Potential event prediction method, device and equipment and storage medium

A forecasting method and event technology, applied in forecasting, computer components, semantic analysis, etc.

Pending Publication Date: 2021-04-16
ONE CONNECT SMART TECH CO LTD SHENZHEN
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to solve the technical problem that the model can provide event response prediction in open 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
  • Potential event prediction method, device and equipment and storage medium
  • Potential event prediction method, device and equipment and storage medium
  • Potential event prediction method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] Embodiments of the present invention provide a potential event prediction method, device, device, and storage medium, through the first data sets in multiple fields, and using a preset piece-by-segment learning paradigm, to train a pre-trained model for potential event prediction for backup ; Then convert the second data set in the target field into training samples in two formats, and train in two pre-trained models to obtain the first and second potential event prediction models, which are used to predict the third event to be predicted The third and fourth potential events corresponding to the sentence and the corresponding first and second occurrence probabilities; compare the first and second occurrence probabilities, and based on the comparison results, select multiple potential events from the third and fourth potential events Events are pushed. The invention realizes predicting the occurrence of potential events according to event sentences in an open scene.

...

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 artificial intelligence, and discloses a potential event prediction method and device, equipment and a storage medium. The method comprises the steps of training a pre-training model of potential event prediction for standby application through a first data set in multiple fields and by adopting a preset segment-by-segment learning normal form; converting a second data set of the target domain into training samples of two formats respectively, and training the training samples in two pre-training models to obtain second and third potential event prediction models for predicting second and third potential events corresponding to a second event sentence and corresponding second and third occurrence probabilities; and comparing the second occurrence probability with the third occurrence probability, and screening a plurality of potential events from the second potential event and the third potential event for pushing based on a comparison result. The invention also relates to a blockchain technology, and each data set is stored in the blockchain. According to the invention, the occurrence of potential events can be predicted according to the event sentences in an open scene.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a potential event prediction method, device, equipment and storage medium. Background technique [0002] With the increasing penetration rate of online services, the increase of users, and the increasing requirements of enterprises for intelligent machine anthropomorphism, how to deal with the response of open scenarios has become an important appeal. This type of new scenario requires the machine to "actively" speculate on some possible directions to advance the topic through the current user's answers, and generate corresponding replies. This type of application scenario requires the model to meet two points: 1) memorize certain experience and common sense; 2) be able to generate prediction results based on the memorized information and new incoming samples. Let the parameters of the model get the best weight in large-scale unlabeled data training, and instead of...

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): G06F16/332G06F40/211G06F40/30G06K9/62G06Q10/04G06Q30/02
CPCG06F16/332G06F40/211G06Q30/02G06Q10/04G06F40/30G06F18/00
Inventor 朱昱锦徐国强
Owner ONE CONNECT SMART TECH CO LTD SHENZHEN
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