Resource-limited O2O service composition recommendation method and system

Abstract

The invention discloses an O2O service combination recommendation method and system with limited resources. The method comprises the following steps: calculating user similarity based on user basic information and external context, and then calculating user similarity of comprehensive context; Acquiring the nearest neighbor of the target user, and calculating a service item list based on the service item prediction score of the target user according to the service item score of the nearest neighbor; Calculating a service item list based on the dynamic state attribute of the supplier, and further calculating a comprehensive list of the service items; recommending The service items in the comprehensive list of service items to the target users, acquiring the target service items selected bythe target users and the target service points in each service point corresponding to the target service items, and calculating the service paths with the shortest time for the target users to reach the target service points based on the shortest path algorithm; and the service paths with the shortest time for the target users to reach the target service points are obtained. Recommends a service composition to the target user. The invention can more reasonably and effectively realize the recommendation of resource-limited O2O service combination.

Description

technical field [0001] The invention relates to the technical field of O2O service recommendation. More specifically, it relates to a resource-constrained O2O service combination recommendation method and system. Background technique [0002] With the development of information technology, society has entered the era of information explosion. The problem of information overload is becoming more and more prominent. In this context, how to filter out the most effective information becomes an imminent problem. "Recommendation technology" is becoming more and more important. Search engines can be regarded as the first generation of recommendation technology, because they require human participation, so they are passive information screening. Subsequent information recommendation is active and is being integrated with other technologies, such as emerging smart speakers, including news recommendations, product recommendations, etc., and is developing into a major information f...

AI Technical Summary

Problems solved by technology

The disadvantage is that because O2O recommendation involves offline services, traditional recommendation lacks comprehensive consideration of the limited offline service resources of suppliers. For example, the service capabilities of restaurants and nail shops will change in real time and offline resource reserves are limited.

[0011] (1) Existing service recommendations only focus on the demand side without considering the supply side, while O2O services require support from offline resources, so the information on the supply side always affects the recommendation effect

Therefore, traditional recommendation strategies lack consideration of the real-time status information of suppliers in O2O services.

[0012] (2) Existing service recommendations only make ordinary recommendations for commodities, without considering the changes in the number of users on the service path between the supply and demand parties after the recommendation, which affects the user experience

Images