Data cooperative processing method, device, electronic device and computer storage medium

Abstract

The embodiment of the present invention discloses a data cooperative processing method, device, electronic equipment, and computer storage medium. The method includes: acquiring training data, wherein the training data includes the first training data with labels and the first training data without labels. The second training data; performing cooperative training according to the training data to obtain a data cooperative processing model; acquiring data to be processed, and using the data cooperative processing model to perform cooperative processing on the pending data to obtain a data cooperative processing result. This technical solution can combine the advantages of different models, which can not only ensure the effectiveness of abnormal operation identification, improve the accuracy of abnormal operation identification, but also improve the flexibility of abnormal operation identification, thereby avoiding losses of operating entities and maintaining the health of the market develop.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of data simulation, and in particular to a data cooperative processing method, device, electronic equipment, and computer storage medium. Background technique [0002] With the development of Internet technology, more and more merchants or service providers provide services to users through the Internet platform. In order to obtain more user transaction data and create more profits, many merchants, service providers or intermediaries There will be rich promotional activities, but during the activities, some abnormal or illegal behaviors have appeared, for example, some users frequently maliciously swiped orders, some merchants cheated such as joining users or pretending to be users to place orders multiple times, etc. These abnormalities The behavior seriously disrupted the market order, brought huge losses to the operating entities, and was not conducive to the healthy development of t...

AI Technical Summary

Problems solved by technology

The above manual rule-based approach has the following disadvantages: 1) Relying on manual experience, the cost of rule configuration is high; 2) The rules are independent of each other and do not affect each other, and it is difficult to share information between different rules; 3) Usually the conditions for rule matching are fixed Yes, the matching result is either a hit or a miss. After the rule is leaked, it is easy to be circumvented, which leads to the failure of the recognition model; 4) Unable to recognize new abnormal operations

In addition, the above-mentioned semi-supervised method has the following disadvantages: 1) It cannot use the existing artificial experience, which affects the effectiveness of the recognition model; 2) The misjudgment rate is high, although the abnormal operations found by clustering operations may be abnormal operations Gangs, but it may also be a centralized trading event or a promotional transaction, etc.

Images