Evaluation recognition and evaluation recognition network model training method and device

A technology for identifying networks and identification methods, which is applied in computing models, instruments, sales/lease transactions, etc., can solve the problems of low identification accuracy of malicious bad reviews and difficulty in accurately defining the responsible party for bad reviews, and achieve the effect of improving the recognition accuracy

CN113888262APending Publication Date: 2022-01-04KOUBEI SHANGHAI INFORMATION TECH CO LTD
0 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-01-04

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an evaluation recognition method, a training method and device for an evaluation recognition network model, and equipment The evaluation recognition method comprises the following steps: obtaining an evaluation text to be recognized, and inputting the evaluation text into a word vector calculation network and an entity recognition network contained in an evaluation recognition network model; according to a head word of the evaluation text output by the entity recognition network and an information entropy of the head word, performing feature enhancement processing on a word vector of the evaluation text output by the word vector calculation network to obtain an enhanced feature vector of the evaluation text; and inputting the enhanced feature vector of the evaluation text and the statistical feature of the evaluation text into a classification model included in the evaluation recognition network model to obtain recognition result information of the evaluation text. By adopting the method, the problem that the poor evaluation responsible party is difficult to define accurately due to the fact that the malicious poor evaluation recognition precision is low is solved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the field of data processing, and in particular to an evaluation and identification method, device and equipment. The present application also relates to a training method, device and equipment for evaluating and recognizing network models. Background technique

[0002] With the development of Internet technology, it is becoming more and more common for users to obtain goods or services from merchants through Internet-based online platforms. Users can publish evaluation information for the obtained goods or services. User evaluation information is an important part of merchant rating calculation. Negative reviews directly affect the level of merchant ratings, and merchant ratings can affect the traffic and ranking of merchants on the platform. In fact, in order to achieve malicious competition, illegal profit and other bad purposes, there may be malicious evaluations of merchants in normal operation. Therefore, it is...

Examples

Embodiment Construction

[0044] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the application. However, the present application can be implemented in many other ways different from those described here, and those skilled in the art can make similar promotions without violating the connotation of the present application. Therefore, the present application is not limited by the specific implementation disclosed below.

[0045] Embodiments of the present application provide an evaluation recognition method, device, electronic device, and storage device. Embodiments of the present application also provide a training method, device, electronic device, and storage device for evaluating and recognizing a network model. Each will be described in the following examples.

[0046] For ease of understanding, the system environment provided by the embodiment of the present application is firstly given. Please refer to figure 1 , including: ...