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

Chatting record analyzing method and device based on hierarchical clustering

A technology of chat records and hierarchical clustering, applied in the computer field, can solve problems such as difficulty in analysis work and ambiguity

Inactive Publication Date: 2018-06-12
灯塔财经信息有限公司
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that text data mining has become one of the research hotspots in the information field at present, and it is of great value in customer service and company decision-making. However, unlike structured data, text data is highly unstructured , but also has a high ambiguity, which also brings difficulties to the specific analysis work

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
  • Chatting record analyzing method and device based on hierarchical clustering
  • Chatting record analyzing method and device based on hierarchical clustering
  • Chatting record analyzing method and device based on hierarchical clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1 of the present invention provides a chat record analysis method based on hierarchical clustering, such as figure 1 shown, including:

[0048] In step 201, chat records and related data information are obtained, and preprocessing is performed on the chat records before the DBSCAN clustering algorithm.

[0049]In the embodiment of the present invention, the chat records include one of customer question records extracted from system logs, chat records between customers, chat records between customers and experts, and responses corresponding to articles published by customers or Multiple items; the relevant data information includes special vocabulary in the financial field, Chinese stop vocabulary, and pre-trained word vector data. Wherein, the chat records can be obtained by crawling data from the whole network and word2vec tools.

[0050] In step 202, the clustering algorithm of DBSCAN is used to cluster the preprocessed data.

[0051] In step 203, use th...

Embodiment 2

[0089] Such as Image 6 , is a schematic diagram of the architecture of the device for analyzing chat records based on hierarchical clustering according to an embodiment of the present invention. The device for analyzing chat records based on hierarchical clustering in this embodiment includes one or more processors 21 and memory 22 . in, Image 6 A processor 21 is taken as an example.

[0090] Processor 21 and memory 22 can be connected by bus or other means, Image 6 Take connection via bus as an example.

[0091] Memory 22 is a non-volatile computer-readable storage medium as a method and device for analyzing chat records based on hierarchical clustering, and can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, as in the embodiment The chat record analysis method based on hierarchical clustering in 1. Processor 21 executes various functional applications and data processing of the chat record analysis device based ...

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 the technical field of computers, and provides a chatting record analyzing method and device based on hierarchical clustering. The method comprises the following steps: acquiring chatting records and related data information, and preprocessing the chatting records before DBSCAN clustering algorithm is carried out; carrying out clustering treatment on the preprocessed databy using the DBSCAN clustering algorithm; and extracting keywords as hot words from result data processed by clustering of DBSCAN by using a TF-IDF algorithm, counting the frequency of the hot words in data items, and taking the hot words of which the frequency of occurrence is the highest as labels of the chatting records. By the chatting record analyzing method based on hierarchical clustering,performance characteristics of the DBSCAN clustering algorithm and the TF-IDF algorithm are combined, existing irregular chatting records are subjected to distinctive label calibration, and thus, thechatting records can be further used in a simplified manner by follow-up operation steps.

Description

【Technical field】 [0001] The invention relates to the field of computer technology, in particular to a method and device for analyzing chat records based on hierarchical clustering. 【Background technique】 [0002] With the rapid development of mobile Internet technology, people are becoming more and more accustomed to online communication and exchange, which has also created a large amount of text data (such as chat records or question-and-answer data). Mining and analyzing these data can often get Very informative. At present, text data mining has become one of the research hotspots in the information field, and it is of great value in customer service and company decision-making. [0003] However, unlike structured data, text data is highly unstructured and highly ambiguous, which also brings challenges to specific analysis work. [0004] In view of this, it is an urgent problem to be solved in this technical field to overcome the defects in the prior art. 【Content of ...

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): G06F17/27G06F17/30G06K9/62
CPCG06F16/355G06F40/216G06F40/289G06F18/23
Inventor 许振兴朱留锋荣强田淑宁
Owner 灯塔财经信息有限公司
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