CN106528682A - Big-data text mining system of call center - Google Patents
Big-data text mining system of call center Download PDFInfo
- Publication number
- CN106528682A CN106528682A CN201610937056.9A CN201610937056A CN106528682A CN 106528682 A CN106528682 A CN 106528682A CN 201610937056 A CN201610937056 A CN 201610937056A CN 106528682 A CN106528682 A CN 106528682A
- Authority
- CN
- China
- Prior art keywords
- data
- business
- call center
- data mining
- mining
- 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.)
- Pending
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Human Resources & Organizations (AREA)
- Finance (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a big-data text mining system of a call center, and constructs the design though and the realization method of the data mining system of the call center on the whole. The system structure of the system takes a data mining algorithm as a core technology, a business model of an independent function is abstracted from a specific business application, a mapping relationship is established between the business model and the data mining algorithm so as to construct the system structure of the data mining system; the mapping relationship established between the business model and the data mining algorithm is not limited to the realization of the single data mining algorithm but is the fusion of a plurality of data mining algorithms; the data mining algorithms are utilized for integrating exiting successful business models; the new business model is researched and developed by aiming at a specific business application, and the combination flexibility of the system and the application is increased; and when industry requirements are changed or a certain business model is increased, only the corresponding business model needs to be revised or increased without developing the whole system again.
Description
Technical field
The invention belongs to call-center technology field, is related to a kind of Text Mining System, specifically a kind of call center is big
Data text digging system.
Background technology
The competition among enterprises of Modern Marketing are a kind of forms of competition with customer as focus, strive for customer, keep customer here, expand
Customer base, set up intimate customer relation, analysis customer demand, create customer demand etc., being all the marketing problem of most critical.It is related
Research shows：If its churn rate is reduced if 5%, its profit can just increase by 25%～85% for one enterprise.Therefore,
Enterprise has to strengthen being closely connected and client between and improves customer loyalty.With means of communications such as phone, faxes
Popularization, many enterprises begin attempt to this new market maneuver.By using the communications such as phone, fax, the Internet, network skill
Art and corresponding computer technology set up Call Center Platform, realize it is planned and organized, expeditiously expand customer
Group, the maneuver for improving customer satisfaction, safeguarding the market behaviors such as customer.In today that the market competition is increasingly fierce, call center
It is proved on corporate client relation management to be a kind of effective pattern, is the important means that enterprise maintains customer relationship,
It is supplied to the most quick passage of enterprise one to go active exposure target customer and keep good with client to contact, and helps enterprise
Segment market, carry out specific aim telemarketing, so as to obtaining the time, obtaining efficiency, gain market therefore by increasingly
Many enterprises are widely used, to improve the competitive strength of its own.
For each application of call center, generate substantial amounts of business datum, these data be no longer in order to
The purpose of analysis and collect, but produced due to (Opportunistic) commercial operation of pure chance.Analyze these data
Also be no longer simple for the needs of research, more mainly real valuable information is provided for business decision, and then obtain profit
Profit.But the common issue that all enterprises face is：Business data amount is very big, and wherein real valuable information is very
It is few, therefore through depth analysiss from substantial amounts of data, acquisition is conducive to commercial operation, improves the information of competitiveness, just as from
Pan gold ore out in Ore the same.And problem varies, so being to be difficult to solve with a general Data Mining Tools collection
's.
The content of the invention
It is an object of the invention to provide a kind of flexibility and reliability, the big data text mining system of call center of convenience and high-efficiency
System.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of call center's big data Text Mining System, including the data acquisition end, application server being connected with each other with
And client；
Described data acquisition end, for obtaining the original service peration data of call center；
Described application server includes that data preprocessing module, customer-centric data warehouse, data mining algorithm storehouse, data are dug
Pick module, business prototype component base, business prototype storehouse；
Described data preprocessing module, for the initial data that data collection terminal is obtained is carried out data cleansing, extracted
Conversion, loading work, the data mode being converted into needed for customer-centric data warehouse；
Described customer-centric data warehouse, for storing the call center's business operation data through pretreatment；
Described data mining algorithm storehouse, for storing the data mining algorithm that concrete business prototype needs；
Described data-mining module, is converted into volume of data mining task according to concrete business problem, digs from data
One or more algorithm is selected in pick algorithms library, data mining is carried out to data in customer-centric data warehouse, created according to Result
Business prototype is built, is stored Dao business prototype storehouse in；
Described business prototype component base, for storing business prototype component, complete concrete business prototype create, delete,
Function of browse；
Described business prototype storehouse, for storing the concrete business prototype that user is excavated by data-mining module；
Described client, for the functional mode request provided with WEB service form for creating, with client Yi Li
The visual means of solution show, allow the user to objectively understand call center's business model content.
Further, described data mining algorithm adopts COM standard implementations, algorithm one COM of correspondence.
Further, described business prototype component adopts COM standards, a pair of COM components of every kind of business prototype correspondence, instruction
Practice COM and service COM, described training COM be used for the establishment of new model, described service COM complete model browse, result it is aobvious
Show, forecast function.
Further, the description of described business prototype and storage are using PMML standards.
Beneficial effects of the present invention：The present invention construct on the whole call center data digging system design philosophy and
Implementation method, the architecture of the system take out independence from specific business application with data mining algorithm as core technology
The business prototype of function, sets up mapping relations between business prototype and data mining algorithm, so as to the data mining system of component
The architecture of system；Mapping relations are set up between business prototype and data mining algorithm and is not limited to individual data mining algorithm
Realize, but the fusion of multiple data mining algorithms, using data mining algorithm, integrated existing successful business prototype, pin
To concrete business application, new business prototype is developed and developed, increased the motility that system and application are combined, work as industry requirement
Change, or when increased certain business prototype, only need to change or increase corresponding business prototype, and without sending out again whole system
System.
Description of the drawings
The present invention is described in further detail with specific embodiment below in conjunction with the accompanying drawings.
Fig. 1 is present system structural representation.
Fig. 2 is business prototype of the present invention and data mining algorithm mapping relations schematic diagram.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.It is based on
Embodiment in the present invention, it is all other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
As shown in figure 1, the invention provides a kind of call center's big data Text Mining System, including the number being connected with each other
According to collection terminal, application server and client.
Data acquisition end, for obtaining the original service peration data of call center.
Application server is the intelligent centre of digging system, including data preprocessing module, customer-centric data warehouse (CDW),
Data mining algorithm storehouse, data-mining module, business prototype component base, business prototype storehouse.
Data preprocessing module, for data cleansing, conversion of extracting, dress are carried out to the initial data that data collection terminal is obtained
Carry work, the data mode being converted into needed for customer-centric data warehouse.
Customer-centric data warehouse, for storage through call center's business operation data of pretreatment, is determined using data warehouse
When update mechanism, the information few to data volume weekly or monthly updating, the information big to data volume, using what is updated daily
Mode.
Data mining algorithm storehouse, for storing the data mining algorithm that concrete business prototype needs, data mining algorithm is adopted
Use COM standard implementations, algorithm one COM of correspondence, this design ensure that the extensibility of system, when needing to change algorithm
And during optimized algorithm, in the case where com interface does not change, it is not necessary to recompilate data digging system, need to only repair
Change corresponding COM components.
Data mining algorithm includes：K-Means algorithms, Apriori algorithm, decision Tree algorithms, neural network algorithm,
FP-TREE algorithms, BP algorithm, abnormality detection and time series algorithm.
Data-mining module, is converted into volume of data mining task according to concrete business problem, from data mining algorithm
One or more algorithm is selected in storehouse, data mining is carried out to data in customer-centric data warehouse, business is created according to Result
Model, stores Dao business prototype storehouse in.
Wherein, mining task includes classification, valuation, prediction, basket analytic, aggregation and description.
Business prototype component base, for storing business prototype component, completes concrete business prototype and creates, deletes, browses work(
Energy；Business prototype component adopts COM standards, by using COM components, facilitating the secondary development and system maintenance of system.Often
Business prototype a pair of COM components of correspondence, training COM and service COM are planted, training COM is used for the establishment of new model, and COM is complete for service
Browse into model, the function such as result shows, predict.
Business prototype storehouse, for storing the concrete business prototype that user is excavated by data-mining module, business prototype
Description and storage using PMML standards.PMML is the oracle model markup language based on XML, by DMG (DATA MINING
GROUP) tissue is issued, and is received the standard as oracle model definition by W3C.
The business prototype that call center data is excavated at present mainly includes：Client accesses disaggregated model, client's real-time characteristic
Assessment models, client's classification Segmentation Model, customer consuming behavior analysis model, churn prediction analysis model and client exception row
For analysis model.
The function of several business prototype is simply described below：
Client accesses disaggregated model：Historical information, call information according to client provides different service response strategies.
Client's real-time characteristic assessment models：Call data of characteristic, client according to client and some are meaningful
The dynamic customer grade model of cohersive and integrated data component.
Client's classification Segmentation Model：According to the internal characteristicses of client automatically by client segmentation.
Customer consuming behavior model：According to customer group's consumption feature one by one is analyzed, policy of targetedly marketing is released.
Churn prediction analysis model：Predict the profit that a particular customer is brought to enterprise in its whole life cycle.
Client's Deviant Behavior analysis model：The people of abnormal call behavior is found out by analysis model, call center is pointed out
Give sufficiently concern and vigilance.
Every kind of business prototype is achieved by calling the algorithm COM in data mining algorithm storehouse.A kind of business type
One or more data annual reporting laws may be called, six kinds of business prototype are as shown in Figure 2 with data mining algorithm mapping relations.
Client, for creating the functional mode request provided with WEB service form, with client is intelligible can
Show depending on change mode, allow the user to objectively understand call center's business model content.
The present invention constructs the design philosophy and implementation method of call center data digging system on the whole, the system
Architecture takes out the business prototype of standalone feature from specific business application with data mining algorithm as core technology,
Mapping relations are set up between business prototype and data mining algorithm, so as to the architecture of the data digging system of component；Commercially
Set up the realization that mapping relations are not limited to individual data mining algorithm between model and data mining algorithm, but multiple data
The fusion of mining algorithm, using data mining algorithm, integrated existing successful business prototype, for concrete business application, is ground
Make and develop new business prototype, increased the motility that system and application are combined, when industry requirement changes, or increased certain
During business prototype, only need to change or increase corresponding business prototype, and without sending out again whole system.
In the description of this specification, the description of reference term " one embodiment ", " example ", " specific example " etc. means
Specific features, structure, material or the feature described with reference to the embodiment or example is contained at least one enforcement of the present invention
In example or example.In this manual, identical embodiment or example are not necessarily referring to the schematic representation of above-mentioned term.
And, the specific features of description, structure, material or feature can be in one or more any embodiments or example closing
Suitable mode is combined.
Above content is only to present configuration example and explanation, affiliated those skilled in the art couple
Described specific embodiment is made various modifications or supplements or substituted using similar mode, without departing from invention
Structure surmounts scope defined in the claims, all should belong to protection scope of the present invention.
Claims (4)
1. a kind of call center's big data Text Mining System, it is characterised in that：Including the data acquisition end, application that are connected with each other
Server and client；
Described data acquisition end, for obtaining the original service peration data of call center；
Described application server includes data preprocessing module, customer-centric data warehouse, data mining algorithm storehouse, data mining mould
Block, business prototype component base, business prototype storehouse；
Described data preprocessing module, for the initial data that data collection terminal is obtained is carried out data cleansing, conversion of extracting,
Load work, the data mode being converted into needed for customer-centric data warehouse；
Described customer-centric data warehouse, for storing the call center's business operation data through pretreatment；
Described data mining algorithm storehouse, for storing the data mining algorithm that concrete business prototype needs；
Described data-mining module, is converted into volume of data mining task according to concrete business problem, calculates from data mining
One or more algorithm is selected in Faku County, data mining is carried out to data in customer-centric data warehouse, business is created according to Result
Industry model, stores Dao business prototype storehouse in；
Described business prototype component base, for storing business prototype component, completes concrete business prototype and creates, deletes, browses
Function；
Described business prototype storehouse, for storing the concrete business prototype that user is excavated by data-mining module；
Described client, it is for the functional mode request provided with WEB service form for creating, intelligible with client
Visual means show, allow the user to objectively understand call center's business model content.
2. a kind of call center's big data Text Mining System according to claim 1, it is characterised in that：Described data
Mining algorithm adopts COM standard implementations, algorithm one COM of correspondence.
3. a kind of call center's big data Text Mining System according to claim 1, it is characterised in that：Described business
Model component adopts COM standards, a pair of COM components of every kind of business prototype correspondence, training COM and service COM, described training
COM is used for the establishment of new model, and described service COM completes that model is browsed, result shows, forecast function.
4. a kind of call center's big data Text Mining System according to claim 1, it is characterised in that：Described business
The description and storage of model is using PMML standards.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610937056.9A CN106528682A (en) | 2016-10-25 | 2016-10-25 | Big-data text mining system of call center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610937056.9A CN106528682A (en) | 2016-10-25 | 2016-10-25 | Big-data text mining system of call center |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106528682A true CN106528682A (en) | 2017-03-22 |
Family
ID=58292182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610937056.9A Pending CN106528682A (en) | 2016-10-25 | 2016-10-25 | Big-data text mining system of call center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106528682A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107277277A (en) * | 2017-05-18 | 2017-10-20 | 贵阳朗玛信息技术股份有限公司 | A kind of call center's interactive system and method |
| CN110222097A (en) * | 2019-06-18 | 2019-09-10 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN117076612A (en) * | 2023-08-31 | 2023-11-17 | 宁夏恒信创达数据科技有限公司 | Call center big data text mining system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1975720A (en) * | 2006-12-27 | 2007-06-06 | 章毅 | Data tapping system based on Wcb and control method thereof |
| CN103699550A (en) * | 2012-09-27 | 2014-04-02 | 腾讯科技（深圳）有限公司 | Data mining system and data mining method |
| CN103870595A (en) * | 2014-04-01 | 2014-06-18 | 深圳市科盾科技有限公司 | Data mining system and method |
| CN104346376A (en) * | 2013-07-31 | 2015-02-11 | 克拉玛依红有软件有限责任公司 | Method and system for dynamically inserting data mining algorithm into data mining platform |
-
2016
- 2016-10-25 CN CN201610937056.9A patent/CN106528682A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1975720A (en) * | 2006-12-27 | 2007-06-06 | 章毅 | Data tapping system based on Wcb and control method thereof |
| CN103699550A (en) * | 2012-09-27 | 2014-04-02 | 腾讯科技（深圳）有限公司 | Data mining system and data mining method |
| CN104346376A (en) * | 2013-07-31 | 2015-02-11 | 克拉玛依红有软件有限责任公司 | Method and system for dynamically inserting data mining algorithm into data mining platform |
| CN103870595A (en) * | 2014-04-01 | 2014-06-18 | 深圳市科盾科技有限公司 | Data mining system and method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107277277A (en) * | 2017-05-18 | 2017-10-20 | 贵阳朗玛信息技术股份有限公司 | A kind of call center's interactive system and method |
| CN107277277B (en) * | 2017-05-18 | 2021-04-13 | 贵阳朗玛信息技术股份有限公司 | Call center interaction system and method |
| CN110222097A (en) * | 2019-06-18 | 2019-09-10 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN117076612A (en) * | 2023-08-31 | 2023-11-17 | 宁夏恒信创达数据科技有限公司 | Call center big data text mining system |
| CN117076612B (en) * | 2023-08-31 | 2024-02-20 | 宁夏恒信创达数据科技有限公司 | Call center big data text mining system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108021929A (en) | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system | |
| US20170329837A1 (en) | Digital analytics system | |
| CN107424070A (en) | A kind of loan user credit ranking method and system based on machine learning | |
| CN110347719A (en) | A kind of enterprise's foreign trade method for prewarning risk and system based on big data | |
| CN111222681A (en) | Data processing method, device, equipment and storage medium for enterprise bankruptcy risk prediction | |
| CN107506451A (en) | abnormal information monitoring method and device for data interaction | |
| CN105069025A (en) | Intelligent aggregation visualization and management and control system for big data | |
| CN107402921A (en) | Identify event-order serie data processing method, the apparatus and system of user behavior | |
| CN106022708A (en) | Method for predicting employee resignation | |
| CN110489749B (en) | Business process optimization method of intelligent office automation system | |
| CN106528682A (en) | Big-data text mining system of call center | |
| CN104573998A (en) | Application data processing method and device | |
| CN110390475A (en) | A kind of early warning and decision support method based on group's big data | |
| CN107392425A (en) | A kind of the tobacco business project implementation SOP management method and system | |
| CN110751317A (en) | Power load prediction system and prediction method | |
| CN108038666A (en) | A kind of company information acquisition system based on internet | |
| CN108846043A (en) | Network trace mining analysis method and system based on internet big data | |
| CN116797098A (en) | Working quality assessment method, device, equipment and medium based on model training | |
| CN109002901A (en) | A kind of province ground county's integration electric network information total management system and device | |
| Yang | Financial big data management and control and artificial intelligence analysis method based on data mining technology | |
| Sun | Research on the cooperative development of university and industry economy based on Internet of Things technology | |
| Shi et al. | Human resources balanced allocation method based on deep learning algorithm | |
| Wu et al. | Design and research of insurance survey claims system based on Big Data analysis | |
| CN109523145A (en) | Electric Design quality control platform | |
| Sui et al. | [Retracted] Optimization Simulation of Supply‐Side Structure of Agricultural Economy Based on Big Data Analysis in Data Sharing Environment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |