CN111242660A - User satisfaction investigation method, device, equipment and computer-readable storage medium - Google Patents
User satisfaction investigation method, device, equipment and computer-readable storage medium Download PDFInfo
- Publication number
- CN111242660A CN111242660A CN201811440581.5A CN201811440581A CN111242660A CN 111242660 A CN111242660 A CN 111242660A CN 201811440581 A CN201811440581 A CN 201811440581A CN 111242660 A CN111242660 A CN 111242660A
- Authority
- CN
- China
- Prior art keywords
- attribute
- determining
- index item
- target
- preset
- 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
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
- 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
-
- 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
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure provides a user satisfaction survey method, apparatus, device and computer readable storage medium, comprising: determining a first questionnaire, and obtaining a first survey result according to the first questionnaire; determining a target attribute category corresponding to the preset index item; determining a target index item according to the attribute category, and determining a second questionnaire according to the target index item; obtaining a second survey result according to the second survey questionnaire; and determining a second attribute type corresponding to the target index item according to the second investigation result, and determining the importance degree adjustment coefficient of the target index item according to the second attribute type corresponding to the target index item. According to the scheme provided by the disclosure, the target index item with high satisfaction degree to the user is determined based on the first questionnaire survey result, the second questionnaire survey is carried out according to the target index item to obtain the second survey result, the second thinner attribute type corresponding to the user feedback result is divided, and the influence of each target index item on the user satisfaction degree can be determined by making money.
Description
Technical Field
The present disclosure relates to a user survey technology, and in particular, to a user satisfaction survey method, apparatus, device, and computer-readable storage medium.
Background
With the development of internet technology, the popularity of the internet is continuously improved, the scale of online shopping users in China is continuously enlarged, and online shopping gradually becomes an indispensable component in daily life of people and an important component of national economy.
The quality of the service quality of the B2C shopping website directly influences the satisfaction and acceptance of online shopping customers, and under the new situation of the Internet, with the continuous reduction of market transparency and the distance among enterprises, clients and competitors, representative factors influencing the satisfaction of the customers are fully known, so that the method has great significance for improving the service quality of online enterprises to obtain competitive advantages, and can stand out in a fierce competitive environment to capture and expand market share.
In the prior art, the problems of attitude, motivation, behavior habits and the like of target crowds can be researched through expert opinions or a group discussion mode, and then the influence factors of the satisfaction degree are determined; the satisfaction information of the user can be collected in a questionnaire mode.
However, although the expert opinions or the group discussion modes have certain value, the method has strong subjectivity and is difficult to quantitatively prove; the questionnaire mode is too direct and stays on the surface of the number, and the survey meter design mode is too mechanized and is not representative. Therefore, the customer satisfaction results obtained by the prior art schemes for investigating customer satisfaction are not accurate enough.
Disclosure of Invention
The present disclosure provides a method, an apparatus, a device and a computer readable storage medium for investigating customer satisfaction, so as to solve the problem that the result of customer satisfaction obtained by the scheme for investigating customer satisfaction in the prior art is not accurate enough.
A first aspect of the present disclosure is to provide a user satisfaction survey method, including:
determining a first questionnaire according to a preset index item, and obtaining a first survey result according to the first questionnaire;
determining a target attribute category corresponding to the preset index item according to the first investigation result;
determining a target index item according to the attribute category, and determining a second questionnaire according to the target index item;
obtaining a second survey result according to the second questionnaire;
and determining a second attribute type corresponding to the target index item according to the second investigation result, and determining an importance adjustment coefficient of the target index item according to the second attribute type corresponding to the target index item.
Another aspect of the present disclosure is to provide a user satisfaction survey apparatus, comprising:
the first survey module is used for determining a first survey questionnaire according to a preset index item and obtaining a first survey result according to the first survey questionnaire;
the first determining module is used for determining the target attribute category corresponding to the preset index item according to the first investigation result;
the second determination module is used for determining a target index item according to the attribute category and determining a second questionnaire according to the target index item;
the second investigation module is used for obtaining a second investigation result according to the second questionnaire;
and the coefficient determining module is used for determining a second attribute category corresponding to the target index item according to the second investigation result, and determining an importance adjusting coefficient of the target index item according to the second attribute category corresponding to the target index item.
It is still another aspect of the present disclosure to provide a user satisfaction survey apparatus, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the user satisfaction survey method according to the first aspect.
It is a further aspect of the present disclosure to provide a computer-readable storage medium having stored thereon a computer program for execution by a processor to implement the user satisfaction survey method according to the first aspect described above.
The technical effects of the user satisfaction investigation method, the device, the equipment and the computer readable storage medium provided by the disclosure are as follows:
the user satisfaction investigation method, the user satisfaction investigation device, the user satisfaction investigation equipment and the computer readable storage medium provided by the disclosure comprise the steps of determining a first questionnaire according to a preset index item, and obtaining a first investigation result according to the first questionnaire; determining a target attribute category corresponding to a preset index item according to the first investigation result; determining a target index item according to the attribute category, and determining a second questionnaire according to the target index item; obtaining a second survey result according to the second survey questionnaire; and determining a second attribute type corresponding to the target index item according to the second investigation result, and determining an importance degree adjustment coefficient of the target index item according to the determination result. The method, the device, the equipment and the computer readable storage medium provided by the disclosure can determine a target index item with a large user satisfaction degree based on a first questionnaire result, perform a second questionnaire survey based on the target index item to obtain a second survey result, arrange the second survey result, divide a finer second attribute category corresponding to a user feedback result, determine an importance adjustment coefficient of the target index item according to the second attribute category corresponding to the target index item, and further determine the influence of each target index item on the user satisfaction degree.
Drawings
FIG. 1 is a flow chart illustrating a user satisfaction survey method in accordance with an exemplary embodiment of the present invention;
FIG. 1A is a diagram illustrating the output of a kano model in accordance with an exemplary embodiment of the present invention;
FIG. 2 is a flowchart illustrating a user satisfaction survey method according to another exemplary embodiment of the present invention;
FIG. 2A is a schematic diagram illustrating a satisfaction factor before and after transformation in accordance with an exemplary embodiment of the present invention;
fig. 3 is a block diagram illustrating a user satisfaction survey apparatus according to an exemplary embodiment of the present invention;
fig. 4 is a block diagram illustrating a user satisfaction survey apparatus according to another exemplary embodiment of the present invention;
fig. 5 is a block diagram illustrating a user satisfaction survey apparatus according to an exemplary embodiment of the present invention.
Detailed Description
For the object-reaching platform, the functions provided by the platform influence the satisfaction degree of the user, specific functions can improve the satisfaction degree of the user, and specific functions which lead to poor satisfaction degree of the user need to be acquired based on a user survey mode, such as questionnaire survey, and the functions which can improve the satisfaction degree of the user are determined according to survey results.
Fig. 1 is a flowchart illustrating a user satisfaction survey method according to an exemplary embodiment of the present invention.
As shown in fig. 1, the user satisfaction survey method provided by the present embodiment includes:
In the method provided by this embodiment, some index items may be preset, and these index items may affect user experience, thereby affecting the satisfaction of the user.
Firstly, a customer satisfaction degree research hypothesis model can be constructed on the basis of an MUG model (the MUG model is a website evaluation model proposed by Microsoft according to market research and research, and comprises five major indexes of website content, website usability, promotion, website customization service and emotional factors) according to the characteristics of a B2C shopping website and from the perspective of user perception; specific preset index items can also be determined based on the research hypothesis model, for example, repeated and crossed index items can be eliminated.
The first questionnaire can also be designed according to the research hypothesis model, and research can be implemented by means of a relevant third-party platform or a paper-based scale to obtain research data.
Specifically, the first survey file may be referred to according to a KANO model, which is a useful tool for classifying and prioritizing user requirements invented by professor of the university of tokyo seikagaku koku, based on analyzing the influence of the user requirements on the user satisfaction, and which embodies a non-linear relationship between product performance and the user satisfaction. Positive and negative problems can be presented to the index items in the questionnaire, for example, the function A corresponding to the preset index item is added in the shopping platform, the customer satisfaction is unsatisfied, tolerable, general, and so on, and the function A corresponding to the preset index item is cancelled in the shopping platform, the customer satisfaction is unsatisfied, tolerable, general, and so on.
The questionnaire may be published in the network and the user may fill out the questionnaire, thereby returning the first survey result. A paper questionnaire can be printed to perform a survey on the street, and the first survey result can be obtained.
And 102, determining a target attribute type corresponding to the preset index item according to the first investigation result.
Further, the first survey results can be sorted, and the attitude of the user to each preset index item can be determined. For example, when most users consider that adding a function corresponding to a certain preset index item is satisfactory and canceling the function is unsatisfactory, the preset index item may be considered to be an expected attribute.
As shown in the following table, the following table may be set for each preset index item according to the reply result of the user, and the target attribute category of the preset index may be determined according to the table.
TABLE 1
Wherein, the probability can be filled in the form, and the specific numerical value can also be filled in the form. The probability is a ratio of the user state corresponding to a certain cell to the total users, for example, a total of 100 users are investigated, the number of users who like or do not like a certain cell is 10 as a result of feedback to one of the preset index items, and then 0.1 is filled in the lower left corner of the table. If the value is filled directly, the position of the lower left corner of the above-mentioned table is filled in 10.
Specifically, each cell may also have a corresponding attribute category, for example, for a preset index item, the attribute category having a high like preference or a low dislike preference may be a desired attribute. Specifically, it can be shown in the following table:
TABLE 2
Where A represents an attractive attribute, meaning a need that is not overly desirable by a customer. As for the charm-type demand, the customer satisfaction is sharply increased as the degree of satisfaction of the customer increases, but once satisfied, the satisfaction of the customer is very high even if the performance is not perfect. On the contrary, even when the expectation is not satisfied, the customer does not thus exhibit significant dissatisfaction.
M represents a mandatory property, which is a basic requirement of a customer for a product or service factor provided by an enterprise. Is an attribute or function that the customer considers the product "to have. When its characteristics are insufficient, the customer is dissatisfied; when the characteristics thereof are sufficient, the customer may not be satisfied thereby.
O represents a desired attribute, and means a demand in which the satisfaction of the customer is proportional to the satisfaction of the demand, and if such a demand is satisfied or performs well, the customer satisfaction significantly increases, and if such a demand is not satisfied or performs well, the customer dissatisfaction also significantly increases.
I represents a non-differentiated attribute, whether provided or not, that has no impact on the user experience. Are neither good nor bad aspects of quality, they do not lead to customer satisfaction or dissatisfaction.
R represents a reverse attribute, leading to strongly unsatisfactory quality characteristics and leading to low levels of satisfactory quality characteristics, since not all consumers have similar preferences. Many users do not have the requirement at all, the user satisfaction is reduced after the provision, and the provision degree is inversely proportional to the user satisfaction degree.
Q represents a suspicious result, which is a result that should not exist normally, for example, for a preset index item, it is impossible to have the index, and the user does not like the index, and therefore, it can be considered that the situation is a user upset or wrong answer.
Specifically, for the same preset index item, the probabilities or numerical values belonging to the same type of attribute may be superimposed, so as to calculate the parameter corresponding to the same attribute type, and then determine the attribute type with the largest parameter as the target attribute type corresponding to the preset index item.
Further, if the probability values of some index items are relatively similar, the attribute of some index items is determined to be inaccurate directly based on the maximum value, at this time, the preset index items can be clustered according to the first investigation result, the approximate index most similar to the preset index item is determined, and the category to which the approximate index belongs is determined as the category of the preset index item. The preset index items are clustered based on the investigation result, namely clustering is performed based on attitudes fed back by the users to the index items, so that attitudes of the users to the index items are similar if the two index items are similar, and therefore the users can be considered to belong to the same category.
Fig. 1A is a schematic diagram of an output result of a kano model according to an exemplary embodiment of the present invention.
As shown in fig. 1A, charm requirements and requisite requirements have a large impact on user satisfaction. Therefore, preset index items belonging to the charm attribute (a), the desired attribute (O), and the requisite attribute (M) may be determined as the target index items. And relating to a second questionnaire based on the target indicator item. The second questionnaire is designed in a similar manner to the first questionnaire.
And 104, determining a second attribute type corresponding to the target index item according to the second investigation result, and determining an importance adjustment coefficient of the target index item according to the second attribute type corresponding to the target index item.
The second survey results can be collated to obtain the results shown in table 1. A probability value or numerical value may be filled in to indicate the number of users belonging to each cell.
Specifically, since the questionnaire is a preset index item for the charm attribute, the required attribute, and the desired attribute, it can be considered that most users in the survey result are in the three cells.
Further, as can be seen from fig. 1A, the relationship between the charm attribute, the essential attribute and the satisfaction is non-linear, and the change of the satisfaction of the user after the adjustment of the preset index item corresponding to these attributes cannot be directly calculated, so that the charm attribute and the essential attribute in the second investigation result can be subdivided to obtain the second attribute category, and the importance adjustment coefficient of the target index item is obtained based on the subdivision result. The higher the importance degree adjustment coefficient is, the greater the influence of the target index item on the satisfaction degree of the user is, so that the target index item can be preferentially adjusted, and the satisfaction degree of the user is improved.
In practical application, the charm attribute can be set as A1、A2、A3With mandatory attribute set to M1、M2、M3Three levels. Specifically, the corresponding relationship between the attitude of the user to the target index item and the attribute category may be determined according to table 3.
TABLE 3
Based on the step, the attribute categories can be further subdivided, so that the accuracy of determining the index item classification is improved.
Wherein A can be aimed at each index item1And A2Calculating an adjustment factor, which can be considered as when the category of the preset index item is from A1Is adjusted to be A2When the satisfaction degree changes, A for each index item can be calculated1And A3And calculating an adjusting coefficient, and determining the integral importance adjusting coefficient according to the two adjusting coefficients. The complete adjustment factor may include A1Is adjusted to be A2When, A2Is adjusted to be A3The adjustment factor of time.
The method provided by the present embodiment is used for investigating the satisfaction degree of a user, and is executed by a device provided with the method provided by the present embodiment, and the device is generally implemented in a hardware and/or software manner.
The user satisfaction survey method provided by the embodiment comprises the steps of determining a first questionnaire according to a preset index item, and obtaining a first survey result according to the first questionnaire; determining a target attribute category corresponding to a preset index item according to the first investigation result; determining a target index item according to the attribute category, and determining a second questionnaire according to the target index item; obtaining a second survey result according to the second survey questionnaire; and determining a second attribute type corresponding to the target index item according to the second investigation result, and determining an importance degree adjustment coefficient of the target index item according to the determination result. The method provided by this embodiment can determine the target index item with a large degree of satisfaction for the user based on the first questionnaire result, perform the second questionnaire survey based on the target index item to obtain a second survey result, sort the second survey result, divide a finer second attribute category corresponding to the user feedback result, determine the importance adjustment coefficient of the target index item according to the second attribute category corresponding to the target index item, and further determine the influence of each target index item on the degree of satisfaction of the user.
Fig. 2 is a flowchart illustrating a user satisfaction survey method according to another exemplary embodiment of the present invention.
As shown in fig. 2, the method for investigating user satisfaction provided by this embodiment includes:
The first questionnaire comprises a plurality of satisfaction degree options, so that the investigated user can select the satisfaction degree corresponding to the preset index item from the satisfaction degree options.
Specifically, the first questionnaire determined based on the Kano model includes positive questions and negative questions. The form of the first questionnaire can be as shown in the following table:
the above table may be set for each preset index item, thereby forming a first questionnaire including each preset index item. The investigated user can check the satisfaction degree option in the table, and for the same preset index item, two satisfaction degree evaluation information of each user can be obtained, wherein one is the satisfaction degree of the user with the function, and the other is the satisfaction degree of the user without the function. Based on the satisfaction information of the two dimensions, the influence of the preset index item on the user satisfaction can be more accurately determined.
Further, the manner of determining the preset index item is similar to that in step 101, and is not described again.
The first questionnaire can be issued in the form of a paper questionnaire and/or a web questionnaire, and the feedback results of the user on the questionnaire are collected to obtain the first survey results.
In practical application, a first corresponding relationship may be preset, where the first corresponding relationship refers to a corresponding relationship between the satisfaction degree option and the attribute category. The first correspondence relationship may be as shown in the following table
For a user, the attribute category of a preset index item for the user may be determined based on the first corresponding relationship, for example, a certain preset index item is a necessary attribute for the user a, and may be a desired attribute for the user b.
The investigation results of the same preset index item may vary from person to person, and therefore, a large number of users need to be investigated, and the index item capable of improving the satisfaction of most users is determined based on the investigation results.
And obtaining which attribute type the preset index item belongs to for each user according to the first survey result and the first corresponding relation. Specifically, the corresponding cell can be found in the table above according to the first survey result, and the attribute category in the cell is used as the attribute category corresponding to the user. For example, one preset index item is charm attribute, charm and requisite attribute for five users.
The scheme provided by this embodiment is to obtain the influence of the preset index item on the satisfaction according to the user feedback information, and therefore, the final target attribute category of the preset index can be determined according to the attribute category to which the preset index item belongs for each user. For example, if a predetermined indicator is an attractive attribute for most users, the predetermined indicator may be considered to be an attractive attribute.
Further, in order to accurately determine the influence of the preset index on the user, a probability value that the preset index item belongs to each attribute category may be determined according to the number of users corresponding to each attribute category, and specifically, a ratio of the number of users corresponding to each attribute category to the total number of survey users may be used as the probability value that the preset index item belongs to the attribute category. For example, if 5 users are investigated, and a preset index item is charm for 4 users and is a requisite attribute for 1 user, the probability that the preset index item belongs to the charm is 80% and the probability that the preset index item belongs to the requisite attribute is 20%.
In practical application, classification can be performed according to the membership degree of each index item by adopting the principle of the maximum membership degree, namely, the attribute class with the maximum probability value is determined as the attribute class of the preset index item. However, when the probability values of two attribute categories of the preset index items are close, the result may be inaccurate by directly adopting the maximum membership principle, for example, the probability value of a charm attribute of a certain preset index item is 47%, the probability value of a necessary attribute is 45%, if the number of survey people is small, the result fed back by one user may cause the condition that the attribute categories of the preset index item are different, and in this condition, if some users do not fill in the questionnaire carefully, the problem of result error may be directly caused.
Therefore, the method provided by this embodiment further determines the first parameter and the second parameter according to the probability value, and determines the attribute category to which the preset index item belongs based on the first parameter and the second parameter.
In the method provided in this embodiment, the attribute categories may specifically include: charm attribute, expected attribute, mandatory attribute, indifferent attribute, reverse attribute, suspicious result.
Determining the first parameter and the second parameter from the probability value may include:
and determining charm attributes, expected attributes, requisite attributes, non-difference attributes, reverse attributes and total probability sum corresponding to suspicious results corresponding to the preset index items.
Specifically, the user satisfaction result corresponding to the preset index item may be counted according to a form of a table, and the probability values of the preset index item belonging to each attribute category are determined according to the table, for example, the investigation result corresponding to a certain preset index item may be:
it can be seen that the probability value that the attitude of the user with a certain preset index item is very much liked and the attitude without the preset index item is very much disliked is 28.8%. The probability value of the preset index item belonging to each attribute category can be determined according to the first corresponding relation, wherein the charm attribute is 36.7%, the expected attribute is 28.8%, the mandatory attribute is 2.9%, the non-difference attribute is 21.6%, the reverse attribute is 0.7%, and the suspicious result is 9.4%.
The probability values of each attribute category may be added to obtain a total probability sum, that is, the probability values are superimposed to obtain a total probability sum of 100.1%.
And determining a first probability sum corresponding to the requisite attribute, the expected attribute and the charm attribute corresponding to the preset index item.
Wherein, the first probability sum can be continuously calculated, the first probability sum refers to the sum of probability values corresponding to the requisite attribute, the expected attribute and the charm attribute, and the first probability sum can be 68.4%.
And determining the maximum value and the minimum value in the probability values corresponding to the preset index items, and determining the difference value between the maximum value and the minimum value, wherein in the above example, the difference value is 36%.
And determining the ratio of the first probability sum to the total probability sum as a first parameter, and determining the ratio of the difference to the total probability sum as a second parameter.
Specifically, a ratio of the first probability to the sum of the total probabilities, i.e., a ratio of 68.3% to 100.1%, may be calculated as the first parameter. The ratio of the difference to the sum of the total probabilities, i.e. 35.96% for 36% to 100.1%, can also be calculated as the second parameter.
Further, the first parameter may be used to represent an influence parameter of the preset index item on the improvement of the user satisfaction, and the higher the first parameter is, the higher the user's requirement on the preset index item is. The second parameter may be used to indicate an average degree of the preset index items belonging to each attribute category, and the lower the second parameter value, the more average the probability value of the preset index items belonging to each attribute category is.
In practical application, if the first parameter is greater than or equal to a first preset value and the second parameter is less than or equal to a second preset value, determining the preset index item as an index item to be determined. The first preset value and the second preset value may be preset, for example, the first preset value may be 60%, and the second preset value may be 6%. If the first parameter is greater than or equal to the first preset value, the function corresponding to the preset index item is considered to be set, the satisfaction degree of a user can be improved, if the second parameter is less than or equal to the second preset value, the average degree of the preset index item belonging to each attribute category can be considered, if the two conditions are met simultaneously, the probability values corresponding to the attribute categories of the preset index item can be considered to be very close, a small number of user investigation results can change the finally determined attribute category, and at the moment, the preset index item can be considered to possibly belong to the attribute category with the maximum probability value and possibly belong to the attribute category with the second highest probability value. At this time, the preset index item may be determined as the index item to be determined.
If the predetermined index is not the to-be-determined index, go to step 206.
And step 206, determining the attribute category corresponding to the maximum probability value as a target attribute category corresponding to the preset index item.
If the preset index item is not the index item to be determined, the target attribute category corresponding to the index item can be determined directly by adopting the maximum membership degree principle.
If the preset index is the index to be determined, step 207 is executed.
And step 207, clustering the preset index items according to the first investigation result, and determining similar index items which belong to the same category as the index items to be determined.
The scheme provided by this embodiment is that the attribute categories determined according to the satisfaction survey results of the user on the preset index items are determined by the satisfaction of the user, and the attribute categories of the preset index items are determined by the satisfaction of the user, so that the preset index items can be clustered according to the first survey results, and the attribute categories of the index items belonging to the same category are also the same. And determining similar index items belonging to the same category as the index items to be determined according to the clustering result.
Specifically, the score corresponding to each preset index item by the surveyed user can be determined according to the satisfaction degree option. The attribute category to which the index item belongs to the user can be determined according to the investigation result of the user on the preset index item, and then the score value can be determined according to the attribute category, for example, the charm attribute can be 5 points, the necessary attribute can be 4 points, the expected attribute can be 3 points, and the like. For the ith surveyed user, the jth preset index can be used as aijA score corresponding to the preset index item is represented, and if m users are included, the score corresponding to the preset index item can be a1j…aij…amj。
Further, an average score corresponding to each preset index item is determined according to the score. The scores corresponding to the same preset index item may be superimposed, and then divided by the number of scores to calculate an average score, for example, a may be calculated1jTo amjOverlapping, dividing by m to obtain average score
And determining a middle parameter value corresponding to each index item according to the score and the average score. The mean variance value between the scores of the m index items and the average score of the index items can be calculated to obtain the intermediate parameter values corresponding to the m index items, for example, the mean variance value can be calculated
And determining the calculation result as an intermediate parameter value corresponding to the index item.
And in actual application, determining a correlation matrix of the preset index according to the intermediate parameter value corresponding to each index item. First of all, can be according toThe intermediate parameter value determines a parameter of the preset index item, and specifically, an average value of the intermediate parameter of the preset index item can be calculated to obtain the parameter of the preset index item, for example, calculating
And after the values are obtained, the values are superposed and then are divided by m to obtain the parameters of the preset index items. The relationship matrix R may be constructed according to the parameter of each preset index item. Assuming that n indexes are in total, the parameters a of n preset index items can be obtained1、a2…aj…an. Wherein, the parameter in the matrix R can be a relation coefficient R between index itemsij，Rij＝ai-aj. The number of rows and columns of the correlation matrix is equal to the number of terms of the preset index items, and if n preset index items are included in total, then R should be an n × n matrix.
And determining similar index items belonging to the same category as the index items to be determined according to the numerical values in the correlation matrix. Since the values in the matrix are the coefficients of the relationship between the index terms, RijThe coefficient value is the coefficient value between the ith preset index item and the jth preset index item, so that similar index items can be determined according to the coefficient value.
Specifically, the maximum element R that can be found by the maximum element method among the off-diagonal elements in the correlation coefficient matrix RijThe index items of the located rows and columns are gathered into a new category. And calculating the correlation coefficient between the new class and other index items according to a minimum method. Suppose u1,u2Poly into a new class, then Ri,12＝min(Ri,1,Ri,2). And judging the correlation coefficient of the mixed index and the non-mixed index, and determining the attribute classification of the mixed index.
And step 208, determining the target attribute category corresponding to the similar index item as the target attribute category corresponding to the index item to be determined.
Further, if the two index categories are similar, the target attribute category corresponding to the similar index item can be determined as the target attribute category corresponding to the index item to be determined. The similar index item is not the index item to be determined, namely the attribute category of the similar index item can be determined by adopting the maximum membership degree principle.
Because the charm attribute, the expected attribute and the necessary attribute have great influence on the satisfaction coefficient of the user, the preset index items of the three types of attributes can be focused, and the three types of preset index items can be determined as target index items.
The second questionnaire comprises a plurality of satisfaction degree options, so that the investigated user can select the satisfaction degree corresponding to the target index item from the satisfaction degree options.
The second questionnaire is determined in a similar manner to the first questionnaire except that the index items are included differently. Of course, the second questionnaire may be specified by directly using the content corresponding to the target index item in the first questionnaire.
The second survey result can be selected from the first survey result according to the second survey questionnaire.
In the scheme provided by the embodiment, in order to more finely determine the satisfaction influence of the target index item on the user, the attribute categories are adjusted, so that the attribute categories are richer. The adjusted attribute category is a second attribute category which comprises charm attribute first level, charm attribute second level, charm attribute third level, expected attribute, essential attribute first level, essential attribute second level, essential attribute third level, non-difference attribute, reverse attribute and suspicious result. The second correspondence of the satisfaction option to the second attribute category may be as shown in the following table:
the influence of the charm attribute level one, the charm attribute level two and the charm attribute level three on the user satisfaction is gradually weakened, and the influence of the requisite attribute level one, the requisite attribute level two and the requisite attribute level three on the user satisfaction is gradually weakened.
And 212, determining the probability value of the target index item belonging to each second attribute category according to the second attribute category of the target index item for each surveyed user.
Specifically, the second survey results may be sorted, and a cell corresponding to the feedback of each user to the target index item in the above table is determined, so as to determine, for each user, a probability value that the target index item belongs to each second attribute category.
And step 213, determining a first satisfaction of the current state of the target index item and a second satisfaction after the target index item is adjusted according to the probability value.
The current state of the target index item refers to a current setting condition of the target index item in a product or a service, and for example, the target index item does not have a certain function. The adjusted state of the target index item means that the function is adjusted, for example, the function is added. Satisfaction results of the two states can be determined separately based on the determined probability values.
The initial customer satisfaction and the initial perception satisfaction can be respectively set as S0And P0The adjusted satisfaction degrees are respectively S1And P1These parameters can be derived from probability values, where S0＝cP0 k，S1＝cP1 k(c is a constant), it is possible to obtain:
let IRadjFor adjusted second satisfaction, IR0For the purpose of the first degree of satisfaction initially,then it is possible to obtain:
IRadj＝(IR0)1/k
and 214, converting to obtain a linear formula according to a preset relation among the first satisfaction degree, the second satisfaction degree and the satisfaction degree coefficient of the target index item.
And step 215, determining the importance degree adjustment coefficient of the target index item according to a linear formula.
According to IRadj＝(IR0)1/kThe k value can be obtained. And then, converting the formula to obtain a linear formula, wherein the charm attribute is taken as an example:
let the importance adjustment coefficient K be equal to 1/K, which can be obtained according to the above formula:
Ln(Radj)＝KLn(IR0)
let X equal Ln (IR)0)，Y＝Ln(IRadj) Obtaining a linear conversion formula: y ═ KX.
Fig. 2A is a schematic diagram illustrating the satisfaction factor before and after transformation in accordance with an exemplary embodiment of the present invention.
As shown in fig. 2A, before transformation, the first satisfaction degree and the second satisfaction degree are in a non-linear relationship, and after transformation, the first satisfaction degree and the second satisfaction degree are in a linear relationship. K, K + a and K + a + b in the figure are the importance adjustment coefficients of charm three-level, charm two-level and charm one-level in sequence.
Wherein K, a and b can be obtained based on the scale survey of the satisfaction degree.
In addition, classification method according to subdivision attribute, and classification of charm attribute including subdivision are combined to form three-level (A)3) Charm attribute two (A)2) And charm attribute level (A)3) The satisfaction degree promotion amplitude is the same, so that the following results can be obtained:
converting the formula to obtain
Therefore, it is also possible to determine K, a and calculate b.
The attribute category of the target index item is from A1Is adjusted to be A2The importance degree adjustment coefficient is a, and the attribute category of the target index item is selected from A2Is adjusted to be A3The importance adjustment coefficient is b. Correspondingly, the importance degree adjustment coefficients of the attribute types of the target index items during adjustment among M1 (essential attribute level one), M2 (essential attribute level two) and M3 (essential attribute level three) can be calculated. Finally, the adjustment coefficients can be sequenced, so that the target index item which has the greatest influence on the satisfaction degree of the user is determined.
Fig. 3 is a block diagram illustrating a user satisfaction survey apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 3, the user satisfaction survey device provided by the present embodiment includes:
the first survey module 31 is configured to determine a first survey questionnaire according to a preset index item, and obtain a first survey result according to the first survey questionnaire;
a first determining module 32, configured to determine, according to the first investigation result, a target attribute category corresponding to the preset indicator;
a second determining module 33, configured to determine a target index item according to the attribute category, and determine a second questionnaire according to the target index item;
a second survey module 34, configured to obtain a second survey result according to the second survey questionnaire;
the coefficient determining module 35 is configured to determine a second attribute category corresponding to the target indicator item according to the second investigation result, and determine an importance adjustment coefficient of the target indicator item according to the second attribute category corresponding to the target indicator item.
The user satisfaction survey device provided by the embodiment comprises: the first survey module is used for determining a first survey questionnaire according to a preset index item and obtaining a first survey result according to the first survey questionnaire; the first determining module is used for determining a target attribute category corresponding to the preset index item according to the first investigation result; the second determination module is used for determining a target index item according to the attribute category and determining a second questionnaire according to the target index item; the second investigation module is used for obtaining a second investigation result according to a second questionnaire; and the coefficient determining module is used for determining a second attribute category corresponding to the target index item according to the second investigation result and determining the importance adjusting coefficient of the target index item according to the second attribute category corresponding to the target index item. The device provided by this embodiment can determine a target index item with a large degree of satisfaction with a user based on a first questionnaire result, perform a second questionnaire survey based on the target index item to obtain a second survey result, sort the second survey result, divide a second finer attribute category corresponding to a user feedback result, determine an importance adjustment coefficient of the target index item according to the second attribute category corresponding to the target index item, and further determine the influence of each target index item on the degree of satisfaction of the user.
The specific principle and implementation of the user satisfaction survey device provided by this embodiment are similar to those of the embodiment shown in fig. 1, and are not described herein again.
Fig. 4 is a block diagram illustrating a user satisfaction survey apparatus according to another exemplary embodiment of the present invention.
As shown in fig. 4, on the basis of the foregoing embodiment, in the user satisfaction survey device provided in this embodiment, the first survey module 31 is specifically configured to:
determining the first questionnaire comprising the preset index items based on a Kano model;
the first questionnaire comprises a plurality of satisfaction degree options, so that the investigated user can select the satisfaction degree corresponding to the preset index item from the satisfaction degree options.
The first determining module 32 is specifically configured to:
acquiring a first preset corresponding relation between the satisfaction degree option and the attribute category;
determining a probability value of the preset index item belonging to each attribute category according to the first investigation result and the first corresponding relation;
determining a first parameter and a second parameter according to the probability value;
and determining whether the preset index item is an index item to be determined according to the first parameter and the second parameter, and if not, determining the attribute category corresponding to the maximum probability value as the target attribute category corresponding to the preset index item.
If it is determined that the preset index item is an index item to be determined, the apparatus further includes a third determining module 36, configured to:
clustering the preset index items according to the first investigation result, and determining similar index items which belong to the same category as the index items to be determined;
and determining the target attribute category corresponding to the similar index item as the target attribute category corresponding to the index item to be determined.
The third determining module 36 is specifically configured to:
determining a score corresponding to each preset index item by the investigated user according to the satisfaction degree option;
determining an average score corresponding to each preset index item according to the score, and determining a middle parameter value corresponding to each index item according to the score and the average score;
determining a correlation matrix of the preset index according to the intermediate parameter value corresponding to each index item;
determining similar index items belonging to the same category as the index items to be determined according to the numerical values in the correlation matrix;
and the number of rows and the number of columns of the correlation matrix are equal to the number of terms of the preset index terms.
The attribute categories include: charm attribute, expected attribute, mandatory attribute, indifferent attribute, reverse attribute and suspicious result;
the first determining module 32 is specifically configured to:
determining the charm attribute, the expected attribute, the required attribute, the non-difference attribute, the reverse attribute and the total probability sum corresponding to the suspicious result corresponding to the preset index item;
determining a first probability sum corresponding to the requisite attribute, the expected attribute and the charm attribute corresponding to the preset index item;
determining a maximum value and a minimum value in the probability values corresponding to the preset index items, and determining a difference value between the maximum value and the minimum value;
determining a ratio of the first probability sum to the total probability sum as the first parameter, and determining a ratio of the difference to the total probability sum as the second parameter.
The first determining module 32 is specifically configured to:
and if the first parameter is greater than or equal to a first preset value and the second parameter is less than or equal to a second preset value, determining the preset index item as an index item to be determined.
The determining of the target index item according to the attribute category includes:
determining the preset index items of which attribute categories are the charm attribute, the desired attribute, and the requisite attribute as the target index items.
The second determining module 33 is specifically configured to:
determining the second questionnaire comprising the target indicator item based on a Kano model;
the second questionnaire comprises a plurality of satisfaction degree options, so that the investigated users select the satisfaction degree corresponding to the target index item from the satisfaction degree options.
The coefficient determining module 35 is specifically configured to:
acquiring a preset second corresponding relation between the satisfaction degree option and a second attribute category;
and determining a second attribute category of the target index item for each investigated user according to the second investigation result and the second corresponding relation.
The coefficient determining module 35 is specifically configured to:
determining a probability value of each second attribute category to which the target index item belongs according to the second attribute category to which the target index item belongs for each investigated user;
determining a first satisfaction degree of the current state of the target index item and a second satisfaction degree of the target index item after adjustment according to the probability value;
converting to obtain a linear formula according to a preset relation among the first satisfaction degree, the second satisfaction degree and a satisfaction degree coefficient of the target index item;
and determining the importance degree adjustment coefficient of the target index item according to the linear formula.
The second attribute category includes:
charm attribute level one, charm attribute level two, charm attribute level three, expectation attribute level one, mandatory attribute level two, mandatory attribute level three, nondifferential attribute, reverse attribute, suspicious results.
The specific principle and implementation of the user satisfaction survey device provided by this embodiment are similar to those of the embodiment shown in fig. 2, and are not described herein again.
Fig. 5 is a block diagram illustrating a user satisfaction survey apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 5, the user satisfaction survey apparatus provided by the present embodiment includes:
a memory 51;
a processor 52; and
a computer program;
wherein the computer program is stored in the memory 51 and configured to be executed by the processor 52 to implement any of the user satisfaction survey methods described above.
The present embodiment also provides a computer-readable storage medium, which is executed by a processor to implement any of the user satisfaction survey methods described above.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (15)
1. A user satisfaction survey method, comprising:
determining a first questionnaire according to a preset index item, and obtaining a first survey result according to the first questionnaire;
determining a target attribute category corresponding to the preset index item according to the first investigation result;
determining a target index item according to the attribute category, and determining a second questionnaire according to the target index item;
obtaining a second survey result according to the second questionnaire;
and determining a second attribute type corresponding to the target index item according to the second investigation result, and determining an importance adjustment coefficient of the target index item according to the second attribute type corresponding to the target index item.
2. The method according to claim 1, wherein the determining a first questionnaire according to a preset index item comprises:
determining the first questionnaire comprising the preset index items based on a Kano model;
the first questionnaire comprises a plurality of satisfaction degree options, so that the investigated user can select the satisfaction degree corresponding to the preset index item from the satisfaction degree options.
3. The method according to claim 2, wherein the determining the target attribute category corresponding to the preset index item according to the first survey result includes:
acquiring a first preset corresponding relation between the satisfaction degree option and the attribute category;
determining a probability value of the preset index item belonging to each attribute category according to the first investigation result and the first corresponding relation;
determining a first parameter and a second parameter according to the probability value;
and determining whether the preset index item is an index item to be determined according to the first parameter and the second parameter, and if not, determining the attribute category corresponding to the maximum probability value as the target attribute category corresponding to the preset index item.
4. The method according to claim 3, wherein if the preset index is determined as the index to be determined, the method further comprises:
clustering the preset index items according to the first investigation result, and determining similar index items which belong to the same category as the index items to be determined;
and determining the target attribute category corresponding to the similar index item as the target attribute category corresponding to the index item to be determined.
5. The method according to claim 4, wherein the clustering the preset index items to determine similar index items belonging to the same category as the index item to be determined comprises:
determining a score corresponding to each preset index item by the investigated user according to the satisfaction degree option;
determining an average score corresponding to each preset index item according to the score, and determining a middle parameter value corresponding to each index item according to the score and the average score;
determining a correlation matrix of the preset index according to the intermediate parameter value corresponding to each index item;
determining similar index items belonging to the same category as the index items to be determined according to the numerical values in the correlation matrix;
and the number of rows and the number of columns of the correlation matrix are equal to the number of terms of the preset index terms.
6. The method of any of claims 3-5, wherein the attribute categories include: charm attribute, expected attribute, mandatory attribute, indifferent attribute, reverse attribute and suspicious result;
determining the first parameter and the second parameter according to the probability value comprises:
determining the charm attribute, the expected attribute, the required attribute, the non-difference attribute, the reverse attribute and the total probability sum corresponding to the suspicious result corresponding to the preset index item;
determining a first probability sum corresponding to the requisite attribute, the expected attribute and the charm attribute corresponding to the preset index item;
determining a maximum value and a minimum value in the probability values corresponding to the preset index items, and determining a difference value between the maximum value and the minimum value;
determining a ratio of the first probability sum to the total probability sum as the first parameter, and determining a ratio of the difference to the total probability sum as the second parameter.
7. The method according to claim 6, wherein the determining whether the preset index item is an index item to be determined according to the first parameter and the second parameter comprises:
and if the first parameter is greater than or equal to a first preset value and the second parameter is less than or equal to a second preset value, determining the preset index item as an index item to be determined.
8. The method of claim 7, wherein the determining a target metric item according to the attribute category comprises:
determining the preset index items of which the target attribute category is the charm attribute, the desired attribute, and the requisite attribute as the target index items.
9. The method of claim 1, wherein determining a second questionnaire based on the target metric term comprises:
determining the second questionnaire comprising the target indicator item based on a Kano model;
the second questionnaire comprises a plurality of satisfaction degree options, so that the investigated users select the satisfaction degree corresponding to the target index item from the satisfaction degree options.
10. The method according to claim 1, wherein the determining, according to the second survey result, a second attribute category corresponding to the target index item includes:
acquiring a preset second corresponding relation between the satisfaction degree option and a second attribute category;
and determining a second attribute category of the target index item for each investigated user according to the second investigation result and the second corresponding relation.
11. The method according to claim 10, wherein the determining the importance degree adjustment coefficient of the target index item according to the second attribute category corresponding to the target index item includes:
determining a probability value of each second attribute category to which the target index item belongs according to the second attribute category to which the target index item belongs for each investigated user;
determining a first satisfaction degree of the current state of the target index item and a second satisfaction degree of the target index item after adjustment according to the probability value;
converting to obtain a linear formula according to a preset relation among the first satisfaction degree, the second satisfaction degree and a satisfaction degree coefficient of the target index item;
and determining the importance degree adjustment coefficient of the target index item according to the linear formula.
12. The method according to claim 10 or 11, wherein the second attribute category comprises:
charm attribute level one, charm attribute level two, charm attribute level three, expectation attribute level one, mandatory attribute level two, mandatory attribute level three, nondifferential attribute, reverse attribute, suspicious results.
13. A user satisfaction survey apparatus, comprising:
the first survey module is used for determining a first survey questionnaire according to a preset index item and obtaining a first survey result according to the first survey questionnaire;
the first determining module is used for determining the target attribute category corresponding to the preset index item according to the first investigation result;
the second determination module is used for determining a target index item according to the attribute category and determining a second questionnaire according to the target index item;
the second investigation module is used for obtaining a second investigation result according to the second questionnaire;
and the coefficient determining module is used for determining a second attribute category corresponding to the target index item according to the second investigation result, and determining an importance adjusting coefficient of the target index item according to the second attribute category corresponding to the target index item.
14. A user satisfaction survey apparatus, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of claims 1-13.
15. A computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement the method of any one of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811440581.5A CN111242660A (en) | 2018-11-29 | 2018-11-29 | User satisfaction investigation method, device, equipment and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811440581.5A CN111242660A (en) | 2018-11-29 | 2018-11-29 | User satisfaction investigation method, device, equipment and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111242660A true CN111242660A (en) | 2020-06-05 |
Family
ID=70863779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811440581.5A Pending CN111242660A (en) | 2018-11-29 | 2018-11-29 | User satisfaction investigation method, device, equipment and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242660A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837514A (en) * | 2020-06-24 | 2021-12-24 | 中国移动通信集团重庆有限公司 | User satisfaction evaluation method and device, computing device and storage medium |
| CN114493636A (en) * | 2022-01-26 | 2022-05-13 | 恒安嘉新（北京）科技股份公司 | User satisfaction determining method and device, electronic equipment and storage medium |
-
2018
- 2018-11-29 CN CN201811440581.5A patent/CN111242660A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837514A (en) * | 2020-06-24 | 2021-12-24 | 中国移动通信集团重庆有限公司 | User satisfaction evaluation method and device, computing device and storage medium |
| CN114493636A (en) * | 2022-01-26 | 2022-05-13 | 恒安嘉新（北京）科技股份公司 | User satisfaction determining method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10949909B2 (en) | Optimized recommendation engine | |
| US20120109714A1 (en) | Confidence Based Selection for Survey Sampling | |
| Ennew et al. | Importance-performance analysis and the measurement of service quality | |
| Ahituv | A systematic approach toward assessing the value of an information system | |
| US8738436B2 (en) | Click through rate prediction system and method | |
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| CN110866782A (en) | Customer classification method and system and electronic equipment | |
| JP2018077615A (en) | Advertising image generation device, advertising image generation method and program for advertising image generation device | |
| CN109636467A (en) | A kind of comprehensive estimation method and system of the internet digital asset of brand | |
| CN109657962A (en) | A kind of appraisal procedure and system of the volume assets of brand | |
| CN110659926A (en) | Data value evaluation system and method | |
| US7596545B1 (en) | Automated data entry system | |
| CN111242660A (en) | User satisfaction investigation method, device, equipment and computer-readable storage medium | |
| CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
| CN116911962A (en) | Article selecting device and method based on data model | |
| CN109190040B (en) | Collaborative evolution-based personalized recommendation method and device | |
| CN114782123A (en) | Credit assessment method and system | |
| Rahmanita et al. | Model multi criteria decision making with fuzzy ANP method for performance measurement small medium enterprise (SME) | |
| US20220114624A1 (en) | Digital Content Text Processing and Review Techniques | |
| CN111598660A (en) | Computer screening device and method for screening suppliers and storage medium | |
| US10210530B1 (en) | Selecting a report | |
| Daneshmandi et al. | A hybrid data mining model to improve customer response modeling in direct marketing | |
| CN115713441A (en) | Teaching quality evaluation method and system based on AHP-Fuzzy algorithm and neural network | |
| CN111209484B (en) | Product data pushing method, device, equipment and medium based on big data | |
| Toruan et al. | Enhancing Gaming Performance: A Recommender System for Selecting Optimal Gaming Headsets Based on SAW Method |
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 |