Target data prediction method and device

A technology of target data and prediction method, applied in the field of neural network, can solve the problem of not being able to take into account fast prediction and capturing super long dependencies at the same time

Pending Publication Date: 2021-04-09
BEIJING SINOVOICE TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the current common natural language processing process has the problem of no

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
  • Target data prediction method and device
  • Target data prediction method and device
  • Target data prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] refer to figure 1 , figure 1 A schematic flowchart of a method for predicting target data according to Embodiment 1 of the present invention is shown.

[0030] The target data prediction method provided by the embodiment of the present invention may specifically include the following steps.

[0031] Step S101, acquiring a plurality of first target data satisfying a preset long-term dependency condition.

[0032] In the embodiment of the present invention, the first target data may be specific data in an actual application scenario. For example, in application scenarios such as banking, securities, express delivery, and airlines, the first target data may be numbers. Moreover, the plurality of first target data satisfying the preset long-term dependency conditions can be a plurality of numbers with super-long dependencies, such as numbers in bank card numbers, numbers in securities transaction numbers, and numbers in express delivery numbers. Numbers, numbers in flig...

Embodiment 2

[0039] refer to figure 2 , figure 2 A schematic flowchart of a neural network model training method according to Embodiment 2 of the present invention is shown.

[0040] The training method of the neural network model provided by the embodiment of the present invention may specifically include the following steps.

[0041] In step S201, a sample data set is obtained, and the sample data set is divided.

[0042] In the embodiment of the present invention, the sample data set may contain multiple paragraphs of text, multiple bank card numbers, multiple order numbers and so on. The embodiments of the present invention are introduced by taking the natural language processing scenario as an example. The sample data sets in other application scenarios may be different, but the execution process of the division processing of the sample data sets can be used for reference. Therefore, the sample data set x in the embodiment of the present invention can be the following text:

[0...

Embodiment 3

[0070] refer to Figure 5 , Figure 5 A schematic structural diagram of an apparatus for predicting target data according to Embodiment 3 of the present invention is shown. The device may specifically include the following modules:

[0071] An acquisition module 51, configured to acquire a plurality of first target data satisfying preset long-term dependency conditions;

[0072] An input module 52, configured to input a plurality of the first target data into the trained neural network model, and output the second target data;

[0073] Wherein, the second target data has a sequence correlation with a plurality of the first target data;

[0074] The device also includes: a training module 53, which is used to divide the sample data set into multiple batches of input items, and input the input items into the initial network model according to the order of the batches, and calculate according to the dilated convolution algorithm The output item of the initial network model is...

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 target data prediction method and device, and relates to the technical field of neural networks. The method comprises the steps of acquiring a plurality of first target data meeting a long-term dependence condition; inputting the plurality of first target data into a neural network model to output second target data; the second target data having sequence correlation with the plurality of first target data; and the neural network model being obtained by training the following steps: dividing a sample data set into a plurality of batches of input items, inputting the input items into an initial network model according to the sequence of the batches, calculating according to an expansion convolution algorithm to obtain output items of the initial network model, and training the initial network model according to the input items, the output items and the loss function to obtain the neural network model. According to the target data prediction method and device provided by the invention, the trained neural network model is utilized to quickly predict the second target data with sequence correlation for the plurality of first target data with the super-long dependency relationship.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a method and device for predicting target data. Background technique [0002] Natural Language Processing (NLP) is an important direction in the field of computer science and artificial intelligence. It studies various theories and methods that can realize effective communication between humans and computers using natural language. Natural language processing is a science that combines linguistics, computer science, and mathematics. Research in this field will therefore involve natural language, the language that people use every day, so it is closely related to the study of linguistics, but has important differences. Natural language processing is not the general study of natural language, but the development of computer systems that can effectively realize natural language communication, especially the software systems. As such it is part of computer science. [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
IPC IPC(8): G06N3/04G06F40/205
CPCG06F40/205G06N3/045
Inventor 吴帅李健陈明武卫东
Owner BEIJING SINOVOICE 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