Unlock instant, AI-driven research and patent intelligence for your innovation.

Model generation method and device, electronic device and storage medium

A model and model generation technology, applied in the fields of electrical digital data processing, instrumentation, computing, etc., can solve the problems of generality, reusability, poor scalability, and difficulty of satisfying natural language understanding tools.

Active Publication Date: 2021-07-09
出门问问创新科技有限公司 +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiments of the present disclosure provide a method and device for generating a model, an electronic device, and a storage medium. A certain degree of versatility, but it is difficult to meet the special needs of different usage 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 generation method and device, electronic device and storage medium
  • Model generation method and device, electronic device and storage medium
  • Model generation method and device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a flow chart of a method for generating a model provided by Embodiment 1 of the present disclosure. The method of this embodiment can be executed by a device for generating a model, which can be implemented by means of hardware and / or software, and can generally be integrated into an electronic equipment, such as servers, etc. The method of this embodiment specifically includes:

[0031] S110. Obtain a target basic function module corresponding to the model to be generated, and a target trigger module corresponding to the model to be generated, wherein the target trigger module at least includes conversion rules for the basic function module corresponding to the model to be generated.

[0032] It can be understood that the model generally performs a series of data conversion operations on the input data to obtain the output data during the working process. Each data conversion operation is used to realize different data processing functions, such as data...

Embodiment 2

[0043] Figure 2a It is a flowchart of a method for generating a model provided in Embodiment 2 of the present disclosure. This embodiment is optimized on the basis of the above embodiments. In this embodiment, a specific implementation manner of adding the type of internal modules of the model is given.

[0044] Correspondingly, the method in this embodiment specifically includes:

[0045] S210. Obtain the target basic function module corresponding to the model to be generated, the target trigger module corresponding to the model to be generated, and the target pipeline model based on a finite state machine corresponding to the module to be generated, wherein the target trigger module includes at least the basic function module corresponding to the model to be generated Functional modules and pipeline model conversion rules, the target pipeline model based on the finite state machine is configured with a trigger module and multiple basic function modules.

[0046] In this e...

Embodiment 3

[0061] image 3 It is a structural diagram of a model generating device provided in Embodiment 3 of the present disclosure. Such as image 3 As shown, the device includes: a module and conversion rule acquisition module 301 and a model generation module 302, wherein:

[0062] The module and conversion rule acquisition module 301 is used to acquire the target basic function module corresponding to the model to be generated, and the target trigger module corresponding to the model to be generated, wherein the target trigger module includes at least the conversion rule of the basic function module corresponding to the model to be generated;

[0063] The model generation module 302 is configured to configure the target basic function module and the target trigger module in the pipeline model based on the finite state machine to obtain a model to be generated.

[0064] An embodiment of the present disclosure provides a device for generating a model. The device first acquires the ...

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 present disclosure discloses a method and device for generating a model, electronic equipment and a storage medium. The method includes: obtaining the target basic function module corresponding to the model to be generated and the target trigger module corresponding to the model to be generated, wherein the target trigger module at least includes the conversion rule of the basic function module corresponding to the model to be generated; the target basic function module and the target The trigger module is configured in the pipeline model based on the finite state machine to obtain the model to be generated. The technical solution of the embodiment of the present disclosure solves the problem of poor versatility, reusability and scalability of natural language understanding tools in the prior art, or technologies that have certain versatility but are difficult to meet the special needs of different usage scenarios Defects, realize that multiple models with different functions can be easily generated by reusing modules with different basic functions and setting the conversion rules of the modules according to the functions of the models, and the functions of the models can also be expanded and extended.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of model generation, and in particular, to a method and device for generating a model, electronic equipment, and a storage medium. Background technique [0002] Nowadays, natural language processing is a relatively popular technology in artificial intelligence, and there are many tools that can process natural language, such as natural language understanding tools. [0003] Most of the existing natural language understanding tools can provide online language processing services, such as parsing the target sentence by calling the remote http restful API to complete tasks such as query analysis and dialogue management. Typical examples include Google's API.ai and Facebook's Wit.ai. Furthermore, existing natural language understanding tools can also be deployed locally to train and adjust their own models according to requirements, such as open source tools such as rasa NLU, etc. [000...

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 Patents(China)
IPC IPC(8): G06F16/332
Inventor 孟振南胡晓慧
Owner 出门问问创新科技有限公司