Statement sorting method and system applied to answer fusion system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of sentences and answers, which is applied in the sentence sorting method and system field of the answer fusion system, can solve the problems that sentences cannot be sorted, and achieve the effects of facilitating understanding, strong readability, and improving user experience
Active Publication Date: 2018-04-03
北京中科汇联科技股份有限公司
View PDF5 Cites 16 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
[0004] At present, the ordering of sentences in most answer fusion systems is mostly based on the relative position of the answer in the original candidate answer, or using the time factor to sort; the sentences extracted from different answers cannot be sorted
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
[0062] This embodiment provides a sentence sorting method applied to the answer fusion system, such as figure 1 shown, including:
[0063] S101. Obtain a sentence pair in the form of an index by preprocessing the input target data; the sentence pair is a candidate answer;
[0064] Specifically, the statement pair in the form of index is obtained by preprocessing the input target data, such as figure 2 shown, including:
[0065] S101a. Segment all target data according to the word segmentation tool, and the target data includes multiple target sentences;
[0066] S101b. Construct multiple target sentences into sentence pairs;
[0067] S101c. Convert the sentence pair into a sequence in the form of index through a sentence conversion function.
[0068] For example, what input described system is a, b, c three sentences:
[0069] Among them: a. "The patent system is designed to protect technology to enjoy exclusive and exclusive rights. Any subject other than the right hold...
Embodiment 2
[0117] This embodiment provides a sentence sorting system applied in the answer fusion system, such as Figure 7 shown, including:
[0118] The preprocessing module 110 is used to preprocess the input target data to obtain a sentence pair in index form, and the sentence pair is a candidate answer;
[0119] Further, the preprocessing module 110 includes:
[0120] The word segmentation unit 111 is used to perform word segmentation on all target data according to the word segmentation tool, and the target data includes a plurality of target sentences;
[0121] Sentence pair construction unit 112, configured to construct a plurality of target sentences into sentence pairs;
[0122] A sentence conversion unit 113, configured to convert the sentence pair into a sequence in the form of an index through a sentence conversion function.
[0123] The relationship probability acquisition module 120 is used to extract the features of the sentence pair, and obtain the relationship probab...
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 statement sorting method and system applied to an answer fusion system. The method comprises the following steps that: preprocessing input target data to obtain a statement pair of an index form, wherein the statement pair is a candidate answer; carrying out feature extraction on the statement pair to obtain the relationship probability of every two adjacent sentences inthe statement pair; according to the relationship probability and a solution space retrieval algorithm, obtaining a sorting result, wherein a target function solved by the retrieval algorithm is Score(s,o)= [Sigma]<k>i=1[Sigma]<k>j=i+1 score (s,o,i,j); and according to the sorting result, obtaining a target answer. The step of carrying out feature extraction on the statement pair to obtain the relationship probability of every two adjacent sentences in the statement pair comprises the following steps that: judging whether sentences in the statement pair are in a sequential order relationshipor not, utilizing a seq2seq model based on an attention mechanism to carry out feature extraction on the statement pair, and inputting an extracted feature into a feedforward neural network to obtaina sentence sequential order probability. By use of the method, sentences extracted from different answers can be sorted, so that the obtained target answer is smooth, is favorable for understanding and is high in readability, and user experience is improved.
Description
technical field [0001] The invention relates to the technical field of data processing, in particular to a sentence sorting method and system applied to an answer fusion system. Background technique [0002] The answer fusion system is a part of the question answering system, which is used to build a candidate answer library. The answer fusion system uses user-generated question-answer pairs provided by platforms such as Baidu Zhizhi and Soso Ask to extract relevant answers and fuse them. The answers extracted by the answer fusion system from the candidate answers are out of order. If they are directly fed back to the user as answers, the readability is poor and it is not conducive to understanding. Specifically, in the answer fusion system, most of the sentences extracted from the candidate answers are out of order, so the obtained answers have great obstacles to people's reading. [0003] However, most of the extracted sentences are related to the question. There is a st...
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