Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Automatic call clustering method and system based on semantic understanding processing

A technology of automatic clustering and semantic understanding, applied in natural language data processing, semantic analysis, electronic digital data processing, etc., can solve problems such as difficult causes, difficult sources of traffic, and low efficiency, and achieve the effect of optimizing accuracy

Pending Publication Date: 2022-07-08
科大国创云网科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: how to solve the problems existing in the existing traffic source analysis technology, such as difficult analysis of traffic sources, difficult recovery of problem causes, manual duplication of work, low efficiency, etc., and provides a semantic understanding based The method of automatic clustering of processed calls; this method supports flexible model tuning and calibration, which can greatly improve the accuracy of call clustering and reduce the cost of manual operation of enterprises

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
  • Automatic call clustering method and system based on semantic understanding processing
  • Automatic call clustering method and system based on semantic understanding processing
  • Automatic call clustering method and system based on semantic understanding processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] This embodiment provides a technical solution: a method for automatic clustering of calls based on semantic understanding processing, comprising the following steps:

[0051] S1: Get call text

[0052] According to actual business needs, connect to the text conversion platform to obtain the original call text content;

[0053] S2: Establish an industry business thesaurus

[0054] Establish a customer service industry business thesaurus, define industry business words and corresponding weight information;

[0055] S3: Build a stop thesaurus

[0056] Perform text preprocessing to filter text content that has no value for clustering;

[0057] S4: Text vectorization

[0058] Combined with the established customer service industry business thesaurus, the word segmentation algorithm is used to count the weight of the word segmentation, and each word in the text is mapped to a fixed-size vector;

[0059] S5: Text Clustering

[0060] The K-Means algorithm is used to calcu...

Embodiment 2

[0093] Embodiments, principles and main processes of the present invention are as follows:

[0094] like figure 1 As shown, it is a schematic diagram of the flow of automatic clustering of call texts, which specifically includes the following steps:

[0095] S11: Obtain historical customer service and user call texts through the intelligent text transcription platform;

[0096] S12: Establish an industry business thesaurus, count professional dictionaries of a certain type of customer service industry, prevent poor word segmentation, and establish the weight ratio of the industry business thesaurus to improve the accuracy of clustering;

[0097] S13: Build a stop word database, the stop words mainly include some adverbs, adjectives and some other conjunctions. By maintaining a list of stop words, it is actually a process of feature extraction, which is essentially a part of feature selection;

[0098] S14: Text preprocessing (solving the problem of high dimensionality of fe...

Embodiment 3

[0108] Taking the following actual scene as an example, according to the technical solution of the present invention, the evidence is analyzed and applied step by step.

[0109] S1: Get call text

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 an automatic call clustering method and system based on semantic understanding processing, and belongs to the technical field of natural language processing, and the method comprises the following steps: S1, obtaining a call text; s2, establishing an industry business word library; s3, establishing a disabled word library; s4, text vectorization; s5, carrying out text clustering; s6, adjusting and optimizing the model; and S7, pushing the service scheme. The invention provides a lexicon capable of customizing management, the weight ratio of the industry lexicon is maintained, a clustering algorithm is combined with services, and the accuracy of telephone clustering is improved; operation of a telephone clustering process is carried out through a visual interface management mode, so that the convenience of telephone clustering operation management is improved; the method is suitable for automatic clustering of customer service telephone texts, the customer service operation management efficiency is effectively improved, and the labor cost is reduced.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method and system for automatic clustering of calls based on semantic understanding processing. Background technique [0002] The existing traffic source analysis technology has certain deficiencies, such as: Difficulty in manual classification of calls (calls): The classification of telephone (calls) problems depends on the operator's experience, the classification is inaccurate, and there is a lack of digital means; Difficulty in data recording: Clustering through manual operations There are few records and incomplete records in the recorded data, and the data is not standardized, and it is difficult to use it later; high operating costs: large traffic volume, large number of phone (call) texts, large workload of manual classification, and high operating costs. high cost. [0003] To sum up, the existing traffic source analysis is carried out by manually ...

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 Applications(China)
IPC IPC(8): G06F16/35G06F40/216G06F40/289G06F40/30
CPCG06F16/355G06F40/216G06F40/289G06F40/30
Inventor 丁常坤夏兵程磊周源冯影
Owner 科大国创云网科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products