Supercharge Your Innovation With Domain-Expert AI Agents!

Method and device for matching text

A text and matching module technology, applied in the computer field, can solve problems such as low customer service efficiency and waste of resources, and achieve the effect of facilitating similarity calculation, fast matching, and solving customer problems

Inactive Publication Date: 2017-11-14
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, the above historical crm event work orders are not used to provide suggestions for the current crm event, resulting in low customer service efficiency and serious waste of resources

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 matching text
  • Method and device for matching text
  • Method and device for matching text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] figure 1 is a schematic diagram of main steps of the text matching method according to this embodiment.

[0047] Such as figure 1As shown, the text matching method of the embodiment of the present invention mainly includes the following steps:

[0048] Step S101: Determine at least one feature word of the current text, and obtain a feature vector of the current text according to the at least one feature word.

[0049] In this step, word segmentation and removal of forbidden words are performed on the current text to obtain feature words with substantial content. After the feature words of the current text are obtained, the weight value of each feature word of the current text in the current text is calculated to generate a feature vector of the current text.

[0050] Specifically, the weight value of the feature words of the current text in the current text can be obtained by the following formula:

[0051]

[0052] Among them, i is a positive integer, W i1 is t...

Embodiment 2

[0069] figure 2 is a schematic diagram of the main parts of the text matching device according to this embodiment.

[0070] Such as figure 2 As shown, the text matching device 200 of this embodiment may include a feature vector acquisition module 201 and a matching module 202 . in:

[0071] The feature vector acquiring module 201 may be configured to determine at least one feature word of the current text, and acquire the feature vector of the current text according to the at least one feature word.

[0072] The matching module 202 can be used to use the feature vector of the current text to calculate the similarity between the current text and any historical text in a plurality of historical texts; select the similarity with the current text that meets the preset rules The historical text is used as the matching text of the current text.

[0073] Preferably, in this embodiment, the feature vector acquisition module 201 is configured to: calculate the weight value of eac...

Embodiment 3

[0083] It can be understood that the text matching method of the embodiment of the present invention can be used for text matching in most technical fields, and the text matching method of the CRM event will be used as an example to introduce the text matching method of the embodiment of the present invention below. It should be pointed out that the specific technical content of the following CRM event text matching does not form any limitation on the text matching method in the embodiment of the present invention.

[0084] The CRM event processing flow of the prior art is as follows: image 3 shown, from image 3 It can be seen that: first, the customer consults the incoming line, and the customer service personnel communicate with the customer after connecting, and record the customer's problem and the event summary category judged based on experience, and generate a new CRM event. Then the system dispatches the CRM event work order and sends it to the designated customer s...

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 matching text and relates to the field of computer. The method specifically comprises the following steps: confirming at least one feature word of the present text and acquiring a feature vector of the present text according to at least one feature word; utilizing the feature vector of the present text to calculate the similarity between the present text and any one historical text of multiple historical texts; selecting the historical text of which the similarity with the present text meets a preset rule as the matching text of the present text. According to the mode of execution, the historical text matching with the present text can be confirmed so that a suggestion can be supplied for solving the present event.

Description

technical field [0001] The invention relates to the computer field, in particular to a text matching method and device. Background technique [0002] At present, the CRM (Customer Relationship Management, customer relationship management) system oriented to process management is widely used in the customer service work of enterprises. Its main function is to record the problems consulted by customers, and form a crm event work order to flow to the corresponding customer service personnel. Handle, record and archive after solving customer problems. [0003] In the process of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: [0004] Among the large number of crm event work orders accumulated in daily work, many work orders are recurring events. For example, when user A inquires about returns and exchanges, the customer service personnel will record the customer's problem, processing process, and processing r...

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): G06F17/30
CPCG06F16/3335G06F16/3344
Inventor 李建星
Owner BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com