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

Active Publication Date: 2018-03-16
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF15 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a model training method and system, server, and storage medium to solve the problems in the prior art of high cost of manual labeling of target queries and poor data reusability in different scenarios

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Model training method and system, server and storage medium
  • Model training method and system, server and storage medium
  • Model training method and system, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

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...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention discloses a model training method and system, a server and a storage medium. The method comprises the steps that first sample data with an annotation is utilized to obtain a basic model through training; the basic model is utilized to obtain a reward model through training according to an analysis result of second sample data and feedback of the analysis result corresponding to the second sample data by a user, wherein the reward model is used for evaluating an analysis result of the basic model; and third sample data is utilized to perform feedback training incombination with the basic model and the reward model, the objective of the reward model is set to be forward feedback, the basic model is corrected to be adjusted towards the objective of the user, and the adjusted basic model is obtained. Through the embodiment, the interaction mode in the model training process can be improved, labor cost of data annotation is lowered, and data reusability in different scenes is improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of natural language processing, and in particular to a model training method and system, a server, and a storage medium. Background technique [0002] In database query comprehension tasks, it is now commonly used to decompose the query into triples including categories, intents, and slots. The category refers to which category the query belongs to, such as weather, map, and constellation. The intent is the purpose of the query, such as viewing, purchasing, asking, or finding directions. The slot is the key information in the query. For example, in "Today's weather in Beijing", "Beijing" is the location slot, and "today" is the time slot. The method of data query and analysis has also changed from traditional statistics and rules to the more commonly used machine learning-based solutions. [0003] However, no matter which scheme is adopted, the required training data is required ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/3344
Inventor 王一鸣孙珂贺文嵩
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap