Intelligent recommendation method based on knowledge graph

A recommendation method and knowledge graph technology, which is applied in the fields of instruments, semantic tool creation, unstructured text data retrieval, etc., can solve problems such as weak correlation and sparse data, achieve fast and accurate push, achieve accuracy, and improve recommendation results. Effect

Active Publication Date: 2022-04-01
北京中科闻歌科技股份有限公司
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides an intelligent recommendation method based on knowledge graphs, which can effectively solve the problems of sparse data and weak correlation existing in existing recommendation methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent recommendation method based on knowledge graph
  • Intelligent recommendation method based on knowledge graph
  • Intelligent recommendation method based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] like figure 1 As shown, this embodiment provides an intelligent recommendation method based on a knowledge map. The method of this embodiment can be implemented on any electronic device, which belongs to the precise recommendation for a specified field. The method of this embodiment may include the following step:

[0069] A1. For the target users of the information to be recommended in the specified field, obtain the type of the target user and obtain the items to be recommended.

[0070] For example, the types of target users in this embodiment include: active users, inactive users and newly registered users.

[0071] Wherein, an inactive user refers to a user who has no user interaction behavior data within a certain time range, and an active user refers to a user who has user behavior data within a certain time range.

[0072] The specified fields in this embodiment may include: the field of commercial public opinion, the field of navigation, the field of arctic e...

Embodiment 2

[0093] Compared with the text content similarity comparison method in the prior art, the content recommendation method based on knowledge graph in this embodiment combines the association relationship of key entities in the knowledge graph, reasonably realizes the recommendation of text content similarity, and improves the Accuracy of recommended results.

[0094] In order to better illustrate the process of obtaining personalized recommendation results based on knowledge map recommendation content in step A2 of the above-mentioned embodiment, the following is combined figure 2 Describe in detail.

[0095] A21. According to the interaction behavior data of the target user within the first preset time period, obtain all information items in the interaction behavior data and entity sets of all information items;

[0096] For all the text information in the item to be recommended, the entity set of each text information is obtained.

[0097] For example, by obtaining the infor...

Embodiment 3

[0124] In order to better illustrate the process of obtaining personalized recommendation results based on the user collaborative filtering recommendation method in step A2 of the above-mentioned embodiment, the following combination image 3 Describe in detail.

[0125] In this embodiment, first, based on the user interaction behavior data within a certain time range, user similarity is mined, and user-information item, information item-user preference matrices (the following first scoring matrix and second scoring matrix) are constructed. , and then the similarity between users is calculated by the matrix, and the nearest neighbor users of the target user are obtained through the similarity, and the time-sensitive text information that the target user has not browsed and meets the timeliness is recommended to the target user. In this way, the diversity of recommendation results is realized, and the recommendation results of thousands of people and faces are realized, and the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to an intelligent recommendation method based on a knowledge graph, and the method comprises the steps: A1, obtaining the type of a target user for the target user of to-be-recommended information in a designated field; a2, if the type of the target user is an active user, obtaining a personalized recommendation result based on a knowledge graph recommendation content mode and a user collaborative filtering recommendation mode according to interaction behavior data of the target user in a first preset time period; wherein the knowledge graph is structured graph information which is pre-constructed and stores a relationship between knowledge and entities in a specified field; the personalized recommendation result comprises the information item corresponding to the nearest neighbor user of the target user and the information item matched with the preference entity of the target user, the method can effectively solve the problems that in an existing recommendation method, data is sparse, and relevance is weak, meanwhile, text information is pushed quickly and accurately, and the user experience is improved. And personalized pushing of thousands of people is realized.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an intelligent recommendation method based on a knowledge map. Background technique [0002] The recommendation system analyzes user behavior, interests and other information, and mines the information that users are interested in in massive data to make personalized recommendations. It is widely used in many Web scenarios to deal with the information overload problem caused by massive information data. Improve user experience. As a kind of effective auxiliary information in hybrid recommender systems, knowledge graphs can effectively solve a series of key problems in recommender systems, such as cold start, recommendation diversity, etc. [0003] However, the recommendation methods based on knowledge graphs in the prior art cannot meet the needs of accurate recommendation, and there is a problem of sparse recommendation data, and the correlation of recommendation data is weak...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06F16/9536G06F16/36G06F16/335G06F40/216G06N3/04
Inventor 王宇琪张佳旭郭建彬郝保王璋盛曹家罗引王磊
Owner 北京中科闻歌科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap