Personalized recommendation method, system and electronic equipment
A recommendation method and similarity technology, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of inability to distinguish geographical space, lack of meaning of existence, etc., and achieve accurate and refined similarity calculation results Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0065] The embodiment of the present invention provides a personalized recommendation method, which specifically includes:
[0066] Construct a spatially heterogeneous information network, and construct a semantic path personalized recommendation based on project collaborative filtering based on the relationship between users and historical items, the semantic path similarity between historical items and items to be recommended, and the spatial weight of items to be recommended Model:
[0067] The model is used to calculate the recommendation index of the item to be recommended, and the recommendation is made to the user according to the calculation result.
[0068] It should be noted that the traditional data expression mainly uses structured data such as tags to describe the composition of information, and the obtained data expression structure is a heterogeneous information network, while the traditional heterogeneous information network often directly describes items The ...
Embodiment 2
[0180] A personalized recommendation system, such as Figure 4 As shown, it includes building blocks, personalized recommendation models and recommendation modules, and the personalized recommendation models are respectively connected with the building blocks and recommendation modules; the building blocks are used to build spatial heterogeneous information networks; the personalized recommendation models are based on the Spatial heterogeneous information network, according to the relationship between users and historical items, the semantic path similarity between historical items and items to be recommended, and the spatial weight of items to be recommended to calculate the recommendation index of items to be recommended: recommendation module, based on personality Recommendations are made to users based on the calculation results of the optimized recommendation model.
[0181] Preferably, the personalized recommendation model is:
[0182] Among them, θ q Indicates the w...
Embodiment 3
[0205] an electronic device such as Figure 5 As shown, it includes a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, it realizes part of any one of the above-mentioned personalized recommendation methods or all steps.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


