CN-122001942-A - Information pushing method, device, terminal and medium

CN122001942ACN 122001942 ACN122001942 ACN 122001942ACN-122001942-A

Abstract

The application relates to the technical field of data processing and information pushing, and provides an information pushing method, device, terminal and medium, wherein the method comprises the steps of receiving pushing demand information input by a target user; the information extraction method comprises the steps of carrying out information extraction according to the push demand information and the multi-dimensional user portrait of the target user to obtain first information to be pushed, carrying out optimization processing on the first information to be pushed to obtain second information to be pushed, pushing the second information to be pushed to the target user, and carrying out push processing after the corresponding information to be pushed is extracted by combining the multi-dimensional user portrait of the user and the push demand information, so that accuracy in information pushing is improved.

Inventors

LIU JINGYI
CHEN GAOHUA
YU XIAOTIAN
LI AIJUN

Assignees

深圳云天励飞技术股份有限公司
青岛云天励飞科技有限公司

Dates

Publication Date: 20260508
Application Date: 20251218

Claims (11)

1. An information pushing method, characterized in that the method comprises: receiving push demand information input by a target user; extracting information according to the pushing demand information and the multi-dimensional user portrait of the target user to obtain first information to be pushed; Optimizing the first information to be pushed to obtain second information to be pushed; and pushing the second information to be pushed to the target user.
2. The information pushing method according to claim 1, wherein the extracting information according to the pushing requirement information and the multi-dimensional user representation of the target user to obtain the first information to be pushed includes: Determining push type information according to the push demand information; and extracting information according to the push type information and the multi-dimensional user portrait to obtain the first information to be pushed.
3. The information pushing method according to claim 2, wherein the extracting information according to the pushing type information and the multi-dimensional user portrait to obtain the first information to be pushed includes: If the push type information is information push, determining news type information according to the push demand information; News type information and the multi-dimensional user portrayal generation information extraction parameters; And extracting the first information to be pushed from a preset news database according to the information extraction parameters.
4. The information pushing method according to claim 2, wherein the extracting information according to the pushing type information and the multi-dimensional user portrait to obtain the first information to be pushed includes: If the pushing type information is intelligent question and answer, carrying out context analysis on the pushing demand information to obtain question and answer key information; extracting reference push information from a preset news database according to the question-answer key information and the multidimensional user portraits; determining an intelligent question-answering result according to the reference push information; and determining the intelligent question and answer result as the first information to be pushed.
5. The information pushing method according to claim 3 or 4, characterized in that the method further comprises: acquiring initial news information in a preset time period; preprocessing according to the initial news information to obtain first intermediate news information; performing duplicate removal processing on the first middle news information to obtain second middle news information; generating abstract information corresponding to the second middle news information; And storing the second intermediate news information and the abstract information in a preset news database in an associated mode.
6. The information pushing method according to claim 5, wherein the storing the second intermediate news information and the summary information in association with each other in the preset news database includes: Classifying the second middle news information to obtain type information; And storing the second middle news information and the abstract information in the preset news database in an associated mode according to the type information.
7. The information pushing method according to claim 6, wherein the optimizing the first information to be pushed to obtain the second information to be pushed includes: determining user associated feature information according to the multi-dimensional user portrait; determining pushing key information from the first information to be pushed according to the user association characteristic information; Determining the labeling information of the push key information; And marking the corresponding push key information in the first information to be pushed by adopting the marking information to obtain the second information to be pushed.
8. The information pushing method according to claim 6 or 7, characterized in that the method further comprises: acquiring multidimensional reading behavior information of the target user; Extracting characteristics of the multidimensional reading behavior information to obtain behavior characteristic information; And carrying out deep portrait analysis processing on the behavior characteristic information to obtain the multidimensional user portrait of the target user.
9. An information pushing apparatus, characterized in that the apparatus comprises: the receiving unit is used for receiving push demand information input by a target user; The extraction unit is used for extracting information according to the pushing demand information and the multi-dimensional user portrait of the target user to obtain first information to be pushed; The optimizing unit is used for optimizing the first information to be pushed to obtain second information to be pushed; and the pushing unit is used for pushing the second information to be pushed to the target user.
10. A terminal comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the information pushing method of any of claims 1-8.
11. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the information pushing method according to any of claims 1-8.

Description

Information pushing method, device, terminal and medium Technical Field The application relates to the technical field of data processing and information pushing, in particular to an information pushing method, an information pushing device, a terminal and a medium. Background The unified news recommendation system mainly relies on keyword matching, collaborative filtering algorithm, simple user behavior (such as click rate) and the like for analysis and processing to obtain information which is pushed finally. So that it can only be pushed in combination with simple user behavior and the like when information is pushed, resulting in lower accuracy when information is pushed. Disclosure of Invention The embodiment of the application provides an information pushing method, an information pushing device, a terminal and a medium, which can extract corresponding information to be pushed by combining multi-dimensional user figures of a user and pushing demand information, and then carry out pushing processing, so that the accuracy of information pushing is improved. A first aspect of an embodiment of the present application provides an information pushing method, where the method includes: receiving push demand information input by a target user; extracting information according to the pushing demand information and the multi-dimensional user portrait of the target user to obtain first information to be pushed; Optimizing the first information to be pushed to obtain second information to be pushed; and pushing the second information to be pushed to the target user. In one possible implementation manner, the information extraction according to the push requirement information and the multi-dimensional user portrait of the target user, to obtain first information to be pushed, includes: Determining push type information according to the push demand information; and extracting information according to the push type information and the multi-dimensional user portrait to obtain the first information to be pushed. In one possible implementation manner, the extracting information according to the push type information and the multi-dimensional user portrait to obtain the first information to be pushed includes: If the push type information is information push, determining news type information according to the push demand information; News type information and the multi-dimensional user portrayal generation information extraction parameters; And extracting the first information to be pushed from a preset news database according to the information extraction parameters. In one possible implementation manner, the extracting information according to the push type information and the multi-dimensional user portrait to obtain the first information to be pushed includes: If the pushing type information is intelligent question and answer, carrying out context analysis on the pushing demand information to obtain question and answer key information; extracting reference push information from a preset news database according to the question-answer key information and the multidimensional user portraits; determining an intelligent question-answering result according to the reference push information; and determining the intelligent question and answer result as the first information to be pushed. In one possible implementation, the method further includes: acquiring initial news information in a preset time period; preprocessing according to the initial news information to obtain first intermediate news information; performing duplicate removal processing on the first middle news information to obtain second middle news information; generating abstract information corresponding to the second middle news information; And storing the second intermediate news information and the abstract information in a preset news database in an associated mode. In one possible implementation manner, the storing the second intermediate news information and the summary information in association with the preset news database includes: Classifying the second middle news information to obtain type information; And storing the second middle news information and the abstract information in the preset news database in an associated mode according to the type information. In one possible implementation manner, the optimizing the first information to be pushed to obtain the second information to be pushed includes: determining user associated feature information according to the multi-dimensional user portrait; determining pushing key information from the first information to be pushed according to the user association characteristic information; Determining the labeling information of the push key information; And marking the corresponding push key information in the first information to be pushed by adopting the marking information to obtain the second information to be pushed. In one possible implementation, the method further includes: acquiring multi