Intelligent recommendation method and device, computer equipment and readable storage medium
A recommendation method and intelligent technology, applied in computer parts, computing, and other database retrieval, etc., can solve problems such as difficulty in quickly and effectively obtaining recommended information, increased server pressure, and huge data volume, so as to reduce the amount of data calculation and storage The effect of increasing the amount, improving the calculation speed, and improving the operation efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0059] see figure 1 , an intelligent recommendation method in this embodiment, comprising:
[0060] S102: Obtain user information, and perform characterization processing on the user information to obtain a user vector.
[0061] S103: Invoke the product quantization process to segment the user vector to obtain several sub-vectors, identify the category of each sub-vector, and summarize the categories to obtain a user category set;
[0062] S104: calling the minimum hash process, comparing the similarity between the user category set and each reference category set in the preset index library, and setting the reference category set whose similarity exceeds the preset similarity threshold as the target category set; Wherein, the reference category set is obtained by pre-characterizing the preset reference information and calling the product quantization process, and is used to reflect the data set of the category of the sub-vector corresponding to the reference information. The...
Embodiment 2
[0069] This embodiment is a specific application scenario of the first embodiment above. Through this embodiment, the method provided by the present invention can be described more clearly and specifically.
[0070] Next, in the server running the intelligent recommendation method, the user vector is segmented to obtain several sub-vectors, and the category of each sub-vector is identified and summarized to obtain a user category set, and the user category set is combined with The reference category sets in the preset index library are compared to obtain the similarity, and the target category set is obtained according to the similarity. Finally, the related information corresponding to the target category set is used as the recommendation information as an example to describe the method provided in this embodiment. It should be noted that this embodiment is only exemplary, and does not limit the protection scope of the embodiment of the present invention.
[0071] figure 2 ...
Embodiment 3
[0154] see Figure 8 , an intelligent recommendation device 1 of this embodiment, comprising:
[0155] An information processing module 12, configured to obtain user information, and perform characterization processing on the user information to obtain a user vector;
[0156] The product quantization module 13 is used to call the product quantization process to segment the user vector to obtain several sub-vectors, identify the category to which each sub-vector belongs, and summarize the categories to obtain a user category set;
[0157] The minimum hash module 14 is used to call the minimum hash process to compare the similarity between the user category set and each reference category set in the preset index library, and compare the similarity of the reference categories whose similarity exceeds the preset similarity threshold. The category set is set as the target category set; wherein, the reference category set is obtained by pre-characterizing the preset reference infor...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com