Intelligent recommending method and system for service commodities

Abstract

The invention provides an intelligent recommending method for service commodities. The method comprises the following steps: a) original user data of a user end and merchant data of a merchant end areobtained; b) the obtained original user data and the obtained merchant data are cleaned, and structural data can be obtained; c) the structural data is input into the following four independently operating engines for calculation, and therefore recommended commodities can be obtained; d) all the recommended commodities obtained via the calculation of the four independently operating engines in step c) are subjected to duplicate removing operation for the same user, probabilities of the user conducting operations on the recommended commodities after the duplicate removing operation are calculated, and the commodities are ranked in a descending order of probabilities; e) the recommended commodities are adjusted after the duplicate removing operation and the ranking operation in step d), andthe adjusted recommended commodities are displayed on the user end. The intelligent recommending system provided in the invention can be used for maximizing resource matching rates.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to an intelligent recommendation method and recommendation system for service commodities. Background technique [0002] Service products are services that are provided to buyers to meet certain needs of buyers. For example, common service products in daily life include confinement services, decoration services, moving services, and freight services. At present, service providers in the market mainly complete order transactions offline, and then have service personnel to complete related services. In the prior art, there is also the situation of completing transaction orders online, but the current transaction platform is simple in sorting service commodities, and has many shortcomings. For example, in the prior art, the ranking of service products is only based on customer evaluation as a factor for ranking service products. A single influencing factor makes it impossible to ...

AI Technical Summary

Problems solved by technology

In the prior art, there is also the situation of completing transaction orders online, but the current transaction platform has many shortcomings in ordering the service commodities simply.

For example, in the prior art, the ordering of service products is only based on customer evaluations as a factor in the ordering of service products. A single influencing factor makes it impossible to find the most suitable service provider in time, and unreasonable matching leads to waste of resources.

[0003] For example, service providers in a certain area have multiple irregular attributes, such as service provider qualifications, service capabilities, service prices, customer service capabilities, distance, etc. At the same time, different types of users have different needs due to individual factors. Therefore, when the user chooses a service provider, the existing recommendation system cannot find the most suitable service provider for recommendation in time, resulting in a waste of resources

Images