Text data diversified recommendation type search method and system

A text data and search method technology, applied in the direction of unstructured text data retrieval, text database query, digital data information retrieval, etc., can solve the problems of unclear user needs, limited information contained, high user requirements, etc., to avoid Intended to identify the risk of errors, improve user experience, and meet search needs

Pending Publication Date: 2021-12-14
北京库睿科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional search engines are only based on the text information entered by users, and it is difficult to solve all the problems of users. The main reason is that,
[0005] First, the input text information is simple, short and contains limited information;
[0006] The second is that the semantics of the text are complex and diverse, it is difficult to clearly express the needs, and the requirements for users are relatively high;
[0007] The third is that the needs of users are not very clear in many cases, it is just a very broad idea
However, the above methods all solve some problems from a certain angle or a single level. Each module or system is separated from each other, and there is no unified integration. Not only will there be misunderstandings, the user experience is not very friendly, and it depends on the user. Only a variety of usage scenarios are feasible, and the maintenance cost of each module and system is very high

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
  • Text data diversified recommendation type search method and system
  • Text data diversified recommendation type search method and system
  • Text data diversified recommendation type search method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Such as figure 1 As shown, according to one aspect of the present disclosure, a text data diversification recommendation search method is provided, including the following steps:

[0063] S1. Obtain query data related to user intent;

[0064] The acquisition of query data, through the integration of scene information and query information, identifies user intentions, provides diversified search intentions, and performs information aggregation, grouping and sorting according to intentions, so as to provide users with more search options and satisfy users. Diversified search requirements reduce the cost for users to use search engines.

[0065] The query data acquisition can be directly input by the user. When the user enters the query to be searched, the query that meets the user's search needs will be returned through the relationship between the query, the scene information, the intent model, and the diversified model, combined with the content data searched by the se...

Embodiment 2

[0105] In the technical application of embodiment 1, this embodiment provides a system to implement the method provided by embodiment 1, such as Figure 4 as shown,

[0106] According to another aspect of the present disclosure, a text data diversified recommendation search system is provided, including a query data acquisition module, a content retrieval module and a result rendering output module, wherein:

[0107] The query data acquisition module: used to acquire query data related to user intent;

[0108] The content retrieval module: for performing diversified content retrieval according to a preset algorithm for the acquired query data related to user intentions, and outputting content data;

[0109] The result rendering output module is used to perform result rendering on the content data and output search results;

[0110] The query data acquisition module, the content retrieval module and the result rendering output module are electrically connected in sequence.

[...

Embodiment 3

[0128] Furthermore, according to another aspect of the present disclosure, an electronic device is also provided.

[0129] refer to Figure 7 , The electronic device provided by the embodiments of the present disclosure includes a processor and a memory for storing instructions executable by the processor. Wherein, the processor is configured to implement the text data diversification recommendation search method described in Embodiment 1 above when executing the executable instructions.

[0130] Here, it should be noted that the number of processors may be one or more. Meanwhile, the electronic device in the embodiment of the present disclosure may further include an input device and an output device. Wherein, the processor, the memory, the input device and the output device may be connected through a bus or in other ways, which are not specifically limited here.

[0131] As a computer-readable storage medium for a text data diversification recommended search method, the m...

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 a text data diversified recommendation type search method and system. The method comprises the following steps: obtaining query data related to a user intention; performing content diversification retrieval on the obtained query data related to the user intention according to a preset algorithm, and outputting content data; and performing result rendering on the content data, and outputting a search result. In the process of guiding a user to deeply search layer by layer, scene information is fused, the intention of the user is recognized through scene information and query information, diversified search intentions are provided, information aggregation, grouping and sorting are performed according to the intentions, and the user can be guided to deeply search layer by layer through text information input by the user; diversified search requirements of the user are met, and various modules do not need to be independently constructed, so that the requirement of the user for obtaining information is met, the cost of using a search engine by the user is reduced, and the user experience is improved.

Description

technical field [0001] The present disclosure relates to the technical field of text information processing applications, and in particular to a method and system for text data diversified recommendation search. Background technique [0002] Search engine is an important way and method for users to obtain information. It is based on the information input by users, through certain strategies and retrieval algorithms, matching and searching among massive data, and after correlation calculation, it can find the information that users need to obtain. [0003] Users usually use a search engine with a clear purpose and achieve the purpose of obtaining information by entering a short and simple text message. However, in many cases, users cannot accurately describe their needs clearly through a short text message. The semantics of the text are complex and diverse, and the cost for users is very high, or the needs of users are not very clear, but very broad, just a simple idea. [0...

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): G06F16/335G06F16/33G06F16/338
CPCG06F16/335G06F16/338G06F16/334
Inventor 刘大伟
Owner 北京库睿科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap