Method for solving conflicts under multiple conditions of voice retrieval

A multi-condition, voice technology, applied in unstructured text data retrieval, semantic tool creation, special data processing applications, etc., can solve problems such as inaccurate output results of voice information, failure to output result information, voice information processing, etc., to achieve Convenient and optimal query content information, improve user experience, and improve the effect of accuracy

Pending Publication Date: 2021-09-21
上海适享文化传播有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for resolving conflicts under multiple conditions of voice retrieval, which can effectively solve the problem in the above-mentioned background technology that the voice information input by the user cannot be processed. There is a problem, which leads to inaccurate output results of the voice information of the problem, and when the user queries the problem result through the voice information, because the voice information entered by the user has different retrieval conditions, the system knowledge map cannot be output and The matching result information, thereby reducing the user's actual experience in the speech retrieval process

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 for solving conflicts under multiple conditions of voice retrieval
  • Method for solving conflicts under multiple conditions of voice retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] Example: such as Figure 1-2 As shown, the present invention provides a kind of technical scheme, solves the conflict method under the many conditions of speech retrieval, comprises following solution steps:

[0038] S1, input query voice;

[0039] S2, user voice recognition;

[0040] S3, extract entity keywords;

[0041] S4, filling the template word slot;

[0042] S5, multi-condition filling processing;

[0043] S6, matching the optimal expression;

[0044] S7, query result sorting;

[0045] S8. Outputting the sorting result.

[0046] Based on the above technical solution, in S1, input query voice means that the user enters the voice information of the query through the voice input device, specifically including the first input and the second input. The first input refers to the user's query through the recording device After the system receives the voice information entered by the user for the first time, the system will display the voice information entered b...

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 for solving conflicts under multiple conditions of voice retrieval. The method comprises the following steps: inputting query voice; recognizing user voice; extracting entity keywords; filling a template word slot; performing multi-condition filling treatment; matching an optimal expression; sorting query results; outputting ranking result. According to the method and the device, the query content information related to the query problem information in the knowledge graph is conveniently and completely completed into the entity keyword filling template according to the query instruction, so that the problem information of the user is quickly queried, and by performing multi-condition filling processing on the keyword filling template, the retrieval contents of multiple different conditions corresponding to the keyword filling template in the knowledge graph can be substituted into the corresponding filling templates respectively, result information can be conveniently inquired according to different retrieval conditions, conflicts under multiple conditions of voice retrieval are solved, and the use experience of a user in the voice retrieval process is improved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method for solving conflicts under multiple conditions of speech retrieval. Background technique [0002] When users query the results of questions through voice information, they generally convert the query voice information of user questions into text through the voice recognition module, and then use the natural language understanding module to analyze and understand and match the text information, and finally search in the knowledge map. And retrieve the question closest to the user's text, and finally display the result information of the query question to the user, and the knowledge map is through the theory and method of applied mathematics, graphics, information visualization technology, information science and other disciplines and metrology citations Combine analysis, co-occurrence analysis and other methods, and use the visualized map to vividly d...

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
IPC IPC(8): G06F16/33G06F16/36
CPCG06F16/3343G06F16/367
Inventor 李抒雁沙涛
Owner 上海适享文化传播有限公司
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