EP-4738792-A1 - NON-TRANSITORY MACHINE-READABLE STORAGE MEDIUM, METHOD AND APPARATUS FOR CHAT MANAGEMENT

EP4738792A1EP 4738792 A1EP4738792 A1EP 4738792A1EP-4738792-A1

Abstract

Provided is a computer-readable medium including computer-readable instructions. When the instructions are executed by a computer, the computer may implement a method. According to this method, contextual information of a plurality of users in a conversation is generated based on messages from the plurality of users over a period of time. Then the contextual information of the plurality of users is sent to a first artificial intelligence (AI) language model as input for training the Al language model and a request is sent to the first Al language model, wherein the request requires a response associated with the contextual information.

Inventors

VAUGHN, ROBERT

Assignees

INTEL Corporation

Dates

Publication Date: 20260506
Application Date: 20251027

Claims (15)

A computer-readable medium including computer-readable instructions, when executed, to implement a method, comprising: generating, based on messages from a plurality of users in a conversation over a period of time, contextual information of the plurality of users; sending the contextual information of the plurality of users to a first artificial intelligence (AI) language model of the conversation, wherein the contextual information is sent as input for training the first Al language model; and sending, after transmission of the contextual information of the plurality of users, a request to the first Al language model, wherein the request requires a response associated with the contextual information.
The computer-readable medium of claim 1, wherein the method further comprises: receiving a first request for starting the conversation for the first user; assigning a first token corresponding to the conversation to the first user; receiving a second request for joining the conversation for the second user, wherein the second request comprises a second token; and determining, based on the second token comprised in the second request, whether the second user is allowed to join the conversation, wherein the first user and the second user are of the plurality of users.
The computer-readable medium of claim 1 or 2, wherein the method further comprises: receiving a response corresponding to request from the first Al language model; and sending the response to the plurality of users respectively.
The computer-readable medium of any one of claims 1 to 3, wherein the contextual information of the plurality of users is generated based on time sequence of receiving the messages from the plurality of users and/or meaning of the messages from the plurality of users; and wherein the response associated with the contextual information is edited information based on the contextual information.
The computer-readable medium of any one of claims 1 to 4, wherein each of the first token and the second token comprises a section of conversation identifier and a section of participant identifier.
The computer-readable medium of any one of claims 1 to 5, wherein each of the first token and the second token is encrypted and wherein each token comprises encryption metadata for decrypting the token.
The computer-readable medium of any one of claims 1 to 6, wherein the period of time starts at commence of the conversation, or starts at a time point between commence and end of the conversation.
The computer-readable medium of any one of claims 1 to 7, wherein the method further comprises: establishing a plurality of sub-sessions coupling the plurality of users respectively with a plurality of dedicated Al language model instances.
The computer-readable medium of claim 8, wherein the method further comprises: sending private contextual information of each of the plurality of users to a corresponding dedicated Al language model instance through a corresponding sub-session of each of the plurality of sub-sessions.
The computer-readable medium of claim 9, wherein the method further comprises: receiving a plurality of responses sent by the plurality of dedicated Al language model instances through the plurality of sub-sessions; and importing the plurality of responses to a public session holding chat messages available to a plurality of users in the conversation.
The computer-readable medium of claim 10, wherein importing the plurality of responses to a public session comprises: sanitizing the plurality of responses; and merging the sanitized responses with public messages from the users in the public session.
The computer-readable medium of any one of claims 9 to 11, wherein the method further comprises: determining, based on a semantic analysis, the private contextual information of the plurality of users from overall information sent from the plurality of users.
The computer-readable medium of any one of claims 1 to 12, wherein the method further comprises: allocating a shared memory for public contextual information from the plurality of users in the conversation; and allocating a plurality of dedicated memories for each of the plurality of users in the conversation for respectively storing private contextual information of the plurality of users.
The computer-readable medium of claim 13, wherein the method further comprises: receiving an access request for accessing a first dedicated memory of the first user from the first Al language model; determining that the access request is for generating a response to a request by the first user; and allowing, based on the determination, access to the first dedicated memory.
A method, comprising: generating, based on messages from a plurality of users in a conversation over a period of time, contextual information of the plurality of users; sending the contextual information of the plurality of users to a first artificial intelligence (AI) language model of the conversation, wherein the contextual information is as input for training the first Al language model; and sending, after transmission of the contextual information, a request to the first Al language model, wherein the request requires a response associated with the contextual information.

Description

Background In the scenario of integrating multiple users into one chat session, some language models either lack the capability or are weak at facilitating multi-user interactions within a single session, which may limit their potential for collaborative, dynamic, and contextually rich communication experiences. Brief description of the Figures Some examples of apparatuses and/or methods will be described in the following by way of example only, and with reference to the accompanying figures, in which Fig. 1A shows a schematic figure of an example of system 100A for Al-based chat management.Fig. 1B shows a schematic figure of an example of system 100B for Al-based chat management.Fig. 1C shows a schematic figure of an example of system 100C for Al-based chat management.Fig. 2 shows an example of method 200 of Al-based chat management.Fig. 3 shows an example of method 300 of Al-based chat management.Fig. 4 shows an example of method 400 associated with Al-based chat management using tokens.Fig. 5 shows an example of method 500 associated with generation of adaptive responses in Al-based chat.Fig. 6 shows an example of method 600 associated with memory and data management in Al-based chat.Fig. 7 shows a block diagram of an example of apparatus 700.Fig. 8 shows a block diagram of an example of apparatus 800. Detailed Description Some examples are now described in more detail with reference to the enclosed figures. However, other possible examples are not limited to the features of these embodiments described in detail. Other examples may include modifications of the features as well as equivalents and alternatives to the features. Furthermore, the terminology used herein to describe certain examples should not be restrictive of further possible examples. Throughout the description of the figures identical or similar reference numerals refer to identical or similar elements and/or features, which may be identical or implemented in a modified form while providing the identical or a similar function. The thickness of lines, layers and/or areas in the figures may also be exaggerated for clarification. When two elements A and B are combined using an "or", this is to be understood as disclosing all possible combinations, i.e., only A, only B as well as A and B, unless expressly defined otherwise in the individual case. As an alternative wording for the identical combinations, "at least one of A and B" or "A and/or B" may be used. This applies equivalently to combinations of more than two elements. If a singular form, such as "a", "an" and "the" is used and the use of only a single element is not defined as mandatory either explicitly or implicitly, further examples may also use several elements to implement the identical function. If a function is described below as implemented using multiple elements, further examples may implement the identical function using a single element or a single processing entity. It is further understood that the terms "include", "including", "comprise" and/or "comprising", when used, describe the presence of the specified features, integers, steps, operations, processes, elements, components and/or a group thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, processes, elements, components and/or a group thereof. In the following description, specific details are set forth, but examples of the technologies described herein may be practiced without these specific details. Well-known circuits, structures, and techniques have not been shown in detail to avoid obscuring an understanding of this description. "An example," "various examples," "some examples," and the like may include features, structures, or characteristics, but not every example necessarily includes the particular features, structures, or characteristics. Some examples may have some, all, or none of the features described for other examples. "First," "second," "third," and the like describe a common element and indicate different instances of like elements being referred to. Such adjectives do not imply element item so described must be in a given sequence, either temporally or spatially, in ranking, or any other manner. "Connected" may indicate elements are in direct physical or electrical contact with each other and "coupled" may indicate elements co-operate or interact with each other, but they may or may be not in direct physical or electrical contact. As used herein, the terms "operating", "executing", or "running" as they pertain to software or firmware in relation to a system, device, platform, or resource are used interchangeably and can refer to software or firmware stored in one or more computer-readable storage media accessible by the system, device, platform, or resource, even though the instructions contained in the software or firmware are not actively being executed by the system, device, platform, or resource. The description may use the phrases "in