Business recommendation method and business recommendation device

Abstract

The invention provides a business recommendation method and a business recommendation device. The business recommendation method comprises the following steps that: obtaining historical business ordering feature information; according to the historical business ordering feature information, determining recommended target feature information; and according to the recommended target feature information, recommending the business to a recommendation target corresponding to the recommended target feature information according to the recommended target feature information. By use of the business recommendation method and the business recommendation device, accurate business recommendation is realized, and the accuracy of user experience and business recommendation is improved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a service recommendation method and a service recommendation device. Background technique [0002] At present, there are many service recommendation methods in the prior art, one of which is: by establishing a user interest model, generating an association relationship between the user interest model and telecommunication services, thereby obtaining a list of recommended services, and recommending services to users. Another service recommendation method is to recommend services for the user according to the density factor between the user and each contact and the business information of each contact, wherein the density factor is used to indicate the frequency of communication between the user and each contact. [0003] However, the service recommendation method in the above prior art has the following disadvantages: [0004] 1. The establishment of a user interest model ...

AI Technical Summary

Problems solved by technology

[0004] 1. The establishment of a user interest model requires comprehensive consideration of information in various systems, and the integration of cross-system information requires Uniform Resource Locator (Uniform Resource Locator, referred to as: URL) analysis, stream processing and other calculations, so that the user interest model The development is difficult, the cycle is long, and the efficiency is low. The range of recommendation results through the user interest model is relatively coarse, which affects the user experience.

[0005] 2. The method of using the density factor of the user and each contact as the basis for business recommendation, the data is relatively single, which reduces the accuracy of business recommendation

Images