Quick matching method based on user portraits
A matching method and user technology, applied in data processing applications, forecasting, logistics, etc., can solve the problems that users cannot push suitable candidates, the matching method is not optimized enough, and corresponding matching cannot be performed, so as to improve algorithm efficiency and high accuracy , the effect of high matching success rate
Pending Publication Date: 2020-02-18
BEIJING UNIV OF TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the above algorithm only studies how to optimize the delivery route to achieve the goal of improving the efficiency of food delivery. It does not consider the user's own preferences, and cannot recommend suitable candidates for the food delivery service to the user, so it cannot be matched accordingly.
Even if it can be matched, because the matching method is not optimized enough, the matching efficiency is low and the accuracy is low
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0035] This fast matching method based on user portraits includes two types of processing of user historical data, one is user behavior path description, and the other is product keyword screening involved in user favorite item tags. The specific process is, after calculating the similarity percentage of the historical behavior paths of the orderer and all alternative meal deliverers, the top L more suitable alternative meal deliverers with a higher percentage are screened out, and then compared with the orders of the orderer. The item attributes and the historical delivery preference labels of these candidate deliverers are randomly selected from the deliverers whose item attributes are consistent with the historical delivery preference labels as the deliverer of this order. The specific operation steps are as follows:
[0036] 1. Organize data and determine the user's original location set
[0037] In the data sorting step, since the high-frequency locations of the top thre...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a quick matching method based on user portraits, and aims at scene features in a campus. In a specific scene, students and teachers have two roles of meal deliverers and mealorders as users; behavior habits of users in campus scenes are relatively fixed. In order to describe behaviors and preferences of users, basic information of the meal deliverer and basic informationof the meal orderer are better matched with each other; according to the method, user portraits are described, historical behavior paths of users are described, behavior path similarity among the users is calculated, required article attributes are compared with article preference labels carried by meal deliverymen, the system pushes the most suitable person to help the meal deliverymen to complete order transaction, and the matching problem of the meal deliverymen and meal orders in a campus is solved.
Description
technical field [0001] The invention provides a quick matching method among users, and in particular relates to a historical behavior path description of user portraits and commodity keyword screening of favorite tags. Background technique [0002] With the advent of the Internet era, online food delivery consumption behavior has gradually become the mainstream. The users of online food delivery are mainly social personnel. In the delivery process, merchants, delivery personnel and users are strictly distinguished. The background of the model is the social environment. However, delivery models are still immature based on specific scenarios, such as university campuses. Different from the complex social environment, the university campus is relatively closed, with higher security and generally better personnel quality. It is completely possible to design a special distribution mode inside the campus, that is, the user group is the teachers and students in the school, and the...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/08G06Q30/02
CPCG06Q10/047G06Q10/0832G06Q30/0201G06Q30/0203
Inventor 李童王楚桐张彦博王思羽姚钧雯
Owner BEIJING UNIV OF TECH