Data label generation method and device based on neural network, terminal and medium

A neural network and data labeling technology, applied in the field of data processing, can solve the problems of low efficiency, low labeling efficiency, and a small number of financial asset labels, and achieve the effect of strong effectiveness and strong practicability

Pending Publication Date: 2020-03-17
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has the following disadvantages: 1) The efficiency of generating tags is low; 2) The number of generated tags is limited; 3) The coverage of generated tags is limited
[0004] Therefore, it is necessary to propose a new financial asset label generation scheme to solve the technical problems of small number and low efficiency of financial asset label generation, so as to improve the prediction accuracy of financial assets

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 label generation method and device based on neural network, terminal and medium
  • Data label generation method and device based on neural network, terminal and medium
  • Data label generation method and device based on neural network, terminal and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] figure 1 It is a flow chart of the neural network-based data label generation method provided by Embodiment 1 of the present invention.

[0063] Such as figure 1 As shown, the neural network-based data label generation method specifically includes the following steps. According to different requirements, the order of the steps in the flow chart can be changed, and some of them can be omitted.

[0064] S11, acquiring historical data.

[0065] In this embodiment, the historical data may include: historical financial asset data, historical human face image data, historical facial expression data, historical car damage image data, etc., the above data are only examples, and any needs to be predicted now or in the future The data of all can be applicable here, and the present invention does not make any limitation here.

[0066] Generally speaking, if you want to make some kind of prediction based on the historical data, you need to process and process the historical data...

Embodiment 2

[0166] figure 2 It is a structural diagram of the neural network-based data label generating device of the present invention.

[0167] In some embodiments, the neural network-based data label generation device 20 may include a plurality of functional modules composed of program code segments. The program codes of the various program segments in the neural network-based data label generation device 20 can be stored in the memory of the terminal, and executed by the at least one processor to execute (see for details figure 1 Description) Functions for neural network-based data label generation.

[0168] In this embodiment, the neural network-based data label generation device 20 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: data acquisition module 201, data processing module 202, parameter initialization module 203, model training module 204, data division module 205, label extraction module 206, sc...

Embodiment 3

[0271] refer to image 3 As shown in , it is a schematic structural diagram of a terminal provided by Embodiment 3 of the present invention. In a preferred embodiment of the present invention, the terminal 3 includes a memory 31 , at least one processor 32 , at least one communication bus 33 and a transceiver 34 .

[0272] Those skilled in the art should understand that, image 3 The structure of the terminal shown does not constitute a limitation of the embodiment of the present invention, it can be a bus structure or a star structure, and the terminal 3 can also include more or less other hardware or software than shown in the figure , or different component arrangements.

[0273] In some embodiments, the terminal 3 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but not limited to microprocessors, application-specific integrated circuits, programmabl...

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 provides a data label generation method based on a neural network. The data label generation method comprises the steps of obtaining historical data; initializing input parameters of a preset neural network; inputting the historical data into the preset neural network for training; after the training is finished, extracting the output of a specified layer of the preset neural networkas a candidate data label; calculating a scoring result of the candidate data label; re-initializing the input parameters of the preset neural network according to the scoring result, and performinga new round of training based on the new input parameters until a preset exploration period is reached; storing the neural network model obtained by each round of training and the candidate data labelextracted from each round of neural network model; and screening out a target data label from the stored candidate data labels according to a preset screening condition. The invention further provides a data label generation device based on the neural network, a terminal and a medium. According to the invention, a large number of data tags can be quickly and effectively generated.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a neural network-based data label generation method, device, terminal and medium. Background technique [0002] The valuation of financial assets and the prediction of future earnings have always been an important topic in the investment field. Due to the strong effectiveness of financial assets, and the distribution of financial asset labels often changes over time, if we want to predict financial assets and obtain high prediction accuracy, we must have enough financial asset labels. [0003] Traditional financial asset labels are generally generated by researchers through logical combination of known basic financial asset data. This method has the following disadvantages: 1) the efficiency of generating labels is low; 2) the number of generated labels is limited; 3) the coverage of generated labels is limited. [0004] Therefore, it is necessary to propose a n...

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): G06F16/21G06F16/28G06K9/62G06N3/04
CPCG06F16/21G06F16/285G06N3/04G06F18/214
Inventor 陆彬杨琳琳
Owner PING AN TECH (SHENZHEN) 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