Check patentability & draft patents in minutes with Patsnap Eureka AI!

Method and system for processing question and answer data based on semantic logic uniqueness judgment

A technology for processing data and logic, applied in the field of information processing, which can solve the problems of greatly different original meanings of data, difficulties in intelligent processing of information, and inability to form a standardized information data system.

Pending Publication Date: 2020-10-30
韩朝晖
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the semantic analysis of the existing technology, most of the semantic analysis is completed based on the user's historical search records and the similarity of the existing data in the database. However, such an analysis process does not make logical judgments on the semantics, so many sentences will be disassembled and parsed. The meaning of the data is very different from the original meaning of the data, and it is also very difficult to correct the results
[0003] At present, there are a lot of information data that must be processed and transformed through question-and-answer data. Among them, information data such as contract clauses and legal provisions are not only widely used, but also must be logically judged in specific use. However, for a long time, due to the lack of scientific and effective It is a professional method and system for processing and transforming question-and-answer data. People can only rely on personal experience to make contract clauses and other information data, which is very random. It is impossible to form a standardized information data system, and it is even more difficult to deal with smart contracting and smart judgment. In artificial intelligence processing, there are two major technical defects in a brief summary:
In the real world, many people often find it difficult to accurately interpret the terms of the contract, and more or less encounter the problem of not being able to understand the logical judgment information such as the contract terms. In turn, they may have multiple understandings of the same contract terms, and even cause contractual disputes. However, looking at the essence through the phenomenon, the most fundamental problem is that there is currently a lack of technology that can detect whether the semantics of logically judged information is unique, so it is very difficult to intelligently process this type of information
[0005] 2. Lack of technologies and systems for quantifiable and accurate processing of logical judgment information
At present, it is difficult for people to be question-oriented and accurately convert question-and-answer information into standardized logical judgment information. Therefore, how many standardized clauses should each contract have, and what kind of question-and-answer information each standardized clause corresponds to is very difficult. Difficult to understand clearly, and this will cause problems for people to process relevant information efficiently and accurately

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
  • Method and system for processing question and answer data based on semantic logic uniqueness judgment
  • Method and system for processing question and answer data based on semantic logic uniqueness judgment
  • Method and system for processing question and answer data based on semantic logic uniqueness judgment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] The data to be processed in this example p i It is a non-standard declarative sentence: "Lessor: Zhang San".

[0051] 1. Data input: input data p i ,p i ="Lessor: Zhang San".

[0052] 2. Preprocessing: detection of p i Can be non- Conjunction (∧), disjunction (∨), condition (→), double condition These five logical connectives are divided into simpler data units, among which "non" usually corresponds to characteristic data such as "no", "non" and "no", and "conjunction" usually corresponds to "and", " And ", "," and other characteristic data, "extraction" usually corresponds to "or", ",", "," and other characteristic data, and "condition" usually corresponds to "if...then", "..., unless not " and other characteristic data, but after testing, it is confirmed that p i Cannot be split by the above connectives.

[0053] 3. Proposition detection: A statement sentence is composed of a subject and a verb. The position of the subject is always on both sides of the verb...

Embodiment 2

[0060] The data to be processed in this example p i A relationship that includes "not": "The lessee cannot change the original use of the house".

[0061] 1. Data input: input data p i ,p i ="The lessee cannot change the original use of the house".

[0062] 2. Preprocessing: through word segmentation detection, find data p i contains the word "not", so it is determined that p i can be replaced by the logical connective "not" If a is split, let a be a smaller data unit, a = "The lessee can change the original use of the house", then

[0063] 3. Proposition detection: After word segmentation and detection of the subject and verb, it can be determined that the data unit a is a statement sentence; but because the data a contains variables such as "can", the system will confirm that the data a cannot solve the logical truth value, and will remove the variable "Can" convert data a to data b, b = "the lessee changes the original use of the house"; at this time, continue to...

Embodiment 3

[0070] The data to be processed in this example p i Relationships containing "or", "and", and "conditions": "The lessee may not sublease the house to others. If the lessee sublets the house to others, it must obtain the written consent of the lessor."

[0071] For the data in this example, people usually have two different semantic interpretations, and the data processing for these two interpretations will be performed separately below.

[0072] The first interpretation: "The lessee cannot sublet the house to others, (and) if the lessee sublets the house to others, the lessor must obtain the written consent of the lessor."

[0073] 1. Data input: input data p i ,p i = "The lessee cannot sublet the house to others, (and) if the lessee sublets the house to others, the lessor must obtain the written consent of the lessor."

[0074] 2. Pretreatment: After testing p i Can be connected with "not" Conjunction (∧) and condition (→) are separated, assuming a = "the lessee can sub...

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 technical field of information processing, in particular to a method and system for processing question and answer data based on semantic logic uniqueness judgment, wherein the method and system can achieve the quantitative analysis of the question and answer data, can achieve the output of standardized results including forward semantics and reverse semantics and therefore improve the information processing efficiency and accuracy effectively. The method is characterized in that the method the following steps: judging whether a current statement pi is a statementsentence capable of solving a logic truth value or not: if not, converting the current statement into the statement sentence capable of solving the logic truth value; if the current statement pi is adescriptive statement capable of solving a logic true value, taking a non-value of the current statement pi, obtaining a reverse logic statement, judging whether 0 is false or not, and if yes, outputting the reverse logic statement, otherwise, judging that the current statement does not have semantic logic uniqueness.

Description

Technical field: [0001] The present invention relates to the field of information processing technology, specifically a semantic logic-based uniqueness method capable of quantitatively analyzing question-and-answer data and outputting standardized results including forward semantics and reverse semantics, thereby effectively improving information processing efficiency and accuracy A method and system for processing question answering data based on judgment. Background technique: [0002] In order to improve the efficiency of human-computer interaction, natural language semantic analysis technology has emerged. After receiving the voice input by the user, this type of voice assistant system first converts the voice data into text data, and then splits and analyzes the text data. , and finally determine the semantics of the speech data. For the semantic analysis of the existing technology, most of the semantic analysis is completed based on the user's historical search record...

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): G06F40/35G06F16/332
CPCG06F40/35G06F16/3329
Inventor 韩朝晖祝小丽杜晓东孟庆宇李楚楚李明怡
Owner 韩朝晖
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More