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

Method and device for feedback answer

An answer, the technology of the best answer, applied in the computer field, can solve problems such as low matching possibility, low accuracy rate, and low frequency of words

Active Publication Date: 2020-07-07
HUAZHONG NORMAL UNIV +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Based on the implementation method of the above-mentioned community question answering system, when the server pushes the answer to the user, it mainly calculates the textual proximity between the question and the answer based on the vocabulary matching degree between the question and the answer, but the answer that the user needs may be different from the The question entered by the user does not have a common vocabulary (that is, there is a vocabulary gap), or the common vocabulary appears less frequently, so that the answer pushed to the user is less likely to match the user's needs, thus causing the server to provide answer feedback is less accurate

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 device for feedback answer
  • Method and device for feedback answer
  • Method and device for feedback answer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] The embodiment of the present invention provides a method for feeding back answers, such as figure 1 As shown, the processing flow of the method may include the following steps:

[0025] Step 101, according to the corresponding relationship between the question, the best answer and other answers stored in the training sample database, based on the training condition that the semantic proximity between the question and the corresponding best answer is greater than the semantic proximity between the question and the corresponding other answers, to The semantic extraction parameters in the preset semantic extraction formula are trained to obtain the training values ​​of the semantic extraction parameters.

[0026] Step 102, when an answer request carrying a target question is received, according to the target question, each answer in the answer query library, the semantic extraction formula, and the training value of the semantic extraction parameters, respectively determi...

Embodiment 2

[0030] The embodiment of the present invention provides a method for feeding back answers. The execution subject of the method may be a server, and the server may be a community question-and-answer website or an application server, and the server may be provided with a processor, a memory, a transceiver, and the processor It can be used for the training of semantic extraction parameters and the processing of feedback answers to questions. The memory can be used to store the data required and generated during the following processing. The transceiver can be used to receive and send data. The following will combine specific implementation methods, figure 1 The processing flow shown is described in detail, and the content can be as follows:

[0031] Step 101, according to the corresponding relationship between the question, the best answer and other answers stored in the training sample database, based on the training condition that the semantic proximity between the question and...

Embodiment 3

[0083] Based on the same technical idea, the embodiment of the present invention also provides a device for feeding back answers, such as image 3 As shown, the device includes:

[0084] The training module 310 is used for training based on the correspondence between the question, the best answer and other answers stored in the training sample library, based on the semantic proximity between the question and the corresponding best answer is greater than the semantic proximity between the question and other corresponding answers condition, training the semantic extraction parameters in the preset semantic extraction formula to obtain the training value of the semantic extraction parameters;

[0085] The determining module 320 is configured to, when receiving an answer request carrying a target question, determine respectively according to the target question, each answer in the answer query database, the semantic extraction formula, and the training value of the semantic extrac...

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 method and a device for feeding back answers, and belongs to the technical field of computers. The method comprises the following steps: according to corresponding relationships among problems, best answers and other answers stored in a training sample library, and based on a training condition that the semantic proximity between the problems and the corresponding best answers is greater than the semantic proximity between the problems and the corresponding other answers, carrying out training on semantic extracting parameters preset in a semantic extracting formula to obtain training values of semantic extracting parameters; when receiving an answering request which carries a target problem, according to the target problem, each answer in an answer inquiry library, the semantic extracting formula, and the training values of the semantic extracting parameters, respectively determining the semantic proximity between each answer and the target problem; and according to the semantic proximity between each answer and the target problem, selecting a target answer from the answers and carrying out feedback on the answering request. By adopting the method and the device disclosed by the invention, the accuracy rate of answer feedback of a server can be improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for feeding back answers. Background technique [0002] With the development of computer and information retrieval technology, people are more and more inclined to seek the answer to a certain question with the help of computer. Correspondingly, the use of question answering system is more and more extensive. [0003] The realization of the existing community Q&A system is generally: the user inputs a question through the terminal, and the server obtains all the pre-stored answers from the answer query database, determines the common words between the question entered by the user and one of the answers, and calculates each common word. The sum of the times that words appear in the answer is used as the text proximity of the answer to the question entered by the user. According to this method, the text proximity of each answer in the answer query library to t...

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 Patents(China)
IPC IPC(8): G06F16/332G06F16/33G06F16/9536
CPCG06F16/3326G06F16/3344G06F16/9535
Inventor 周光有肖磊张小鹏王巨宏管刚刘婷婷
Owner HUAZHONG NORMAL UNIV