CN105574171A - Method and system for monitoring customer sentiment value - Google Patents
Method and system for monitoring customer sentiment value Download PDFInfo
- Publication number
- CN105574171A CN105574171A CN201510953842.3A CN201510953842A CN105574171A CN 105574171 A CN105574171 A CN 105574171A CN 201510953842 A CN201510953842 A CN 201510953842A CN 105574171 A CN105574171 A CN 105574171A
- Authority
- CN
- China
- Prior art keywords
- data
- signal
- client
- client perception
- value
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
-
- 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
-
- 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
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for monitoring customer sentiment value. The method comprises steps as follows: customer sentiment data are collected; data with representative features are extracted; the data with the representative features are subjected to dimensionality division, and corresponding signal data are generated; a threshold value score corresponding to each threshold value is configured according to multiple threshold values of each signal data, and a signal score of the corresponding signal data is calculated; the multiple signal data are grouped, signal data groups are formed, and signal group scores of the signal data groups are calculated; a customer sentiment index of customer sentiment value is calculated and reflected with a weighted average algorithm according to the signal data groups and the corresponding signal group scores. Effective factors influencing customer satisfaction are automatically analyzed according to related customer data from various data sources and with various dimensionalities, the customer sentiment index is quickly calculated, and the satisfaction of a current customer for products and service can be known constantly in real time.
Description
Technical field
The present invention relates to client perception monitoring field, be specifically related to a kind of monitoring method and monitoring system of Customers'perceptible value.
Background technology
CSI (CustomerSentimentIndex, client's affection index) index computation model is the measurement system of the comprehensive evaluation index based on client-related data, can objectively respond client's emotion perception value and the level of satisfaction to service.In order to degree of depth insight into customer, in numerous and disorderly client's dependent event, understand the key factor that customer satisfaction level becomes customer insight intuitively, exactly.
The Fei Naier logical model that traditional customer satisfaction survey mainly uses the Ke Luosifeinaier at Univ Michigan-Ann Arbor USA business school quality research center (Claesfornell) doctor to study calculates, and the aspect factors such as the price of the perception after user expectation, purchase, purchase are formed an econometrics model.This model combines the psychological response that the mathematical algorithms of customer satisfaction and client buy commodity or service.Solving with the minimum quadratic power of this model use partial differential the index obtained, is exactly customer satisfactory index.But this Fei Naier logical model must obtain by forms such as surveys " client to service expectation ", " client is to the perception of service quality ", premised on " client is to the perception of value of services " these three kinds of factors, calculate customer satisfaction by Fei Naier logical model and can not meet the demand that enterprise grasps customer satisfaction in real time constantly, also do not reflect the trend of client's emotion change.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of monitoring method and monitoring system of Customers'perceptible value, can understand the satisfaction of client to product and service in real time, constantly.
The technical scheme that the present invention solves the problems of the technologies described above is as follows:
On the one hand, the invention provides a kind of monitoring method of Customers'perceptible value, comprising:
The client perception data of S1, collection reflection Customers'perceptible value;
S2, data model is set up, and according to the client perception data of the descriptor in data model from the representative feature of described client perception extracting data to the described client perception data of collecting;
S3, the client perception data of described representative feature are carried out to the division of dimension, and by signal data corresponding for the client perception data genaration of each dimension;
S4, multiple threshold values according to each signal data, configure the threshold values score value corresponding with each threshold values, and according to the threshold values score value of described multiple threshold values and correspondence, utilize Weighted Average Algorithm to calculate signal score value corresponding to this signal data;
S5, according to characteristic similarity, multiple signal data to be divided into groups, form signal data group, and according to the signal score value of the multiple signal data in each signal data group and correspondence, utilize Weighted Average Algorithm to calculate signal component value corresponding to this signal data group;
S6, signal component value according to multiple signal data group and correspondence, utilize Weighted Average Algorithm to calculate the client perception index of reflection Customers'perceptible value.
Beneficial effect of the present invention is: method provided by the invention can go out affect the efficiency factor of customer satisfaction by automatic analysis from the client-related data of various Data Source, multiple dimension, and calculate client perception index fast, the satisfaction of existing customer to product and service can be understood in real time constantly.
On the basis of technique scheme, the present invention can also do following improvement.
Further, described step S1 specifically comprises:
Collect the network public-opinion data that the client perception data of the reflection Customers'perceptible value that client is produced by internet, client trading data, Customer Service Information, client feedback evaluating data and client are issued by social network media.
Described further beneficial effect is: the wide material sources of client perception data, and to the analysis of a large amount of client perception data, the client perception index finally calculated is more accurate.
Further, described step S2 also comprises:
Remove the interfering data in the described client perception data of collecting and noise data.
Further, in described step S3, the division that the client perception data of described representative feature carry out dimension is specifically comprised:
Method for normalizing or the client perception data of standardized method to described representative feature are used to carry out the division of dimension.
Further, also comprise:
According to multiple client perception indexes of the correspondence calculated in multiple schedule time, analyze the variation tendency of client perception index along with the time;
When signal component value reaches Second Threshold lower than the downtrending of first threshold or client perception index, judge to reach customer defection early warning standard, and carry out customer defection early warning.
Described further beneficial effect is: when the analysis by data learn reach customer defection early warning standard time, carry out customer defection early warning, to take measures timely, prevent the loss of client as far as possible.
Further, also comprise:
The variation tendency of the multiple client perception index calculated and client perception index is carried out visual presentation with the form of figure or form.
Described further beneficial effect is: shown in visual mode by client perception index, facilitates user to check.
On the other hand, the invention provides a kind of monitoring system of Customers'perceptible value, comprising:
Data collection module, for collecting the client perception data of reflection Customers'perceptible value;
Data extraction module, for setting up data model to the described client perception data of collecting, and according to the client perception data of the descriptor in data model from the representative feature of described client perception extracting data;
Dimension divides module, for carrying out the division of dimension to the client perception data of described representative feature, and by signal data corresponding for the client perception data genaration of each dimension;
Signal score value computing module, for the multiple threshold values according to each signal data, configure the threshold values score value corresponding with each threshold values, and according to the threshold values score value of described multiple threshold values and correspondence, utilize Weighted Average Algorithm to calculate signal score value corresponding to this signal data;
Signal component value computing module, for dividing into groups to multiple signal data according to characteristic similarity, form signal data group, and according to the signal score value of the multiple signal data in each signal data group and correspondence, utilize Weighted Average Algorithm to calculate component value corresponding to this signal data group;
Perception index computing module, for the signal component value according to multiple signal data group and correspondence, utilizes Weighted Average Algorithm to calculate the client perception index of reflection Customers'perceptible value.
Beneficial effect of the present invention is: from the client-related data of various Data Source, multiple dimension, can go out affect the efficiency factor of customer satisfaction by automatic analysis, and calculate client perception index fast, the satisfaction of existing customer to product and service can be understood in real time constantly.
On the basis of technique scheme, the present invention can also do following improvement.
Further, also comprise:
Denoising module, for removing interfering data in the described client perception data of collection and noise data.
Further, also comprise:
Analysis of trend module, for according to the multiple client perception indexes calculated in the schedule time, analyzes the variation tendency of client perception index along with the time;
Warning module, for when signal data component value reaches Second Threshold lower than the downtrending of first threshold or client perception index, judges to reach customer defection early warning standard, and carries out customer defection early warning.
Described further beneficial effect is: when the analysis by data learn reach customer defection early warning standard time, carry out customer defection early warning, to take measures timely, prevent the loss of client as far as possible.
Further, also comprise:
Display module, for carrying out visual presentation by the variation tendency of the multiple client perception index calculated and client perception index with the form of figure or form.
Described further beneficial effect is: client perception index is carried out visual presentation in visual mode, facilitates user to check.
Accompanying drawing explanation
Fig. 1 is the monitoring method process flow diagram of a kind of Customers'perceptible value of the embodiment of the present invention 1;
Fig. 2 calculates multiple threshold values score value schematic diagram corresponding to each signal data in embodiment 1;
Fig. 3 calculates signal component value schematic diagram in embodiment 1;
Fig. 4 calculates client perception index schematic diagram in embodiment 1;
Fig. 5 is the whole workflow diagram of embodiment 1;
Fig. 6 is the monitoring system schematic diagram of a kind of Customers'perceptible value of the embodiment of the present invention 2.
Embodiment
Be described principle of the present invention and feature below in conjunction with accompanying drawing, example, only for explaining the present invention, is not intended to limit scope of the present invention.
The monitoring method of embodiment 1, a kind of Customers'perceptible value.Below in conjunction with Fig. 1-Fig. 5, the method that the present embodiment provides is described.
See Fig. 1, the method that the present embodiment provides comprises: the client perception data of S1, collection reflection Customers'perceptible value.
Concrete, the present embodiment mainly collects the network public-opinion data that the client perception data of the reflection Customers'perceptible value that client is produced by internet, client trading data, Customer Service Information, client feedback evaluating data and client are issued by social network media.Concrete Data Source comprises the following aspects: the client perception data such as client is logged in by internet, browse, search for, collect, comment on, recommend, purchase; Sales price, consumption sum, quantity purchase, purchase batch, the client trading data such as billing cycle, Payment Methods, delivery cycle; The Customer Service Information such as client returns, complaint, report, hotline, instant message service; The report of customer service request, abnormal data and client feedback data; The network public-opinion data that client is issued by social network media.
S2, data model is set up, and according to the client perception data of the descriptor in data model from the representative feature of described client perception extracting data to the described client perception data of collecting.
Concrete, by step S1 from have collected a large amount of client perception data by all kinds of means, interfering data in a large amount of client perception data and noise data are removed, strengthen useful information, data model is set up for a large amount of client perception data after removing interfering data and noise data, wherein, signal data descriptor is included in data model.According to the client perception data of the signal data descriptor in data model from the representative feature of client perception extracting data.
S3, the client perception data of described representative feature are carried out to the division of dimension, and by signal data corresponding for the client perception data genaration of each dimension.
Concrete, the client perception data of the representative feature extracted are carried out to the division of dimension, in the present embodiment, method for normalizing or standardized method is adopted to carry out the division of dimension to data, and the dimension of data is reduced to suitable size, the former data message of reservation as much as possible simultaneously, and by signal data corresponding for the client perception data genaration of each dimension.
S4, multiple threshold values according to each signal data, configure the threshold values score value corresponding with each threshold values, and according to the threshold values score value of described multiple threshold values and correspondence, utilize Weighted Average Algorithm to calculate signal score value corresponding to this signal data.
Concrete, can see Fig. 2, the signal data of the corresponding dimension of a signal data descriptor in above-mentioned data model, a corresponding multiple threshold values of signal data, such as, user logs in or browses the number of times in certain store, for the threshold values that this signal data is different, the threshold values score value that configuration is corresponding.Such as, such as, certain client logs in the number of times in certain store at 5 ~ 6 times, then for the threshold values score value of its configuration is 6, certain client logs in the number of times in certain store at 7 ~ 8 times, then for the threshold values score value of its configuration is 7.Therefore, there is multiple threshold values in each signal data, the corresponding threshold values score value of each threshold values, and utilize Weighted Average Algorithm to calculate signal score value corresponding to this signal data.
S5, according to characteristic similarity, multiple signal data to be divided into groups, form signal data group, and according to the signal score value of the multiple signal data in each signal data group and correspondence, utilize Weighted Average Algorithm to calculate signal component value corresponding to this signal data group.
Concrete, can see Fig. 3, according to characteristic similarity, multiple signal data is divided into groups, form signal data group, namely the signal data set that a stack features is similar, several signal data group comprises multiple signal data, the corresponding signal score value of each signal data, give different weights to different signal datas, and utilize Weighted Average Algorithm to calculate signal component group corresponding to each signal data group.
S6, signal component value according to multiple signal data group and correspondence, utilize Weighted Average Algorithm to calculate the client perception index of reflection Customers'perceptible value.
Concrete, can see Fig. 4, above-mentioned steps S5 calculates signal component value corresponding to each signal data group, this step is according to multiple signal data group and signal component value corresponding to each signal data group, different weights is given to different signal data groups, and utilize Weighted Average Algorithm to calculate the client perception index of reflection Customers'perceptible value, i.e. CSI (CustomerSentimentIndex).
In addition, according to the multiple client perception indexes calculated in the different schedule time, analyze the variation tendency of client perception index along with the time; When signal data component value reaches Second Threshold lower than the downtrending of first threshold or client perception index, judge to reach customer defection early warning standard, and carry out customer defection early warning.In addition, the variation tendency of the multiple client perception index calculated and client perception index is shown with the form of figure or form.
Below in conjunction with Fig. 5, the method that the present embodiment provides is further illustrated, see Fig. 5, first from multiple source collection client perception data, the client perception data of representative characteristic are provided from a large amount of client perception extracting data of collecting, and carry out dimension division, and by signal data corresponding for the data genaration of each dimension.For multiple threshold values of each signal data, configure the threshold values score value corresponding with each threshold values, and utilize Weighted Average Algorithm to calculate number score value of each signal data; According to characteristic similarity, multiple signal data is divided into groups, form signal data group, i.e. signal data set, a signal data group comprises multiple signal data, according to the signal score value of the multiple signal data in a signal data group and correspondence, give different weights to different signal datas, utilize Weighted Average Algorithm to calculate the signal component value of each signal data group.Finally, according to the signal component value of each signal data group and correspondence, give different weights to different signal data groups, utilize Weighted Average Algorithm to calculate client perception index.The present embodiment, also according to the client perception index calculated in different predetermined amount of time, calculates client perception index variation tendency within a certain period of time.When each signal data component value or client perception index variation trend reach customer defection early warning standard, carry out customer defection early warning, to take measures in time, prevent customer churn.In addition, the present embodiment also by the variation tendency of the multiple client perception index calculated and client perception index to scheme or the form of form carries out visual presentation.
The monitoring system of embodiment 2, a kind of Customers'perceptible value.Below in conjunction with Fig. 6, the system that the present embodiment provides is described.
See Fig. 6, the system that the present embodiment provides comprises data collection module 60, denoising module 61, data extraction module 62, dimension division module 63, signal score value computing module 64, signal component value computing module 65, client perception index computing module 66, analysis of trend module 67, warning module 68 and display module 69.
Wherein, data collection module 60, for collecting the client perception data of reflection Customers'perceptible value.
Denoising module 61, for removing interfering data in the described client perception data of collection and noise data.
Data extraction module 62, for setting up data model to the described client perception data of collecting, and according to the client perception data of the descriptor in data model from the representative feature of described client perception extracting data.
Dimension divides module 63, for carrying out the division of dimension to the client perception data of described representative feature, and by signal data corresponding for the client perception data genaration of each dimension.
Signal score value computing module 64, for the multiple threshold values according to each signal data, configure the threshold values score value corresponding with each threshold values, and according to the threshold values score value of described multiple threshold values and correspondence, utilize Weighted Average Algorithm to calculate signal score value corresponding to this signal data.
Signal component value computing module 65, for dividing into groups to multiple signal data according to characteristic similarity, form signal data group, and according to the signal score value of the multiple signal data in each signal data group and correspondence, utilize Weighted Average Algorithm to calculate signal component value corresponding to this signal data group.
Perception index computing module 66, for the signal component value according to multiple signal data group and correspondence, utilizes Weighted Average Algorithm to calculate the client perception index of reflection Customers'perceptible value.
Analysis of trend module 67, for according to the multiple client perception indexes calculated in the schedule time, analyzes the variation tendency of client perception index along with the time.
Warning module 68, for when signal component value reaches Second Threshold lower than the downtrending of first threshold or client perception index, judges to reach customer defection early warning standard, and carries out customer defection early warning.
Display module 69, for showing the multiple client perception index calculated and client perception index variation trend with the form of figure or form.
The monitoring method of a kind of Customers'perceptible value provided by the invention and monitoring system, from the client-related data of various Data Source, multiple dimension, can go out affect the efficiency factor of customer satisfaction by automatic analysis, and calculate client perception index fast, the satisfaction of existing customer to product and service can be understood in real time constantly.According to the variation tendency of the client perception index analysis client perception index of different time sections, if downtrending is severe, reach customer defection early warning standard, then carry out customer defection early warning, to take measures in time, prevent customer churn.The client perception index of each time period calculated and the variation tendency of client perception index are also carried out visual presentation by the present invention, allow enterprise understand the consumption experience of client to product and service more visual and clearly, deepen the emotional relationship between enterprise and client.
In the description of this instructions, concrete grammar, device or feature that the description of reference term " embodiment one ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not must for be identical embodiment or example.And the specific features of description, method, device or feature can combine in one or more embodiment in office or example in an appropriate manner.In addition, when not conflicting, the feature of the different embodiment described in this instructions or example and different embodiment or example can carry out combining and combining by those skilled in the art.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. a monitoring method for Customers'perceptible value, is characterized in that, comprising:
The client perception data of S1, collection reflection Customers'perceptible value;
S2, data model is set up, and according to the client perception data of the descriptor in data model from the representative feature of described client perception extracting data to the described client perception data of collecting;
S3, the client perception data of described representative feature are carried out to the division of dimension, and by signal data corresponding for the client perception data genaration of each dimension;
S4, multiple threshold values according to each signal data, configure the threshold values score value corresponding with each threshold values, and according to the threshold values score value of described multiple threshold values and correspondence, utilize Weighted Average Algorithm to calculate signal score value corresponding to this signal data;
S5, according to characteristic similarity, multiple signal data to be divided into groups, form signal data group, and according to the signal score value of the multiple signal data in each signal data group and correspondence, utilize Weighted Average Algorithm to calculate signal component value corresponding to this signal data group;
S6, signal component value according to multiple signal data group and correspondence, utilize Weighted Average Algorithm to calculate the client perception index of reflection Customers'perceptible value.
2. the monitoring method of Customers'perceptible value as claimed in claim 1, it is characterized in that, described step S1 specifically comprises:
Collect the network public-opinion data that the client perception data of the reflection Customers'perceptible value that client is produced by internet, client trading data, Customer Service Information, client feedback evaluating data and client are issued by social network media.
3. the monitoring method of Customers'perceptible value as claimed in claim 1, it is characterized in that, described step S2 also comprises:
Remove the interfering data in the described client perception data of collecting and noise data.
4. the monitoring method of Customers'perceptible value as claimed in claim 1, is characterized in that, specifically comprises in described step S3 to the division that the client perception data of described representative feature carry out dimension:
Method for normalizing or the client perception data of standardized method to described representative feature are used to carry out the division of dimension.
5. the monitoring method of Customers'perceptible value as claimed in claim 1, is characterized in that, also comprise:
According to multiple client perception indexes of the correspondence calculated in multiple schedule time, analyze the variation tendency of client perception index along with the time;
When signal component value reaches Second Threshold lower than the downtrending of first threshold or client perception index, judge to reach customer defection early warning standard, and carry out customer defection early warning.
6. the monitoring method of Customers'perceptible value as claimed in claim 5, is characterized in that, also comprise:
The variation tendency of the multiple client perception index calculated and client perception index is carried out visual presentation with the form of figure or form.
7. a monitoring system for Customers'perceptible value, is characterized in that, comprising:
Data collection module, for collecting the client perception data of reflection Customers'perceptible value;
Data extraction module, for setting up data model to the described client perception data of collecting, and according to the client perception data of the descriptor in data model from the representative feature of described client perception extracting data;
Dimension divides module, for carrying out the division of dimension to the client perception data of described representative feature, and by signal data corresponding for the client perception data genaration of each dimension;
Signal score value computing module, for the multiple threshold values according to each signal data, configure the threshold values score value corresponding with each threshold values, and according to the threshold values score value of described multiple threshold values and correspondence, utilize Weighted Average Algorithm to calculate signal score value corresponding to this signal data;
Signal component value computing module, for dividing into groups to multiple signal data according to characteristic similarity, form signal data group, and according to the signal score value of the multiple signal data in each signal data group and correspondence, utilize Weighted Average Algorithm to calculate component value corresponding to this signal data group;
Perception index computing module, for the signal component value according to multiple signal data group and correspondence, utilizes Weighted Average Algorithm to calculate the client perception index of reflection Customers'perceptible value.
8. the monitoring system of Customers'perceptible value as claimed in claim 7, is characterized in that, also comprise:
Denoising module, for removing interfering data in the described client perception data of collection and noise data.
9. the monitoring system of Customers'perceptible value as claimed in claim 8, is characterized in that, also comprise:
Analysis of trend module, for according to the multiple client perception indexes calculated in the schedule time, analyzes the variation tendency of client perception index along with the time;
Warning module, for when signal data component value reaches Second Threshold lower than the downtrending of first threshold or client perception index, judges to reach customer defection early warning standard, and carries out customer defection early warning.
10. the monitoring system of Customers'perceptible value as claimed in claim 9, is characterized in that, also comprise:
Display module, for carrying out visual presentation by the variation tendency of the multiple client perception index calculated and client perception index with the form of figure or form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510953842.3A CN105574171A (en) | 2015-12-17 | 2015-12-17 | Method and system for monitoring customer sentiment value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510953842.3A CN105574171A (en) | 2015-12-17 | 2015-12-17 | Method and system for monitoring customer sentiment value |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105574171A true CN105574171A (en) | 2016-05-11 |
Family
ID=55884302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510953842.3A Pending CN105574171A (en) | 2015-12-17 | 2015-12-17 | Method and system for monitoring customer sentiment value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105574171A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053230A (en) * | 2017-11-29 | 2018-05-18 | 无锡雅座在线科技股份有限公司 | public sentiment management method and device |
| CN109993562A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of satisfaction emulation mode, device and terminal device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101562830A (en) * | 2009-04-20 | 2009-10-21 | 深圳市优网科技有限公司 | Customer perception evaluation method and system |
| CN101640609A (en) * | 2009-08-31 | 2010-02-03 | 北京邮电大学 | Method and device for evaluating quality indicators of communication services |
| CN104680328A (en) * | 2015-03-16 | 2015-06-03 | 朗新科技股份有限公司 | Power grid construction quality monitoring method based on client perception values |
-
2015
- 2015-12-17 CN CN201510953842.3A patent/CN105574171A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101562830A (en) * | 2009-04-20 | 2009-10-21 | 深圳市优网科技有限公司 | Customer perception evaluation method and system |
| CN101640609A (en) * | 2009-08-31 | 2010-02-03 | 北京邮电大学 | Method and device for evaluating quality indicators of communication services |
| CN104680328A (en) * | 2015-03-16 | 2015-06-03 | 朗新科技股份有限公司 | Power grid construction quality monitoring method based on client perception values |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053230A (en) * | 2017-11-29 | 2018-05-18 | 无锡雅座在线科技股份有限公司 | public sentiment management method and device |
| CN109993562A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of satisfaction emulation mode, device and terminal device |
| CN109993562B (en) * | 2018-01-02 | 2021-09-14 | 中国移动通信有限公司研究院 | Satisfaction degree simulation method and device and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Grigoroudis et al. | Customer satisfaction evaluation: Methods for measuring and implementing service quality | |
| CN104463637A (en) | Commodity recommendation method and device based on electronic business platform and server | |
| CN109902441B (en) | KANO model principle-based vehicle performance index weight distribution system and method | |
| CN107665448A (en) | For determining the method, apparatus and storage medium of consumption contributed value | |
| CN104813315A (en) | Customer-data analysis/evaluation system | |
| KR101703529B1 (en) | Market analysis service provision method in accordance with market analysis thereof | |
| CN103984998A (en) | Sale forecasting method based on big data mining of cloud service platform | |
| CN104424247A (en) | Product information filtering recommendation method and device | |
| CN109146611A (en) | A kind of electric business product quality credit index analysis method and system | |
| CN108364191A (en) | Top-tier customer Optimum Identification Method and device based on random forest and logistic regression | |
| EP2534629A1 (en) | Art evaluation engine and method for automatic development of an art index | |
| CN105574171A (en) | Method and system for monitoring customer sentiment value | |
| CN114118793A (en) | Local exchange risk early warning method, device and equipment | |
| CN113283673A (en) | Model performance attenuation evaluation method, model training method and device | |
| Govindaraju et al. | Stakeholder role in e-commerce adoption by small and medium enterprises | |
| KR101536536B1 (en) | Method for evaluating technology by adjusted reproduction cost approaching | |
| CN116385045A (en) | Data processing method, device and equipment for receiving and hosting additional service | |
| EP2933771A1 (en) | Method and system for identifying defective goods based on user purchasing behaviour | |
| Pradhan et al. | Measuring customer lifetime value: application of analytic hierarchy process in determining relative weights of ‘lrfm’ | |
| CN109697203A (en) | Index unusual fluctuation analysis method and equipment, computer storage medium, computer equipment | |
| Kalra et al. | TQM-A Management Philosophy in Indian Automobile Industry (NCR) | |
| CN114817741A (en) | Financial product accurate recommendation method and device | |
| CN112434954A (en) | Power failure sensitivity evaluation method and device | |
| CN112348281A (en) | Power data processing method and device | |
| Razak et al. | Sustainability risk management using failure mode effect analysis: evidence from Malaysia |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160511 |
|
| RJ01 | Rejection of invention patent application after publication |