Model interpretation method and equipment and readable storage medium
A model and model input technology, applied in neural learning methods, biological neural network models, encryption devices with shift registers/memory, etc., can solve problems such as poor model interpretation effect
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2020-09-01
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The present application relates to the artificial intelligence field of financial technology (Fintech), and in particular to a model interpretation method, device and readable storage medium. Background technique
[0002] With the continuous development of financial technology, especially Internet technology and finance, more and more technologies (such as distributed, blockchain, artificial intelligence, etc.) Requirements, such as the distribution of corresponding to-do items in the financial industry also have higher requirements.
[0003] With the continuous development of computer software and artificial intelligence, the application fields of deep learning are becoming more and more extensive, and the performance of models based on deep learning is getting better and better. However, because the models based on deep learning are all black-box models, it is difficult to accurately Explain under what circumstances the model will fail and be effect...
Examples
Embodiment Construction
[0080] It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.
[0081] The embodiment of the present application provides a model interpretation method. In the first embodiment of the model interpretation method of the present application, refer to figure 1 , the model interpretation method includes:
[0082] Step S10, obtain the input features of each model corresponding to the preset black box model, and input the prediction data set corresponding to each model input feature into the first hash coding model optimized based on each preset sample category, and the prediction data set Perform hash encoding to obtain the first hash encoding result;
[0083] In this embodiment, it should be noted that the preset black box model is a model obtained by training based on the training data set corresponding to each of the model input features, and the first hash coding model is base...