Method, apparatus, electronic device and medium for model building and analysis

Abstract

The present disclosure provides an analysis method, comprising: in response to receiving an analysis instruction for a target object, determining an analysis time period, where the analysis time period is related to a timestamp of predetermined time series data of the target object; acquiring that the target object is located within the analysis time period based on the first time series data; obtain a first time series feature set based on the first time series data; input at least the first time series feature set into a pre-established first analysis sub-model to obtain a first intermediate result; and send the first intermediate result to The platform device is combined, so that the combined platform device obtains the analysis result based on the first intermediate result and the second intermediate result from the server of the second institution, and the second institution is an institution that is jointly analyzed with the first institution. The present disclosure also provides a model construction method, an analysis apparatus, a model construction apparatus, a joint analysis system, an electronic device, and a computer-readable storage medium.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and more particularly, to an analysis method, an analysis apparatus, a model construction method, a model construction apparatus, a joint analysis system, an electronic device, and a computer-readable storage medium. Background technique [0002] In recent years, with the growing demand for joint establishment of analytical models among different institutions, federated learning technology has developed rapidly. Federated learning can build analytical models jointly with multiple institutions while meeting the requirements of user privacy protection, data security and government regulations. And apply the model for analysis. [0003] In the process of realizing the concept of the present disclosure, the inventor found that at least the following problems exist in the related art: [0004] When joint modeling is performed through federated learning technology, the two parties involved ...

AI Technical Summary

Problems solved by technology

[0004] When federated learning technology is used for joint modeling, the two parties involved in the modeling cannot interact with time series data in real time, resulting in the inability to incorporate behavior-sequence-based features into the federated learning model. Only non-behavior sequence features can be used for modeling, and in some In the scenario, the user's behavior sequence features as a key factor will have a greater impact on the accuracy of the model. If the behavior sequence-based features are not included in the federated learning, the accuracy of the model will be low and the analysis results will not be credible.

Images