Catering type determination method and device

Abstract

The embodiment of the invention provides a catering type determination method, which comprises the steps of vectorizing a first entity and a second entity through Word2vec to generate a first set; vectorizing a pre-established relationship between the first entity and the second entity through TransE to generate a second set; and extracting a first vector in the first set and a third vector corresponding to the second vector in the second set from statements of the knowledge graph and the network encyclopedia data through remote supervision. According to the embodiment of the invention, extracting the relationship between each pair of entities in the entity set from the knowledge graph and the network encyclopedia data through remote supervision; compared with the prior art, the method hasthe advantages that since remote supervision has little dependence on manual work, the extracted relationship can be greatly expanded, the extracted relationship is more comprehensive, and the overall accuracy of the extracted relationship can be ensured, so that the relationship between the first entity and the second entity, namely the catering type corresponding to the catering name, can be comprehensively and accurately determined subsequently.

Description

technical field [0001] The present disclosure relates to the technical field of data analysis, and in particular to a method for determining a food type, a device for determining a food type, electronic equipment, and a computer-readable storage medium. Background technique [0002] With the development of intelligence in the catering industry, users can be provided with more convenient services and a better service experience. For example, when ordering takeaway or shopping, users can input the type of catering they want to eat. Query the name of the restaurant under this type, this service is mainly completed by classifying the name of the restaurant. [0003] However, the current method of determining the type of food and drink is mainly completed by manual labeling, that is, manually determining the name of the food and drink and the type of food that have a relationship, and then establishing and storing the relationship between the name of the food and the type of food...

AI Technical Summary

Problems solved by technology

[0004] This manual labeling method requires manual operations, and the efficiency of manual operations is very limited, so the types and names of restaurants that can be marked are also very limited, and the relationship that can be determined is very limited.

Moreover, some catering names belong to multiple catering types, and artificial standards are difficult to comprehensively analyze, resulting in some relationships not being marked, resulting in omissions in the relationship between catering names and catering types

Images