Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Data processing method and device, computer equipment and storage medium

A data processing and data technology, applied in the field of machine learning, can solve problems such as increasing development costs and maintenance costs, and achieve the effect of reducing development costs, maintenance costs, and quantity.

Pending Publication Date: 2021-11-12
广州三七互娱科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the industrial application of machine learning, more and more open source frameworks are developed by Pytorch. The advantages of model definition, training and readability far exceed Tensorflow. However, when deploying to the mobile terminal, some projects still need to use Tflite (a lightweight reasoning library mainly used for mobile terminals), at this time, the format of the model information file for AI (Artificial Intelligence, artificial intelligence) deployed on the mobile terminal is different from that of the AI ​​model information file deployed on the server side. In order to be able to use model information files in different formats for inference, it is necessary to develop multiple sets of analysis tools to analyze model information files in different formats, which will increase development costs and maintenance costs

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
  • Data processing method and device, computer equipment and storage medium
  • Data processing method and device, computer equipment and storage medium
  • Data processing method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0041] The invention provides a data processing method. In an embodiment, the data processing method can be applied to a computing device deployed with AI, and the computing device can use the AI ​​to process business data to obtain inferred data, which can be used to instruct the target object to take the next action The data. Taking the game scene as an example, the game AI can be deployed in the game logic server (game server), the game inference server (AI server) or the game client. Assuming that the game AI is deployed in the game client, start the game in the game client Finally, ...

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 invention relates to the field of machine learning, in particular to a data processing method and device, computer equipment and a storage medium. The method comprises the following steps: when service data is obtained, firstly converting the obtained service data into standard format data; then obtaining a model information file corresponding to the business type of the business data; analyzing the model information file to obtain a model file format, a target platform identifier and a data conversion mode; converting the standard format data into model input data according to the model file format, the target platform identifier and the data conversion mode; then loading the model information file into a memory; generating a neural network layer according to the model information file; and inferring model input data by using the neural network layer to obtain a model inference result. According to the embodiment of the invention, the model information files in different formats can be analyzed and deduced uniformly through one tool, so that the development cost and the maintenance cost are reduced.

Description

technical field [0001] The present application relates to the field of machine learning, in particular to a data processing method, device, computer equipment and storage medium. Background technique [0002] In the industrial application of machine learning, more and more open source frameworks are developed by Pytorch. The advantages of model definition, training and readability are far superior to Tensorflow. However, when deploying to the mobile terminal, some projects still need to use Tflite (a lightweight reasoning library mainly used for mobile terminals), at this time, the format of the model information file for AI (Artificial Intelligence, artificial intelligence) deployed on the mobile terminal is different from that of the AI ​​model information file deployed on the server side. In order to be able to use model information files in different formats for inference, it is necessary to develop multiple sets of analysis tools to analyze model information files in di...

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
IPC IPC(8): G06F8/20G06F16/178G06N3/04G06N3/08G06N5/04G06N20/00
CPCG06F8/20G06F16/1794G06N5/041G06N3/04G06N3/08G06N20/00
Inventor 刘舟杨帆黎广璘马柏威
Owner 广州三七互娱科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products