, the chatbot system 300 is operably connected to an Internet search engine or the like, and a user can use the chatbot system 300 as an intelligent search engine to search the Internet.

[0111] In some examples, the chatbot system 300 is operably connected to a specialized database, and the user can use the chatbot system 300 as an intelligent search assistant for searching the specialized database.

[0112] In some examples, LLM 338 is continuously retrained using information about advertising content 358 stored in advertisement and campaign database 346. For example, LLM 338 is trained on the latest products offered by advertisers on interactive system 100 and provides product information about the latest models of a particular product category in response to a request by a user for those products.

[0113] In some examples, the LLM 338 is continuously retrained or fine-tuned based on user interactions with the advertising content 358. For example, the interactive system 100 collects advertising content engagement metrics and stores the metrics in the advertising analytics database 344. The metrics are then used to provide reinforcement to the LLM 338 when the LLM 338 provides response sequences that result in successful user intent determinations and, therefore, appropriately targeted advertising content 358 with which the user interacts.

[0114] In some examples, the chatbot system 300 uses conversations between users and other chatbots as input into the intent processing component 348. Other chatbots can be sponsored chatbots, custom chatbots built by users from self-service tools / templates, etc.

[0115] In some examples, the number of messages that the chatbot system 300 can receive after the chatbot system 300 enters the conversation is limited in number, limited in the time the chatbot system 300 can retain the messages, and / or limited in the scope of what the chatbot system 300 can do with the messages. In some examples, for transparency, the chatbot system 300 explicitly indicates that the chatbot system 300 has joined the conversation. In some examples, the chatbot system 300 provides disclosure about what is being shared via both a presence indicator and / or other chat affordances. In some examples, the disclosure includes a statement that the chatbot system 300 is receiving messages to improve the service provided to the user.

[0116] In some examples, the information the chatbot system 300 extracts from the conversation focuses on user intent. Furthermore, the chatbot system 300 facilitates conversations with users by understanding their intent (e.g., if a user asks for good hotels in Cancun, the chatbot system 300 responds with, "Here's a list of hotels. I also know a great promotion for a hotel, would you like to see it?"). This provides a way to extract user intent from the user, match that intent with potential ads, and embed that knowledge into the response. In some examples, the chatbot system 300 enhances responses with "popular with friends" lists.

[0117] In some examples, the text component of the advertisement is used to fine-tune the response of the LLM 338, thereby regulating the response of the LLM 338. This improves the suggestions of the chatbot system 300 and improves user engagement.

[0118] Figure 3D is an illustration of a process flow diagram of an advertisement creation process according to some examples. The chatbot system 300 uses the advertisement creation process to create advertisement content 358 that is provided to users outside the context of an interactive chat session.

[0119] In operation 312, the chatbot system 300 receives a landing page website or application from an advertiser for analysis. For example, the chatbot system 300 receives a landing page website or application from an advertiser. This landing page or application contains up-to-date and accurate information about the advertiser's product or service offerings. The chatbot system 300 uses natural language processing technology to analyze the received landing page / application to extract useful details such as product features, visual assets, and brand elements. The chatbot system 300 extracts this information so that it can then generate targeted and relevant ad creatives that accurately reflect the advertiser's offerings. By receiving and analyzing the advertiser's own landing page / application, the chatbot system 300 is able to create customized ad content that aligns with the advertiser's messaging and branding.

[0120] In operation 314, the chatbot system 300 receives additional media assets such as images and videos from the advertiser. For example, in operation 314, the chatbot system 300 receives additional media assets such as images and videos from the advertiser. By obtaining these supplementary visual media assets directly from the advertiser, the chatbot system 300 can incorporate elements that authentically represent the advertiser's brand identity and product offerings. The chatbot system 300 uses computer vision technology to analyze the received images and videos to identify relevant visual components. These components (such as product images, brand logos, and video testimonials) provide additional creative elements that the chatbot system 300 can integrate when generating customized advertising content for the advertiser. By obtaining authentic brand images and videos from the advertiser, the chatbot system 300 is equipped to generate compelling advertising creatives that resonate with the advertiser's target audience.

[0121] In operation 316, the chatbot system 300 receives additional context from the advertiser, such as product specifications, product catalogs, and other relevant assets. For example, in operation 316, the chatbot system 300 receives additional context from the advertiser, such as product specifications, product catalogs, and other relevant assets. By obtaining supplemental information directly from the advertiser, the chatbot system 300 can better understand the full capabilities and value proposition of the advertiser's offering. The chatbot system 300 uses natural language processing to analyze the received product details and catalogs to identify key attributes and messaging. These insights (such as technical specifications, usage scenarios, and benefits) enable the chatbot system 300 to create ad copy and creative that accurately captures the essence of the product or service. By obtaining relevant contextual information from the advertiser, the chatbot system 300 can generate ads with customized messaging and visuals to promote the unique selling points and differences of the offering. The additional context equips the chatbot system 300 to produce ads that resonate with the target audience.

[0122] In operation 318, the chatbot system 300 receives a selection from the advertiser of various potential directional themes and templates for creating an ad creative. For example, the chatbot system 300 receives a selection from the advertiser of potential directional themes and templates for creating an ad creative. By enabling the advertiser to select from different creative themes and templates, the chatbot system 300 aligns the visual style and messaging tone of the generated ad with the advertiser's brand and objectives. The advertiser's selection provides guiding creative direction to the chatbot system 300 as it assembles visual, textual, and contextual components into an ad creative. With the advertiser's input on preferred themes and templates, the chatbot system 300 can generate customized ads that align with the look, feel, and messaging the advertiser aims to project in their marketing campaign. The selected creative direction guides the chatbot system 300 to generate ads with a design, layout, and copy that helps the advertiser's content resonate with its target audience.

[0123] In operation 320, the chatbot system 300 receives target keywords and concepts from advertisers. For example, in operation 320, the chatbot system 300 receives target keywords and concepts from advertisers. By obtaining specific keywords and concepts directly from advertisers, the chatbot system 300 can incorporate messaging into the generated advertisements that are directly relevant to the advertiser's offering and target audience. The chatbot system 300 uses natural language processing to analyze the received keywords to identify key messaging topics. These targeted keywords and expanded concepts enable the chatbot system 300 to generate ad copy and creatives that contain precise terms and messaging to effectively reach and resonate with the intended audience. The keywords and concepts supplied by the advertiser provide the chatbot system 300 with the exact language needed to create compelling advertisements that are customized to promote the advertiser's products or services to the desired customer segments.

[0124] In operation 322, the chatbot system 300 extracts potential additional assets and metadata from the destination website or app, taking into account the input keywords and concepts. For example, in operation 322, the chatbot system 300 extracts potential additional assets and metadata from the advertiser's website or app, taking into account the input keywords and concepts. By programmatically analyzing the advertiser's digital presence, the chatbot system 300 can discover complementary creative elements, such as images, videos, and textual content. The chatbot system 300 utilizes computer vision, natural language processing, and data mining techniques to identify relevant components from websites and apps. These extracted creative assets and metadata, combined with the advertiser's supplied keywords and concepts, equip the chatbot system 300 with a robust set of components for assembling compelling, branded advertising creatives. By algorithmically harvesting assets from the advertiser's channels, the chatbot system 300 can generate customized ads tailored to promote the advertiser's brand and offerings.

[0125] In operation 324, the chatbot system 300 uses the creative generation component 356 to generate a series of advertising content creatives based on the information. For example, the creative generation component 356 of the chatbot system 300 uses all the collected information and assets to automatically generate a set of advertising content creatives. Specifically, the creative generation component 356 uses the product details, brand guidelines, target keywords, creative direction, and digital assets collected in previous operations to algorithmically generate multiple versions of advertisements customized for the advertiser. Using advanced generative AI technology, the creative generation component 356 synthesizes a unique combination of images, text, logos, and layouts into customized advertising creatives that are consistent with the advertiser's brand, products, and target audience. By putting together all the input provided by the advertiser along with the extracted metadata and assets, the creative generation component 356 can efficiently and automatically generate high-quality, strategic advertising creatives on behalf of the advertiser.

[0126] In operation 326, the chatbot system 300 modifies the delivery of advertising content based on user engagement with the advertising content. For example, the chatbot system 300 modifies the delivery of advertising content based on user engagement with the advertisement. Specifically, the chatbot system 300 tracks metrics such as click-through rate, conversion rate, and dwell time for the generated advertisements. Using this engagement data, the chatbot system 300 can determine the best-performing advertisements and optimize ad delivery accordingly. For example, advertisements with higher click-through rates or conversion rates may be shown more frequently or to a wider audience. Conversely, poorly performing advertisements may be shown less frequently or stopped altogether. The chatbot system 300 can also iterate on ad creative, copy, placement, etc. based on observed user engagement patterns. By leveraging user feedback and ad performance data, the chatbot system 300 refines both ad creation and ad delivery to maximize results for advertisers. This enables the system to automatically optimize campaigns and deliver advertisements that resonate most with target users.

[0127] In some examples, the chatbot system 300 uses the ad content delivery and bidding component 352 to provide advertisers with the opportunity to bid on certain actions by selecting keywords or an expanded set of concepts (auto-expansion) to select their potential target audience and display ad content 358 that will be delivered to users who match the criteria within their intent vector. Overall, the ad content delivery and bidding component 352 of the chatbot system 300 enables advertisers to more accurately find their target audience by mapping conversations to a set of keywords and concepts and adding a time factor to the set of keywords and concepts, and ultimately mapping these to user intent and profiles.

[0128] In some examples, the chatbot system 300 includes an ad targeting component 378. Ad targeting component 378 leverages user intent and interests extracted from conversations with the chatbot system 300 to target and deliver relevant ads to users. For example, ad targeting component 378 analyzes the user intent vector, which includes weighted keywords and concepts, determined by intent processing component 348. It matches these keywords and concepts with the targeting criteria specified by advertisers for their ad campaigns, stored in the ad and campaign database 346. Ads are ranked based on the degree of match between the user intent vector and the advertiser's goals. Ads with higher relevance are delivered first. The ad targeting component also considers other targeting parameters from the user profile database 354, such as user demographics, location, and platform engagement history. Furthermore, ad targeting component 378 uses feedback stored in the ad analytics database 344 to track user engagement with delivered ads. Ad targeting component 378 optimizes ad targeting over time by determining which ads drive higher engagement for which user intents.

[0129] In some examples, the chatbot system 300 includes an ad ranking component 380. The ad ranking component 380 determines the priority and order in which ads are displayed to users of the interactive platform. Ad Targeting The ad ranking component 380 uses user intent from the chatbot conversation to deliver highly personalized, relevant ads to each user.

[0130] In some examples, ad ranking component 380 ranks and scores ads using various criteria, such as, but not limited to:

[0131] Relevance to user intent vector — Ads are ranked higher if they closely match keywords / concepts that the user expressed interest in during the chatbot conversation.

[0132] Expected Engagement – ​​Scores ads based on historical click-through rates, conversion rates, and dwell time for different user intents.

[0133] Bid Amount – Advertisers can bid for specific keywords / concepts. Higher bids affect ad ranking.

[0134] Landing Page Relevance – Analyzes your ad’s landing page for relevance to user intent. More relevant landing pages improve ad ranking.

[0135] Advertiser Budget - Ad ranking takes into account the remaining budget of an advertiser's campaign.

[0136] In some examples, ad ranking component 380 uses a machine learning model to combine one or more factors to assign a final ranking score to an ad. Ad ranking component 380 selects the top-ranked ads to display to each user.

[0137] In some examples, the ad ranking component 380 continuously monitors engagement with ranked ads and refines the model to improve ranking accuracy over time. This allows the most relevant ads to be surfaced to the user based on the user's conversational intent with the chatbot system.

[0138] In some examples, ad ranking component 380 can expand or contract targeting as it learns which concepts map better to user responses.

[0139] In some examples, the AI-driven ad creative generation component 356 of the chatbot system 300 assists advertisers by simplifying the process of creating ad creatives. By providing input such as a website, target app, additional assets, and target keywords, the chatbot system 300 can automatically generate ad creatives. This can save advertisers time and resources, allowing them to focus on other aspects of their advertising campaigns.

[0140] In some examples, the chatbot system 300 utilizes machine learning methods to optimize ad content 358 creatives over time. The chatbot system 300 tests multiple permutations of generated ad content 358 to determine which permutations perform best. This process is particularly applicable to dynamic product ads generated based on the dynamic catalog stored in the ad and campaign database 346. This improves ad performance and increases the chance of success, ultimately providing advertisers with a better return on investment. The chatbot system 300 not only saves advertisers time and resources, but also increases the chance of success by providing the most relevant and effective ad content 358 creatives to the target audience.

[0141] In some examples, the chatbot system 300 measures the similarity between the expanded concept of the conversation with the user and the advertiser's ad concept or context. This allows advertisers to use not only specific words but also sentences and descriptions that they want to promote. In some examples, ad relevance is the distance between the ad concept or context of the conversation and the expanded concept.

[0142] According to some examples, Figure 4A Is a chat robot system 300 ( Figure 3A ), and Figure 4B is an activity diagram of a method of the chatbot system 300 .

[0143] In operation 402, a user uses an interactive platform application 408 (e.g., Figure 1 The chatbot system 300 is accessed through an application 106 executed on the client system 102, allowing users to chat with the chatbot system 300 or add it to an existing chat. For example, users access the chatbot system 300 using the interactive platform application 408, allowing them to chat directly with the chatbot system 300 or add it to an existing conversation. The interactive platform application 408 provides a user interface through which users can interact with the chatbot system 300. Within the interactive platform application 408, users have the option of initiating a one-on-one chat session with the chatbot system 300 or bringing the chatbot system 300 into a group chat or messaging thread. This gives users the flexibility to engage the chatbot system 300 in personalized conversations or within the context of ongoing discussions with other users. Through the interactive platform application 408, users can send text prompts to the chatbot system 300 and receive conversational responses. By accessing the chatbot system 300 through the interactive platform application 408, users can leverage the chatbot's capabilities to obtain information, recommendations, and other services through a natural flow of conversation.

[0144] In operation 404, the complete conversation 410 is transmitted to the LLM 338. For example, the entire conversation between the user and the chatbot system 300 is transmitted to the large language model (LLM) 338. This provides the LLM 338 with the complete context of the interactive conversation, including the initial prompt from the user and any subsequent messages. By analyzing the complete exchange, including the complete conversation, the LLM 338 can better understand the intent and meaning behind the user's query. In addition, having access to the complete conversation flow enables the LLM 338 to maintain continuity and generate responses that logically follow the previous part of the conversation. Compared to just viewing the individual messages in isolation, this conversation context enables the LLM 338 to produce more natural, relevant responses. Feeding the complete back-and-forth conversation back to the LLM 338 enables it to have a more comprehensive understanding of the interaction and, in turn, generate better responses.

[0145] In operation 406, the response 412a and chat are sent back to the user from the output selector component 342. The response 412a and chat may include a text response, a link to the content, related advertisements, or any other response. For example, the output selector component 342 determines the most appropriate response type to be returned, which may include a text response, a link to related content, an advertisement directed to the user's interests, or any other appropriate response. In some examples, the output selector component 342 may determine that a text response is most suitable for factual questions, while an advertisement for a product or service may be most relevant for a commercial query. The output selector component 342 selects from the available response types to provide the user with the most useful customized information. By supporting multiple response formats such as text, links, and advertisements, the chatbot system 300 can dynamically provide the user with the most appropriate reply type for each conversation round. This allows the chatbot system 300 to have a diverse and engaging conversation with the user.

[0146] In some examples, in addition to short replies, more detailed text responses are generated by the chatbot system 300. To this end, the LLM 338 generates longer, more elaborate responses. The output selector component 342 provides additional context 414 to the LLM 338 to help construct this longer response. For example, the output selector component 342 can supply conversation history, user profile data, or other supplemental information to give the LLM 338 more context. Equipped with this additional context, the LLM 338 is able to produce richer, more natural-sounding long responses. The output selector component 342 determines when a conversation requires more elaboration and leverages the LLM 338's ability to generate clear, contextual responses that are multiple sentences or paragraphs in length. This enables the chatbot system 300 to handle user queries that require more than just short, simple responses.

[0147] In some examples, LLM 338 is fine-tuned to conduct conversations within the context of the interactive platform hosting chatbot system 300, taking into account additional user profile data 416 from user profile database 354. LLM 338 is customized to incorporate details from user profiles on the interactive platform, such as their demographics, interests, and past activities. This enables LLM 338 to gain a fundamental understanding of who the user is and tailor its responses accordingly. In some examples, LLM 338 is adapted to utilize additional contextual 414 signals that may be relevant to conversations on the interactive platform. This includes factors such as the user's friends, location, time of day, and recent interactions on the platform. By considering these contextual clues, LLM 338 can generate more contextual and personalized responses. By fine-tuning LLM 338 using profile data and additional context from the interactive platform, chatbot system 300 can generate more natural, intuitive, and engaging conversations for users within the specific environment of the interactive platform. This platform-optimized training helps meet user needs and expectations for conversations on the interactive platform.

[0148] In some examples, the LLM 338 response 418 is sent to the intent processing component 348 along with the LLM 338 context (conversation embedding) and additional context, such as the initial intent from the LLM 338. The intent processing component 348 defines the skill context 434 and details (e.g., keywords) to the various relevant skill modules 422, and detects user intent and conversation state 420. For example, the intent processing component 348 analyzes the conversation between the user and the chatbot system 300 to extract important keywords, entities, and details. It passes these contextual clues to the various skill modules that can generate relevant responses. In addition, the intent processing component 348 utilizes machine learning models to infer the user's true intent and the state of the conversation from contextual signals. For example, the output selector component 342 detects whether the user is asking to buy diapers or requesting a Wikipedia definition. By extracting conversation details and detecting user intent, the intent processing component 348 enables downstream components to generate responses customized to the user's needs.

[0149] In some examples, skill module 422 includes dynamic content module 426. Dynamic content module 426 provides relevant, personalized information to users during a conversation by leveraging various data sources and generative techniques. Some examples of dynamic content operations include:

[0150] Retrieve user-specific data such as preferences, purchase history, calendar events, etc. to provide customized responses.

[0151] Generate personalized recommendations for products, services, content, etc. tailored to the user.

[0152] Synthesize relevant news articles, social media posts, weather forecasts, etc. about the topic being discussed.

[0153] Instantly create dynamic visualizations such as charts, graphs, maps, etc. to visualize user-requested data.

[0154] Generate custom images or multimedia to illustrate points in a conversation.

[0155] Generate audio clips with relevant sound effects, background music, etc. to engage users.

[0156] Integrate with APIs, databases, and websites to get the latest information as needed.

[0157] Adapt responses based on real-time data to reflect the latest offers, deals, product pricing, and more.

[0158] Update responses with real-time data such as sports scores, stock prices, traffic, etc.

[0159] Synthesize previous parts of the conversation into a summary to provide context.

[0160] The dynamic content module 426 utilizes various data sources and generative models to create unique, personalized dynamic content on the fly during a conversation. This makes the conversation more engaging and relevant to each user.

[0161] In some examples, the skills module 422 includes a dynamic interactive platform advertising module 424. The dynamic interactive platform advertising module 424 provides relevant targeted advertisements to the user during the conversation. The operations of the dynamic interactive platform advertising module 424 include:

[0162] Analyze conversation context and user profiles to determine user interests and intent.

[0163] Use this understanding of user intent to retrieve and rank relevant ads from ad inventory.

[0164] Instantly generate personalized ad copy and creative tailored to the user.

[0165] Dynamically insert highly relevant ads at appropriate points in the conversation.

[0166] Adapt ad creative elements like images, video, and audio to the context of the conversation.

[0167] Update ads with the latest pricing, deals, and offers pulled from real-time ad data.

[0168] Pull real-time performance data to optimize ad targeting and increase relevance.

[0169] Provide interactive ad experiences such as mini-games, polls, special offers, etc.

[0170] • Enable users to provide feedback on ads to further refine targeting.

[0171] Measure ad engagement, clicks, and conversion rates to evaluate and improve ad performance.

[0172] Follow platform advertising policies and adhere to user preferences.

[0173] The dynamic interactive platform advertising module 424 leverages user intent, conversation context, and advertising data to deliver highly dynamic, personalized, and relevant advertising within the conversation experience. This helps users see the ads they want to see and helps advertisers connect with the right customers.

[0174] In some examples, the skills module 422 includes an open domain knowledge module 428. Operations of the open domain knowledge module 428 include:

[0175] Answer factual questions by searching knowledge bases such as Wikipedia, Wikidata, and DBpedia.

[0176] Provide definitions, explanations, and descriptions of concepts that users inquire about.

[0177] Summarize key information from a long article, paper, or paragraph that is relevant to the user's query.

[0178] Produce visual aids such as infographics, charts, timelines, and maps to illustrate complex topics.

[0179] Enables clarifying follow-up questions from users to refine their information needs.

[0180] · Rank and filter responses to provide the most relevant and helpful information to users.

[0181] For transparency, cite sources and link to the original references.

[0182] Leverage large language models pre-trained on a large text corpus to generate informative responses.

[0183] Ingest new information from various structured data sources.

[0184] Ask users for feedback to improve the quality of the information provided.

[0185] Follow ethical guidelines regarding accuracy, attribution, and reliability of information.

[0186] The open domain knowledge module 428 provides users with informative, trustworthy, and useful information on any topic they query by leveraging open data resources in a responsible manner. The goal is to enhance the conversational experience with the world's knowledge.

[0187] In some examples, the skills module 422 includes a generative AI response module 430. Some operations of the generative AI response module 430 include:

[0188] Generate natural language responses to user input using large language models such as LLM 338

[0189] • Allow open discussion on a wide range of topics beyond questions and answers.

[0190] Maintain context and consistency across multiple turns of a conversation.

[0191] Demonstrate personality and emotional intelligence through word choice and tone.

[0192] Provide nuanced, non-repetitive responses tailored to each user input.

[0193] Incorporate world knowledge from a pre-training corpus into responses.

[0194] Enable hybrid proactive conversations where both users and AI contribute.

[0195] Dynamically adjust response style, length, and depth based on user preferences.

[0196] ●Seamlessly integrated with other modules such as speech, vision, and knowledge.

[0197] ●Learn from user feedback and conversations to improve over time.

[0198] Ensure responses comply with platform content policies and community guidelines.

[0199] · Attribution of sources when incorporating external information into responses.

[0200] Indicate whether the response is speculative or factual.

[0201] The generative AI reply module 430 leverages AI to produce human-like, engaging conversations tailored to each user and conversation context while satisfying interactive platform policies.

[0202] Various related skill modules 422 return skill responses 432 as ( Figure 3AThe skill reply 432 is sent back to the output selector component 342 as a potential response 364 to continue the dialogue 410, which may include suggestions for dynamic content, related ads, open field responses, etc. following the output of the skill module described above.

[0203] The output selector component 342 determines which response is more appropriate for the current stage of the conversation 410 and returns the skill reply 432 to the LLM 338 for natural answer generation, or uses the already generated responses 412a and 412b and returns them directly to the interactive platform application 408 and the user.

[0204] In some examples, LLM338 is fine-tuned for chatting in an approved chat style for an approved interactive platform, providing safe responses, respecting interactive platform values, providing multiple persona traits as described above, incorporating user context and / or previous conversation history, and optionally returning high-level intent.

[0205] In some examples, the intent processing component 348 is based on AI components such as neural networks and / or business logic designed to determine important interactive platform intents (e.g., information search, playing games, chatting, etc.) and their attributes (information search - baby diaper replacement). The model is trained to extract intent from the LLM 338 context or other embeddings of the conversation and conversation history. In addition to the model, simpler models such as keyword extraction and classification can also be applied to enrich the intent details. The intent processing component 348 provides these details to the various skill modules 422. In some examples, the skill modules 422 are a set of parallel modules, each designed to return a response based on a separate capability and focus. For example, given the intent and details, the dynamic interactive platform advertising module 424 re-ranks and selects the most appropriate advertisements to place as results, while given the intent and context, the generative AI reply module 430 will use generative AI capabilities to generate multimedia results.

[0206] In some examples, not all skill modules are necessarily used for every intent, but for some intents, several modules may be used to generate several alternatives for responses. The output selector component 342 applies business logic to select the most appropriate outcome at each turn based on business policies, their relative effectiveness, and other metrics.

[0207] Figure 5A and Figure 5B is an illustration of a user interface according to some examples. Figure 3BThe chatbot system 300 uses a user interface to communicate that the chatbot system 300 is active and available for interaction with a user, and can obtain information about the user's interaction with the interactive platform. User interaction with the chatbot system 300 can be multimodal. In some examples, a user can directly interact with the chatbot system 300 through a direct exchange of user prompts and chatbot responses. In some examples, two or more users can interact with each other, while the chatbot system 300 monitors the interactions to discern user intent from one or more users. In some examples, the chatbot system 300 is available in the user interface for a user to invoke during a chat session with another user.

[0208] In some examples, the chatbot system 300 shows that the chatbot system 300 is listening to the conversation by adding a chatbot icon 502 as a member of the chat in the presence bar (i.e., alongside friend Bitmojis, characters). In some examples, the chatbot system 300 provides a chatbot icon 504 to represent the chatbot system 300 as a member of the chat using an avatar. The user clicks the chatbot icon 504 on the presence bar to start asking the chatbot system 300 a question or writes @chatbot in the chat bar. In some examples, when the chatbot system 300 is preparing a response to a query, 300 uses an "X typing" style visual as a loading indicator. In some examples, the user uses "@" to add the chatbot system 300 to the chat and directly summon 300 to help with the query.

[0209] In some examples, a user learns about, creates, and gets help with nearly anything during an interactive session with the chatbot system 300. In some examples, the interactive session is a private interactive session with the chatbot system 300. In some examples, the interactive session includes one or more other users, and one or more users directly ask the chatbot system 300 for help during the interactive session. In some examples, the chatbot system 300 provides help to the user when accessing different features of the interactive system hosting the chatbot system 300 or another interactive system or Internet location.

[0210] In some examples, the chatbot system 300 assists the user in the same manner that an intelligent friend would, for example, by communicating directly with the user and the user's friends using a chat interface and by sending social media content and other content directly to the user.

[0211] In some examples, the user utilizes the chatbot system 300 as the primary user interface with the interactive system hosting the chatbot system 300. Because the chatbot system 300 infers user intent from interactions with the user and has a saved dialog state, the chatbot system 300 also infers what the user is interested in based on what the chatbot system 300 learns from chats it has access to (including 1:1 chat threads with the chatbot system 300), the user's general use of the interactive system hosting the chatbot system 300, other third-party communications with the user, how the user communicates, who the user's friends are and the user intent, profiles, geolocation, interests of those friends, and the chatbot system 300 helps the user learn about, create, and participate in new activities.

[0212] In some examples, the chatbot system 300 influences the content that a user sees on the interactive system hosting the chatbot system 300 and in chats in which the chatbot system 300 is a participant. For example, if a user asks for fun games to play with the user's baby, the chatbot system 300 may suggest newborn advice videos or advertisements recommending baby products on the content platform.

[0213] In some examples, the chatbot system 300 can send any kind of content that a user of the interactive platform hosting the chatbot system 300 can send, such as, but not limited to, chat, any type of media such as images, videos, audio recordings, social network posts, chat media, web links, map locations, AI-generated media, media from the user's own data stores, and the like.

[0214] In some examples, implementations of the chatbot system 300 in a conversational interface integrated within an interactive application provide messaging, content, and display advertising (including AI-generated ads based on keyword-winning links), which also helps provide signals for ranking all content provided by the chatbot system 300 (including display ads, media, and AR).

[0215] In some examples, interactions with the chatbot system 300 across all features of the interactive system hosting the chatbot system 300 improve the LLM 338 over time. The interaction data collected and used to train the LLM 338 includes, but is not limited to, content of questions asked, follow-up questions, reporting of answers in the application, reactions to answers in the application, forwarding of answers, sharing of answers, retention, frequency of use, advertising interactions, other searches, other actions, visual content of social network media content, camera albums, user data stores of interactive application interactions, and the like.

[0216] In some examples, the chatbot system 300 provides interactive system-wide and individual conversation training for each user by retraining the LLM 338. In some examples, the LLM 338 is trained as part of the system-wide model based on all interactive system interactions. In some examples, the LLM 338 is trained per user and even per conversation model (i.e., "What should I / we do today" produces different results for different people and for the same person asking it in different conversations).

[0217] In some examples, the chatbot system 300 provides suggested chat topics as chatbot system prompts both before and after answering a question. For example, the chatbot system 300 provides the chatbot system with prompts for what the user could say or do next. Clicking on the suggested prompts re-sends them to the chatbot system 300 as new user prompts.

[0218] In some examples, the chatbot system 300 provides a hybrid or multimodal chat session as an interactive session. For example, the chatbot system 300 infers when to send pure text chat data to the user and when other types of media are needed to fulfill the user's request. In some examples, the user can silently send user prompts to the chatbot system 300 within an existing interactive session with one or more other users. In some examples, the chatbot system 300 provides the user with the ability to send requests to the chatbot system 300 within the conversation without other participants seeing the questions or answers unless the user chooses to make those interactions visible.

[0219] In some examples, the chatbot system 300 provides the user with the ability to modify the personality of the chatbot system 300, such as, but not limited to, receiving interpretations of how the user wants the chatbot system 300 to act directly, changing the persona based on the user's preferences for how to communicate and how the user's friends communicate with the user, providing a visual interface to change the persona of the chatbot system 300, using user profile information such as age, location, and content preferences to change the persona, and the like.

[0220] In some examples, the chatbot system 300 uses a chat reporting feature of the interactive system hosting the chatbot system 300 to provide a report of the answers in the chat, and uses the report to improve the LLM 338 by enabling the user to provide correct responses.

[0221] In some examples, the chatbot system 300 provides for assigning an accuracy score to the user providing feedback.

[0222] In some examples, the chatbot system 300 provides human review of frequently asked questions. In some examples, the chatbot system 300 provides verified answer frameworks.

[0223] In some examples, the chatbot system 300 provides for personalized adjustments to responses, such as "I don't think I know for sure, but I think the closest answer I can give you is..."

[0224] In some examples, the chatbot system 300 provides a confidence score for the response that is used to modify how the chatbot system 300 generates the response, e.g., “Well, while not 100% sure, my best guess is…”

[0225] In some examples, the chatbot system 300 provides for single or private interactive sessions, and users can provide user prompts on topics such as, but not limited to, relationship advice, finding content, homework help, general learning, fashion, correlating verbal chat requests with a visual search database, and the like.

[0226] In some examples, the chatbot system 300 provides an e-commerce front end by allowing verbal or textual user prompts to search for products or services (e.g., "2012 Nissan Ultra under $15k," best car for a newborn).

[0227] In some examples, the chatbot system 300 provides quick searching by receiving short queries that are extrapolated to more detailed queries based on queries that the interactive platform's community has provided as user prompts (e.g., "History of Nike" is automatically extrapolated into questions such as: "100 words about how Nike got started," "What do Nike's leaders have in common?").

[0228] In some examples, the chatbot system 300 provides for a user to interact with one or more other users and the chatbot system 300, and the chatbot system 300 responds with context-sensitive responses (e.g., "Pick someone to cook tonight!", "Write a story about our friendship", "Find a place near us for breakfast on Thursday").

[0229] In some examples, the chatbot system 300 provides users with the ability to program chat-based applications or functions using spoken commands (e.g., creating an account entirely about positivity and sending inspiring quotes to users).

[0230] In some examples, the chatbot system 300 provides the ability to easily forward responses of the chatbot system 300 to other interactive sessions with clear attribution.

[0231] In some examples, the chatbot system 300 provides the ability to export photos or videos of a conversation as partial social network media including a watermark.

[0232] In some examples, the chatbot system 300 provides an accelerated, timed style of typed questions and answers.

[0233] In some examples, the chatbot system 300 provides the user with the ability to select different styles.

[0234] In some examples, the chatbot system 300 caches other user prompts and responses and suggests user prompts and / or responses based on what the user is entering as the current user prompt and the cached user prompts and chatbot system 300 responses.

[0235] In some examples, the chatbot system 300 provides users with the ability to view user prompts entered by friends as suggestions. Users click on a previous user prompt to see who asked the question and what the response was. In some such examples, users can react and leave comments.

[0236] In some examples, the chatbot system 300 provides comments on answers by users and provides "fact checks" for other users to review.

[0237] In some examples, the chatbot system 300 provides sharing of query results on social media by sharing a typed video of questions and answers or a recording of the Q&A responses with an image (still or video) of the user's reaction rendered in a different style of visual overlay (or adding memory or color / asset / generative media items as a background instead of a live camera).

[0238] In some examples, the chatbot system 300 provides users with the ability to send social media posts to get edits and sometimes responses.

[0239] In some examples, the chatbot system 300 provides users with the ability to send social media posts (including with text questions) to the chatbot system 300 using an in-chat camera, with the text field appearing by default on the preview.

[0240] In some examples, the chatbot system 300 receives a user prompt from a user in the form of a request to generate an image or video.

[0241] In some examples, the chatbot system 300 provides users with the ability to name friends and use their cameo personas (or other likenesses) to generate artificial intelligence media (e.g., "Me and @chuckie_mills on a boat in Barbados").

[0242] In some examples, the chatbot system 300 provides the user with the ability to send a social media post to the chatbot system 300 along with instructions (e.g., “make these all have balanced lighting,” “combine these two faces to make this one more interesting”).

[0243] In some examples, the chatbot system 300 provides users with the ability to combine visual media with chat input (i.e., [send a picture of a refrigerator] "What can I cook with this," [send an interactive platform post with an image of my face] "Make me look like a vampire.") In some such examples, the user interface includes an in-chat camera with an always-scanning feature.

[0244] Machine Learning Pipeline

[0245] Figure 7 is a flow chart depicting a machine learning pipeline 700 according to some examples. The machine learning pipeline 700 can be used to generate a trained machine learning program 702, for example, ( Figure 3B ) Creative Generation Component 356, ( Figure 3B LLM338 and ( Figure 3B ) intent processing component 348 to perform operations associated with performing the search and generating the query response.

[0246] Overview

[0247] Broadly speaking, machine learning can involve using computer algorithms to automatically learn patterns and relationships in data, potentially without explicit programming. Machine learning algorithms can be divided into three main categories: supervised learning, unsupervised learning, and reinforcement learning.

[0248] Supervised learning involves training a model using labeled data to predict outputs for new, unseen inputs. Examples of supervised learning algorithms include linear regression, decision trees, and neural networks.

[0249] Unsupervised learning involves training a model on unlabeled data to find hidden patterns and relationships in the data. Examples of unsupervised learning algorithms include clustering, principal component analysis, and generative models such as autoencoders.

[0250] Reinforcement learning involves training a model to make decisions in a dynamic environment by receiving feedback in the form of rewards or penalties. Examples of reinforcement learning algorithms include Q-learning and policy gradient methods.

[0251] According to some examples, examples of specific machine learning algorithms that can be deployed include logistic regression, which is a type of supervised learning algorithm for binary classification tasks. Logistic regression models the probability of a binary response variable based on one or more predictor variables. Another example type of machine learning algorithm is Naive Bayes, which is another supervised learning algorithm for classification tasks. Naive Bayes is based on Bayes' theorem and assumes that the predictor variables are independent of each other. Random forest is another type of supervised learning algorithm used for classification, regression, and other tasks. Random forest builds a collection of decision trees and combines their outputs to make predictions. Another example includes a neural network, which includes interconnected layers of nodes (or neurons) that process information based on input data and make predictions. Matrix factorization is another type of machine learning algorithm used for recommendation systems and other tasks. Matrix factorization decomposes a matrix into two or more matrices to discover hidden patterns or relationships in the data. Support vector machine (SVM) is a type of supervised learning algorithm used for classification, regression, and other tasks. SVM finds a hyperplane that separates different categories in the data. Other types of machine learning algorithms include decision trees, k-nearest neighbors, clustering algorithms, and deep learning algorithms such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer models. The choice of algorithm depends on the nature of the data, the complexity of the problem, and the performance requirements of the application.

[0252] The performance of a machine learning model is often evaluated on a separate test dataset not used during training to ensure that the model can generalize to new, unseen data.

[0253] Although this article discusses several specific examples of machine learning algorithms, the principles discussed in this article can also be applied to other machine learning algorithms. Deep learning algorithms such as convolutional neural networks, recurrent neural networks, and transformers can be used in various machine learning applications, as well as more traditional machine learning algorithms such as decision trees, random forests, and gradient boosting.

[0254] Three example types of problems in machine learning are classification problems, regression problems, and generation problems. Classification problems (also known as categorization problems) aim to classify an item into one of several class values ​​(e.g., is the object an apple or an orange?). Regression algorithms aim to quantize some items (e.g., by providing values ​​that are real numbers). Generation algorithms aim to generate new examples that are similar to the examples provided for training. For example, a text generation algorithm is trained on many text documents and is configured to generate new coherent text that has similar statistical properties to the training data.

[0255] Training phase 704

[0256] Generating a trained machine learning program 702 may include multiple stages that form part of a machine learning pipeline 700, including, for example, Figure 6 The following stages are shown in:

[0257] Data collection and preprocessing 602: This phase may include acquiring and cleaning the data to ensure it is suitable for use in a machine learning model. This phase may also include removing duplicates, handling missing values, and converting the data into a suitable format.

[0258] Feature construction 604: This stage can include selecting and transforming training data 706 to create features useful for predicting a target variable. Feature construction can include (1) receiving features 708 (e.g., as structured or labeled data in supervised learning) and / or (2) identifying features 708 in training data 706 (e.g., unstructured or unlabeled data in unsupervised learning).

[0259] Model selection and training 606: This stage may include selecting an appropriate machine learning algorithm and training it on the preprocessed data. This stage may also include splitting the data into training and test sets, evaluating the model using cross-validation, and adjusting hyperparameters to improve performance.

[0260] Model evaluation 608: This stage can include evaluating the performance of the trained model (e.g., the trained machine learning program 702) on a separate test dataset. This stage can help determine whether the model is overfitting or underfitting, and whether the model is suitable for deployment.

[0261] • Predict 610: This stage involves using a trained model (e.g., trained machine learning program 702) to generate predictions on new, unseen data.

[0262] • Validation, Refinement, or Retraining 612: This phase may include updating the model based on feedback generated from the prediction phase, such as new data or user feedback.

[0263] Deployment 614: This phase can include integrating the trained model (e.g., trained machine learning program 702) into a broader system or application (e.g., a web service, mobile application, or IoT device). This phase can involve installing APIs, building user interfaces, and ensuring the model is scalable and can handle large amounts of data.

[0264] Figure 7Further details of two example phases are shown, namely a training phase 704 (e.g., part of model selection and training 606) and a prediction phase 710 (part of prediction 610). Prior to the training phase 704, feature building 604 is used to identify features 708. This can include identifying informative, discriminative, and independent features for effectively operating the trained machine learning program 702 in pattern recognition, classification, and regression. In some examples, the training data 706 includes labeled data for pre-identified features 708 and one or more outcomes. Each of the features 708 can be a variable or attribute, such as a respective measurable characteristic of a process, item, system, or phenomenon represented by a data set (e.g., training data 706). By way of example only, features 708 can also be of different types, such as numeric features, strings, and graphs, and can include one or more of content 712, concepts 714, attributes 716, historical data 718, and / or user data 720.

[0265] In the training phase 704 , the machine learning pipeline 700 uses the training data 706 to find correlations between features 708 that influence the predicted results or predicted / inferred data 722 .

[0266] The trained machine learning program 702 is trained during a training phase 704 during machine learning program training 724 using the training data 706 and the identified features 708. The machine learning program training 724 evaluates the value of the features 708 as they relate to the training data 706. The result of the training is the trained machine learning program 702 (e.g., a trained or learned model).

[0267] In addition, the training phase 704 can involve machine learning, where the training data 706 is structured (e.g., labeled during preprocessing operations). The trained machine learning program 702 implements a neural network 726 capable of performing, for example, classification and clustering operations. In other examples, the training phase 704 can involve deep learning, where the training data 706 is unstructured, and the trained machine learning program 702 implements a deep neural network 726 that can perform both feature extraction and classification / clustering operations.

[0268] In some examples, neural network 726 can be generated during training phase 704 and implemented within trained machine learning program 702. Neural network 726 includes a hierarchical (e.g., layered) organization of neurons, where each layer consists of multiple neurons or nodes. Neurons in the input layer receive input data, while neurons in the output layer produce the final output of the network. Between the input layer and the output layer, there can be one or more hidden layers, each hidden layer consisting of multiple neurons.

[0269] Each neuron in the neural network 726 is operable to calculate a function, such as an activation function, which takes as input a weighted sum of the outputs of the neurons in the previous layer and a bias term. The output of the function is then passed as input to the neurons in the next layer. If the output of the activation function exceeds a certain threshold, the output is transmitted from the neuron (e.g., the transmitting neuron) to the connected neurons in the consecutive layer (e.g., the receiving neuron). The connections between neurons have associated weights that define the influence of the input from the transmitting neuron to the receiving neuron. During the training phase, these weights are adjusted by a learning algorithm to optimize the performance of the network. Different types of neural networks can use different activation functions and learning algorithms, thereby affecting their performance on different tasks. The hierarchical organization of neurons and the use of activation functions and weights enable the neural network to model complex relationships between inputs and outputs and generalize to new inputs that have not been seen during training.

[0270] In some examples, by way of example only, the neural network 726 may also be one of several different types of neural networks, such as a single-layer feedforward network, a multi-layer perceptron (MLP), an artificial neural network (ANN), a recurrent neural network (RNN), a long short-term memory network (LSTM), a bidirectional neural network, a symmetrically connected neural network, a deep belief network (DBN), a convolutional neural network (CNN), a generative adversarial network (GAN), an autoencoder neural network (AE), a restricted Boltzmann machine (RBM), a Hopfield network, a self-organizing map (SOM), a radial basis function network (RBFN), a spiking neural network (SNN), a liquid state machine (LSM), an echo state network (ESN), a neural Turing machine (NTM), or a transformer network.

[0271] In addition to the training phase 704, a validation phase can be performed on a separate dataset called a validation dataset. The validation dataset is used to adjust the model's hyperparameters, such as the learning rate and regularization parameters. The hyperparameters are adjusted to improve the model's performance on the validation dataset.

[0272] Once the model is fully trained and validated, it can be tested on a new dataset during the testing phase. The testing dataset is used to evaluate the performance of the model and ensure that the model has not overfitted to the training data.

[0273] In the prediction phase 710, the trained machine learning program 702 uses the features 708 to analyze the query data 728 to generate inferences, results, or predictions, as examples of prediction / inference data 722. For example, during the prediction phase 710, the trained machine learning program 702 generates an output. In response to receiving the query data 728, the query data 728 is provided as input to the trained machine learning program 702, and the trained machine learning program 702 generates prediction / inference data 722 as output.

[0274] In some examples, trained machine learning program 702 may be a generative AI model. Generative AI is a term that may refer to any type of artificial intelligence that can create new content from training data 706. For example, generative AI may produce text, images, video, audio, code, or synthetic data that is similar to, but not identical to, the original data.

[0275] Some of the techniques that can be used in generative AI are:

[0276] Convolutional Neural Networks (CNNs): CNNs can be used for image recognition and computer vision tasks. For example, a CNN can be designed to extract features from an image by using filters or kernels that scan the input image and highlight important patterns.

[0277] Recurrent Neural Networks (RNNs): For example, RNNs can be used to process sequential data such as speech, text, and time series data. RNNs employ feedback loops that allow them to capture temporal dependencies and remember past inputs.

[0278] Generative Adversarial Networks (GANs): GANs can consist of two neural networks: a generator and a discriminator. The generator network attempts to create realistic content that can "fool" the discriminator network, while the discriminator network attempts to distinguish between real content and fake content. The generator and discriminator networks compete with each other and improve over time.

[0279] Variational Autoencoders (VAEs): VAEs can encode input data into a latent space (e.g., a compressed representation) and then decode it back into output data. The latent space can be manipulated to generate new variations of the output data. VAEs can use self-attention mechanisms to process input data, allowing them to handle long text sequences and capture complex dependencies.

[0280] Transformer model: The Transformer model can use an attention mechanism to learn the relationships between different parts of input data (such as words or pixels) and generate output data based on these relationships. The Transformer model can process sequential data such as text or speech, as well as non-sequential data such as images or code.

[0281] In a generative AI example, query data 728 may include text, audio, images, video, digital, or media content prompts, and output inference / prediction data 722 includes text, images, video, audio, code, or synthetic data.

[0282] Data Architecture

[0283] Figure 8 is a diagram illustrating a data structure 800 that may be stored in a database 804 of an interactive server system 800, according to certain examples. Although the contents of the database 804 are shown as including a plurality of tables, it will be appreciated that data may be stored in other types of data structures (e.g., as an object-oriented database).

[0284] Database 804 includes message data stored in message table 806. For any particular message, the message data includes at least message sender data, message recipient (or receiver) data, and payload. Figure 8 Additional details regarding information that may be included in a message and included within the message data stored in message table 806 are described.

[0285] The entity table 808 stores entity data and is linked (e.g., by reference) to the entity graph 810 and the profile data 802. Entities for which records are maintained within the entity table 808 may include individuals, corporate entities, organizations, objects, places, events, and the like. Regardless of the entity type, any entity for which the interactive server system 110 stores data may be an identified entity. Each entity is provided with a unique identifier and an entity type identifier (not shown).

[0286] The entity graph 810 stores information about relationships and associations between entities. By way of example only, such relationships may be interest-based or activity-based social relationships, professional relationships (e.g., working at a common company or organization). Some relationships between entities may be unidirectional, such as a subscription by an individual user to digital content from a business or publishing user (e.g., a newspaper or other digital media outlet or brand). Other relationships may be bidirectional, such as a "friend" relationship between various users of the interactive system 100.

[0287] Certain permissions and relationships can be attached to each relationship, and also to each direction of the relationship. For example, a bidirectional relationship (e.g., a friend relationship between respective users) can include authorization for the publication of digital content items between the respective users, but can impose certain restrictions or filters on the publication of these digital content items (e.g., based on content characteristics, location data, or time of day data). Similarly, a subscription relationship between a personal user and a business user can impose varying degrees of restrictions on the publication of digital content from the business user to the personal user, and can significantly restrict or prevent the publication of digital content from the personal user to the business user. A particular user, as an example of an entity, can have certain restrictions recorded in its record for that entity within entity table 808 (e.g., by way of privacy settings). Such privacy settings can apply to all types of relationships within the context of interactive system 100, or can selectively apply to only certain types of relationships.

[0288] Profile data 802 stores various types of profile data about a particular entity. Based on the privacy settings specified by the particular entity, profile data 802 can be selectively used and presented to other users of the interactive system 100. In the case where the entity is a person, profile data 802 includes, for example, the user's name, phone number, address, settings (e.g., notification and privacy settings), and an avatar representation (or a collection of such avatar representations) selected by the user. The particular user can then selectively include one or more of these avatar representations within the content of messages transmitted via the interactive system 100 and on a map interface displayed to other users by the interactive client 104. The collection of avatar representations can include a "status avatar," which presents a graphical representation of the user's status or activity that the user can choose to transmit at a particular time.

[0289] Where the entity is a group, the profile data 802 for the group may similarly include one or more avatar representations associated with the group, in addition to the group name, members, and various settings for the relevant group (eg, notifications).

[0290] Database 804 also stores enhancement data, such as overlays or filters, in enhancement table 812. The enhancement data is associated with and applied to videos (video data is stored in video table 814) and images (image data is stored in image table 816).

[0291] In some examples, filters are displayed as overlays on an image or video during presentation to a message recipient. Filters can be of various types, including user-selected filters from a set of filters presented to the message sender by the interactive client 104 when the message sender is composing the message. Other types of filters include geolocation filters (also known as geofilters), which can be presented to the message sender based on geolocation. For example, geolocation filters specific to a nearby or special location can be presented within the user interface by the interactive client 104 based on geolocation information determined by a global positioning system (GPS) unit of the client system 102.

[0292] Another type of filter is a data filter, which can be selectively presented to the message sender by the interaction client 104 based on other input or information collected during the message creation process by the client system 102. Examples of data filters include the current temperature at a particular location, the current speed at which the message sender is traveling, the battery life of the client system 102, or the current time.

[0293] Other augmentation data that may be stored in the image table 816 include augmented reality content items (e.g., corresponding to an applied lens or augmented reality experience). Augmented reality content items may be real-time special effects and sounds that may be added to an image or video.

[0294] As described above, augmented data includes augmented reality (AR), virtual reality (VR), and mixed reality (MR) content items, overlays, image transformations, images, and modifications that can be applied to image data (e.g., video or images). This includes real-time modifications, where the image is modified as it is captured using the client system 102's device sensors (e.g., one or more cameras), and the modified image is then displayed on the client system 102 screen. This also includes modifications to stored content (e.g., video clips in a collection or group that can be modified). For example, in a client system 102 with access to multiple augmented reality content items, a user can use a single video clip with multiple augmented reality content items to see how different augmented reality content items will modify the stored clip. Similarly, real-time video capture can use modifications to show how the video image currently being captured by the client system 102's sensors will modify the captured data. Such data can simply be displayed on the screen without being stored in memory, or the content captured by the device sensors can be recorded and stored in memory with or without modifications (or both). In some systems, a preview feature can simultaneously display how different augmented reality content items will appear within different windows on the display. For example, this may enable multiple windows with different pseudo-random animations to be viewed simultaneously on a display.

[0295] Thus, using data from an augmented reality content item and various systems or other such transformation systems that use this data to modify the content can involve: detecting various objects (e.g., faces, hands, bodies, cats, dogs, surfaces, objects, etc.) in a video frame; tracking such objects as they leave, enter, and move around the field of view; and modifying or transforming such objects while being tracked. In various examples, different methods for implementing such transformations can be used. Some examples can involve: generating a three-dimensional mesh model of one or more objects; and using transformations of the model and animated textures within the video to implement the transformations. In some examples, tracking points on the objects can be used to place an image or texture (which can be two-dimensional or three-dimensional) at the tracked locations. In yet another example, neural network analysis of the video frame can be used to place the image, model, or texture within the content (e.g., an image or video frame). Thus, an augmented reality content item involves both the images, models, and textures used to create the transformations within the content, as well as the additional modeling and analysis information required to implement such transformations using object detection, tracking, and placement.

[0296] Real-time video processing can be performed using any type of video data (e.g., video streams, video files, etc.) stored in the memory of any type of computerized system. For example, a user can load video files and store them in the device's memory, or a device's sensors can be used to generate a video stream. In addition, computer animation models can be used to process any object, such as a human face and body parts, an animal, or an inanimate object (e.g., a chair, a car, or other objects).

[0297] In some examples, when a specific modification is selected along with the content to be transformed, the element to be transformed is identified by a computing device and then detected and tracked if the element to be transformed is present in a frame of the video. The elements of the object are modified according to the modification request, thereby transforming the frame of the video stream. For different types of transformations, the frames of the video stream can be transformed by different methods. For example, for frame transformations that primarily involve changing the form of the elements of the object, characteristic points are calculated for each element of the object (e.g., using an active shape model (ASM) or other known methods). A grid based on the characteristic points is then generated for each element of the object. This grid is used in subsequent stages of tracking the elements of the object in the video stream. During the tracking process, the grid for each element is aligned with the position of each element. Additional points are then generated on the grid.

[0298] In some examples, a transformation that uses elements of an object to change some areas of an object can be performed by calculating characteristic points for each element of the object and generating a grid based on the calculated characteristic points. Points are generated on the grid, and then various areas based on these points are generated. The elements of the object are then tracked by aligning the area of ​​each element with the position of each element of at least one element, and the properties of the area can be modified based on the modification request, thereby transforming the frame of the video stream. Depending on the specific requirements of the modification, the properties of the mentioned area can be transformed in different ways. Such modifications can involve: changing the color of the area; removing some parts of the area from the frame of the video stream; including new objects in the area based on the modification request; and modifying or distorting the elements of the area or object. In various examples, any combination of such modifications or other similar modifications can be used. For certain models to be animated, some characteristic points can be selected as control points for the entire state space to be used to determine the options for model animation.

[0299] In some examples of computer animation models that use face detection to transform image data, faces are detected on an image using a specific face detection algorithm (e.g., Viola-Jones). An active shape model (ASM) algorithm is then applied to the facial region of the image to detect facial feature reference points.

[0300] Other methods and algorithms suitable for face detection can be used. For example, in some examples, landmarks are used to locate features, which represent distinguishable points that are present in most of the images considered. For example, for facial landmarks, the location of the left pupil can be used. If the initial landmarks are not identifiable (for example, if the person is wearing an eye patch), secondary landmarks can be used. Such a landmark identification process can be used for any such object. In some examples, a set of landmarks forms a shape. The coordinates of the points in the shape can be used to represent the shape as a vector. One shape is aligned with another shape using a similarity transformation (allowing translation, scaling, and rotation) that minimizes the average Euclidean distance between the shape points. The mean shape is the average of the aligned training shapes.

[0301] The transformation system can capture an image or video stream on a client device (e.g., client system 102) and perform complex image manipulations locally on the client system 102 while maintaining an appropriate user experience, computational time, and power consumption. Complex image manipulations can include size and shape changes, emotion transformations (e.g., changing a face from a frown to a smile), state transitions (e.g., aging a subject, reducing apparent age, changing gender), style transformations, application of graphical elements, and any other suitable image or video manipulations enabled by a convolutional neural network that has been configured to execute efficiently on the client system 102.

[0302] In some examples, a computer-animated model for transforming image data can be used by a system in which a user can capture an image or video stream of the user (e.g., a selfie) using a client system 102 having a neural network operating as part of an interactive client 104 operating on the client system 102. The transformation system operating within the interactive client 104 determines the presence of a face within the image or video stream and provides a modification icon associated with the computer-animated model to transform the image data, or the computer-animated model can be presented in association with an interface described herein. The modification icon includes changes that serve as a basis for modifying the user's face within the image or video stream as part of the modification operation. Once the modification icon is selected, the transformation system initiates a process that transforms the user's image to reflect the selected modification icon (e.g., generating a smiley face on the user). Once the image or video stream is captured and the specified modification is selected, the modified image or video stream can be presented in a graphical user interface displayed on the client system 102. The transformation system can implement a complex convolutional neural network on a portion of the image or video stream to generate and apply the selected modification. That is, a user can capture an image or video stream and, once a modification icon has been selected, be presented with the modified result in real time or near real time. Furthermore, when the video stream is being captured, the modification can be persistent and the selected modification icon remains toggled. Machine-taught neural networks can be used to implement such modifications.

[0303] The graphical user interface presenting the modifications performed by the transformation system can provide the user with additional interactive options. Such options can be based on the interface used to initiate the selection of a particular computer-animated model and content capture (e.g., from a content creator user interface). In various examples, the modifications can be persistent after the initial selection of the modification icon. The user can turn the modifications on or off by tapping or otherwise selecting a face modified by the transformation system, and store them for later viewing or browsing to other areas of the imaging application. In the event that multiple faces are modified by the transformation system, the user can globally turn the modifications on or off by tapping or selecting a single face modified and displayed within the graphical user interface. In some examples, each face in a group of multiple faces can be modified individually, or such modifications can be toggled by tapping or selecting a single face or a series of single faces displayed within the graphical user interface.

[0304] The story table 818 stores data about a collection of messages and associated images, video, or audio data that are compiled into a collection (e.g., a story or gallery). The creation of a particular collection can be initiated by a particular user (e.g., each user for whom a record is maintained in the entity table 808). A user can create a "personal story" in the form of a collection of content that has been created and sent / broadcasted by the user. To this end, the user interface of the interactive client 104 can include a user-selectable icon that enables the message sender to add specific content to his or her personal story.

[0305] A collection may also constitute a "live story," which is a collection of content from multiple users that is created manually, automatically, or using a combination of manual and automatic techniques. For example, a "live story" may constitute a curated stream of user-submitted content from different locations and events. Users whose client devices have location services enabled and who are at a co-located event at a particular time may be presented with the option to contribute content to a particular live story, for example, via the user interface of the interactive client 104. Live stories may be identified to the user by the interactive client 104 based on his or her location. The end result is a "live story" told from the group's perspective.

[0306] Another type of content collection is called a "location story," which enables users whose client systems 102 are located within a specific geographic location (e.g., on a college or university campus) to contribute to a particular collection. In some examples, contributions to location stories may require secondary authentication to verify that the end user belongs to a specific organization or other entity (e.g., is a student on a university campus).

[0307] As mentioned above, video table 814 stores video data that, in some examples, is associated with messages for which records are maintained within message table 806. Similarly, image table 816 stores image data associated with messages whose message data is stored in entity table 808. Entity table 808 can associate various enhancements from enhancement table 812 with various images and videos stored in image table 816 and video table 814.

[0308] Database 804 also includes social network information collected by the interactive platform's interactive system. This social network information may include, but is not limited to, relationships and communication data among users of the interactive platform. This social network information can be used to group two or more users and provide additional functionality for the interactive system 100. Examples of relationships include, but are not limited to, best friends where two or more users are identified as mutual best friends based on the frequency of their interactions, users with a shared interest in current events, and users who share connections through social clubs or charitable organizations. Examples of communications include, but are not limited to, chats, private and public messaging, and the exchange of media such as images, videos, and audio recordings.

[0309] Data communication architecture

[0310] Figure 9 is a schematic diagram illustrating the structure of a message 900 according to some examples, the message 900 being generated by an interaction client 104 for transmission to another interaction client 104 via an interaction server 124. The content of a particular message 900 is used to populate a message table 806 stored within a database 804 accessible by the interaction server 124. Similarly, the content of the message 900 is stored in memory as "in-transit" or "in-flight" data of the client system 102 or interaction server 124. The message 900 is shown as including the following example components:

[0311] Message identifier 902 : A unique identifier that identifies the message 900 .

[0312] Message text payload 934 : Text to be generated by the user via the user interface of client system 102 and included in message 900 .

[0313] • Message image payload 904 : Image data captured by the camera component of the client system 102 or retrieved from the memory component of the client system 102 and included in the message 900 . Image data for a message 900 sent or received may be stored in an image table 906 .

[0314] • Message Video Payload 908: Video data captured by the camera component or retrieved from the memory component of the client system 102 and included in the message 900. The video data for a message 900 sent or received may be stored in a video table 910.

[0315] • Message audio payload 912 : audio data captured by a microphone or retrieved from a memory component of the client system 102 and included in the message 900 .

[0316] Message enhancement data 914: Enhancement data representing enhancements (e.g., filters, stickers, or other annotations or enhancements) to be applied to the message image payload 904, message video payload 908, or message audio payload 912 of the message 900. Enhancement data for a sent or received message 900 may be stored in an enhancement table 916.

[0317] • Message duration parameter 918: A parameter value indicating the amount of time in seconds that the content of the message (eg, message image payload 904, message video payload 908, message audio payload 912) will be presented to or accessible to the user via the interactive client 104.

[0318] Message geolocation parameters 920: Geolocation data (e.g., latitude and longitude coordinates) associated with the content payload of the message. Multiple message geolocation parameter 920 values ​​may be included in the payload, with each of these parameter values ​​being associated with a content item included in the content (e.g., a specific image within the message image payload 904 or a specific video within the message video payload 908).

[0319] Message story identifier 922: An identifier value that identifies one or more content collections (e.g., a "story" identified in stories table 924) associated with a particular content item in the message image payload 904 of the message 900. For example, the identifier value can be used to associate multiple images within the message image payload 904 with multiple content collections.

[0320] Message Tags 926: Each message 900 may be tagged with a plurality of tags, each of which indicates the subject matter of the content included in the message payload. For example, if a particular image included in the message image payload 904 depicts an animal (e.g., a lion), a tag value may be included within the message tags 926 indicating the relevant animal. The tag value may be manually generated based on user input, or may be automatically generated using, for example, image recognition.

[0321] • Message sender identifier 928: An identifier (eg, a messaging system identifier, an email address, or a device identifier) ​​that indicates the user of the client system 102 on which the message 900 was generated and from which the message 900 was sent.

[0322] • Message recipient identifier 930: An identifier (eg, a messaging system identifier, an email address, or a device identifier) ​​that indicates the user of the client system 102 to which the message 900 is addressed.

[0323] The content (e.g., value) of each component of message 900 may be a pointer to a location in a table where the content data value is stored. For example, the image value in message image payload 904 may be a pointer (or address) to a location in image table 906. Similarly, the value in message video payload 908 may point to data stored in video table 910, the value stored in message enhancement data 914 may point to data stored in enhancement table 916, the value stored in message story identifier 922 may point to data stored in story table 924, and the values ​​stored in message sender identifier 928 and message recipient identifier 930 may point to user records stored in entity table 932.

[0324] Time-based access restriction architecture

[0325] Figure 10 is a schematic diagram illustrating an access restriction process 1000 in which access to content (e.g., an ephemeral message 1002 and an associated multimedia data payload) or a collection of content (e.g., an ephemeral message group 1004) can be time-restricted (e.g., made ephemeral).

[0326] The ephemeral message 1002 is shown as being associated with a message duration parameter 1006, the value of which determines the amount of time that the ephemeral message 1002 will be displayed by the interactive client 104 to the receiving user of the ephemeral message 1002. In some examples, the receiving user may view the ephemeral message 1002 for up to 10 seconds, depending on the amount of time specified by the message sender using the message duration parameter 1006.

[0327] The message duration parameter 1006 and the message recipient identifier 1008 are shown as inputs to a message timer 1010, which is responsible for determining the amount of time that the ephemeral message 1002 is displayed to the particular receiving user identified by the message recipient identifier 1008. In particular, the ephemeral message 1002 is displayed to the associated receiving user for a period of time determined by the value of the message duration parameter 1006. The message timer 1010 is shown as providing an output to a more generalized messaging system 1012, which is responsible for the overall timing of displaying content (e.g., the ephemeral message 1002) to the receiving user.

[0328] exist Figure 10In the example of FIG. 1 , ephemeral message 1002 is shown as being included in ephemeral message group 1004 (e.g., a collection of messages in a personal story or event story). Ephemeral message group 1004 has an associated group duration parameter 1014, the value of which determines the duration for which ephemeral message group 1004 is presented and accessible to users of interactive system 100. Group duration parameter 1014 could, for example, be the duration of a concert, wherein ephemeral message group 1004 is a collection of content related to the concert. Alternatively, a user (either an owning user or a curator user) could specify the value of group duration parameter 1014 when performing setup and creation of ephemeral message group 1004.

[0329] In addition, each ephemeral message 1002 within the ephemeral message group 1004 has an associated group participation parameter 1016, the value of which determines the duration for which the ephemeral message 1002 is accessible within the context of the ephemeral message group 1004. Thus, a particular ephemeral message group 1004 can "expire" and become inaccessible within the context of the ephemeral message group 1004 before the ephemeral message group 1004 itself expires according to the group duration parameter 1014. The group duration parameter 1014, the group participation parameter 1016, and the message recipient identifier 1008 each provide input to a group timer 1018, which first operatively determines whether a particular ephemeral message 1002 of the ephemeral message group 1004 is to be displayed to a particular recipient user, and if so, for how long. Note that, due to the message recipient identifier 1008, the ephemeral message group 1004 can also identify the identity of a particular recipient user.

[0330] 1004 , and the group timer 1018 can be used to determine the duration of a particular ephemeral message 1002 displayed to a receiving user. The group timer 1018 can be used to determine the duration of a particular ephemeral message 1002 displayed to a receiving user, regardless of whether the receiving user is viewing the ephemeral message 1002 within the context of the ephemeral message group 1004 or outside the context of the ephemeral message group 1004.

[0331] Furthermore, the messaging system 1012 may be operable to remove a particular ephemeral message 1002 from the ephemeral message group 1004 based on a determination that the particular ephemeral message 1002 has exceeded the associated group participation parameter 1016. For example, when the sending user has established a group participation parameter 1016 of 24 hours from posting, the messaging system 1012 will remove the associated ephemeral message 1002 from the ephemeral message group 1004 after the specified 24 hours. The messaging system 1012 is also operable to remove an ephemeral message group 1004 when the group participation parameter 1016 for each ephemeral message 1002 within the ephemeral message group 1004 has expired, or when the ephemeral message group 1004 itself has expired according to the group duration parameter 1014.

[0332] In some use cases, the creator of a particular ephemeral message group 1004 may specify an indefinite group duration parameter 1014. In this case, the expiration of the group participation parameter 1016 for the last remaining ephemeral message 1002 within the ephemeral message group 1004 will determine when the ephemeral message group 1002 itself expires. In this case, a new ephemeral message 1002 with a new group participation parameter 1016 added to the ephemeral message group 1004 effectively extends the life of the ephemeral message group 1004 to the value of the group participation parameter 1016.

[0333] In response to the messaging system 1012 determining that the ephemeral message group 1004 has expired (e.g., is no longer accessible), the messaging system 1012 communicates with the interactive system 100 (and, for example, in particular, the interactive client 104) to cause the indicia (e.g., an icon) associated with the relevant ephemeral message group 1004 to no longer be displayed within the user interface of the interactive client 104. Similarly, when the messaging system 1012 determines that the message duration parameter 1006 of a particular ephemeral message 1002 has expired, the messaging system 1012 causes the interactive client 104 to no longer display the indicia (e.g., an icon or textual identification) associated with the ephemeral message 1002.

[0334] Machine Architecture

[0335] Figure 111 is a diagrammatic representation of a machine 1100 within which instructions 1102 (e.g., software, programs, applications, applet, apps, or other executable code) may be executed for causing the machine 1100 to perform any one or more of the methodologies discussed herein. For example, the instructions 1102 may cause the machine 1100 to perform any one or more of the methodologies described herein. The instructions 1102 transform a general-purpose, unprogrammed machine 1100 into a specialized machine 1100 that is programmed to perform the functions described and illustrated in the manner described. The machine 1100 may operate as a standalone device or may be coupled (e.g., networked) to other machines. In a networked deployment, the machine 1100 may operate in the capacity of a server or a client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine 1100 may include, but is not limited to, a server computer, a client computer, a personal computer (PC), a tablet computer, a notebook computer, a netbook, a set-top box (STB), a personal digital assistant (PDA), an entertainment media system, a cellular phone, a smartphone, a mobile device, a wearable device (e.g., a smart watch), a smart home device (e.g., a smart appliance), other smart devices, a web appliance, a network router, a network switch, a network bridge, or any machine capable of executing instructions 1102 that specify actions to be taken by the machine 1100, either sequentially or otherwise. Furthermore, while a single machine 1100 is shown, the term "machine" should also be construed to include a collection of machines that individually or jointly execute instructions 1102 to perform any one or more of the methodologies discussed herein. For example, the machine 1100 may include a client system 102 or any one of a plurality of server devices forming part of an interactive server system 110. In some examples, the machine 1100 may also include both a client system and a server system, wherein some operations of a particular method or algorithm are performed on the server side, and wherein some operations of a particular method or algorithm are performed on the client side.

[0336] The machine 1100 may include a processor 1104, a memory 1106, and input / output I / O components 1108 that may be configured to communicate with each other via a bus 1110. In an example, the processor 1104 (e.g., a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a radio frequency integrated circuit (RFIC), another processor, or any suitable combination thereof) may include, for example, a processor 1112 that executes instructions 1102 and a processor 1114. The term "processor" is intended to include multi-core processors, which may include two or more independent processors (sometimes referred to as "cores") that can execute instructions concurrently. Although Figure 11 Multiple processors 1104 are shown, but the machine 1100 may include a single processor with a single core, a single processor with multiple cores (e.g., a multi-core processor), multiple processors with a single core, multiple processors with multiple cores, or any combination thereof.

[0337] The memory 1106 includes a main memory 1116, a static memory 1118, and a storage unit 1120, all of which are accessible by the processor 1104 via the bus 1110. The main memory 1106, the static memory 1118, and the storage unit 1120 store instructions 1102 that embody any one or more of the methodologies or functionality described herein. The instructions 1102 may also reside, completely or partially, within the main memory 1116, within the static memory 1118, within the machine-readable medium 1122 within the storage unit 1120, within at least one of the processors 1104 (e.g., within a cache memory of the processor), or within any suitable combination thereof during execution thereof by the machine 1100.

[0338] The I / O components 1108 may include various components for receiving input, providing output, generating output, sending information, exchanging information, capturing measurements, etc. The specific I / O components 1108 included in a particular machine will depend on the type of machine. For example, a portable machine such as a mobile phone may include a touch input device or other such input mechanism, while a headless server machine may not include such a touch input device. It will be understood that the I / O components 1108 may include Figure 11Many other components are not shown in the drawings. In various examples, the I / O components 1108 may include user output components 1124 and user input components 1126. The user output components 1124 may include visual components (e.g., displays such as plasma display panels (PDPs), light emitting diode (LED) displays, liquid crystal displays (LCDs), projectors, or cathode ray tubes (CRTs)), acoustic components (e.g., speakers), tactile components (e.g., vibration motors, resistance mechanisms), other signal generators, etc. The user input components 1126 may include alphanumeric input components (e.g., keyboards, touch screens configured to receive alphanumeric input, optical keyboards, or other alphanumeric input components), point-based input components (e.g., mice, touch pads, trackballs, joysticks, motion sensors, or other pointing instruments), tactile input components (e.g., physical buttons, touch screens that provide location and force of touches or touch gestures, or other tactile input components), audio input components (e.g., microphones), etc.

[0339] In another example, the I / O component 1108 may include a biometric component 1128, a motion component 1130, an environmental component 1132, or a position component 1134, as well as various other components. For example, the biometric component 1128 includes components for detecting expressions (e.g., hand expressions, facial expressions, vocal expressions, body posture, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweat, or brain waves), identifying people (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition), etc. The motion component 1130 includes an acceleration sensor component (e.g., an accelerometer), a gravity sensor component, and a rotation sensor component (e.g., a gyroscope). The biometric component 1128 may include a brain-computer interface (BMI) system that allows communication between the brain and an external device or machine. This can be achieved by recording brain activity, converting the brain activity into a format understandable by a computer, and then using the resulting signals to control the device or machine.

[0340] Example types of BMI technology include:

[0341] • BMIs based on electroencephalography (EEG), which use electrodes placed on the scalp to record electrical activity in the brain.

[0342] Invasive BMIs, where electrodes are surgically implanted directly into the brain.

[0343] Optogenetic BMIs, which use light to control the activity of specific nerve cells in the brain.

[0344] BMI based on functional magnetic resonance imaging (fMRI), which uses magnetic fields to measure blood flow in the brain, which can be used to infer brain activity.

[0345] Any biometric data collected by the biometric component 1128 is captured and cached only with user approval and is deleted upon user request. In addition, such biometric data can be used for very limited purposes (e.g., identification verification). To ensure the restricted and authorized use of biometric information and other personally identifiable information (PII), access to this data is limited to authorized personnel (if any). Any use of biometric data can be strictly limited to identification verification purposes, and the biometric data may not be shared or sold to any third party without the user's explicit consent. In addition, appropriate technical and organizational measures are implemented to ensure the security and confidentiality of this sensitive information.

[0346] Environmental components 1132 include, for example, one or more cameras (with still image / photo and video capabilities), lighting sensor components (e.g., a photometer), temperature sensor components (e.g., one or more thermometers that detect ambient temperature), humidity sensor components, pressure sensor components (e.g., a barometer), acoustic sensor components (e.g., one or more microphones that detect background noise), proximity sensor components (e.g., an infrared sensor that detects nearby objects), gas sensors (e.g., a gas detection sensor for detecting concentrations of hazardous gases for safety purposes or for measuring pollutants in the atmosphere), or other components that can provide indications, measurements, or signals corresponding to the surrounding physical environment.

[0347] With respect to cameras, client system 102 can have a camera system that includes, for example, a front-facing camera on the front surface of client system 102 and a rear-facing camera on the rear surface of client system 102. The front-facing camera can, for example, be used to capture still images and videos of a user of client system 102 (e.g., a "selfie"), which can then be enhanced with the enhancement data (e.g., filters) described above. The rear-facing camera can, for example, be used to capture still images and videos in a more traditional camera mode, where these images are similarly enhanced with the enhancement data. In addition to the front-facing camera and the rear-facing camera, client system 102 can also include a 360° camera for capturing 360° photos and videos.

[0348] Additionally, the camera system of the client system 102 may include dual rear cameras (e.g., a main camera and a depth sensing camera), or even triple, quad, or quintuple rear camera configurations on both the front and back sides of the client system 102. For example, these multiple camera systems may include a wide-angle camera, an ultra-wide-angle camera, a telephoto camera, a macro camera, and a depth sensor.

[0349] The location component 1134 includes a positioning sensor component (eg, a GPS receiver component), an altitude sensor component (eg, an altimeter or a barometer that detects air pressure from which altitude can be obtained), an orientation sensor component (eg, a magnetometer), and the like.

[0350] Various technologies can be used to implement communications. The I / O components 1108 also include a communications component 1136 that is operable to couple the machine 1100 to a network 1138 or device 1140 via corresponding couplings or connections. For example, the communications component 1136 may include a network interface component or another suitable device that interfaces with the network 1138. In other examples, the communications component 1136 may include a wired communications component, a wireless communications component, a cellular communications component, a near field communications (NFC) component, a Components (e.g. Low power consumption), Components and other communication components for providing communication via other modalities. Device 1140 can be another machine or any of a variety of peripheral devices (e.g., a peripheral device coupled via USB).

[0351] In addition, the communication component 1136 can detect an identifier or include a component operable to detect an identifier. For example, the communication component 1136 can include a radio frequency identification (RFID) tag reader component, an NFC smart tag detection component, an optical reader component (e.g., an optical sensor for detecting one-dimensional bar codes such as Universal Product Code (UPC) bar codes, multi-dimensional bar codes such as Quick Response (QR) codes, Aztec codes, Data Matrix, Dataglyph, MaxiCode, PDF417, UltraCode, UCC RSS-2D bar codes, and other optical codes) or an acoustic detection component (e.g., a microphone for identifying an audio signal of a tag). In addition, various information can be obtained via the communication component 1136, such as a location obtained via Internet Protocol (IP) geolocation, ... Positioning derived from signal triangulation, positioning derived via detection of NFC beacon signals that can indicate a specific position, etc.

[0352] Various memories (e.g., main memory 1116, static memory 1118, and memory of processor 1104) and storage unit 1120 may store one or more sets of instructions and data structures (e.g., software) embodied or used by any one or more of the methods or functions described herein. These instructions (e.g., instructions 1102) when executed by processor 1104 cause various operations to implement the disclosed examples.

[0353] Instructions 1102 may be sent or received over network 1138 using a transmission medium via a network interface device (e.g., a network interface component included in communications component 1136) and using any of several well-known transmission protocols (e.g., Hypertext Transfer Protocol (HTTP)). Similarly, instructions 1102 may be sent or received via a coupling (e.g., a peer-to-peer coupling) to device 1140 using a transmission medium.

[0354] Software Architecture

[0355] Figure 12 12 is a block diagram 1200 illustrating a software architecture 1202 that can be installed on any one or more of the devices described herein. The software architecture 1202 is supported by hardware, such as a machine 1204, which includes a processor 1206, memory 1208, and I / O components 1210. In this example, the software architecture 1202 can be conceptualized as a stack of layers, where each layer provides specific functionality. The software architecture 1202 includes layers such as an operating system 1212, libraries 1214, frameworks 1216, and applications 1218. In operation, the applications 1218 invoke API calls 1220 through the software stack and receive messages 1222 in response to the API calls 1220.

[0356] The operating system 1212 manages hardware resources and provides common services. The operating system 1212 includes, for example, a kernel 1224, services 1226, and drivers 1228. The kernel 1224 serves as an abstraction layer between the hardware and other software layers. For example, the kernel 1224 provides memory management, processor management (e.g., scheduling), component management, network and security settings, and other functions. Services 1226 can provide other common services to other software layers. Drivers 1228 are responsible for controlling or interfacing with the underlying hardware. For example, drivers 1228 may include display drivers, camera drivers, or Low-power drivers, Flash drivers, serial communication drivers (e.g., USB drivers), drivers, audio drivers, power management drivers, etc.

[0357] The libraries 1214 provide a common low-level infrastructure used by the applications 1218. The libraries 1214 may include a system library 1230 (e.g., a C standard library) that provides functions such as memory allocation functions, string manipulation functions, mathematical functions, etc. In addition, the libraries 1214 may include an API library 1232, such as a media library (e.g., a library for supporting the presentation and manipulation of various media formats, such as Moving Picture Experts Group-4 (MPEG4), Advanced Video Coding (H.264 or AVC), Moving Picture Experts Group Layer-3 (MP3), Advanced Audio Coding (AAC), Adaptive Multi-Rate (AMR) audio codec, Joint Photographic Experts Group (JPEG or JPG), or Portable Network Graphics (PNG)), a graphics library (e.g., an OpenGL framework for rendering graphical content on a display in two dimensions (2D) and three dimensions (3D), a database library (e.g., SQLite providing various relational database functions), a web library (e.g., WebKit providing web browsing functions), etc. The library 1214 may also include various other libraries 1234 to provide many other APIs to the application 1218 .

[0358] The framework 1216 provides a common high-level infrastructure used by applications 1218. For example, the framework 1216 provides various graphical user interface (GUI) functions, advanced resource management, and advanced positioning services. The framework 1216 can provide a wide range of other APIs that can be used by applications 1218, some of which may be specific to a particular operating system or platform.

[0359] In an example, applications 1218 may include a home application 1236, a contacts application 1238, a browser application 1240, a book reader application 1242, a location application 1244, a media application 1246, a messaging application 1248, a game application 1250, and a variety of other applications such as third-party applications 1252. Applications 1218 are programs that perform functions defined in the program. Various programming languages ​​may be used to create one or more of the applications 1218 structured in various ways, such as an object-oriented programming language (e.g., Objective-C, Java, or C++) or a procedural programming language (e.g., C or assembly language). In a specific example, third-party applications 1252 (e.g., those written by entities other than the vendor of a particular platform using ANDROID) may be used to create a third-party application 1252. TM or IOS TM Software Development Kit (SDK) can be used to develop applications on platforms such as IOS TM ANDROID TM 、 Mobile software running on the mobile operating system of the phone or other mobile operating systems. In this example, third-party applications 1252 can activate API calls 1220 provided by the operating system 1212 to facilitate the functions described herein.

[0360] Additional examples include:

[0361] Example 1 is a method of one or more processors, the method comprising: receiving, by the one or more processors, a prompt from a user from a client system during a first interactive session; generating, by the one or more processors, a response using the prompt and a large language model; transmitting, by the one or more processors, the response to the client system for display to the user during the first interactive session; determining, by the one or more processors, user intent based on the user prompt; determining, by the one or more processors, advertising content based on the user intent; and transmitting, by the one or more processors, the advertising content to the client system for display to the user during a second interactive session.

[0362] In Example 2, the subject matter of Example 1 includes, wherein the first interactive session is a chat session with a chatbot, and the second interactive session is not a chat session with a chatbot.

[0363] In Example 3, the subject matter of any of Examples 1 to 2 includes, wherein generating a response further comprises: generating an original response based on the user prompt; generating an adjusted input prompt based on the original response; and generating the response based on the adjusted input prompt.

[0364] In Example 4, the subject matter of any one of Examples 1 to 3 includes, wherein generating the adjusted input further comprises: generating a set of potential responses; and selecting the response from the set of potential responses.

[0365] In Example 5, the subject matter of any one of Examples 1 to 4 includes, wherein determining the user intent is further based on the potential responses.

[0366] In Example 6, the subject matter of any one of Examples 1 to 5 includes, wherein determining the user intent is further based on a user profile.

[0367] In Example 7, the subject matter of any one of Examples 1 to 6 includes, wherein the user profile comprises social network data of a social network of the user.

[0368] Example 8 is at least one machine-readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations for implementing any of Examples 1-7.

[0369] Example 9 is an apparatus comprising means for implementing any one of Examples 1 to 7.

[0370] Example 10 is a system implementing any one of Examples 1 to 7.

[0371] in conclusion

[0372] Changes and modifications may be made to the disclosed examples without departing from the scope of the present disclosure. These and other changes or modifications are intended to be included within the scope of the present disclosure.

[0373] Glossary

[0374] "Carrier signal" refers to any intangible medium that can store, encode, or carry instructions for execution by a machine and includes digital or analog communication signals or other intangible media to facilitate communication of such instructions. Instructions can be sent or received over a network using a transmission medium via a network interface device.

[0375] "Client device" refers to any machine that interfaces with a communications network to obtain resources from one or more server systems or other client devices. A client device may be, but is not limited to, a mobile phone, a desktop computer, a laptop computer, a portable digital assistant (PDA), a smartphone, a tablet computer, an ultrabook, a netbook, multiple laptop computers, a multiprocessor system, a microprocessor-based or programmable consumer electronics product, a game console, a set-top box, or any other communications device that a user may use to access a network.

[0376] "Communications network" means one or more parts of a network, which may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless LAN (WLAN), a wide area network (WAN), a wireless WAN (WWAN), a metropolitan area network (MAN), the Internet, a part of the Internet, a part of the Public Switched Telephone Network (PSTN), a Plain Old Telephone Service (POTS) network, a cellular telephone network, a wireless network, The coupling may be a network, another type of network, or a combination of two or more such networks. For example, the network or a portion of the network may include a wireless network or a cellular network, and the coupling may be a code division multiple access (CDMA) connection, a global system for mobile communications (GSM) connection, or other type of cellular or wireless coupling. In this example, the coupling may implement any of various types of data transmission technologies, such as single carrier radio transmission technology (1xRTT), evolution data optimized (EVDO) technology, general packet radio service (GPRS) technology, enhanced data rates for GSM evolution (EDGE) technology, the third generation partnership project (3GPP) including 3G, fourth generation wireless (4G) networks, universal mobile telecommunications system (UMTS), high speed packet access (HSPA), world wide interoperability for microwave access (WiMAX), long term evolution (LTE) standards, other data transmission technologies defined by various standards setting organizations, other long distance protocols, or other data transmission technologies.

[0377] "Component" refers to a device, physical entity, or logic with the following boundaries: the boundaries are defined by function or subroutine calls, branch points, APIs, or other technologies provided for partitioning or modularizing specific processing or control functions. A component can be combined with other components via its interface to perform machine processing. A component can be a packaged functional hardware unit designed for use with other components, and can be part of a program that generally performs a specific function among related functions. A component can constitute a software component (e.g., code embodied on a machine-readable medium) or a hardware component. A "hardware component" is a tangible unit that can perform certain operations and can be configured or arranged in a certain physical manner. In various examples, one or more computer systems (e.g., a stand-alone computer system, a client computer system, or a server computer system) or one or more hardware components of a computer system (e.g., a processor or a processor group) can be configured by software (e.g., an application or an application portion) to be a hardware component that operates to perform certain operations as described herein. A hardware component can also be implemented mechanically, electronically, or in any suitable combination thereof. For example, a hardware component can include a dedicated circuit system or logic that is permanently configured to perform certain operations. The hardware component can be a dedicated processor, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). The hardware component can also include a programmable logic or circuit system that is temporarily configured to perform certain operations by software. For example, the hardware component can include software executed by a general-purpose processor or other programmable processor. Once configured by such software, the hardware component becomes a specific machine (or a specific component of a machine), which is uniquely customized to perform the configured function and is no longer a general-purpose processor. It will be appreciated that it can be decided whether to mechanically implement the hardware component in a dedicated and permanently configured circuit system or in a temporarily configured circuit system (for example, configured by software) for cost and time considerations. Therefore, the phrase "hardware component" (or "hardware-implemented component") should be understood to include a tangible entity, that is, an entity that is physically constructed, permanently configured (for example, hardwired) or temporarily configured (for example, programmed) to operate in some way or perform certain operations described herein. Considering an example in which a hardware component is temporarily configured (for example, programmed), it is not necessary to configure or instantiate each hardware component in the hardware component at any one time. For example, where a hardware component includes a general-purpose processor that is configured by software to become a special-purpose processor, the general-purpose processor can be configured as different special-purpose processors (e.g., including different hardware components) at different times. The software configures one or more specific processors accordingly, such as to constitute a specific hardware component at one time and to constitute different hardware components at different times. A hardware component can provide information to other hardware components and receive information from other hardware components.Therefore, the hardware components described can be considered to be coupled in communication. In the case of multiple hardware components being present at the same time, communication can be achieved by signal transmission between or among two or more hardware components in the hardware components (for example, by appropriate circuits and buses). In the example where multiple hardware components are configured or instantiated at different times, communication between such hardware components can be achieved, for example, by storing information in a memory structure accessible to multiple hardware components and retrieving information in the memory structure. For example, a hardware component can perform an operation, and the output of the operation is stored in a memory device coupled in communication with it. Then, other hardware components can access the memory device at a subsequent time to retrieve the stored output and process it. The hardware component can also initiate communication with an input device or an output device, and can operate on resources (for example, a collection of information). The various operations of the example methods described herein can be performed at least in part by a temporary configuration (for example, by software) or one or more processors that are permanently configured to perform related operations. Whether it is a temporary configuration or a permanent configuration, such a processor can constitute a processor-implemented component that operates to perform one or more operations or functions described herein. As used herein, a "processor-implemented component" refers to a hardware component implemented using one or more processors. Similarly, the method described herein can be implemented at least in part by a processor, wherein specific one or more processors are examples of hardware. For example, at least some of the operation of the method can be performed by one or more processors or the components implemented by the processor. In addition, one or more processors can also operate to support the execution of related operations in a "cloud computing" environment or operate as "software as a service" (SaaS). For example, at least some of the operation can be performed by a group of computers (as an example of a machine including a processor), wherein these operations can be accessed via a network (for example, the Internet) and via one or more appropriate interfaces (for example, API). The execution of certain operations in the operation can be distributed between processors, not only resides in a single machine, but also deployed across multiple machines. In some examples, a processor or the components implemented by the processor can be located in a single geographic location (for example, in a home environment, an office environment, or a server farm). In other examples, a processor or the components implemented by the processor can be distributed across multiple geographic locations.

[0378] "Machine-readable storage media" refers to both machine storage media and transmission media. Thus, these terms include both storage devices / media and carrier / modulated data signals. The terms "computer-readable medium," "machine-readable medium," and "device-readable medium" mean the same thing and may be used interchangeably in this disclosure.

[0379] An "ephemeral message" is a message that is accessible for a limited duration. An ephemeral message can be text, an image, a video, or the like. The access time for an ephemeral message can be set by the sender of the message. Alternatively, the access time can be a default setting or a setting specified by the recipient. Regardless of the setting technique, the message is ephemeral.

[0380] “Machine storage media” refers to a single or multiple storage devices and media (e.g., centralized or distributed databases, and associated caches and servers) that store executable instructions, routines, and data. Thus, the term should be taken to include, but is not limited to, solid-state memory and optical and magnetic media, including memory internal or external to the processor. Specific examples of machine storage media, computer storage media, and device storage media include: non-volatile memory, including, for example, semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGAs, and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The terms “machine storage media,” “device storage media,” and “computer storage media” mean the same thing and are used interchangeably in this disclosure. The terms “machine storage media,” “computer storage media,” and “device storage media” expressly exclude carrier waves, modulated data signals, and other such media, at least some of which are encompassed by the term “signal media.”

[0381] “Non-transitory machine-readable storage medium” refers to a tangible medium capable of storing, encoding, or carrying instructions for execution by a machine.

[0382] "Signal medium" refers to any intangible medium that is capable of storing, encoding, or carrying instructions for execution by a machine, and includes digital or analog communication signals or other intangible media to facilitate the communication of software or data. The term "signal medium" should be construed to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. The terms "transmission medium" and "signal medium" mean the same thing and may be used interchangeably in this disclosure.

Claims

1. A method of one or more processors, the method comprising: receiving, by the one or more processors, a prompt from a user from a client system during a first interactive session; generating, by the one or more processors, a response using the prompt and the large language model; transmitting, by the one or more processors, the response to the client system for display to the user during the first interactive session; determining, by the one or more processors, user intent based on the user prompt; determining, by the one or more processors, advertising content based on the user intent; as well as The advertising content is transmitted, by the one or more processors, to the client system for display to the user during a second interactive session.

2. The method according to claim 1, wherein The first interactive session is a chat session with a chatbot, and the second interactive session is not a chat session with a chatbot.

3. The method according to claim 1, wherein Generate a response that also includes: generating an original response based on the user prompt; generating an adjusted input prompt based on the original response; and The response is generated based on the adjusted input prompt.

4. The method according to claim 3, wherein: Generating the adjusted input further comprises: Generate a set of potential responses; and The response is selected from the set of potential responses.

5. The method according to claim 4, wherein Determining the user intent is also based on the potential responses.

6. The method according to claim 1, wherein Determining the user intent is also based on a user profile.

7. The method according to claim 6, wherein: The user profile includes social network data of the user's social network.

8. A machine comprising: one or more processors; as well as a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising: receiving a prompt from a user from a client system during a first interactive session; generating a response using the prompt and a large language model; transmitting the response to the client system for display to the user during the first interactive session; Determine user intent based on user prompts; determining advertising content based on the user intent; and The advertising content is transmitted to the client system for display to the user during a second interactive session.

9. The machine according to claim 8, wherein The first interactive session is a chat session with a chatbot, and the second interactive session is not a chat session with a chatbot.

10. The machine according to claim 8, wherein Generate a response that also includes: generating an original response based on the user prompt; generating an adjusted input prompt based on the original response; and The response is generated based on the adjusted input prompt.

11. The machine according to claim 10, wherein: Generating the adjusted input further comprises: Generate a set of potential responses; and The response is selected from the set of potential responses.

12. The machine according to claim 11, wherein Determining the user intent is also based on the potential responses.

13. The machine according to claim 8, wherein: Determining the user intent is also based on a user profile.

14. The machine according to claim 13, wherein The user profile includes social network data of the user's social network.

15. A machine storage medium storing instructions that, when executed by a machine, cause the machine to perform operations comprising: receiving a prompt from a user from a client system during a first interactive session; generating a response using the prompt and a large language model; transmitting the response to the client system for display to the user during the first interactive session; Determine user intent based on user prompts; determining advertising content based on the user intent; as well as The advertising content is transmitted to the client system for display to the user during a second interactive session.

16. The computer-readable medium of claim 15, wherein: The first interactive session is a chat session with a chatbot, and the second interactive session is not a chat session with a chatbot.

17. The computer-readable medium of claim 15, wherein: Generate a response that also includes: generating an original response based on the user prompt; generating an adjusted input prompt based on the original response; and The response is generated based on the adjusted input prompt.

18. The computer-readable medium of claim 17, wherein: Generating the adjusted input further comprises: Generate a set of potential responses; and The response is selected from the set of potential responses.

19. The computer-readable medium of claim 18, wherein: Determining the user intent is also based on the potential responses.

20. The computer-readable medium of claim 15, wherein: Determining the user intent is also based on a user profile.

Images