Search

CN-122019690-A - Knowledge acquisition method, apparatus, medium, program product and system

CN122019690ACN 122019690 ACN122019690 ACN 122019690ACN-122019690-A

Abstract

The application relates to the technical field of computers, and discloses a knowledge acquisition method, a knowledge acquisition device, a knowledge acquisition medium, a knowledge acquisition program product and a knowledge acquisition system. In the method, the first terminal device generates answer content based on knowledge information related to the question information determined by the cloud side device and the end side user portrait. The answer content is more relevant to the content of interest to the user than the knowledge obtained directly based on the questioning information. The user does not need to perform other operations such as re-acquisition, page turning and the like to acquire the interested contents, so that the use experience of the user can be improved.

Inventors

  • CAO YAN
  • LU DONGCAI
  • LI SONGYUAN
  • XIA MINGZHEN

Assignees

  • 华为终端有限公司

Dates

Publication Date
20260512
Application Date
20241108

Claims (12)

  1. 1. A knowledge acquisition method, comprising: The method comprises the steps that a first terminal device receives a question input for acquiring knowledge; The first terminal device sends the questioning information to cloud side device according to the questioning input; The first terminal equipment receives knowledge information from the cloud side equipment, wherein the knowledge information is generated according to the questioning information; The first terminal device generates answer content based on the knowledge information and a first user representation, wherein the first user representation is determined based on a first history of user operation of at least one terminal device.
  2. 2. The method of claim 1, wherein the first terminal device generates answer content based on the knowledge information and the first user representation, comprising: The first terminal device generates the answer content through a generated artificial intelligence model based on the knowledge information and the first user portrait, or The first terminal device screens and/or sorts a plurality of contents in the knowledge information based on the first user image, so as to generate the answer content.
  3. 3. The method of claim 1 or 2, wherein the content of the first history record comprises at least one of: Knowledge acquisition record of at least one application, stored file, content related to interaction; wherein the interactive operation function comprises at least one of viewing, sharing, collecting, commenting and downloading.
  4. 4. A method according to any one of claims 1 to 3, characterized in that the first history is information recorded by the at least one terminal device in a state in which the user is logged into the at least one terminal device.
  5. 5. The method according to any of claims 1 to 4, wherein the at least one terminal device comprises the first terminal device.
  6. 6. The method of any one of claims 1 to 5, wherein the form of the question input comprises at least one of text, image, audio, video.
  7. 7. A terminal device, comprising: A memory for storing computer program instructions; A processor for executing the computer program instructions to support the terminal device to implement the method of any of claims 1 to 6.
  8. 8. A computer readable storage medium, characterized in that it has stored thereon computer program instructions which, when executed by a processing circuit, implement the method according to any of claims 1-6.
  9. 9. A computer program product comprising computer program instructions which, when executed on a device, cause the device to carry out the method of any one of claims 1 to 6.
  10. 10. The knowledge acquisition system is characterized by comprising a first terminal device and cloud side devices; The first terminal device being configured to perform the method of any of claims 1-6; The cloud side device is used for acquiring knowledge information according to the questioning information and sending the knowledge information to the first terminal device.
  11. 11. The knowledge acquisition system of claim 10, wherein the cloud-side device is further to: The knowledge information is generated by generating an artificial intelligence model based on the questioning information and a second user profile, wherein the second user profile is determined based on a second history of the user operating at least one terminal device and/or user information of the user, the second history being different from the first history.
  12. 12. The knowledge acquisition system of claim 11, wherein the first history record is for recording a history of the user using at least one terminal device during a first time interval and the second history record is for recording a history of the user using at least one terminal device during a second time interval, wherein the second time interval comprises the first time interval.

Description

Knowledge acquisition method, apparatus, medium, program product and system Technical Field The present application relates to the field of computer technology, and in particular, to a knowledge acquisition method, apparatus, medium, program product, and system. Background The user may perform knowledge acquisition via an application program that includes knowledge acquisition functionality. For example, a user may obtain corresponding encyclopedia knowledge through a question input in the form of text, voice, or the like in an encyclopedia-like application (hereinafter referred to as an encyclopedia application), which obtains and returns a plurality of encyclopedia terms and/or encyclopedia content related to the user's question input based on the user's question input for viewing by the user. Current knowledge acquisition is typically based on matching user question inputs or semantic information related to the user question inputs with data in a database and returning the encyclopedia knowledge matched with the user question inputs as answer content to the corresponding user's question inputs. However, the content of interest of different users may be different, and the answer content obtained may be identical for the same question input of different users, which may result in a single answer content returned by the application for the same question input of different users, and thus in a poor user experience. Disclosure of Invention The present application aims to provide a knowledge acquisition method, device, medium, program product and system. The first aspect of the application provides a knowledge acquisition method, which comprises the steps that a first terminal device receives a question input for acquiring knowledge, the first terminal device sends the question information to a cloud side device according to the question input, the first terminal device receives knowledge information from the cloud side device, the knowledge information is generated according to the question information, and the first terminal device generates answer content based on the knowledge information and a first user portrait, wherein the first user portrait is determined based on a first history of user operation of at least one terminal device. In the embodiment of the application, the questioning information can be questioning input itself, and the questioning information can also be characteristic information of the questioning input. Wherein the feature information includes, but is not limited to, semantic features, image features, audio features, feature vectors obtained based on the above features, and the like. The first user representation may be an end-side user representation. The user may be a specific user, such as a first user. It will be appreciated that the answer content is generated based on knowledge information and end-side user portraits, and that the answer content is more relevant to the content of interest to the user than is not based on knowledge determined by the user portraits. Therefore, the user does not need to acquire interested contents again, turn pages and other operations, and the use experience of the user can be improved. In a possible implementation of the first aspect, the first terminal device generates the answer content based on the knowledge information and the first user portrait, which includes that the first terminal device generates the answer content through a generated artificial intelligence model based on the knowledge information and the first user portrait, or that the first terminal device filters and/or sorts a plurality of contents in the knowledge information based on the first user portrait, so as to generate the answer content. In the embodiment of the application, the first terminal equipment determines an end side knowledge acquisition plan (or called end side knowledge acquisition strategy) based on the questioning information and the end side user portrait, then inputs the end side knowledge acquisition plan and the knowledge information into the generated artificial intelligent model, and generates answer content by the generated artificial intelligent model. Or the first terminal device determines the priority of the plurality of content modules in the knowledge information based on the end-side user portrait, and ranks (e.g., descending order ranks) the plurality of content modules in the knowledge information based on the priority, so as to obtain the answer content. The higher the priority, the higher the matching degree of the corresponding content module and the end-side user portraits, i.e. the higher the probability of being content of interest to the user. In one possible implementation of the first aspect, the content of the first history record includes at least one of a knowledge acquisition record of at least one application, a stored file, and content related to an interactive operation, where a function of the interactive operation include