CN106250398A - A kind of complaint classifying content decision method complaining event and device - Google Patents

A kind of complaint classifying content decision method complaining event and device Download PDF

Info

Publication number
CN106250398A
CN106250398A CN201610569823.5A CN201610569823A CN106250398A CN 106250398 A CN106250398 A CN 106250398A CN 201610569823 A CN201610569823 A CN 201610569823A CN 106250398 A CN106250398 A CN 106250398A
Authority
CN
China
Prior art keywords
complaint
event
content
complaining
sample set
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201610569823.5A
Other languages
Chinese (zh)
Other versions
CN106250398B (en
Inventor
刘国亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201610569823.5A priority Critical patent/CN106250398B/en
Publication of CN106250398A publication Critical patent/CN106250398A/en
Application granted granted Critical
Publication of CN106250398B publication Critical patent/CN106250398B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G06F16/355—Class or cluster creation or modification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G06F16/353—Clustering; Classification into predefined classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention provides a kind of complaint classifying content decision method complaining event and device, and method includes: obtain the complaint text of each complaint event, generates and complains text detail list；According to default complaint classifying content, generate and complain classification samples table；Merge this complaint text detail list and this complaint classification samples table, complain tables of data to generate, and generate frequency matrix according to this complaint tables of data；Utilize this frequency matrix, set up each complaint sample set complaining classifying content, and calculate the word frequency number complaining content in this complaint tables of data；Calculate each barycenter complaining sample set；Calculate each complaint event distance to the barycenter of each complaint sample set, take the minima of these distances, confirm that each complaint event is sorted out according to each complaint sample set closest with it, generate the result of determination complaining classifying content.Effectively achieved by the present invention and a large amount of complaint contents complaining event are accurately identified and precise classification.

Description

A kind of complaint classifying content decision method complaining event and device
Technical field
The present invention relates to computer software fields, be specifically related to a kind of complaint classifying content decision method complaining event and Device.
Background technology
Industry client service center of electricity commercial business at present, for the complaint of client, is only the single complaint event of passive process, and does not has Analyze the basic reason of complaint on the whole.Since there is customer complaint, turning out user and products & services being existed discontented, only There is quantization to complain data, just can get a real idea of customer complaint reason, find deficiency present in products & services, change further Enter, complaint event could be reduced, promote Consumer's Experience.
Electricity Shang client service center is main in the following manner to judgement and the classification of customer complaint content at present:
1. client initiates to complain and selects corresponding complaint reason option to make a distinction；
2. contact staff reads customer complaint content, carries out complaining reason to judge classification.
But, said method has following defects that
1., by the way of client oneself mark complains reason, client the most only uses the option of acquiescence or chooses at random, Accuracy is poor, and adds the triviality complaining flow process, causes poor Consumer's Experience.
2. by the way of contact staff's artificial judgment and classification, taking higher human cost, speed is slow and result is easy Affected by contact staff's subjective intention.
Summary of the invention
In view of the foregoing, it is an object of the invention to provide a kind of complaint classifying content decision method complaining event and dress Put, thus quantify to complain data, it is achieved substantial amounts of complaint content is accurately identified and precise classification.
The technical scheme is that a kind of complaint classifying content decision method complaining event of offer, method includes:
Obtain the complaint text of each complaint event, generate and complain text detail list；
According to default complaint classifying content, generate and complain classification samples table；
Merge this complaint text detail list and this complaint classification samples table, complain tables of data to generate, and according to this complaint Tables of data generates frequency matrix；
Utilize this frequency matrix, set up each complaint sample set complaining classifying content, and calculate this complaint tables of data The word frequency number of middle complaint content；
Calculate each barycenter complaining sample set；
Calculate each complaint event distance to the barycenter of each complaint sample set, take the minima of these distances, confirm Each complaint event is sorted out according to each complaint sample set closest with it, generates the judgement knot complaining classifying content Really.
Alternatively, this complaint text detail list includes: complains event and complains content.
Alternatively, this complaint classification samples table including but not limited to for product, logistics, service, after sale and other five Class complains properties collection.
Alternatively, generate frequency matrix according to this complaint tables of data to include: utilize segmentation methods to complain content to split by m Become n participle；Utilize character string to remove function and combine the punctuation mark in regular expression deletion complaint content and everyday words；Will Participle carries out m*n matrix arrangement.
Alternatively, the method also includes: according to the complaint classifying content result of determination to each complaint event, throw these The barycenter telling sample set is updated.
The present invention also provides for a kind of complaint classifying content decision maker complaining event, and device includes:
Text collection module, for obtaining the complaint text of each complaint event, generates and complains text detail list；
Sample typing module, for according to the complaint classifying content preset, generates and complains classification samples table；
Text data processing module, is used for merging this complaint text detail list and this complaint classification samples table, to generate throwing Tell tables of data, and generate frequency matrix according to this complaint tables of data；
Classified counting module, is used for utilizing this frequency matrix, sets up each complaint sample set complaining classifying content, and Calculate the word frequency number complaining content in this complaint tables of data；Calculate each barycenter complaining sample set；Calculate each complaint event The distance of barycenter complaining sample set to each, takes the minima of these distances, confirm each complaint event according to its distance Nearest each complains sample set to sort out, and generates the result of determination complaining classifying content.
Alternatively, this complaint text detail list includes: complains event and complains content.
Alternatively, this complaint classification samples table including but not limited to for product, logistics, service, after sale and other five Class complains properties collection.
Alternatively, text data processing module is used for: utilize segmentation methods that m complaint content is split into n participle； Utilize character string to remove function and combine the punctuation mark in regular expression deletion complaint content and everyday words；Participle is carried out m* N matrix arranges.
Alternatively, this device also includes: barycenter more new module, for according to the complaint classifying content judgement to the event of complaint As a result, the barycenter complaining sample set is updated.
The complaint classifying content decision method of the complaint event provided by the present invention and device, it is achieved that complain a large amount of The complaint content of event carries out accurately identifying and precise classification, is effectively increased the work efficiency complaining classifying content.This Outward, owing to improve efficiency and the accuracy of the classification complaining content, therefore effective decision-making guarantee is provided for enterprise.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, in embodiment being described below required for make Accompanying drawing be briefly described, it should be apparent that, below describe in accompanying drawing be only some embodiments of the present invention, for From the point of view of those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other according to these accompanying drawings Accompanying drawing.In the accompanying drawings:
Fig. 1 is the schematic flow sheet complaining classifying content decision method of the complaint event of one embodiment of the invention；
Fig. 2 is the schematic diagram complaining classifying content decision maker of the complaint event of embodiment of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the accompanying drawings to this Bright embodiment is described in further details.Here, the schematic description and description of the present invention is used for explaining the present invention, but also Not as a limitation of the invention.
Art technology skilled artisan knows that, embodiments of the present invention can be implemented as a kind of system, device, equipment, Method or computer program.Therefore, the disclosure can be to be implemented as following form, it may be assumed that hardware, the softest completely Part (includes firmware, resident software, microcode etc.), or the form that hardware and software combines.
In this article, it is to be understood that in involved term:
Data warehouse, is the decision-making process for all ranks of enterprise, it is provided that the strategy collection that all types data are supported Close.
Illustrative methods
As it is shown in figure 1, provide a kind of complaint classifying content decision method flow chart complaining event, method bag for the present invention Include:
Step S101: obtain the complaint text of each complaint event, generates and complains text detail list；
Step S102: according to default complaint classifying content, generates and complains classification samples table；
Step S103: merge this complaint text detail list and this complaint classification samples table, complains tables of data to generate, and root Frequency matrix is generated according to this complaint tables of data；
Step S104: utilize this frequency matrix, sets up each complaint sample set complaining classifying content, and calculates this throwing Tell the word frequency number complaining content in tables of data；
Step S105: calculate each barycenter complaining sample set；
Step S106: calculate the distance of barycenter that each complaint event complains sample set to each, takes these distances Little value, confirms that each complaint event is sorted out according to each complaint sample set closest with it, generates and complain content to divide The result of determination of class.
Alternatively, this complaint text detail list includes: complains event and complains content.
Alternatively, this complaint classification samples table including but not limited to for product, logistics, service, after sale and other five Class complains properties collection.
Alternatively, generate frequency matrix according to this complaint tables of data to include: utilize segmentation methods to complain content to split by m Become n participle；Utilize character string to remove function and combine the punctuation mark in regular expression deletion complaint content and everyday words；Will Participle carries out m*n matrix arrangement.
Alternatively, the method also includes: according to the complaint classifying content result of determination to each complaint event, throw these The barycenter telling sample set is updated.
Below in conjunction with a specific embodiment, the present invention is specifically described, however, it should be noted that this is embodied as Example, merely to preferably describe the present invention, is not intended that inappropriate limitation of the present invention.
First, X86 framework (SuSE) Linux OS server is used, from the Distributed Data Warehouse system built with Hadoop System obtains the complaint text of each complaint event, and in data warehouse, generates complaint text detail list.
Specifically, by using the Hive instrument in Hadoop framework to write script by the preservation of this complaint text detail list In data warehouse, wherein this complaint text detail list includes complaint event (apply_id) and complains content (complaint_content)。
Secondly, the known customer complaint classifying content judged in advance according to electricity business, it is recorded as sample data sets, and will This sample data sets imports and stores to this data warehouse generation and complains classification samples table.
Specifically, this complaint classification samples table comprises the sample data sets of five ranks of A, B, C, D, E, respectively correspondence " product ", " logistics ", " service ", " after sale ", " other " five classification set complaining content.
By using R language development platform RStudio, this complaint text detail list and this complaint classification samples table are closed And it is generated as a complaint tables of data, and field " class " will be increased by this complaint classification samples table, five classes complain classification samples tables Class value in the class value of middle data corresponding A, B, C, D, E, and this complaint text detail list respectively is empty.Then, root Frequency matrix is generated according to this complaint tables of data.
Specifically, according to complaining tables of data generation frequency matrix to include:
Use the segmentCN algorithm in the Rwordseg bag of R language that m complaint content in this complaint tables of data is entered Row word segmentation processing generates n participle；
Use R language character string remove function combine regular expression delete these complain contents participles after in Literary composition punctuation mark and everyday words (such as, you, I, he, be)；
These participles are carried out m*n matrix arrangement, generates frequency matrix A.
Wherein, this frequency matrix A has m to complain content of text, and all the elements have n after removing everyday words duplicate removal Word, value A in this frequency matrix AijRepresent the frequency that i-th word occurs in j-th strip complains content.
By using R language development platform RStudio, utilize frequency matrix, set up each complaint sample complaining classification Collection and calculate the word frequency number of complaint content of each complaint event.
Concrete grammar is as follows:
If A class complains the complaint event number of sample set to be that o, B class complains the complaint event number of sample set to be that p, C class is complained The complaint event number of sample set is that k, D class complains sample set to complain event number to be that m, E class complains sample set to complain event number to be l, Using vector set to represent all kinds of complaint sample set, use n-dimensional vector to represent complaint event, n is all in this complaint tables of data going Weight word number, the coordinate figure of vector is followed successively by this complaint content the word frequency number of correspondence, and i.e. each complains sample set to be respectively as follows:
{a1,a2,...,ao}ai∈Rn(i=1,2 ..., o)
{b1,b2,...,bp}bi∈Rn(i=1,2 ..., p)
{c1,c2,...,ck}ci∈Rn(i=1,2 ..., k)
{d1,d2,...,dm}di∈Rn(i=1,2 ..., m)
{e1,e2,...,el}di∈Rn(i=1,2 ..., l)
Calculate each barycenter complaining sample set；
μ a = 1 o Σ i = 1 o a i , μ b = 1 p Σ i = 1 p b i , μ c = 1 k Σ i = 1 k c i , μ d = 1 m Σ i = 1 m d i , μ e = 1 l Σ l = 1 l e l
Calculate each complaint event distance to the barycenter of each complaint sample set；
Specifically, if, it is determined that complaint properties collection is F, use N-dimensional vector representation complain event, vector coordinate figure It is followed successively by the word frequency number that this complaint content is corresponding, takes one and complain event vector Nx, x is to complaining event number from 1, calculating to A, B, C, D, E five complains the distance of sample set barycenter, i.e.
Dis_a=| | Nx-μa||2
Dis_b=| | Nx-μb||2
Dis_c=| | Nx-μc||2
Dis_d=| | Nx-μd||2
Dis_e=| | Nx-μe||2
Finally, take this complaint event N minima to the distance of the barycenter of each complaint sample set, if this complaint event N To the sample set of the minimum range of each complaint sample set, i.e.
Min (Dis_a, Dis_b, Dis_c, Dis_d, Dis_e)
Confirm that this complaint event is sorted out according to the complaint sample set closest with it, generate this complaint classifying content Result of determination.
If this complaint event belongs to A class and complains content, the center of mass point of renewal complaint sample set A:
μ a = μ a · o + N x o + 1
O=o+1
If this complaint event belongs to B class and complains content, the center of mass point of renewal complaint sample set B:
μ b = μ b · p + N x p + 1
P=p+1
If this complaint event belongs to C class and complains content, the center of mass point of renewal complaint sample set C:
μ c = μ c · k + N x k + 1
K=k+1
If this complaint event belongs to D class and complains content, the center of mass point of renewal complaint sample set D:
μ d = μ d · m + N x m + 1
M=m+1
If this complaint event belongs to E class and complains content, the center of mass point of renewal complaint sample set E:
μ e = μ e · l + N x l + 1
L=l+1
It is noted that to complaining each complaint event in set F to repeat said process, until complaining set In F, the complaint content of all complaint events to be determined has all performed, and A, B, C, D, E finally given five complains category set Closing, remove sample data therein, obtain is exactly the classification result of determination of the complaint content of all complaint events.
As in figure 2 it is shown, the schematic diagram complaining classifying content decision maker of the complaint event provided for the present invention, this device 2 include:
Text collection module 21, for obtaining the complaint text of each complaint event, generates and complains text detail list；
Sample typing module 22, for according to the complaint classifying content preset, generates and complains classification samples table；
Text data processing module 23, is used for merging this complaint text detail list and this complaint classification samples table, to generate Complain tables of data, and generate frequency matrix according to this complaint tables of data；
Classified counting module 24, is used for utilizing this frequency matrix, sets up each complaint sample set complaining classifying content, and And calculate the word frequency number complaining content in this complaint tables of data；Calculate each barycenter complaining sample set；Calculate each and complain thing Part complains the distance of barycenter of sample set to each, takes the minima of these distances, confirm each complaint event according to its away from Sort out from each nearest complaint sample set, generate the result of determination complaining classifying content.
Alternatively, this complaint text detail list includes: complains event and complains content.
Alternatively, this complaint classification samples table including but not limited to for product, logistics, service, after sale and other five Class complains properties collection.
Alternatively, text data processing module 23 is used for: utilize segmentation methods that m complaint content is split into n point Word；Utilize character string to remove function and combine the punctuation mark in regular expression deletion complaint content and everyday words；Participle is entered Row m*n matrix arrangement.
Alternatively, this device also includes: barycenter more new module 25, sentences the complaint classifying content of the event of complaint for basis Determine result, the barycenter complaining sample set is updated.
Owing to the device complaining classifying content to judge of the complaint event of present invention offer is the device that said method is corresponding, Therefore do not repeat at this.
The complaint classifying content decision method of the complaint event provided by the present invention and device, it is achieved that complain a large amount of The complaint content of event carries out accurately identifying and precise classification, is effectively increased the work efficiency complaining classifying content.This Outward, owing to improve efficiency and the accuracy of the classification complaining content, therefore effective decision-making guarantee is provided for enterprise.
Although additionally, describe the operation of the inventive method in the accompanying drawings with particular order, but, this do not require that or Hint has to carry out the most shown operation could realize desired result.Additionally or alternatively, it is convenient to omit some step, Multiple steps are merged into a step perform, and/or a step is decomposed into the execution of multiple step.
Particular embodiments described above, has been carried out the purpose of the present invention, technical scheme and beneficial effect the most in detail Describe in detail bright, be it should be understood that the specific embodiment that the foregoing is only the present invention, the guarantor being not intended to limit the present invention Protect scope, all within the spirit and principles in the present invention, any modification, equivalent substitution and improvement etc. done, should be included in this Within the protection domain of invention.

Claims (10)

1. the complaint classifying content decision method complaining event, it is characterised in that described method includes:
Obtain the complaint text of each complaint event, generate and complain text detail list；
According to default complaint classifying content, generate and complain classification samples table；
Merge described complaint text detail list and described complaint classification samples table, complain tables of data to generate, and according to described throwing Tell tables of data and generate frequency matrix；
Utilize described frequency matrix, set up each complaint sample set complaining classifying content, and calculate described complaint tables of data The word frequency number of middle complaint content；
Calculate the barycenter of each described complaint sample set；
Calculate each described complaint event to the distance of the barycenter of complaint sample set each described, take the minima of described distance, Confirm that each described complaint event is sorted out according to each closest described complaint sample set described with it, generate described Complain the result of determination of classifying content.
Method the most according to claim 1, it is characterised in that described complaint text detail list includes: complain event and Complain content.
Method the most according to claim 1, it is characterised in that described complaint classification samples table is including but not limited to for producing Product, logistics, service, after sale and other five classes complain properties collections.
Method the most according to claim 1, it is characterised in that generate frequency matrix according to described complaint tables of data and include:
Utilize segmentation methods that m described complaint content is split into n participle；
Utilize character string to remove function and combine the punctuation mark in the regular expression described complaint content of deletion and everyday words；
Described participle is carried out m*n matrix arrangement.
Method the most according to claim 1, it is characterised in that also include: according to the complaint content to described complaint event Classification result of determination, is updated the barycenter of described complaint sample set.
6. the complaint classifying content decision maker complaining event, it is characterised in that described device includes:
Text collection module, for obtaining the complaint text of each complaint event, generates and complains text detail list；
Sample typing module, for according to the complaint classifying content preset, generates and complains classification samples table；
Text data processing module, is used for merging described complaint text detail list and described complaint classification samples table, to generate throwing Tell tables of data, and generate frequency matrix according to described complaint tables of data；
Classified counting module, is used for utilizing described frequency matrix, sets up each complaint sample set complaining classifying content, and counts Calculate the word frequency number complaining content in described complaint tables of data；Calculate the barycenter of each described complaint sample set；Calculate described in each Complaint event, to the distance of the barycenter of complaint sample set each described, takes the minima of described distance, confirms each described complaint Event is sorted out according to each closest described complaint sample set described with it, generates sentencing of described complaint classifying content Determine result.
Device the most according to claim 6, it is characterised in that described complaint text detail list includes: complain event and Complain content.
Device the most according to claim 6, it is characterised in that described complaint classification samples table is including but not limited to for producing Product, logistics, service, after sale and other five classes complain properties collections.
Device the most according to claim 6, it is characterised in that described text data processing module is used for:
Utilize segmentation methods that m described complaint content is split into n participle；
Utilize character string to remove function and combine the punctuation mark in the regular expression described complaint content of deletion and everyday words；
Described participle is carried out m*n matrix arrangement.
Device the most according to claim 6, it is characterised in that also include:
Barycenter more new module, for according to the complaint classifying content result of determination to described complaint event, to described complaint sample The barycenter of collection is updated.
CN201610569823.5A 2016-07-19 2016-07-19 Method and device for classifying and judging complaint content of complaint event Active CN106250398B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610569823.5A CN106250398B (en) 2016-07-19 2016-07-19 Method and device for classifying and judging complaint content of complaint event

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610569823.5A CN106250398B (en) 2016-07-19 2016-07-19 Method and device for classifying and judging complaint content of complaint event

Publications (2)

Publication Number Publication Date
CN106250398A true CN106250398A (en) 2016-12-21
CN106250398B CN106250398B (en) 2020-03-27

Family

ID=57613353

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610569823.5A Active CN106250398B (en) 2016-07-19 2016-07-19 Method and device for classifying and judging complaint content of complaint event

Country Status (1)

Country Link
CN (1) CN106250398B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107844559A (en) * 2017-10-31 2018-03-27 国信优易数据有限公司 A kind of file classifying method, device and electronic equipment
CN107992609A (en) * 2017-12-15 2018-05-04 广东电网有限责任公司信息中心 A kind of complaint tendency determination methods based on Text Classification and decision tree
CN108573031A (en) * 2018-03-26 2018-09-25 上海万行信息科技有限公司 A kind of complaint sorting technique and system based on content
CN109255499A (en) * 2018-10-25 2019-01-22 阿里巴巴集团控股有限公司 Complaint, tip-offs about environmental issues processing method, device and equipment
CN110337118A (en) * 2019-04-24 2019-10-15 中国联合网络通信集团有限公司 Customer complaint immediate processing method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101520802A (en) * 2009-04-13 2009-09-02 腾讯科技（深圳）有限公司 Question-answer pair quality evaluation method and system
CN101645083A (en) * 2009-01-16 2010-02-10 中国科学院声学研究所 Acquisition system and method of text field based on concept symbols
CN103699523A (en) * 2013-12-16 2014-04-02 深圳先进技术研究院 Product classification method and device
CN104636447A (en) * 2015-01-21 2015-05-20 上海天呈医流科技股份有限公司 Intelligent evaluation method and system for medical instrument B2B website users

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101645083A (en) * 2009-01-16 2010-02-10 中国科学院声学研究所 Acquisition system and method of text field based on concept symbols
CN101520802A (en) * 2009-04-13 2009-09-02 腾讯科技（深圳）有限公司 Question-answer pair quality evaluation method and system
CN103699523A (en) * 2013-12-16 2014-04-02 深圳先进技术研究院 Product classification method and device
CN104636447A (en) * 2015-01-21 2015-05-20 上海天呈医流科技股份有限公司 Intelligent evaluation method and system for medical instrument B2B website users

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
段晓燕: "投诉信息自动分类与推送系统的研究与设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107844559A (en) * 2017-10-31 2018-03-27 国信优易数据有限公司 A kind of file classifying method, device and electronic equipment
CN107992609A (en) * 2017-12-15 2018-05-04 广东电网有限责任公司信息中心 A kind of complaint tendency determination methods based on Text Classification and decision tree
CN107992609B (en) * 2017-12-15 2021-05-18 广东电网有限责任公司信息中心 Complaint tendency judgment method based on text classification technology and decision tree
CN108573031A (en) * 2018-03-26 2018-09-25 上海万行信息科技有限公司 A kind of complaint sorting technique and system based on content
CN109255499A (en) * 2018-10-25 2019-01-22 阿里巴巴集团控股有限公司 Complaint, tip-offs about environmental issues processing method, device and equipment
CN109255499B (en) * 2018-10-25 2021-12-07 创新先进技术有限公司 Complaint and complaint case processing method, device and equipment
CN110337118A (en) * 2019-04-24 2019-10-15 中国联合网络通信集团有限公司 Customer complaint immediate processing method and device

Also Published As

Publication number Publication date
CN106250398B (en) 2020-03-27

Similar Documents

Publication Publication Date Title
Swathi et al. An optimal deep learning-based LSTM for stock price prediction using twitter sentiment analysis
CN110119413B (en) Data fusion method and device
CN106250398A (en) A kind of complaint classifying content decision method complaining event and device
WO2019108603A1 (en) Machine learning techniques for evaluating entities
CN113590698B (en) Artificial intelligence technology-based data asset classification modeling and hierarchical protection method
CN110704572A (en) Suspected illegal fundraising risk early warning method, device, equipment and storage medium
Hariharakrishnan et al. Survey of pre-processing techniques for mining big data
CN115002200B (en) Message pushing method, device, equipment and storage medium based on user portrait
CN110968695A (en) Intelligent labeling method, device and platform based on active learning of weak supervision technology
CN110990529B (en) Industry detail dividing method and system for enterprises
CN107918657A (en) The matching process and device of a kind of data source
CN110377744A (en) A kind of method, apparatus, storage medium and the electronic equipment of public sentiment classification
Agarwal et al. Sentiment analysis in stock price prediction: a comparative study of algorithms
CN109471965A (en) A kind of network public-opinion data sampling and processing method and monitoring platform based on big data
CN103957116A (en) Decision-making method and system of cloud failure data
CN110851611A (en) Hidden danger data knowledge graph construction method, device, equipment and medium
CN110533466A (en) Method, system and storage medium based on big data auxiliary product development
CN105335446A (en) Short text classification model generation method and classification method based on word vector
CN111210332A (en) Method and device for generating post-loan management strategy and electronic equipment
CN110069686A (en) User behavior analysis method, apparatus, computer installation and storage medium
CN107609171A (en) Data source tracing method and device based on data warehouse
CN108460049A (en) A kind of method and system of determining information category
Modrušan et al. Intelligent Public Procurement Monitoring System Powered by Text Mining and Balanced Indicators
CN116795978A (en) Complaint information processing method and device, electronic equipment and medium
CN116402546A (en) Store risk attribution method and device, equipment, medium and product thereof

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant