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

Judgment penalty deviation prediction method and device

A prediction method and deviation degree technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve problems such as wasting manpower and energy, and reducing evaluation efficiency

Active Publication Date: 2019-09-27
IFLYTEK CO LTD
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing judgment method is mainly to analyze the judgment guidelines, repeatedly consider the plot elements in the case, and then refer to a large number of similar cases to artificially evaluate the judgment results to obtain the degree of deviation of the current judgment results, but this method will waste A large amount of manpower and energy lead to a significant reduction in evaluation efficiency

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
  • Judgment penalty deviation prediction method and device
  • Judgment penalty deviation prediction method and device
  • Judgment penalty deviation prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0095] see figure 1 , which is a schematic flow chart of a method for predicting the deviation degree of referee and sentencing provided in this embodiment, the method includes the following steps:

[0096] S101: Obtain target dossier materials.

[0097] In this embodiment, any dossier material that uses this embodiment to realize the prediction of the deviation degree of judgment and sentencing is defined as the target dossier material, and the case described by the target dossier material is defined as the target case.

[0098] Among them, the target dossier materials are usually composed of multiple documents, which mainly include evidence submitted by the parties in the target case, judgment documents, and other key documents, such as court records, complaints, and defenses. Among them, the evidence submitted by the parties and various Documents are an important source of information in a case. And this embodiment does not limit the type of target dossier material and th...

no. 2 example

[0121] This embodiment will introduce the specific implementation process of "predicting the degree of deviation of the judgment result corresponding to the target dossier material according to the sentencing-related information" in step S103 in the first embodiment.

[0122] see figure 2 , which shows a schematic flow chart of predicting the degree of deviation of the judgment result corresponding to the target dossier material according to the sentencing-related information provided by this embodiment, and the flow includes the following steps:

[0123] S201: Generate representation results of each target case element.

[0124] In this embodiment, after obtaining each target case element in the target case material, data processing can be performed on each target case element to generate a representation result of each target case element. It should be noted that this embodiment does not limit The form in which the result is represented, for example, can be in vector form....

no. 3 example

[0231] This embodiment will introduce the construction process of the deviation degree prediction model mentioned in the above embodiments. Specifically, the following steps E1-E3 may be included:

[0232] Step E1: A large amount of training sample data is collected.

[0233] In this embodiment, in order to construct the deviation degree prediction model, it is necessary to collect a large number of dossier materials of past judgment cases in advance (these dossier materials can be used to construct the above-mentioned semantic knowledge base), and each dossier material is used as training sample data. It should be noted that each piece of training sample data can be acquired according to the acquisition method of the target dossier material introduced in S101 in the first embodiment.

[0234] After collecting a large amount of training sample data, each training sample data can be sorted, classified and labeled manually according to the specific actual situation, that is, t...

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 discloses a judgment penalty deviation prediction method and a judgment penalty deviation prediction device. The method comprises the following steps of: obtaining a target volume material needing deviation prediction; according to the association relationship between each target case element and each sample case element, obtaining a case result; predicting the deviation degree of the judgment result corresponding to the target volume material; wherein each sample case factor is extracted from a large number of existing sample file materials with known judgment results; wherein the sample case factors are key factors which have influence on judgment results of the sample file materials to which the sample case factors belong. T herefore, the target case factors and the sample case factors associated with the target case factors are taken as reference bases. The possible influence of the target case factor on the judgment result of the target file material can be accurately predicted according to the influence of the sample case factor on the judgment result of the sample file material, so that the deviation degree of the judgment result of the target file material can be more accurately and quickly predicted.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a method and device for predicting deviation degree of judgment and sentencing. Background technique [0002] With the advent of the information age and the era of intelligence, the demand for judicial informatization and intelligence is becoming more and more prominent. Following the pace of the national judicial informatization call, more and more informatization and artificial intelligence technologies have been applied to the judicial field, providing convenient technologies and channels for the people and the staff of the judicial department. With the development of the wave of artificial intelligence, how to make artificial intelligence technology better serve the judiciary has become a recent upsurge. In the judgment of previous cases and the retrospective process of old cases, judges need to carefully read the complicated evidence of the par...

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): G06F16/33G06F17/27
CPCG06F16/3344G06F16/3334G06F40/30
Inventor 孙瑜声徐威威李宝善
Owner IFLYTEK CO LTD