Speech contradiction detection method, device and equipment and storage medium

A detection method, contradictory technology, applied in the field of intelligent justice

Pending Publication Date: 2021-03-09
IFLYTEK CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, with the perfection and progress of our country's judicial system, the people's legal needs are increasing day by day. In the process of reviewing files, prosecutors and judges are often faced with a situation where there are fewer people and more cases. , and the single method of "adding people" cannot completely alleviate this problem. If natural language processing technology can be used to assist in document review and automatically judge whether the suspect's words are contradictory, it will greatly ease the pressure on prosecutors and judges. , and how to automatically judge the verbal contradictions of criminal suspects is an urgent problem to be solved at present.

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
  • Speech contradiction detection method, device and equipment and storage medium
  • Speech contradiction detection method, device and equipment and storage medium
  • Speech contradiction detection method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0078] see figure 1 , which shows a schematic flow chart of the verbal contradiction detection method provided by the embodiment of the present application, which may include:

[0079] Step S101: Obtain question-answer pairs related to the facts of the target case from the first text corresponding to the first object, form a first set of question-answer pairs, and obtain the facts of the target case from the second text corresponding to the second object Related question-answer pairs form a second set of question-answer pairs.

[0080] Among them, the first object and the second object can be two criminal suspects in the target case, if there are only two criminal suspects in the target case, then the first object and the second object are the two suspects, if the target case There are more than two criminal suspects, then the first object and the second object are any two of all criminal suspects.

[0081] The first text corresponding to the first object and the second text...

no. 2 example

[0093] In this embodiment, the "step S101: Obtain question-answer pairs related to the facts of the target case from the first text corresponding to the first object in the above-mentioned embodiment, form a first question-answer pair set, and obtain In the second text, the question-answer pairs related to the case of the target case are obtained to form the second question-answer pair set".

[0094] Since the process of obtaining question-answer pairs related to the facts of the target case from the first text is similar to the process of obtaining question-answer pairs related to the facts of the target case from the second text, this embodiment takes a text T as an example, and The process of obtaining question-answer pairs related to the facts of the target case is introduced in Text T.

[0095] The process of obtaining question-answer pairs related to the facts of the target case from the text T may include:

[0096] Step a1, identifying question-answer pairs from the te...

no. 3 example

[0105] Mentioned in the first embodiment, when extracting the criminal elements from a question-answer pair, the sentence of the specified event type can be determined from the question-answer pair earlier as the target sentence, and then the criminal elements are extracted from the target sentence. The process of determining the sentence of the specified event type (ie, the target sentence) from a question-answer pair is introduced.

[0106] see image 3 , showing a schematic flow diagram of determining a sentence (i.e. a target sentence) of a specified event type from a question-answer pair, which may include:

[0107] Step S301: Segment the question-answer pair into sentences, and form a sentence set from the segmented sentences.

[0108] It should be noted that a question-and-answer pair often includes events of many event types. For example, in a question-and-answer pair that contains a criminal suspect’s description of the crime, it often includes events of event types ...

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 application provides a speech contradiction detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining question and answer pairs related to a case detail of a target case from a first text corresponding to a first object, and forming a first question and answer pair set, obtaining question and answer pairs related to the case detail of the targetcase from a second text corresponding to a second object to form a second question and answer pair set; extracting crime committing elements from the question and answer pairs in the first question and answer pair set to form a first crime committing element set, and extracting crime committing elements from the question and answer pairs in the second question and answer pair set to form a secondcrime committing element set; and according to the first crime committing element set and the second crime committing element set, determining whether the verbal words of the first object and the second object are contradictory. According to the speech contradiction detection method provided by the invention, whether the speech contradiction of the first object and the speech contradiction of thesecond object exist or not can be automatically judged according to the first text corresponding to the first object and the second text corresponding to the second object.

Description

technical field [0001] The present application relates to the technical field of intelligent justice, and in particular to a verbal contradiction detection method, device, equipment and storage medium. Background technique [0002] In the review process of criminal cases by prosecutors and judges, it is an important task to judge whether the suspect's words are contradictory according to the interrogation / interrogation transcripts recorded during the interrogation process. The current way of discriminating verbal contradictions is mainly manual discrimination, that is, the prosecutor and the judge compare the content recorded in the interrogation / interrogation transcript of a criminal suspect in a certain case with the interrogation / inquiry of other criminal suspects in the case. According to the content recorded in the transcript, it can be judged whether the words of the criminal suspect and other criminal suspects contradict each other. [0003] However, with the perfect...

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): G06F40/35G06F40/279G06F16/35
CPCG06F16/35G06F40/279G06F40/35
Inventor 张大康李浩郭冬杰盛志超
Owner IFLYTEK 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