Business object search/attribute determination method, device, system and equipment

Abstract

The invention discloses a business object searching system, method and device and related methods, devices, systems and equipment. The business object search method comprises the steps of receiving a similar business object search request for a target business object; obtaining first attribute decoupling representation vectors of the target business object and the candidate business object; according to the first attribute decoupling representation vector and the attribute value difference information, determining a service object which has the attribute value difference information on the target attribute and is the same as or similar to the target service object on the non-target attribute from the candidate service objects; and returning the similar business object to the requester. By the adoption of the processing mode, on one hand, the search dimension of single-factor control search can be effectively increased, the search effect based on user mind is achieved, and therefore user experience is improved; and on the other hand, the recall rate and accuracy of the search result can be effectively improved.

Description

technical field

[0001] The present application relates to the technical field of data processing, and specifically relates to a business object search method, device and system, a business object recommendation method, device and system, and electronic equipment. Background technique

[0002] When shopping on e-commerce websites, users usually use search engines or filters to quickly locate target products. Traditional search engines provide the following search sorting methods:

[0003] (1) Keyword-based query: perform a matching search based on keywords entered by the user or prompted by the system, or product attributes Q, and perform single-attribute or multi-attribute sorting based on the explicit attributes in the entity. The system first constructs an index for the entity, such as building an inverted index for the title, description text, and category attributes, and then expands and rewrites the attribute Q, and then searches the index.

[0004] (2) Similar query ...

Images