Model training method and system, server and storage medium
A model training and model technology, applied in the direction of instruments, special data processing applications, electrical digital data processing, etc., can solve the problems of high cost of manual labeling, poor data reusability, etc., to improve interaction methods, increase reusability, reduce The effect of human cost
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] figure 1 It is a flow chart of the model training method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of model training. The method can be executed by a model training system, which can be implemented by software and / or hardware. And can be integrated in the server. Such as figure 1 As shown, the method specifically includes:
[0027] S110. Use the labeled first sample data to train to obtain a basic model.
[0028] The basic model is the target model, which can be used for query understanding. The purpose of basic model training is to endow the model with initial analytical capabilities.
[0029] S120. Using the trained basic model to analyze the results of the second sample data and the user's feedback on the analysis results corresponding to the second sample data, train and obtain a reward model, wherein the reward model is used to evaluate the analysis results of the basic model.
[0030] The purpose of training ...
Embodiment 2
[0037] figure 2 It is a flow chart of the model training method provided by Embodiment 2 of the present invention. This embodiment is further optimized on the basis of Embodiment 1. Such as figure 2 As shown, the method specifically includes:
[0038] S210. Use the labeled first sample data to train to obtain a basic model.
[0039] Optionally, the sample data includes query and feature information corresponding to the query, including word segmentation results of the query, part of speech and proper nouns, etc., and the annotation of the sample data includes the type, intent, and slot of the query.
[0040] The input in the training process of the basic model is the query and corresponding features of the training data, and the output is the labeling result of the query, that is, category, intent and slot.
[0041] S220. Taking the analysis result of the second sample data by the basic model as input, and the user's feedback on the analysis result corresponding to the se...
Embodiment 3
[0049] image 3 It is a flow chart of the model training method provided by Embodiment 3 of the present invention, and this embodiment is further optimized on the basis of the foregoing embodiments. Such as image 3 As shown, the method specifically includes:
[0050] S310. Use the labeled first sample data to train to obtain a basic model.
[0051] S320. Taking the analysis result of the basic model for the second sample data as input, and the user's feedback for the analysis result corresponding to the second sample data as the target, train and obtain the reward model, wherein the user's feedback for the analysis result corresponding to the second sample data Feedback is divided into positive feedback and negative feedback according to the preset template sentences.
[0052] S330. Use the third sample data to perform feedback training in combination with the basic model and the reward model, and set the target of the reward model as positive feedback, so as to correct th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com