CN114092123A - Satisfaction intelligent analysis system - Google Patents
Satisfaction intelligent analysis system Download PDFInfo
- Publication number
- CN114092123A CN114092123A CN202010769166.5A CN202010769166A CN114092123A CN 114092123 A CN114092123 A CN 114092123A CN 202010769166 A CN202010769166 A CN 202010769166A CN 114092123 A CN114092123 A CN 114092123A
- Authority
- CN
- China
- Prior art keywords
- client
- data
- satisfaction
- intelligent
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 52
- 238000011835 investigation Methods 0.000 claims abstract description 28
- 238000011160 research Methods 0.000 claims abstract description 27
- 238000003066 decision tree Methods 0.000 claims abstract description 20
- 238000003064 k means clustering Methods 0.000 claims abstract description 18
- 230000007935 neutral effect Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 7
- 238000000034 method Methods 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000003032 molecular docking Methods 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a satisfaction intelligent analysis system, which relates to the field of intelligent analysis and comprises a data acquisition model and an intelligent report analysis model; the data acquisition module is used for acquiring research result data and historical consumption data of a client, correlating the research result data and the historical consumption data and calculating a net recommendation value of the client; the intelligent report analysis model comprises a k-means clustering algorithm model and a decision tree algorithm model; the k-means clustering algorithm model is used for clustering the customer value according to the investigation result data and the historical consumption data to obtain customer classification; the decision tree algorithm model is used for analyzing key influence factors according to investigation problems and influence factors. The invention automatically analyzes the report form of the investigation result data based on the computer technology, aims to improve the recommendation will of the client, helps enterprises/brands to obtain the analysis result of the satisfaction degree of the client, and realizes a more efficient investigation mechanism and more accurate strategy application.
Description
Technical Field
The invention relates to the field of intelligent analysis, in particular to a satisfaction intelligent analysis system.
Background
In recent years, customer satisfaction survey has gained general attention, and customer satisfaction survey in the service industry has become one of the important means for enterprises to find problems and improve services. Customer satisfaction is a perceived state of pleasure or disappointment created by the customer's perceived effect on a product as compared to its expected value. The function of evaluating the customer satisfaction is to help enterprises to focus limited resources on the most important aspect of customers, so that the purposes of establishing and improving customer loyalty and promoting customer retention are achieved.
At present, many large-scale brands investigate different brands and customer groups through lines, provide basis for layering, shunting and differentiated services, and know and measure customer demands; the core of the research of the client group is to maximize the resource value, and help enterprises to realize the preferential allocation of limited resources to the most valuable customers; for enterprises taking services as a core, research is carried out to help the enterprises to research service standards, processes and gaps between service delivery and customer expectations, customer concerns and service short boards are found, and corresponding improvement suggestions are made on the basis of the customer concerns and service short boards.
The net recommendation value (NPS) evaluation index is used for knowing the satisfaction degree and loyalty degree of a client to a business by measuring the recommendation willingness of the client. The core problem of NPS research is usually to ask the customer in a simple form, then to score the customer between 1-10 according to the degree of desired recommendation, and to classify the customer into three broad categories according to the score, for example: 1. recommenders (score between 9-10); 2. neutrals (scores between 7-8 points); 3. derogator (score between 0-6 points).
Design net recommendation (NPS) questionnaire: first, the following four key variables are divided into four dimensions:
background information: the customer's past experience with the product or experience service;
experience to expected match: how well users' expectations about brands match their usage experiences with the products themselves;
public praise perception: the psychological impact of the external social environment on the producing user;
after-sale experience: possible after-sales behavior, which can be understood as a potential risk factor;
then, designing questions according to the four dimensions from the inquiry satisfaction degree, the main reason of satisfaction/dissatisfaction and the willingness degree of recommending others; for example: a fashion-type brand that is more concerned about the user's buying experience may consult the user "do you be satisfied with the services of the store's sales consultant, please score", if the user scores 5 points (between 0-6 points), the client would then need to answer "what aspects of the service you find to be the sales consultant, which aspects need to be enhanced", if the client scores 9 points (between 9-10 points), the client would also need to continue to answer the next question: "what aspects of the sales advisor you find satisfactory" to learn about the content of the service that the consumer is interested in; the design net recommendation (NPS) questionnaire further helps brand optimization service experience and flow by combining a 10-part problem model with a form of asking "why".
Finally, the net recommended value (NPS) for the brand or product is derived by the following calculation: NPS ═ number of recommenders/total samples) × 100% - (number of derogators/total samples) × 100%; for example: 10 clients, recommender is 1 and derogator is 3, please refer to fig. 1, the net recommendation value is: 1/10% -3/10% ═ 20%.
Today more and more enterprises learn the degree of satisfaction of a consumer with a product or service by using a net recommendation value (NPS) as an evaluation criterion. The net recommendation value (NPS) focuses on the overall experience and recommendation willingness of the user to the brand, product or service, and can more specifically evaluate the loyalty/recommendation degree of the user to the brand, so as to know the overall word-of-mouth image of the brand and the potential of word-of-mouth marketing, therefore, a high net recommendation value (NPS) score not only represents high loyalty of the customer, but also predicts the increased potential of a new customer.
However, many current brands have problems in implementing a net recommendation (NPS) questionnaire survey process, which results in the inability to accurately find the most critical factors affecting customer satisfaction, the direction and priority to be optimized according to the questionnaire results. The reason is mainly that defects exist in the process of research and design, and the defects are mainly reflected in the following two aspects:
1. because the types of questions in the net recommendation (NPS) questionnaire are not complex, and are dominated by choice questions, brands tend to ignore the importance of logical associations between questions when designing questionnaires, such as: the problem of the overall recommendation will be put forward first or last, which directly affects the final investigation result, so that before designing the content of the NPS questionnaire and defining the sequence of each problem, the enterprise must clearly investigate the core target and the current business situation, and introduce the docking requirement of the historical data and the portrait analysis association of the investigation crowd while designing the net recommendation value (NPS) questionnaire.
2. When many brands are conducting NPS research result analysis, because an automatic correlation algorithm model is not introduced in the questionnaire designing stage, a large amount of time is needed for manual processing of recovery data, and such a processing process easily results in omission in data analysis, and logical correlation among various detailed problems cannot be evaluated in an all-round manner, thereby affecting the high efficiency and precision of the whole research.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide an intelligent analysis system for satisfaction, which performs automatic report analysis on research result data based on a computer technology, and helps an enterprise/brand to quickly obtain an analysis result of customer satisfaction, so as to achieve a more efficient research mechanism and a more accurate policy application, with the purpose of improving the recommendation will (i.e., public praise marketing potential) of the customer.
The invention provides a satisfaction intelligent analysis system, which comprises a data acquisition model and an intelligent report analysis model; the data acquisition module is used for acquiring research result data and historical consumption data of a client, correlating the research result data and the historical consumption data and calculating a net recommendation value of the client; the intelligent report analysis model comprises a k-means clustering algorithm model, a self-defined correlation module, a decision tree algorithm model and an analysis report module; the k-means clustering algorithm model is used for clustering the customer value according to the investigation result data and the historical consumption data to obtain customer classification; the user-defined correlation module is used for researching the correlation between the problems and the subdivision of the influence factors; the decision tree algorithm model is used for analyzing key influence factors according to investigation problems and influence factors; and the analysis report module is used for generating a visual analysis report according to the key influence factors.
In an embodiment of the present invention, the data acquisition module operates according to the following principle:
(1) carrying out research data acquisition on a client through a preset net recommended value questionnaire;
(2) acquiring the liveness of the client through a client relationship management system, and correlating the liveness of the client with research data;
(3) and calculating the net recommendation values of the clients with different liveness degrees through a preset net recommendation value formula.
In an embodiment of the present invention, the operation principle of the k-means clustering algorithm model is as follows:
(1) clustering the value of the client through k-means clustering according to the activity, consumption characteristics and net recommendation value of the client;
(2) classifying customers into: positive recommendation type clients, negative recommendation type clients, positive neutral type clients, negative neutral type clients, positive detraction type clients, negative detraction type clients.
In an embodiment of the present invention, the working principle of the custom association module is as follows:
(1) acquiring subdivision definition of a client through a client relationship management system;
(2) counting the net recommendation value questionnaire detail items through the detail definition;
(3) each segment through the net recommendation questionnaire is associated with a brand or product influencing factor.
In an embodiment of the present invention, the working principle of the decision tree algorithm model is as follows:
(1) taking the scores of the investigation result data corresponding to the influence factors of the brand or the product as sample characteristics to form a sample set;
(2) taking the sample set as a child node of the decision tree to calculate the information gain rate of the sample set, if the information gain rate is greater than a preset value, segmenting the sample set, and taking the segmented sample set as the child node of the decision tree, otherwise, stopping segmenting the sample set;
(3) and recursively executing the two steps to obtain key influence factors through division.
As described above, the intelligent satisfaction analyzing system of the present invention has the following beneficial effects:
1. by carrying out automatic docking of historical data, clustering of client values and custom association of research problems in a net recommendation value (NPS) questionnaire designing stage, enterprises/brands are helped to solve a series of problems of prevention of research and realization of accurate analysis due to unclear crowd positioning, unreasonable problem sequencing setting, incapability of automatically acquiring user figures and the like after recovery of research problems.
2. A user-defined association module is built by combining subdivision logic defined by customer value clustering and net recommendation value (NPS) questionnaire content, the value contribution and recommendation willingness of a customer are automatically positioned, the priority of a customer strategy is formulated, and customer subdivision is completed; and by combining the high-value customer portrait, obtaining the satisfaction and recommendation degree promotion key points of the high-value customers through the automatic correlation analysis of the net recommendation value (NPS), thereby formulating the sub-population operation strategy and priority.
3. Factors and correlation influence degree influencing the recommendation intention of the client are identified through a pre-defined decision tree model, so that an enterprise/brand is helped to intuitively and clearly find advantages and disadvantages of products/services of the enterprise/brand, the recommendation intention of the client is improved, and a core direction and a strategy for optimizing the products/services are formulated.
Drawings
Fig. 1 shows a schematic view of the client differentiation disclosed in the prior art of the present invention.
Fig. 2 is a block diagram showing a structure of a satisfaction degree intelligent analysis system disclosed in the embodiment of the present invention.
Fig. 3 is a schematic diagram of the operation of the data acquisition module disclosed in the embodiment of the present invention.
FIG. 4 is a schematic diagram illustrating the operation of the k-means clustering algorithm model disclosed in the embodiment of the present invention.
FIG. 5 is a schematic diagram of the operation of the custom association module disclosed in the embodiments of the present invention.
Fig. 6 is a schematic diagram illustrating the operation of the decision tree algorithm model disclosed in the embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The intelligent satisfaction analysis system provided by the invention helps enterprises/brands to solve a series of problems of hindering investigation and realizing accurate analysis due to unclear crowd positioning, unreasonable problem sequencing setting, incapability of automatically acquiring user figures and the like after the investigation problem is recovered by carrying out automatic butt joint of historical data, clustering of client value and self-defined correlation of the investigation problem in a stage of designing a net recommendation value (NPS) questionnaire; through automatic data docking and model building, questionnaire results can be timely and quickly provided and custom analysis reports can be output after investigation feedback, additional data processing is not needed, and a quick and efficient analysis approach is provided for enterprise/brand user satisfaction investigation.
Before analysis by the satisfaction intelligent analysis system, firstly, the design needs to be carried out manually: 1. service combing and investigation positioning; 2. researching the flow and planning the mechanism; 3. designing a questionnaire scoring system; 4. designing a crowd subdivision and communication mechanism; 5. collecting, customizing and designing a questionnaire; 6. building an intelligent analysis report model; then, a computer is required to perform the operations of: 7. performing investigation implementation and result recovery based on a data acquisition model which is customized and set by questionnaire collection; 8. and displaying the analysis report based on the intelligent analysis report model.
Referring to fig. 2, the present invention provides a satisfaction intelligent analysis system, which includes a data collection model and an intelligent report analysis model; the data acquisition module is used for acquiring research result data and historical consumption data of a client, correlating the research result data and the historical consumption data and calculating a net recommendation value of the client; the intelligent report analysis model comprises a k-means clustering algorithm model, a self-defined correlation module, a decision tree algorithm model and an analysis report module; the k-means clustering algorithm model is used for clustering the customer value according to the investigation result data and the historical consumption data to obtain customer classification; the user-defined correlation module is used for researching the correlation between the problems and the subdivision of the influence factors; the decision tree algorithm model is used for analyzing key influence factors according to investigation problems and influence factors; and the analysis report module is used for generating a visual analysis report according to the key influence factors.
The invention takes all the members who have consumed within two years of a certain cosmetic brand as clients, explains the work flow of the satisfaction intelligent analysis system, and excavates public praise marketing potential and promotion key points of members with different brands and different values by investigating result data, member life cycle stages and cross analysis of various product consumptions.
Specifically, the application process of the satisfaction intelligent analysis system is as follows:
the method comprises the following steps: acquiring the research result data and the historical consumption data of the member through a data acquisition module, correlating the research result data and the historical consumption data with each other, and calculating a net recommendation value of the member, please refer to fig. 3;
(1) performing investigation data acquisition on the member through a preset net recommendation value questionnaire;
(2) acquiring the liveness of the member through a customer relationship management system (CRM), wherein the liveness of the member is correlated with the investigation data;
(3) calculating net recommendation values of clients with different liveness degrees through a preset net recommendation value formula;
wherein, the customer relationship management system (CRM) defines the activity of the member according to the consumption frequency, consumption time, consumption amount, etc. of the member, for example: active, sleeping and lost.
Step two: clustering member values according to the investigation result data and the historical consumption data through a k-means clustering algorithm model to obtain member classifications, and referring to fig. 4;
(1) clustering member value through k-means clustering according to the member activity, consumption characteristics (such as single consumption amount, total consumption amount and the like) and net recommendation value;
(2) classifying the members into: positive recommendation type members, negative recommendation type members, positive neutral type members, negative neutral type members, positive detraction type members, negative detraction type members.
The k-means clustering algorithm is an algorithm which inputs k clusters of which the number is k, comprises a database of n data objects and outputs k clusters meeting the minimum variance standard; the k-means clustering algorithm receives an input k, divides n data objects into k clusters, such that the obtained clusters satisfy: the clustering similarity of the same class of objects is high, and the clustering similarity of different classes of objects is low.
The cluster similarity is calculated by using a "center object" (gravity center) obtained by the mean of the objects in each cluster, and given a sample set D ═ { x1, x2, …, xm }, the k-means clustering algorithm minimizes the square error for the cluster partition C ═ C1, C2, …, Ck } for the cluster obtained by clustering:
wherein,
x is a cluster ciThe mean vector of (2); intuitively, the E describes the compactness of the intra-cluster samples around the mean vector to a certain extent, and the smaller the E value is, the higher the similarity of the intra-cluster samples is.
Given sample xi＝(xi1，xi2，…，xin) And xj＝xj1，xj2，…，xjn) Calculating the Euclidean distance between clusters:
wherein the larger the Euclidean distance between clusters, the lower the sample similarity between clusters.
The value of k corresponding to the coefficient larger is determined and selected using a contour coefficient (silouette coeffient).
Calculating the average distance a from the sample i to other samples in the same clusteri，aiThe smaller, the more sample i should be clustered to the cluster; a is toiIntra-cluster dissimilarity, called sample i, cluster partition C, a of all samplesiThe mean is referred to as cluster dissimilarity for cluster partition C.
Calculating sample i to some other cluster CjAverage distance b of all samplesijReferred to as sample i and cluster CjIs defined as the inter-cluster dissimilarity of sample i: bi＝min{bi1，bi2，…，bik}，biThe larger the sample i is, the less the sample i belongs to other clusters.
According to the intra-cluster dissimilarity a of the sample iiDegree of dissimilarity with clusters biDefining the contour coefficients of sample i:
the contour coefficient is in the range of [ -1, 1]The larger the value is, the more reasonable siIf the cluster is close to 1, the clustering of the sample i is reasonable; si is close to-1, indicating that sample i should be more classified into another cluster; if siAn approximation of 0 indicates that sample i is on the boundary of two clusters.
S of all samplesiThe mean value of (2) is called the contour coefficient of the clustering result, is a measure of whether the clustering is reasonable and effective, is determined by using the contour coefficient, and selects the corresponding k value which makes the coefficient larger.
Step three: the research question and the influence factor are subdivided and associated through a custom association module, please refer to fig. 5;
(1) acquiring subdivision definition of a client through a client relationship management system;
(2) counting the net recommendation value questionnaire detail items through the detail definition;
(3) each segment through the net recommendation questionnaire is associated with a brand or product influencing factor.
Since the net recommendation value (NPS) questionnaire is issued by the brand customer relationship management system (CRM) for the member, the member can be defined in detail in conjunction with the brand customer relationship management system (CRM), for example: new members, old members, members purchased for a certain product, etc., statistics of the breakdown based on the net recommendation value (NPS) questionnaire of the members, and association to brand/product factors by each breakdown, such as: sales promotion, price, efficacy, service, etc.
Step four: analyzing key influence factors according to the investigation problem and the influence factors through a decision tree algorithm model, please refer to fig. 6;
(1) taking the scores of the investigation result data corresponding to the influence factors of the brand or the product as sample characteristics to form a sample set;
in the embodiment, the grade of each detail item of each client in a net recommendation value (NPS) questionnaire is selected as a sample characteristic to form a sample set; such as PRICE (PRICE), commodity (PRODUCT), marketing CAMPAIGN (CAMPAIGN), SERVICE (SERVICE), etc.
(2) Taking the sample set as a child node of the decision tree to calculate the information gain rate of the sample set, if the information gain rate is greater than a preset value, segmenting the sample set, and taking the segmented sample set as the child node of the decision tree, otherwise, stopping segmenting the sample set;
the decision tree algorithm selects attributes in an information gain rate mode, and selects the attribute with the maximum gain rate as a splitting attribute;
information gain ratio is information gain/characteristic entropy, i.e.:
wherein, the denominator expression is as follows:
the molecular information gain is defined as the difference between the original information requirement and the new requirement, and the molecular expression is: gain (a) Info (d) -InfoA(D)；
Where D is the set of sample feature outputs and A is the sample feature.
(3) And recursively executing the two steps to obtain key influence factors through division.
In summary, the invention performs automatic report analysis on the investigation result based on the computer technology, so as to help the enterprise to quickly obtain the analysis result of the customer satisfaction with the aim of improving the customer recommendation will (i.e. public praise marketing potential), thereby realizing a more efficient investigation mechanism and a more accurate strategy application. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (5)
1. A satisfaction intelligent analysis system which is characterized in that: the system comprises a data acquisition model and an intelligent report analysis model; the data acquisition module is used for acquiring research result data and historical consumption data of a client, correlating the research result data and the historical consumption data and calculating a net recommendation value of the client; the intelligent report analysis model comprises a k-means clustering algorithm model, a self-defined correlation module, a decision tree algorithm model and an analysis report module; the k-means clustering algorithm model is used for clustering the customer value according to the investigation result data and the historical consumption data to obtain customer classification; the user-defined correlation module is used for researching the correlation between the problems and the subdivision of the influence factors; the decision tree algorithm model is used for analyzing key influence factors according to investigation problems and influence factors; and the analysis report module is used for generating a visual analysis report according to the key influence factors.
2. A satisfaction intelligent analysis system according to claim 1, characterized by: the working principle of the data acquisition module is as follows:
(1) carrying out research data acquisition on a client through a preset net recommended value questionnaire;
(2) acquiring the liveness of the client through a client relationship management system, and correlating the liveness of the client with research data;
(3) and calculating the net recommendation values of the clients with different liveness degrees through a preset net recommendation value formula.
3. A satisfaction intelligent analysis system according to claim 2, characterized in that: the working principle of the k-means clustering algorithm model is as follows:
(1) clustering the value of the client through k-means clustering according to the activity, consumption characteristics and net recommendation value of the client;
(2) classifying customers into: positive recommendation type clients, negative recommendation type clients, positive neutral type clients, negative neutral type clients, positive detraction type clients, negative detraction type clients.
4. A satisfaction intelligent analysis system according to claim 3, characterized by: the working principle of the user-defined correlation module is as follows:
(1) acquiring subdivision definition of a client through a client relationship management system;
(2) counting the net recommendation value questionnaire detail items through the detail definition;
(3) each segment through the net recommendation questionnaire is associated with a brand or product influencing factor.
5. The intelligent satisfaction analysis system of claim 4, wherein: the working principle of the decision tree algorithm model is as follows:
(1) taking the scores of the investigation result data corresponding to the influence factors of the brand or the product as sample characteristics to form a sample set;
(2) taking the sample set as a child node of the decision tree to calculate the information gain rate of the sample set, if the information gain rate is greater than a preset value, segmenting the sample set, and taking the segmented sample set as the child node of the decision tree, otherwise, stopping segmenting the sample set;
(3) and recursively executing the two steps to obtain key influence factors through division.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010769166.5A CN114092123A (en) | 2020-08-03 | 2020-08-03 | Satisfaction intelligent analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010769166.5A CN114092123A (en) | 2020-08-03 | 2020-08-03 | Satisfaction intelligent analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114092123A true CN114092123A (en) | 2022-02-25 |
Family
ID=80295135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010769166.5A Pending CN114092123A (en) | 2020-08-03 | 2020-08-03 | Satisfaction intelligent analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114092123A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151872A (en) * | 2022-11-28 | 2023-05-23 | 荣耀终端有限公司 | Product characteristic analysis method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20050089189A (en) * | 2004-03-04 | 2005-09-08 | 한국과학기술원 | Customer satisfaction index analysis system and method |
| CN107230090A (en) * | 2016-03-23 | 2017-10-03 | 中国移动通信集团上海有限公司 | A kind of net recommendation NPS sorting techniques and device |
| CN110942098A (en) * | 2019-11-28 | 2020-03-31 | 江苏电力信息技术有限公司 | Power supply service quality analysis method based on Bayesian pruning decision tree |
-
2020
- 2020-08-03 CN CN202010769166.5A patent/CN114092123A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20050089189A (en) * | 2004-03-04 | 2005-09-08 | 한국과학기술원 | Customer satisfaction index analysis system and method |
| CN107230090A (en) * | 2016-03-23 | 2017-10-03 | 中国移动通信集团上海有限公司 | A kind of net recommendation NPS sorting techniques and device |
| CN110942098A (en) * | 2019-11-28 | 2020-03-31 | 江苏电力信息技术有限公司 | Power supply service quality analysis method based on Bayesian pruning decision tree |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151872A (en) * | 2022-11-28 | 2023-05-23 | 荣耀终端有限公司 | Product characteristic analysis method and device |
| CN116151872B (en) * | 2022-11-28 | 2023-11-14 | 荣耀终端有限公司 | Product characteristic analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Seng et al. | An analytic approach to select data mining for business decision | |
| Chen | Ranking discovered rules from data mining with multiple criteria by data envelopment analysis | |
| CN108921602B (en) | User purchasing behavior prediction method based on integrated neural network | |
| CN117829914B (en) | Digital media advertisement effect evaluation system | |
| Sun et al. | GPHC: A heuristic clustering method to customer segmentation | |
| CN104346698A (en) | Catering member big data analysis and checking system based on cloud computing and data mining | |
| Zhou et al. | Quality function deployment: A bibliometric-based overview | |
| Orogun et al. | Predicting consumer behaviour in digital market: a machine learning approach | |
| Oliveira | Analytical customer relationship management in retailing supported by data mining techniques | |
| Wang et al. | A reliable location design of unmanned vending machines based on customer satisfaction | |
| Abdulla | Application of MIS in E-CRM: A literature review in FMCG supply chain | |
| Anusha et al. | Segmentation of retail mobile market using HMS algorithm | |
| CN114092123A (en) | Satisfaction intelligent analysis system | |
| Halkiopoulos et al. | E-marketing and Online Advertising: Case Study in Greek Companies during Economic Crisis | |
| CN117291651A (en) | Method for creating natural repurchase prediction model in cosmetic industry and application thereof | |
| Daneshmandi et al. | A hybrid data mining model to improve customer response modeling in direct marketing | |
| Wang et al. | Research on precision marketing strategy based on cluster analysis algorithm | |
| Bahri et al. | Data Mining Techniques To Uncovering Customer Segments: K-Means Clustering Using The Elbow Method Approach In Medium-Scale Grocery | |
| Casabayó et al. | Using AI techniques in the grocery industry: Identifying the customers most likely to defect | |
| Danubianu et al. | Improving customer relationship management in hotel industry by data mining techniques | |
| Bochkaryov et al. | Application of the ensemble clustering algorithm in solving the problem of segmentation of users taking into account their loyalty | |
| Guo et al. | Decision support system for industrial designer based on Kansei engineering | |
| Xu | Design of CRM Hotel Management System Based on Machine Learning Algorithm | |
| Liu | Research on E-commerce Enterprise Customer Segmentation Based on Cluster Analysis-Taking Jingdong Century Trading Co., Ltd as an Example | |
| Duque et al. | A network based approach towards industry clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |