# US 12,585,886 B2 · Conversation methods, apparatus, electronic devices, storage media, and products

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,585,886 B2
- Document ID: US12585886B2
- Status: Granted
- Kind: B2
- Application number: 19/094,630
- Filed: 2025-03-28
- Published: 2025-10-02
- Granted: 2026-03-24
- Earliest claimed: 2024-03-29
- Assignees: Beijing Zitiao Network Technology Co., Ltd.
- Applicants: Beijing Zitiao Network Technology Co., Ltd.
- Inventors: Daoyu Wang; Hui Sun; Ziyang Zheng
- Web page: https://patentgrep.com/patent/US12585886B2

## CPC

- G06F 40/35: Discourse or dialogue representation
- G06F 40/30: Semantic analysis
- G06Q 10/101: Collaborative creation, e.g. joint development of products or services
- G06Q 10/40: Business processes related to social networking or social networking services
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

This disclosure relates to a conversation method, an apparatus, an electronic device, a storage medium, and a product, which relates to the field of artificial intelligence technology. The conversation method includes: displaying a first conversation between a first user and a second user on a client of the first user, calling one or more robots for the first user based on information of the first conversation; generating auxiliary conversation information of the robots based on the first conversation; and displaying the auxiliary conversation information.

## Claims

### Claim 1

A conversation method, comprising:
displaying a first conversation between a first user and a second user on a client of the first user;
calling one or more robots for the first user based on information of the first conversation;
generating auxiliary conversation information of the one or more robots based on the first conversation; and
displaying the auxiliary conversation information, wherein the calling the one or more robots for the first user based on the information of the first conversation comprises:
determining a conversation scenario between the first user and the second user based on the information of the first conversation;
calling, in response to the conversation scenario being a first type, the one or more robots for participating in the conversation between the first user and the second user for the first user, and
calling, in response to the conversation scenario being a second type, the one or more robots for providing reference information for the first user.

### Claim 2 (depends on 1)

The conversation method according to claim 1, wherein:
the auxiliary conversation information is information sent from the one or more robots during a process of participating in the conversation between the first user and the second user, or
the auxiliary conversation information is information provided to the first user for reference.

### Claim 3 (depends on 1)

The conversation method according to claim 1, wherein the one or more robots corresponds to the first conversation, the information of the first conversation comprises semantic information of the first conversation, and the calling the one or more robots for the first user based on the information of the first conversation comprises:
determining the one or more robots corresponding to the first conversation based on the semantic information of the first conversation; and
calling the one or more robots corresponding to the first conversation for the first user.

### Claim 4 (depends on 3)

The conversation method according to claim 3, further comprising:
taking a specified amount of last generated conversation message(s) in the first conversation as a target conversation, or taking conversation message(s) last generated within a specified time period in the first conversation as the target conversation, or taking conversation messages belonging to a same topic in the first conversation as the target conversation; and
determining the semantic information of the first conversation based on the target conversation.

### Claim 5 (depends on 3)

The conversation method according to claim 3, further comprising:
determining topic(s) involved in one or more rounds of conversation in the first conversation; and determining, in response to a number of topic(s) involved in the one or more rounds of conversation not exceeding a specified value, summary information of the first conversation as the semantic information of the first conversation; or
extracting key information from the first conversation as the semantic information of the first conversation.

### Claim 6 (depends on 3)

The conversation method according to claim 3, wherein the determining the one or more robots corresponding to the first conversation based on the semantic information of the first conversation comprises:
determining, in response to a number of topic(s) involved in the semantic information being greater than a specified value, or the semantic information of the first conversation is unclear, a conversation guide robot as a robot corresponding to the first conversation; and
matching, in response to the number of topic(s) involved in the semantic information not being greater than the specified value, the semantic information of the first conversation with attribute(s) of one or more candidate robots; and
determining the one or more robots corresponding to the first conversation based on a matching result.

### Claim 7 (depends on 1)

The conversation method according to claim 1, wherein the calling the one or more robots for the first user comprises:
displaying a first calling control for a robot corresponding to the first conversation; and
triggering, in response to the first user performing a trigger operation on the first calling control, generation of the auxiliary conversation information.

### Claim 8 (depends on 7)

The conversation method according to claim 7, wherein the calling control comprises instruction information to the robot corresponding to the first conversation, the instruction information being generated according to semantic information of the first conversation, and triggering the generation of the auxiliary conversation information comprises:
triggering, in response to a trigger operation of the first user on the first calling control, generation of the auxiliary conversation information based on the instruction information and the first conversation.

### Claim 9 (depends on 7)

The conversation method according to claim 7, wherein the auxiliary conversation information comprises at least one of reference information associated with the first conversation, a summary of the first conversation, or a response to the second user.

### Claim 10 (depends on 1)

The conversation method according to claim 1, further comprising:
displaying a second conversation message sent from the first user, wherein the second conversation message is determined based on the auxiliary conversation information, wherein the auxiliary conversation information is not visible to the second user.

### Claim 11 (depends on 1)

The conversation method according to claim 1, wherein the displaying the auxiliary conversation information comprises:
displaying, on a conversation interface of the first user and the second user, the auxiliary conversation information, wherein the auxiliary conversation information is sent from a robot participating in the conversation between the first user and the second user.

### Claim 12 (depends on 1)

The conversation method according to claim 1, wherein the generating the auxiliary conversation information of the one or more robots based on the first conversation comprises:
generating, in response to the first conversation corresponding to a service intent, the auxiliary conversation information, wherein the auxiliary conversation information comprises at least one of a product card or a service subscription card.

### Claim 13 (depends on 1)

The conversation method according to claim 1, further comprising:
displaying, in response to a calling operation of the first user on a robot, a robot determined based on the information of the first conversation or a robot specified by the operation; or
displaying a second calling control corresponding to a candidate robot, and displaying, in response to a trigger operation on the second calling control, a response of the candidate robot to the first conversation.

### Claim 14 (depends on 1)

An electronic device, comprising:
at least one memory; and
at least one processor coupled to the at least one memory, the at least one processor configured to, based on instructions stored in the at least one memory, carry out the conversation method of claim 1.

### Claim 15 (depends on 1)

A non-transitory computer-readable storage medium with a computer program stored thereon that, when executed by at least one processor, implements the conversation method of claim 1.

### Claim 16

A conversation method, comprising:
displaying a first conversation between a first user and a second user on a client of the first user;
calling one or more robots for the first user based on information of the first conversation;
generating auxiliary conversation information of the one or more robots based on the first conversation; and
displaying the auxiliary conversation information;
the information of the first conversation comprises a category of the second user, and the calling the one or more robots for the first user based on the information of the first conversation comprises:
calling, in response to the category of the second user being a specified category, a conversation guide robot for participating in a subsequent conversation between the first user and the second user for the first user.

### Claim 17 (depends on 16)

The conversation method according to claim 16, wherein the auxiliary conversation information is a message sent from the conversation guide robot during a process of participating in the subsequent conversation, and the generating the auxiliary conversation information of the one or more robots comprises:
generating association information of semantic information of both the first conversation and the subsequent conversation based on the semantic information of both the first conversation and the subsequent conversation, and information of the first user and information of the second user; and
generating a message sent from the conversation guide robot based on the association information.

### Claim 18 (depends on 16)

An electronic device, comprising:
at least one memory; and
at least one processor coupled to the at least one memory, the at least one processor configured to, based on instructions stored in the at least one memory, carry out the conversation method of claim 16.

### Claim 19

A conversation method, comprising:
displaying a first conversation between a first user and a second user on a client of the first user;
calling one or more robots for the first user based on information of the first conversation;
generating auxiliary conversation information of the one or more robots based on the first conversation; and
displaying the auxiliary conversation information;
the information of the first conversation comprises a sending time of conversation, and the calling the one or more robots for the first user based on the information of the first conversation comprises:
calling, in response to a last conversation message in the first conversation being sent from the second user and an interval between a sending time of the last conversation message and a current time being greater than a specified threshold, a robot serving as a virtual avatar of the first user to reply to the second user.

### Claim 20 (depends on 19)

The conversation method according to claim 19, wherein a profile photo of the virtual avatar robot is generated based on an image specified by the first user, and a voice of the virtual avatar robot is generated based on a voice specified by the first user.
