# US 2022/0019747 A1 · Method for information processing in user conversation, electronic device and storage medium thereof

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

- Number: US 2022/0019747 A1
- Document ID: US20220019747A1
- Status: Published application
- Kind: A1
- Application number: 17/237,797
- Filed: 2021-04-22
- Published: 2022-01-20
- Earliest claimed: 2020-07-20
- Assignees: Beijing Baidu Netcom Science Technology Co., Ltd.
- Applicants: Beijing Baidu Netcom Science and Technology Co., Ltd.
- Inventors: Zhen Guo; Wenquan Wu; Zhanyi Liu
- Web page: https://patentgrep.com/patent/US20220019747A1

## CPC

- G06F 16/435: Filtering based on additional data, e.g. user or group profiles
- G06F 40/35: Discourse or dialogue representation
- G06F 16/3329: Natural language query formulation
- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 40/279: Recognition of textual entities
- G06N 5/04: Inference or reasoning models
- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G06T 11/00: Two-dimensional [2D] image generation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for information processing in a user conversation, an electronic device and a storage medium thereof, which relate to the field of artificial intelligence and the natural language processing field, are disclosed. The method may include: acquiring conversation preceding information in a conversation between a first user and a second user; acquiring a target conversation strategy employed by the first user; generating initial reply content with a pre-trained response generating model according to the target conversation strategy and the conversation preceding information; and sending the initial reply content to a client of the first user, so as to display the initial reply content on a conversation interface of the first user with the second user.

## Claims

### Claim 1

A method for information processing in a user conversation, comprising:
acquiring conversation preceding information in a conversation between a first user and a second user;
acquiring a target conversation strategy employed by the first user;
generating initial reply content with a pre-trained response generating model according to the target conversation strategy and the conversation preceding information; and
sending the initial reply content to a client of the first user, so as to display the initial reply content on a conversation interface of the first user with the second user.

### Claim 2 (depends on 1)

The method of claim 1, wherein acquiring the target conversation strategy employed by the first user comprises:
acquiring the target conversation strategy selected by the first user from a preset conversation strategy set.

### Claim 3 (depends on 1)

The method of claim 1, wherein acquiring the target conversation strategy employed by the first user comprises:
predicting the target conversation strategy with a pre-trained conversation-strategy predicting model and historical conversation information of the first and second users.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
transforming a style of the initial reply content to obtain target reply content.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
based on the initial reply content, generating a picture or an animation with information of a keyword of the initial reply content as the target reply content.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
generating a cartoon using a cartoon generating model based on a keyword of the initial reply content; and
sending the cartoon to the client of the first user, so as to display the cartoon on the conversation interface of the first user with the second user.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
analyzing emotion information of the second user with an emotion analyzing model based on historical conversation information of the first and second users, sending the emotion information of the second user to the client of the first user, and displaying the emotion information on the conversation interface of the first user with the second user.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
analyzing whether the second user is interested in the current topic with a topic-interest-degree analyzing model based on the historical conversation information of the first and second users, sending the analysis result to the client of the first user, and displaying the analysis result on the conversation interface of the first user with the second user.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
predicting an interested target topic of the second user with a topic predicting model based on historical conversation information of the first and second users, sending the interested target topic of the second user to the client of the first user, and displaying the interested target topic on the conversation interface of the first user with the second user.

### Claim 10

An electronic device, comprising:
at least one processor; and
a memory connected with the at least one processor communicatively;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to carry out a method for information processing in a user conversation, which comprises:
acquiring conversation preceding information in a conversation between a first user and a second user;
acquiring a target conversation strategy employed by the first user;
generating initial reply content with a pre-trained response generating model according to the target conversation strategy and the conversation preceding information; and
sending the initial reply content to a client of the first user, so as to display the initial reply content on a conversation interface of the first user with the second user.

### Claim 11 (depends on 10)

The electronic device of claim 10, wherein acquiring the target conversation strategy employed by the first user comprises:
acquiring the target conversation strategy selected by the first user from a preset conversation strategy set.

### Claim 12 (depends on 10)

The electronic device of claim 10, wherein acquiring the target conversation strategy employed by the first user comprises:
predicting the target conversation strategy with a pre-trained conversation-strategy predicting model and historical conversation information of the first and second users.

### Claim 13 (depends on 10)

The electronic device of claim 10, wherein the method further comprises:
transforming a style of the initial reply content to obtain target reply content.

### Claim 14 (depends on 10)

The electronic device of claim 10, wherein the method further comprises:
based on the initial reply content, generating a picture or an animation with information of a keyword of the initial reply content as the target reply content.

### Claim 15 (depends on 10)

The electronic device of claim 10, wherein the method further comprises:
generating a cartoon using a cartoon generating model based on a keyword of the initial reply content; and
sending the cartoon to the client of the first user, so as to display the cartoon on the conversation interface of the first user with the second user.

### Claim 16 (depends on 10)

The electronic device of claim 10, wherein the method further comprises:
analyzing emotion information of the second user with an emotion analyzing model based on historical conversation information of the first and second users, sending the emotion information of the second user to the client of the first user, and displaying the emotion information on the conversation interface of the first user with the second user.

### Claim 17 (depends on 10)

The electronic device of claim 10, wherein the method further comprises:
analyzing whether the second user is interested in the current topic with a topic-interest-degree analyzing model based on the historical conversation information of the first and second users, sending the analysis result to the client of the first user, and displaying the analysis result on the conversation interface of the first user with the second user.

### Claim 18 (depends on 10)

The electronic device of claim 10, wherein the method further comprises:
predicting an interested target topic of the second user with a topic predicting model based on historical conversation information of the first and second users, sending the interested target topic of the second user to the client of the first user, and displaying the interested target topic on the conversation interface of the first user with the second user.

### Claim 19

A non-transitory computer readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out a method for information processing in a user conversation, which comprises:
acquiring conversation preceding information in a conversation between a first user and a second user;
acquiring a target conversation strategy employed by the first user;
generating initial reply content with a pre-trained response generating model according to the target conversation strategy and the conversation preceding information; and
sending the initial reply content to a client of the first user, so as to display the initial reply content on a conversation interface of the first user with the second user.

### Claim 20 (depends on 19)

The non-transitory computer readable storage medium of claim 19, wherein the method further comprises:
transforming a style of the initial reply content to obtain target reply content.
