Unlock instant, AI-driven research and patent intelligence for your innovation.
Key sentence extraction method and system and computer readable storage medium
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An extraction method and key sentence technology, applied in the field of data processing, can solve the problems of long reply text and difficulty for users to quickly understand the relevant information of the answer, and achieve the effect of high work efficiency
Active Publication Date: 2021-10-15
无码科技(杭州)有限公司
View PDF7 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] In the question-and-answer search or retrieval-type question-and-answer scenario, the corresponding answer text is retrieved and fed back based on the question raised by the user. When the searched answer text is large or the answer text is long, it is difficult for the user to quickly understand the answer-related information
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0073] Embodiment 1, a kind of key sentence extracting method, as figure 1 shown, including the following steps:
[0074] S100, obtaining a target question and a target answer;
[0075] The target question is a question input by the user, and the target question will have at least one corresponding answer text, and each answer text is used as the target answer in turn to extract key sentences.
[0076] S200. Sentenceprocessing is performed on the target answer to obtain several answer sentences;
[0077] S300. Calculate the correlation between each answer sentence and the target question, and obtain a corresponding correlation score;
[0078] S400. Combine each answer sentence in pairs to obtain several answer pairs, calculate the coherence between the two answer sentences in the answer pair, and obtain a corresponding coherence score;
[0079] The answer sentence described in this step is also the answer sentence obtained by the step S200 clause processing;
[0200] The data construction module 100 is used to obtain the target question and the target answer and is also used to perform sentence processing on the target answer to obtain several answer sentences;
[0201] A correlation calculation module 200, configured to calculate the correlation between each answer sentence and the target question, and obtain a corresponding correlation score;
[0202] The coherence calculation module 300 is used to combine each answer sentence in pairs to obtain a number of answer pairs, calculate the coherence between the two answer sentences in the answer pair, and obtain a corresponding coherence score;
[0203] Clustering module 400, for clustering each answer sentence based on the coherence score, to obtain several groups of sentence clusters;
[0204] The sentence cluster scoring module 500 is used to extract the correlation...
Embodiment 3
[0221] Embodiment 3. A computer-readable storage medium, which stores a computer program. When the program is executed by a processor, the steps of any key sentence extraction method in Embodiment 1 are implemented.
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
Login to View More
Abstract
The invention discloses a key sentence extraction method and system, and a computer readable storage medium. The key sentence extraction method comprises the following steps: obtaining a target question and a target answer; performing sentence segmentation processing on the target answer to obtain a plurality of answer sentences; calculating the correlation between each answer sentence and the target question to obtain a corresponding correlation score; combining every two answer sentences to obtain a plurality of answer pairs, and calculating the coherence between two answer sentences in the answer pairs to obtain a corresponding coherence score; clustering the answer sentences based on the coherence score to obtain a plurality of groups of sentence class clusters; extracting a correlation score corresponding to each answer sentence in the sentence class cluster, and calculating the correlation between the sentence class cluster and the target question based on the extracted correlation score; and extracting the answer sentences in the sentence class cluster with the maximum relevancy to obtain corresponding key sentences. The key sentences extracted by the method give consideration to coherence and correlation at the same time, and the central content of the target answer can be accurately expressed.
Description
technical field [0001] The invention relates to the field of data processing, in particular to a key sentence extraction technology. Background technique [0002] With the explosive growth of Internet information, the cost of obtaining effective information is getting higher and higher. How to quickly obtain useful information from massive amounts of information is particularly important. [0003] In the question-and-answer search or retrieval-style question-and-answer scenario, the corresponding answer text is retrieved and fed back based on the question raised by the user. When there are many answer texts retrieved or the answer text is long, it is difficult for the user to quickly understand the information related to the answer. Contents of the invention [0004] The present invention aims at the shortcoming that it is difficult for users to quickly obtain and understand effective information in reply texts in the prior art, and provides a key sentence extraction techn...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More