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

Prediction method, system and device for complaint text category and storage medium

A prediction method and prediction system technology, applied in the field of data processing, can solve problems such as insufficient accuracy, long training time, and inability to perform parallel processing, and achieve the effects of improving work efficiency, precision, and accuracy.

Active Publication Date: 2019-10-18
CTRIP COMP TECH SHANGHAI
View PDF12 Cites 10 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 to provide a prediction of the category of the complaint text on the OTA platform in order to overcome the shortcomings of the prior art that the algorithm for classifying the complaint text cannot be processed in parallel, the training time is long or the accuracy does not meet the requirements Method, system, device and storage medium

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
  • Prediction method, system and device for complaint text category and storage medium
  • Prediction method, system and device for complaint text category and storage medium
  • Prediction method, system and device for complaint text category and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 As shown, the prediction method of the complaint text category of the OTA platform of the present embodiment includes:

[0059] S101. Obtain the historical complaint text data corresponding to the OTA platform within the historically set time period;

[0060] S102, mark the historical complaint text data, and obtain the complaint category corresponding to each historical complaint text data;

[0061] S103. Obtain the historical dimension data and historical entity data corresponding to the historical complaint text data in the OTA platform;

[0062] Among them, historical dimension data is multi-dimensional data used to represent users, orders and / or hotels;

[0063] Historical entity data is data used to characterize proper nouns in the hotel field;

[0064] Specifically, historical dimension data includes order information, hotel information, and user information, among which order information includes but is not limited to the payment method, tran...

Embodiment 2

[0073] Such as figure 2 As shown, the prediction method of the complaint text category of the OTA platform of this embodiment is a further improvement on Embodiment 1, specifically:

[0074] After step S101, before step S102 also includes:

[0075] S1020. Using a clustering algorithm to cluster the historical complaint text data;

[0076] Among them, clustering algorithms include but are not limited to K-MEANS clustering algorithm (k-means clustering algorithm), DBSCAN clustering algorithm (a density-based clustering algorithm), mean shift clustering algorithm, hierarchical clustering algorithm and Synthetic clustering.

[0077] Step S102 includes:

[0078] S1021. Mark the historical complaint text data belonging to the same clustering result as the same complaint category.

[0079] Specifically, in the process of labeling, relevant staff members are selected in combination with business needs and clustering results to label historical complaint text data.

[0080] After...

Embodiment 3

[0093] Such as image 3 As shown, the prediction system of the complaint text category of the OTA platform of the present embodiment includes a historical text data acquisition module 1, an annotation processing module 2, a dimension and entity data acquisition module 3, a measurement model building module 4, a target text data acquisition module 5, A probability value acquisition module 6 and a target complaint category acquisition module 7 .

[0094] The historical text data acquisition module 1 is used to obtain the corresponding historical complaint text data of the OTA platform in the historical setting time period;

[0095] The annotation processing module 2 is used for annotating the historical complaint text data, and obtaining the complaint category corresponding to each historical complaint text data;

[0096] The dimension and entity data acquisition module 3 is used to acquire the historical dimension data and historical entity data corresponding to the historical...

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 prediction method, system and device for a complaint text category of an OTA platform and a storage medium. The prediction method comprises the steps of obtaining historicalcomplaint text data of the OTA platform; clustering and labeling the historical complaint text data to obtain a complaint category of each piece of historical complaint text data; acquiring historicaldimension data and historical entity data; establishing a prediction model for predicting a complaint category to which the complaint text data belongs; obtaining target complaint text data; inputting the target complaint text data into a prediction model, and obtaining a probability value of the target complaint text data belonging to each complaint category; and determining a target complaint category to which the target complaint text data belongs according to the probability value. According to the method, the text classification precision is improved, the user complaint content is automatically classified, so that related responsible personnel can process complaint types in charge of themselves in time, and a large amount of manpower is saved while the user experience is improved.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method, system, device and storage medium for predicting complaint text categories of an OTA platform. Background technique [0002] In the OTA (Online Travel Agency, online travel) platform, it is necessary to classify and process the complaint text to determine its corresponding complaint category, and then adopt different solutions to improve the user experience according to different complaint categories. [0003] At present, in text classification scenarios, RNN (Recurrent Neural Network) or CNN (Convolutional Neural Network) algorithms based on word embedding are mostly used. However, although the RNN-based text classification algorithm can effectively model the text context and capture the context semantics, the latter moment needs to rely on the calculation results of the previous moment, that is, parallel processing cannot be achieved, so it often requires a lo...

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): G06F16/35G06Q30/02G06Q50/12G06Q50/14
CPCG06F16/35G06Q30/0202G06Q50/14G06Q50/12
Inventor 杨森罗超胡泓
Owner CTRIP COMP TECH SHANGHAI
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com