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

Method and system for one-stop construction of AI model in urban brain scene

A brain and model technology, applied in the field of one-stop building AI models, to achieve the effect of saving training costs and training time, and simplifying the construction process

Inactive Publication Date: 2021-12-24
BEIJING ZHONGHAIJIYUAN DIGITAL TECH DEV CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The city brain is a new breakthrough in the urban governance model, city service model, and city industry model. It is both an opportunity and a challenge. The city brain has complex business scenarios and various types of AI models. Facing such complex business applications, how to effectively implement There is no complete method and system for the one-stop construction and control of AI models. How to realize the intelligentization of AI model construction is an urgent problem to be solved.

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
  • Method and system for one-stop construction of AI model in urban brain scene

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0061] User A collects data through this system, prepares the data to be processed, and then clicks on data processing to screen and analyze the data to prepare for the model training. After data preprocessing, the processed data can be used to train the user's model. In order to achieve the goal of successful recognition, the user can adjust the configuration parameters accordingly, and configure different parameter values ​​for different inputs. After the model is successfully deployed, application services can be provided externally.

example 2

[0063] According to the feedback of AI application results, as well as the increase or change of requirements, user B updates the model, processes the optimized data according to the actual needs and re-trains the model, and refers to the scores given by the model evaluation, chooses to deploy a new model, and performs the model upgrade. replace.

example 3

[0065] During the model building process, the monitoring system monitors that there is an obvious abnormal memory resource usage during model training, and immediately displays an alarm message. User C can take corresponding solutions based on the alarm message and return to the previous stage to use the correctly marked data set. User C can ensure the smooth progress of model construction by viewing real-time monitoring information.

[0066] The method of the present invention can be implemented as a computing device including a memory and a processor.

[0067] The processor can be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware com...

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 a method and a system for one-stop construction of an AI model in an urban brain scene. The method comprises the following steps: preparing data; processing data; performing model training; performing model management and model optimization; performing model deployment; retraining the model; carrying out data optimization and reprocessing; and carrying out full-link monitoring. According to the scheme provided by the invention, in combination with the life cycle of AI model production, functions including data processing, model training, model management, model deployment, model updating and the like are provided. According to the AI model one-stop construction method and system, through intelligent data processing and convenient model management, a one-stop deep learning model construction function is provided for a user, and a deep learning full link is opened. Therefore, the model training cost and the training time are saved, the construction process of the AI model is simplified, the AI model is more effectively applied, the purposes that the AI model can be continuously integrated and timely improved and perfected are achieved, and a user can conveniently construct the AI model in a one-stop mode.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, and in particular to a method and system for building an AI model in one stop in a city brain scene. Background technique [0002] With the rapid development of big data technology and artificial intelligence technology, a network decision-making and service information system for all areas of the city, that is, the city brain, came into being. The city brain is a new breakthrough in the urban governance model, city service model, and city industry model. It is both an opportunity and a challenge. The city brain has complex business scenarios and various types of AI models. Facing such complex business applications, how to effectively implement There is not yet a complete set of methods and systems for the one-stop construction and management of AI models. How to realize the intelligentization of AI model construction is an urgent problem to be solved. Contents of the invention ...

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): G06K9/62
CPCG06F18/214G06F18/241
Inventor 张艳芳孙兴雷李浩浩梅一多何彬王辉谷雨明
Owner BEIJING ZHONGHAIJIYUAN DIGITAL TECH DEV CO LTD