Trademark pattern matching method and corresponding device, equipment and medium

Abstract

The invention discloses a trademark pattern matching method and a corresponding device, equipment and medium, and the method comprises the steps of obtaining the image features of a trademark pattern contained in a to-be-compared picture, constructing a to-be-compared feature matrix, and storing the image features of a single trademark pattern in each row vector; obtaining a preset compared feature matrix of a compared trademark library, wherein each row vector stores an image feature of a single compared trademark in the compared trademark library; calculating the similarity based on the to-be-compared feature matrix and the compared feature matrix to obtain a similar matrix; and screening out elements of which the similarity meets a preset condition from the similar matrix so as to determine suspected trademark patterns having similarity association with the compared trademarks from the trademark patterns, and matching a plurality of first compared trademarks most similar to each suspected trademark pattern for each suspected trademark pattern. According to the invention, operation and judgment of approximate matching of the trademark are realized based on matrix operation, the operation efficiency is high, the response is quick, the overhead is relatively low, and the invention is suitable for identifying suspected trademark infringement information from the product picture.

Description

technical field [0001] The embodiment of the present application relates to the field of e-commerce information technology, and in particular to a trademark pattern matching method and corresponding devices, equipment, and media. Background technique [0002] Intellectual property rights issues are becoming more and more prominent. In the different links of the life cycle of trademarks such as application, examination, review, and litigation, trademark searches are often required, and the similarity search of trademark patterns has always been a technical difficulty. In the stage of trademark rights enforcement, a typical application field is the e-commerce field. The e-commerce field often provides product information with commodity patterns, and the commodity patterns usually include trademark patterns. [0003] There are a large number of product trademark infringement problems on e-commerce platforms, especially brand infringement problems caused by random use of tradema...

AI Technical Summary

Problems solved by technology

[0004] In the patent application No. CN106530194A published on March 22, 2017, a method and device for detecting pictures of suspected infringing products are disclosed. This solution alleviates the problems of slow review, detection accuracy and limited recall based on manual rule review to a certain extent. problem, but there are also some problems:

[0005] For example, in the logo detection part, the scheme uses the ergodicity of the logo patterns in the pre-established logo pattern library to match the product pictures to be recognized, and requires to know the category of the product pictures to be recognized in advance. Only when the matching degree exceeds a certain threshold, the product is considered There are corresponding suspected infringing logos in the image of the product to be identified. This process still requires a large amount of calculation, and since the category of the image of the product to be identified needs to be known in advance, this further depends on the judgment of the category of the image of the product to be identified. Accuracy; In addition, if a logo involves categories in different fields, it will also interfere with the final trademark judgment. A typical example is the YAMAHA brand, which involves many different categories of products such as pianos and motorcycles. Simple In the detection of trademarks under the category, there may be missing detection problems; in addition, this scheme uses a variety of local feature algorithms to extract relevant feature points, and the number of feature points extracted for relatively blurred images is relatively small, while for objects with smooth edges It may not be possible to accurately extract relevant feature points, and misjudgments may occur in these cases, etc.

Images