CN117911085B - User management system, method and terminal based on enterprise marketing - Google Patents
User management system, method and terminal based on enterprise marketing Download PDFInfo
- Publication number
- CN117911085B CN117911085B CN202410303185.7A CN202410303185A CN117911085B CN 117911085 B CN117911085 B CN 117911085B CN 202410303185 A CN202410303185 A CN 202410303185A CN 117911085 B CN117911085 B CN 117911085B
- Authority
- CN
- China
- Prior art keywords
- user
- marketing
- user information
- key features
- parameter
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000006399 behavior Effects 0.000 claims abstract description 68
- 238000006243 chemical reaction Methods 0.000 claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims description 71
- 230000000875 corresponding effect Effects 0.000 claims description 56
- 238000012216 screening Methods 0.000 claims description 51
- 230000006870 function Effects 0.000 claims description 31
- 238000007726 management method Methods 0.000 claims description 26
- 238000007621 cluster analysis Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
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
- G06Q30/0204—Market segmentation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of enterprise user management, and particularly relates to a user management system, method and terminal based on enterprise marketing. According to the method and the system for the marketing push of the enterprise, through monitoring of the user behaviors, the users can be classified into a plurality of grades and a plurality of user groups, so that the enterprise can more accurately understand the user demands, the enterprise is helped to formulate marketing push contents adapting to all the user groups, the marketing efficiency of the enterprise is improved, and after each marketing push is finished, the user grades are dynamically adjusted according to the conversion rate, the participation rate, the user grades and the like of the users, so that the division of the user groups is continuously optimized, the marketing push is more accurate and effective, the enterprise can better adapt to market changes and the user demands, and continuous user growth and service expansion are realized.
Description
Technical Field
The invention belongs to the technical field of enterprise user management, and particularly relates to a user management system, method and terminal based on enterprise marketing.
Background
User management is one of key factors for enterprises to acquire market advantages, and with the development of technologies such as big data, cloud computing and artificial intelligence, enterprises have more means and possibilities to understand and manage users, and the application of the technologies enables the enterprises to extract valuable information from massive user data, so that the enterprises can better position users, and personalized marketing strategies are realized according to behavior information of the users.
The traditional user management method mainly focuses on the collection and storage of user information, and lacks the capability of deeply analyzing user behaviors and demands, so that a marketing campaign cannot accurately locate a target user group, the marketing efficiency and effect are reduced, meanwhile, after the content of each marketing is released, a period of time is needed to count feedback of users, the marketing content is regulated according to the feedback of the users, but the marketing is finished, the interests of the users to products are correspondingly changed, and at the moment, the original user location is still used for formulating the optimization of the marketing content, which is obviously not preferable.
Disclosure of Invention
The invention aims to provide a user management system, a method and a terminal based on enterprise marketing, which can dynamically adjust the user grade after marketing pushing, and ensure that the adjustment of the subsequent marketing content is more accurate.
The technical scheme adopted by the invention is as follows:
A user management method based on enterprise marketing, comprising:
acquiring user data, and preprocessing the user data to obtain first user information;
Acquiring screening conditions, screening the first user information according to the screening conditions, and calibrating the screened first user information as second user information;
extracting the characteristics of the second user information to obtain key characteristics and non-key characteristics, and classifying the users in multiple stages according to the key characteristics and the non-key characteristics;
Performing cluster analysis on the second user information to obtain a plurality of user groups and user portraits of the user groups;
and executing marketing pushing according to the user portrait, counting the user conversion rate and the user participation rate after the marketing pushing in real time, outputting a marketing score according to the user conversion rate, the user participation rate and the user grade, and adjusting the user grade according to the marketing score.
In a preferred embodiment, the step of obtaining the user data and preprocessing the user data to obtain the first user information includes:
Constructing a monitoring period, and counting all user data in the monitoring period;
Cleaning, denoising and filling missing values to the user data to obtain front data;
And carrying out format conversion on the preamble data, and calibrating the preamble data after format conversion as first user information.
In a preferred embodiment, the step of obtaining the screening condition, performing screening processing on the first user information according to the screening condition, and calibrating the screened first user information as the second user information includes:
Acquiring first user information in the monitoring period;
obtaining user screening conditions, wherein the screening conditions comprise a lower limit of user activity, a lower limit of purchase frequency and a lower limit of browsing time;
Screening the first user information in the monitoring period according to the screening condition;
And removing the first user information which is lower than any one of the lower limit of the user activity, the lower limit of the purchase frequency and the lower limit of the browsing time, reserving the first user information which is greater than or equal to any one of the lower limit of the user activity, the lower limit of the purchase frequency and the lower limit of the browsing time, and calibrating the first user information as the second user information.
In a preferred embodiment, the step of extracting the features of the second user information to obtain key features and non-key features, and classifying the users in multiple stages according to the key features and the non-key features includes:
extracting features of the second user information, and extracting purchasing behavior features and browsing behavior features of the user, wherein the purchasing behavior features comprise purchasing frequency, purchasing amount and purchasing time, and the browsing behavior features comprise browsing duration, browsing page number and browsing time;
Acquiring the execution frequency of purchasing behavior characteristics and browsing behavior characteristics of all users before completing transactions, calibrating the execution frequency as parameters to be evaluated, and arranging the parameters to be evaluated according to the sequence from big to small;
Acquiring an evaluation threshold value, and comparing the evaluation threshold value with a parameter to be evaluated;
If the parameter to be evaluated is greater than or equal to the evaluation threshold, the corresponding purchasing behavior feature or browsing behavior feature is marked as a key feature;
If the parameter to be evaluated is smaller than the evaluation threshold, marking the parameter to be evaluated and the corresponding purchasing behavior feature or browsing behavior feature as non-key features;
assigning an evaluation score to the key features and the non-key features, wherein the evaluation score is positively correlated with the value of the parameter to be evaluated;
Acquiring an evaluation function, inputting the evaluation scores corresponding to the users into the evaluation function, and calibrating the output result as parameters to be classified;
And acquiring multi-level classification threshold values, comparing the multi-level classification threshold values with the parameters to be classified one by one, and outputting the user level of each user according to the comparison result.
In a preferred embodiment, the step of performing cluster analysis on the second user information to obtain a plurality of user groups includes:
acquiring evaluation scores of key features and non-key features of each user, and respectively comparing to obtain user deviation;
Acquiring an allowable deviation threshold value, and comparing the allowable deviation threshold value with a user deviation degree;
If the user deviation degree is greater than or equal to the allowable deviation threshold, indicating that the purchase behavior or browsing behavior between the corresponding users is too large, and not classifying the corresponding users into the same user group;
If the user deviation degree is smaller than the allowable deviation threshold, the purchasing behavior or browsing behavior between the corresponding users is similar, and the corresponding users are classified into the same user group;
The number of the matched user groups of the same user is 1-n, and the value of n is a positive integer.
In a preferred scheme, after the key features and the non-key features are output, the key features and the non-key features are summarized with user grades, and then user portraits are generated by combining basic information of users.
In a preferred embodiment, the step of outputting the marketing score according to the user conversion rate, the user participation rate and the user grade includes:
acquiring user conversion rate, user participation rate and user grade;
carrying out numerical processing on the user grade, wherein the higher the user grade is, the larger the converted numerical value is, and the converted numerical value is calibrated as a reference parameter;
and obtaining a scoring function, inputting the user conversion rate, the user participation rate and the reference parameter into the scoring function, and calibrating an output result as a marketing score.
In a preferred embodiment, the step of adjusting the user level according to the marketing score includes:
Obtaining marketing scores corresponding to all user groups;
acquiring an evaluation threshold value and comparing the evaluation threshold value with a marketing score;
If the marketing score is larger than the evaluation threshold, indicating that the corresponding user group is satisfied with marketing pushing, recording the difference between the corresponding marketing score and the evaluation threshold, and calibrating the difference as a first deviation parameter;
If the marketing score is smaller than or equal to the evaluation threshold value, the user group corresponding to the marketing score is not satisfied with the marketing pushing, the difference value between the marketing score corresponding to the user group and the evaluation threshold value is recorded, and the second deviation parameter is calibrated;
Obtaining a standard function, inputting each first deviation parameter and each second deviation parameter corresponding to a user into the standard function together, and calibrating an output result of the first deviation parameter and the second deviation parameter as parameters to be checked;
If the value of the parameter to be checked is smaller than zero, the user grade of the corresponding user is adjusted down;
If the value of the parameter to be checked is equal to zero, keeping the user grade of the application unchanged;
and if the value of the parameter to be checked is greater than zero, the user grade of the corresponding user is increased.
The invention also provides a user management system based on enterprise marketing, which is applied to the user management method based on enterprise marketing, and comprises the following steps:
the data acquisition module is used for acquiring user data and preprocessing the user data to obtain first user information;
The screening processing module is used for acquiring screening conditions, screening the first user information according to the screening conditions, and calibrating the screened first user information as second user information;
the feature extraction module is used for extracting features of the second user information to obtain key features and non-key features, and classifying the users in multiple stages according to the key features and the non-key features;
the cluster analysis module is used for carrying out cluster analysis on the second user information to obtain a plurality of user groups and user portraits of the user groups;
And the user adjustment module is used for executing marketing pushing according to the user portrait, counting the user conversion rate and the user participation rate after the marketing pushing in real time, outputting a marketing score according to the user conversion rate, the user participation rate and the user grade, and adjusting the user grade according to the marketing score.
And, a user management terminal based on enterprise marketing, comprising:
At least one processor;
An internal memory and an external memory communicatively coupled to the at least one processor, and an input device and an output device communicatively coupled to the processor and the internal memory;
Wherein the internal memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the enterprise marketing-based user management method described above.
The invention has the technical effects that:
According to the invention, through monitoring the user behaviors, the users can be classified into a plurality of grades and a plurality of user groups, so that an enterprise can more accurately understand the user demands, thereby helping the enterprise to formulate marketing push contents adapting to each user group, improving the marketing efficiency of the enterprise, and after each marketing push is finished, dynamically adjusting the user grades according to the conversion rate, participation rate, user grade and the like of the users so as to continuously optimize the division of the user groups, so that the marketing push is more accurate and effective, the enterprise can better adapt to market changes and user demands, and continuous user growth and service expansion are realized.
Drawings
FIG. 1 is a flow chart of a method provided by the present invention;
FIG. 2 is a block diagram of a system provided by the present invention;
Fig. 3 is a diagram of a terminal structure according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Referring to fig. 1, the present invention provides a user management method based on enterprise marketing, comprising:
s1, acquiring user data, and preprocessing the user data to obtain first user information;
S2, acquiring screening conditions, screening the first user information according to the screening conditions, and calibrating the screened first user information as second user information;
s3, extracting features of the second user information to obtain key features and non-key features, and classifying the users in multiple stages according to the key features and the non-key features;
S4, carrying out cluster analysis on the second user information to obtain a plurality of user groups and user portraits of the user groups;
And S5, carrying out marketing pushing according to the user portrait, counting the user conversion rate and the user participation rate after the marketing pushing in real time, outputting marketing scores according to the user conversion rate, the user participation rate and the user grades, and adjusting the user grades according to the marketing scores.
In the above steps S1-S5, in the market environment with intense competition today, whether the marketing of the enterprise is successful or not often depends on the effectiveness of the user management policy, in this embodiment, firstly, user data is acquired and preprocessed, in the data acquisition stage, the enterprise needs to utilize various channels and means, such as market research, user investigation, online behavior tracking, and the like, in the data preprocessing stage, the enterprise needs to perform operations such as cleaning, formatting, and the like on the raw data to eliminate noise in the data, so as to improve the quality and usability of the data, next, the enterprise needs to set corresponding screening conditions according to the marketing targets and policies of the enterprise, the conditions may include multiple aspects of the consumption capability, the activity level, and the like of users, and by screening the screening conditions, the enterprise can accurately extract target user groups from huge user data, and is calibrated to be second user information, and then needs to perform feature extraction on the second user information, the process includes extracting key features and non-key features from the user data, such as purchasing frequencies, amounts, extracting features on the user data, and the like, further classifying the user groups, and clustering patterns can be further defined to be more clearly and more important to the user groups by the characteristics, and clustering requirements are further, and the user groups can be more clearly classified by the user groups, and the user groups are more classified by the user groups and the user patterns are better and the user group has the characteristics and the characteristics are better and the user group classification characteristics and the user group is better and the user-classified by the user group has the user classification characteristics and the user classification and the user information has the user classification performance and the user classification and the user management method, and finally, marketing pushing is executed according to the user portraits, in the pushing process, enterprises need to count key indexes such as user conversion rate, user participation rate and the like in real time so as to adjust and optimize marketing strategies in time, and meanwhile, the enterprises can calculate marketing scores according to a plurality of factors such as the user conversion rate, the user participation rate, user grades and the like, and dynamically adjust and optimize the user grades and user groups according to the score conditions.
In a preferred embodiment, the step of obtaining user data and preprocessing the user data to obtain first user information includes:
S101, constructing a monitoring period, and counting all user data in the monitoring period;
S102, cleaning, denoising and filling missing values for user data to obtain preposed data;
s103, performing format conversion on the preamble data, and calibrating the preamble data after format conversion as first user information.
As described in the above steps S101-S103, when preprocessing user data, a monitoring period is constructed in advance to define a collection range and a time frame of the data, so that collected data can comprehensively reflect behavior characteristics of the user in a specific period, by setting a reasonable monitoring period, data of the user at each time point can be systematically collected, a solid foundation is provided for subsequent data analysis, then the user data is cleaned, denoised and filled with missing values, in an actual data collection process, due to various reasons (such as equipment failure, network delay and the like), noise and missing values often exist in the data, the problems not only affect the accuracy of the data, but also possibly cause deviation of the subsequent analysis, format conversion is required to be performed on the front data after the data cleaning is completed, so as to obtain the first user data, the purpose is to convert the original data into a format suitable for the subsequent analysis, which may involve the processing of standardization, normalization, encoding and the like of the data, and the format conversion can ensure consistency and comparability of the data, and provide convenience for the subsequent data analysis and mining.
In a preferred embodiment, the steps of obtaining a screening condition, screening the first user information according to the screening condition, and calibrating the screened first user information as the second user information include:
s201, acquiring first user information in a monitoring period;
S202, acquiring user screening conditions, wherein the screening conditions comprise a lower limit of user activity, a lower limit of purchase frequency and a lower limit of browsing time;
s203, screening the first user information in the monitoring period according to the screening condition;
S204, removing the first user information which is lower than any one of the lower limit of the user activity, the lower limit of the purchase frequency and the lower limit of the browsing time, reserving the first user information which is greater than or equal to any one of the lower limit of the user activity, the lower limit of the purchase frequency and the lower limit of the browsing time, and calibrating the first user information as the second user information.
As described in the above steps S201-S204, when determining the second user information, first user information in the monitoring period is first obtained, then screening conditions are defined, these conditions are usually based on key indexes such as user activity, purchase frequency and browsing time, for example, we can set the lower limit of user activity to be logged in once a day, purchase frequency to be purchased at least once a month, browsing time to be browsed for at least one hour a week, these conditions can be adjusted and optimized according to specific service requirements, then screening processing is performed on the first user information according to these screening conditions, data of each user is checked one by one, those users who do not meet the conditions will be directly removed, and finally, the retained user information is calibrated as the second user information.
In a preferred embodiment, the step of extracting features of the second user information to obtain key features and non-key features, and classifying the user in multiple stages according to the key features and the non-key features includes:
s301, extracting characteristics of second user information, and extracting purchasing behavior characteristics and browsing behavior characteristics of a user, wherein the purchasing behavior characteristics comprise purchasing frequency, purchasing amount and purchasing time, and the browsing behavior characteristics comprise browsing duration, browsing page number and browsing time;
s302, acquiring the execution frequency of purchasing behavior characteristics and browsing behavior characteristics of all users before completing transactions, calibrating the execution frequency as parameters to be evaluated, and arranging the parameters to be evaluated according to the sequence from big to small;
S303, acquiring an evaluation threshold value, and comparing the evaluation threshold value with the parameter to be evaluated;
if the parameter to be evaluated is greater than or equal to the evaluation threshold, the corresponding purchasing behavior feature or browsing behavior feature is marked as a key feature;
if the parameter to be evaluated is smaller than the evaluation threshold, the parameter to be evaluated and the corresponding purchasing behavior feature or browsing behavior feature are marked as non-key features;
s304, distributing evaluation scores to the key features and the non-key features, wherein the evaluation scores are positively correlated with the values of the parameters to be evaluated;
s305, acquiring an evaluation function, inputting evaluation scores corresponding to all users into the evaluation function, and calibrating output results of the evaluation functions as parameters to be classified;
S306, acquiring multi-level classification threshold values, comparing the multi-level classification threshold values with parameters to be classified one by one, and outputting user grades of all users according to comparison results.
As described in the above steps S301-S306, after determining the second user information, the purchasing behavior features and browsing behavior features of the user are extracted, where the purchasing behavior features mainly concern purchasing frequency, purchasing amount and purchasing time of the user, these features may reflect consuming capacity and consuming habit of the user, the browsing behavior features concern browsing duration, browsing page number and browsing time of the user, these features may reveal interests and preferences of the user, then all the users purchase behavior features and executing frequency of the browsing behavior features before completing the transaction are acquired, these parameters are ranked according to the order from big to small, so as to facilitate subsequent comparison and classification, in order to determine the key features and non-key features, an evaluation threshold is required to be acquired, the evaluation threshold is a standard set according to the service requirement and the data distribution situation, and is used to distinguish the key features and the non-key features, the evaluation threshold is compared with the parameters to be evaluated, if the parameters to be evaluated are greater than or equal to the evaluation threshold, the corresponding purchasing behavior features or browsing behavior features are calibrated as key features, if the parameters to be evaluated are smaller than the threshold, the corresponding behavior features are required to be evaluated as the key features, and the non-key features are required to be evaluated, and the score is required to be evaluated as a high score is required to be determined by the user to evaluate the key features after the evaluation is greater than the key features, and the key features are required to be evaluated as the key features are evaluated, and inputting the evaluation scores corresponding to the users into an evaluation function, wherein the expression of the evaluation function is as follows: In the above, the ratio of/> Representing parameters to be classified,/>Evaluation score representing key feature,/>Representing the number of key features,/>Representing the number of non-critical features,/>And finally, acquiring a multi-level classification threshold value, comparing the multi-level classification threshold value with the parameters to be classified one by one, and outputting user grades of each user according to the comparison result, wherein the grades can reflect information on values, liveness, interest preferences and the like of the users, so that decision support is provided for enterprises and organizations.
In a preferred embodiment, the step of performing cluster analysis on the second user information to obtain a plurality of user groups includes:
s401, acquiring evaluation scores of key features and non-key features of each user, and respectively comparing to obtain user deviation;
s402, acquiring an allowable deviation threshold, and comparing the allowable deviation threshold with a user deviation degree;
If the user deviation degree is greater than or equal to the allowable deviation threshold, the purchasing behavior or browsing behavior between the corresponding users is indicated to be too large, and the corresponding users are not classified into the same user group;
If the user deviation degree is smaller than the allowable deviation threshold, the purchasing behavior or browsing behavior between the corresponding users is similar, and the corresponding users are classified into the same user group;
The number of the matched user groups of the same user is 1-n, and the value of n is a positive integer.
As described in the above steps S401 to S402, when assigning user groups, first, the evaluation scores of the key features and the non-key features of the respective users are obtained, then these scores are compared, the degree of deviation of the users (the difference between the evaluation scores corresponding to the different users) is calculated, the degree of deviation of the users reflects the degree of difference in purchasing behavior or browsing behavior between the users, by comparing the scores of the different users on these features, the degree of deviation between them can be calculated, then, an allowable deviation threshold value is required to be set according to the actual demand and the data characteristics, which determines the criteria for classifying the users into the same user group, specifically, according to the actual demand setting, if the degree of deviation of the users is greater than or equal to this threshold value, the degree of deviation of purchasing behavior or browsing behavior between them is considered to be too great to be suitable for being classified into the same user group, conversely, if the deviation of users is smaller than the threshold, the purchasing behavior or browsing behavior between users can be considered similar, and can be classified into the same user group, in this way, users in each group can be divided into a plurality of different user groups, users in each group have similar purchasing and browsing behaviors, and it is noted that the same user can match a plurality of user groups, depending on their behavior characteristics and the set threshold, for example, one user can belong to both a high-value user group and an active user group, the multiple classification provides richer user portraits (after key characteristics and non-key characteristics are output, the user portraits are summarized with user grades, and then basic information of the users are combined to generate user portraits) and deeper market insights, in practical application, the user cluster analysis can help enterprises to better understand user demands and behaviors, so that more accurate marketing strategies are formulated.
In a preferred embodiment, the step of outputting the marketing score based on the user conversion rate, the user engagement rate, and the user rating comprises:
S501, obtaining user conversion rate, user participation rate and user grade;
S502, carrying out numerical processing on the user grade, wherein the higher the user grade is, the larger the converted numerical value is, and the converted numerical value is calibrated as a reference parameter;
S503, obtaining a scoring function, inputting the user conversion rate, the user participation rate and the reference parameters into the scoring function, and calibrating the output result as a marketing score.
As described in the above steps S501-S503, when determining the marketing score, firstly, the user conversion rate, the user participation rate and the user grade need to be obtained, the user conversion rate reflects the interest degree of the user in the product or service, the user participation rate reflects the enthusiasm of the user for the brand interaction, the user grade represents the value and the position of the user in the brand ecosystem, then the user grade is subjected to the numerical processing, so as to convert the user grade into a quantifiable and comparable value for subsequent calculation and analysis, generally, the higher the user grade is, the greater the converted value is, for example, the general user can be set to be 1, the advanced user can be set to be 2, the vip user is set to be 3, and so on, these values become the reference parameters, so as to provide important references for the subsequent scoring function, and then, a suitable scoring function is obtained, and the expression of the scoring function is: In the above, the ratio of/> ，/>And/>Weight coefficients respectively representing user conversion rate, user participation rate and reference parameters,/>Representing marketing score,/>、/>And/>The method is characterized in that the method respectively represents user conversion rate, user participation rate and reference parameters, the scoring function is used for taking the user conversion rate, the user participation rate and the reference parameters as inputs and outputting a comprehensive marketing score, the marketing score is used for reflecting the marketing pushing effect, and enterprises are helped to better know the marketing pushing advantages and disadvantages.
In a preferred embodiment, the step of adjusting the user rating based on the marketing score comprises:
S504, obtaining marketing scores corresponding to all user groups;
S505, acquiring an evaluation threshold value, and comparing the evaluation threshold value with the marketing score;
If the marketing score is greater than the evaluation threshold, indicating that the corresponding user group is satisfied with marketing pushing, recording the difference between the corresponding marketing score and the evaluation threshold, and calibrating the difference as a first deviation parameter;
If the marketing score is smaller than or equal to the evaluation threshold value, the user group corresponding to the marketing score is not satisfied with the marketing pushing, the difference value between the marketing score corresponding to the user group and the evaluation threshold value is recorded, and the second deviation parameter is calibrated;
S506, acquiring a standard function, inputting each first deviation parameter and each second deviation parameter corresponding to the user into the standard function together, and calibrating an output result of the first deviation parameter and the second deviation parameter as parameters to be checked;
If the value of the parameter to be checked is smaller than zero, the user grade of the corresponding user is adjusted down;
If the value of the parameter to be checked is equal to zero, keeping the user grade of the application unchanged;
if the value of the parameter to be checked is larger than zero, the user grade of the corresponding user is increased.
As described in the above steps S504-S506, after the marketing score is outputted, an evaluation threshold is set, which may be determined according to historical data, industry standard or market research, and the evaluation threshold is compared with the marketing score of each user group, so as to help the enterprise judge the satisfaction degree of the user for marketing pushing, when the marketing score of a certain user group is greater than the evaluation threshold, the user group is satisfied with the marketing pushing, in order to measure the difference of the satisfaction degree more carefully, the difference between the marketing score of the user group and the evaluation threshold may be recorded and calibrated as a first deviation parameter, and the greater the parameter is, the higher the user satisfaction degree is, on the contrary, when the marketing score of a certain user group is less than or equal to the evaluation threshold, the difference between the marketing score of the user group and the evaluation threshold is recorded and calibrated as a second deviation parameter, and the smaller the parameter is, the lower the user satisfaction degree is indicated as the first deviation parameter is, and the second deviation parameter is obtained, and a function is introduced to perform further analysis according to a specific analysis function, which may be set as a requirement standard according to the specific implementation mode: In the above, the ratio of/> Representing the parameters to be checked,/>Representing the number of first deviation parameters,/>Representing the number of second deviation parameters,/>Representing a first departure parameter,/>The second deviation parameters are represented, the first deviation parameters and the second deviation parameters corresponding to the user are input into the standard function together, the obtained output result is calibrated to be the parameter to be verified, the user grade can be correspondingly adjusted according to the value of the parameter to be verified, when the value of the parameter to be verified is smaller than zero, the user grade corresponding to the user is relatively low, so that the requirement of the user can be better met, when the value of the parameter to be verified is equal to zero, the user grade corresponding to the user is kept unchanged, when the value of the parameter to be verified is equal to zero, the user grade corresponding to the user is relatively high, the user grade corresponding to the user can be properly adjusted to provide better service and experience, and after new marketing is formulated, the user management method can be re-executed according to the adjusted user grade.
As shown in FIG. 2, the invention also provides a user management system based on enterprise marketing, which is applied to the user management method based on enterprise marketing, and comprises the following steps:
the data acquisition module is used for acquiring user data and preprocessing the user data to obtain first user information;
The screening processing module is used for acquiring screening conditions, screening the first user information according to the screening conditions, and calibrating the screened first user information as second user information;
the feature extraction module is used for extracting features of the second user information to obtain key features and non-key features, and classifying the users in multiple stages according to the key features and the non-key features;
the cluster analysis module is used for carrying out cluster analysis on the second user information to obtain a plurality of user groups and user portraits of the user groups;
And the user adjustment module is used for executing marketing pushing according to the user portrait, counting the user conversion rate and the user participation rate after the marketing pushing in real time, outputting marketing scores according to the user conversion rate, the user participation rate and the user grades, and adjusting the user grades and the user groups according to the marketing scores.
The system comprises a data acquisition module, a screening processing module, a feature extraction module, a cluster analysis module and a user adjustment module, wherein the data acquisition collects user data in a multi-channel and multi-mode manner, after the data acquisition, the system performs preprocessing work such as cleaning, deduplication, formatting and the like on the data to ensure the accuracy and consistency of the data, the preprocessed data is marked as first user information, a solid data basis is provided for subsequent analysis and marketing pushing, the screening processing module screens the first user information according to screening conditions set by an enterprise so as to identify user groups meeting specific conditions, the screened user information is marked as second user information, target objects are provided for subsequent feature extraction and classification, the feature extraction module performs multi-level classification on the users based on the features by extracting key features and non-key features of the users, the cluster analysis module divides the users into a plurality of user groups, each group has similar features and behaviors, simultaneously, the system generates user figures for each user group, namely, the characteristics and the typical user behaviors of the group are not only beneficial to the user groups, but also can participate in the dynamic evaluation of the marketing system according to the requirements of the marketing system, and the user figures are better estimated according to the marketing requirements, the user figures are better adjusted according to the dynamic user figures, the user figures are better calculated by the user figures, the marketing figures are better matched with the user figures, and the user figures are better matched with the user figures, after each marketing push, the user grade can be accurately positioned, and corresponding data support is provided for adjustment of subsequent marketing push.
As shown in fig. 3, a user management terminal based on enterprise marketing includes:
At least one processor;
an internal memory and an external memory communicatively coupled to the at least one processor, and an input device and an output device communicatively coupled to the processor and the internal memory;
The internal memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the user management method based on enterprise marketing.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that comprises the element.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention. Structures, devices and methods of operation not specifically described and illustrated herein, unless otherwise indicated and limited, are implemented according to conventional means in the art.
Claims (5)
1. A user management method based on enterprise marketing is characterized in that: comprising the following steps:
acquiring user data, and preprocessing the user data to obtain first user information;
Acquiring screening conditions, screening the first user information according to the screening conditions, and calibrating the screened first user information as second user information;
extracting the characteristics of the second user information to obtain key characteristics and non-key characteristics, and classifying the users in multiple stages according to the key characteristics and the non-key characteristics;
Performing cluster analysis on the second user information to obtain a plurality of user groups and user portraits of the user groups;
executing marketing pushing according to the user portrait, counting the user conversion rate and the user participation rate after the marketing pushing in real time, outputting a marketing score according to the user conversion rate, the user participation rate and the user grade, and adjusting the user grade according to the marketing score;
the step of extracting the features of the second user information to obtain key features and non-key features, and classifying the users in multiple stages according to the key features and the non-key features comprises the following steps:
extracting features of the second user information, and extracting purchasing behavior features and browsing behavior features of the user, wherein the purchasing behavior features comprise purchasing frequency, purchasing amount and purchasing time, and the browsing behavior features comprise browsing duration, browsing page number and browsing time;
Acquiring the execution frequency of purchasing behavior characteristics and browsing behavior characteristics of all users before completing transactions, calibrating the execution frequency as parameters to be evaluated, and arranging the parameters to be evaluated according to the sequence from big to small;
Acquiring an evaluation threshold value, and comparing the evaluation threshold value with a parameter to be evaluated;
If the parameter to be evaluated is greater than or equal to the evaluation threshold, the corresponding purchasing behavior feature or browsing behavior feature is marked as a key feature;
If the parameter to be evaluated is smaller than the evaluation threshold, marking the parameter to be evaluated and the corresponding purchasing behavior feature or browsing behavior feature as non-key features;
assigning an evaluation score to the key features and the non-key features, wherein the evaluation score is positively correlated with the value of the parameter to be evaluated;
Acquiring an evaluation function, inputting evaluation scores corresponding to all users into the evaluation function, and calibrating output results of the evaluation function as parameters to be classified, wherein the expression of the evaluation function is as follows: In the above, the ratio of/> Representing parameters to be classified,/>Evaluation score representing key feature,/>Representing the number of key features,/>Representing the number of non-critical features,An evaluation score representing a non-critical parameter;
Acquiring multi-level classification threshold values, comparing the multi-level classification threshold values with the parameters to be classified one by one, and outputting user grades of all users according to comparison results;
the step of performing cluster analysis on the second user information to obtain a plurality of user groups includes:
acquiring evaluation scores of key features and non-key features of each user, and respectively comparing to obtain user deviation;
Acquiring an allowable deviation threshold value, and comparing the allowable deviation threshold value with a user deviation degree;
If the user deviation degree is greater than or equal to the allowable deviation threshold, indicating that the purchase behavior or browsing behavior between the corresponding users is too large, and not classifying the corresponding users into the same user group;
If the user deviation degree is smaller than the allowable deviation threshold, the purchasing behavior or browsing behavior between the corresponding users is similar, and the corresponding users are classified into the same user group;
Wherein the number of the matched user groups of the same user is 1-n, and the value of n is a positive integer;
After the key features and the non-key features are output, the key features and the non-key features are summarized with user grades, and then user portraits are generated by combining basic information of users;
the step of outputting the marketing score according to the user conversion rate, the user participation rate and the user grade comprises the following steps:
acquiring user conversion rate, user participation rate and user grade;
carrying out numerical processing on the user grade, wherein the higher the user grade is, the larger the converted numerical value is, and the converted numerical value is calibrated as a reference parameter;
Obtaining a scoring function, inputting the user conversion rate, the user participation rate and the reference parameter into the scoring function together, and calibrating an output result as a marketing score;
the step of adjusting the user grade according to the marketing score comprises the following steps:
Obtaining marketing scores corresponding to all user groups;
acquiring an evaluation threshold value and comparing the evaluation threshold value with a marketing score;
If the marketing score is larger than the evaluation threshold, indicating that the corresponding user group is satisfied with marketing pushing, recording the difference between the corresponding marketing score and the evaluation threshold, and calibrating the difference as a first deviation parameter;
If the marketing score is smaller than or equal to the evaluation threshold value, the user group corresponding to the marketing score is not satisfied with the marketing pushing, the difference value between the marketing score corresponding to the user group and the evaluation threshold value is recorded, and the second deviation parameter is calibrated;
The method comprises the steps of obtaining a standard function, inputting first deviation parameters and second deviation parameters corresponding to a user into the standard function, calibrating output results of the first deviation parameters and the second deviation parameters to be verified, and enabling an expression of the standard function to be: In the method, in the process of the invention, Representing the parameters to be checked,/>Representing the number of first deviation parameters,/>Representing the number of second deviation parameters,/>Representing a first departure parameter,/>Representing a second deviation parameter;
If the value of the parameter to be checked is smaller than zero, the user grade of the corresponding user is adjusted down;
If the value of the parameter to be checked is equal to zero, keeping the user grade of the application unchanged;
and if the value of the parameter to be checked is greater than zero, the user grade of the corresponding user is increased.
2. The enterprise marketing-based user management method of claim 1, wherein: the step of obtaining user data and preprocessing the user data to obtain first user information comprises the following steps:
Constructing a monitoring period, and counting all user data in the monitoring period;
Cleaning, denoising and filling missing values to the user data to obtain front data;
And carrying out format conversion on the preamble data, and calibrating the preamble data after format conversion as first user information.
3. The enterprise marketing-based user management method of claim 2, wherein: the step of obtaining the screening condition, screening the first user information according to the screening condition, and calibrating the screened first user information as second user information comprises the following steps:
Acquiring first user information in the monitoring period;
obtaining user screening conditions, wherein the screening conditions comprise a lower limit of user activity, a lower limit of purchase frequency and a lower limit of browsing time;
Screening the first user information in the monitoring period according to the screening condition;
And removing the first user information which is lower than any one of the lower limit of the user activity, the lower limit of the purchase frequency and the lower limit of the browsing time, reserving the first user information which is greater than or equal to any one of the lower limit of the user activity, the lower limit of the purchase frequency and the lower limit of the browsing time, and calibrating the first user information as the second user information.
4. A user management system based on enterprise marketing, which is applied to the user management method based on enterprise marketing as set forth in any one of claims 1 to 3, and is characterized in that: comprising the following steps:
the data acquisition module is used for acquiring user data and preprocessing the user data to obtain first user information;
The screening processing module is used for acquiring screening conditions, screening the first user information according to the screening conditions, and calibrating the screened first user information as second user information;
the feature extraction module is used for extracting features of the second user information to obtain key features and non-key features, and classifying the users in multiple stages according to the key features and the non-key features;
the cluster analysis module is used for carrying out cluster analysis on the second user information to obtain a plurality of user groups and user portraits of the user groups;
And the user adjustment module is used for executing marketing pushing according to the user portrait, counting the user conversion rate and the user participation rate after the marketing pushing in real time, outputting a marketing score according to the user conversion rate, the user participation rate and the user grade, and adjusting the user grade according to the marketing score.
5. A user management terminal based on enterprise marketing is characterized in that: comprising the following steps:
At least one processor;
An internal memory and an external memory communicatively coupled to the at least one processor, and an input device and an output device communicatively coupled to the processor and the internal memory;
Wherein the internal memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the enterprise marketing-based user management method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410303185.7A CN117911085B (en) | 2024-03-18 | 2024-03-18 | User management system, method and terminal based on enterprise marketing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410303185.7A CN117911085B (en) | 2024-03-18 | 2024-03-18 | User management system, method and terminal based on enterprise marketing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117911085A CN117911085A (en) | 2024-04-19 |
| CN117911085B true CN117911085B (en) | 2024-06-11 |
Family
ID=90689317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410303185.7A Active CN117911085B (en) | 2024-03-18 | 2024-03-18 | User management system, method and terminal based on enterprise marketing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117911085B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118469612A (en) * | 2024-05-17 | 2024-08-09 | 湖北宽通科技有限公司 | Digital marketing management system based on big data |
Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006127227A (en) * | 2004-10-29 | 2006-05-18 | Sato Corp | Point management system |
| CN101004816A (en) * | 2007-01-30 | 2007-07-25 | 华为技术有限公司 | Method, device, and system for maintaining levels of clients |
| CN102194000A (en) * | 2011-05-13 | 2011-09-21 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and terminal for processing information |
| CN102289528A (en) * | 2011-09-28 | 2011-12-21 | 王楠 | Individualized network report system |
| CN103870547A (en) * | 2014-02-26 | 2014-06-18 | 华为技术有限公司 | Grouping processing method and device of contact persons |
| KR20150094923A (en) * | 2014-02-12 | 2015-08-20 | 김성규 | User participatory method for providing stock price prediction service |
| CN106530073A (en) * | 2016-09-12 | 2017-03-22 | 国网辽宁省电力有限公司鞍山供电公司 | Method of analyzing user credit rate based on CART algorithm |
| CN106851431A (en) * | 2016-12-07 | 2017-06-13 | 乐视控股（北京）有限公司 | A kind of method and apparatus of user interaction |
| CN106980991A (en) * | 2017-04-06 | 2017-07-25 | 百度在线网络技术（北京）有限公司 | A kind of method for pushing of marketing message, device, equipment and storage medium |
| CN108171553A (en) * | 2018-01-17 | 2018-06-15 | 焦点科技股份有限公司 | The potential customers' digging system and method for a kind of periodic service or product |
| CN108810300A (en) * | 2018-04-28 | 2018-11-13 | 平安科技（深圳）有限公司 | The method and its control method and device of adjustment intelligent terminal the tinkle of bells |
| AU2019100428A4 (en) * | 2019-04-23 | 2019-06-27 | Data One Technologies Pty Ltd | An intelligent in-store shopping platform for customers and retailers. With this, customers can select, scan, and pay for the products via smartphones and check-out of the store with minimal human intervention. The system uses hi-end technologies such as artificial intelligence for anti-shoplifting, automated decision making, Computer Vision, weighing techniques, electronic circuitry and RFID. The framework uses intricate IoT (Internet of Things) technology and self-learning algorithms, big data analytics, customer engagement and pattern analysis using data extraction and knowledge mining. |
| US10339563B1 (en) * | 2011-10-19 | 2019-07-02 | West Corporation | Method and apparatus of providing messaging to targeted lifestyle segments |
| CN110135971A (en) * | 2019-04-15 | 2019-08-16 | 上海良鑫网络科技有限公司 | Assessing credit risks System and method for based on weak variable data |
| CN110287250A (en) * | 2019-06-25 | 2019-09-27 | 世纪龙信息网络有限责任公司 | User gradation quantization method and device |
| CN110322899A (en) * | 2019-06-18 | 2019-10-11 | 平安银行股份有限公司 | User's intelligent method for classifying, server and storage medium |
| CN110659318A (en) * | 2019-08-15 | 2020-01-07 | 中国平安财产保险股份有限公司 | Big data based strategy pushing method and system and computer equipment |
| CN111966995A (en) * | 2020-08-17 | 2020-11-20 | 福建工程学院 | User permission dynamic control method and device based on user behavior and equipment |
| CN112488746A (en) * | 2020-11-03 | 2021-03-12 | 广州易起行信息技术有限公司 | Secondary marketing method of travel product based on big data user behavior, electronic device and storage medium |
| KR20210046312A (en) * | 2019-10-18 | 2021-04-28 | 최호석 | Customer class classification and management |
| CN113297461A (en) * | 2020-02-24 | 2021-08-24 | 北京达佳互联信息技术有限公司 | Target user identification method, target user group identification method and related product |
| CN115271282A (en) * | 2021-04-29 | 2022-11-01 | 中移动金融科技有限公司 | Customer value determination method and device based on fuzzy logic |
| CN115759401A (en) * | 2022-11-17 | 2023-03-07 | 江苏电力交易中心有限公司 | Method and system for generating bidding behavior prediction labels of members in power market |
| CN116843356A (en) * | 2023-05-26 | 2023-10-03 | 宾邦(厦门)传媒科技有限公司 | Food trial eating effect analysis system based on consumer trial eating behaviors |
| CN117113315A (en) * | 2022-12-26 | 2023-11-24 | 深圳市沐腾科技有限公司 | User identity verification authorization method and device based on third party platform |
| CN117150313A (en) * | 2023-09-01 | 2023-12-01 | 国网江苏省电力有限公司盐城供电分公司 | Power information communication method and system based on abnormal state identification |
| CN117216419A (en) * | 2023-11-08 | 2023-12-12 | 江西为易科技有限公司 | Data analysis method based on AI technology |
| WO2023245999A1 (en) * | 2022-06-20 | 2023-12-28 | 上海二三四五网络科技有限公司 | User multi-interest recommendation method and apparatus based on clustering technology, and device and medium |
| CN117391765A (en) * | 2023-05-23 | 2024-01-12 | 武汉科技大学 | Construction method for pharmacy member group portraits |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009092149A1 (en) * | 2008-01-24 | 2009-07-30 | Suncor Energy Inc. | Method, system and media for wireless process control of mobile equipment |
| US20170364930A1 (en) * | 2016-06-17 | 2017-12-21 | 24/7 Customer, Inc. | Method and apparatus for assessing customer value based on customer interactions with advertisements |
| WO2019112993A1 (en) * | 2017-12-06 | 2019-06-13 | Cognant Llc | System and method for user-level lifetime value prediction |
| US10956541B2 (en) * | 2019-06-05 | 2021-03-23 | EMC IP Holding Company LLC | Dynamic optimization of software license allocation using machine learning-based user clustering |
| US11842299B2 (en) * | 2020-01-14 | 2023-12-12 | Dell Products L.P. | System and method using deep learning machine vision to conduct product positioning analyses |
-
2024
- 2024-03-18 CN CN202410303185.7A patent/CN117911085B/en active Active
Patent Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006127227A (en) * | 2004-10-29 | 2006-05-18 | Sato Corp | Point management system |
| CN101004816A (en) * | 2007-01-30 | 2007-07-25 | 华为技术有限公司 | Method, device, and system for maintaining levels of clients |
| CN102194000A (en) * | 2011-05-13 | 2011-09-21 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and terminal for processing information |
| CN102289528A (en) * | 2011-09-28 | 2011-12-21 | 王楠 | Individualized network report system |
| US10339563B1 (en) * | 2011-10-19 | 2019-07-02 | West Corporation | Method and apparatus of providing messaging to targeted lifestyle segments |
| KR20150094923A (en) * | 2014-02-12 | 2015-08-20 | 김성규 | User participatory method for providing stock price prediction service |
| CN103870547A (en) * | 2014-02-26 | 2014-06-18 | 华为技术有限公司 | Grouping processing method and device of contact persons |
| CN106530073A (en) * | 2016-09-12 | 2017-03-22 | 国网辽宁省电力有限公司鞍山供电公司 | Method of analyzing user credit rate based on CART algorithm |
| CN106851431A (en) * | 2016-12-07 | 2017-06-13 | 乐视控股（北京）有限公司 | A kind of method and apparatus of user interaction |
| CN106980991A (en) * | 2017-04-06 | 2017-07-25 | 百度在线网络技术（北京）有限公司 | A kind of method for pushing of marketing message, device, equipment and storage medium |
| CN108171553A (en) * | 2018-01-17 | 2018-06-15 | 焦点科技股份有限公司 | The potential customers' digging system and method for a kind of periodic service or product |
| CN108810300A (en) * | 2018-04-28 | 2018-11-13 | 平安科技（深圳）有限公司 | The method and its control method and device of adjustment intelligent terminal the tinkle of bells |
| CN110135971A (en) * | 2019-04-15 | 2019-08-16 | 上海良鑫网络科技有限公司 | Assessing credit risks System and method for based on weak variable data |
| AU2019100428A4 (en) * | 2019-04-23 | 2019-06-27 | Data One Technologies Pty Ltd | An intelligent in-store shopping platform for customers and retailers. With this, customers can select, scan, and pay for the products via smartphones and check-out of the store with minimal human intervention. The system uses hi-end technologies such as artificial intelligence for anti-shoplifting, automated decision making, Computer Vision, weighing techniques, electronic circuitry and RFID. The framework uses intricate IoT (Internet of Things) technology and self-learning algorithms, big data analytics, customer engagement and pattern analysis using data extraction and knowledge mining. |
| CN110322899A (en) * | 2019-06-18 | 2019-10-11 | 平安银行股份有限公司 | User's intelligent method for classifying, server and storage medium |
| CN110287250A (en) * | 2019-06-25 | 2019-09-27 | 世纪龙信息网络有限责任公司 | User gradation quantization method and device |
| CN110659318A (en) * | 2019-08-15 | 2020-01-07 | 中国平安财产保险股份有限公司 | Big data based strategy pushing method and system and computer equipment |
| KR20210046312A (en) * | 2019-10-18 | 2021-04-28 | 최호석 | Customer class classification and management |
| CN113297461A (en) * | 2020-02-24 | 2021-08-24 | 北京达佳互联信息技术有限公司 | Target user identification method, target user group identification method and related product |
| CN111966995A (en) * | 2020-08-17 | 2020-11-20 | 福建工程学院 | User permission dynamic control method and device based on user behavior and equipment |
| CN112488746A (en) * | 2020-11-03 | 2021-03-12 | 广州易起行信息技术有限公司 | Secondary marketing method of travel product based on big data user behavior, electronic device and storage medium |
| CN115271282A (en) * | 2021-04-29 | 2022-11-01 | 中移动金融科技有限公司 | Customer value determination method and device based on fuzzy logic |
| WO2023245999A1 (en) * | 2022-06-20 | 2023-12-28 | 上海二三四五网络科技有限公司 | User multi-interest recommendation method and apparatus based on clustering technology, and device and medium |
| CN115759401A (en) * | 2022-11-17 | 2023-03-07 | 江苏电力交易中心有限公司 | Method and system for generating bidding behavior prediction labels of members in power market |
| CN117113315A (en) * | 2022-12-26 | 2023-11-24 | 深圳市沐腾科技有限公司 | User identity verification authorization method and device based on third party platform |
| CN117391765A (en) * | 2023-05-23 | 2024-01-12 | 武汉科技大学 | Construction method for pharmacy member group portraits |
| CN116843356A (en) * | 2023-05-26 | 2023-10-03 | 宾邦(厦门)传媒科技有限公司 | Food trial eating effect analysis system based on consumer trial eating behaviors |
| CN117150313A (en) * | 2023-09-01 | 2023-12-01 | 国网江苏省电力有限公司盐城供电分公司 | Power information communication method and system based on abnormal state identification |
| CN117216419A (en) * | 2023-11-08 | 2023-12-12 | 江西为易科技有限公司 | Data analysis method based on AI technology |
Non-Patent Citations (5)
| Title |
|---|
| Discovering e-commerce user groups from online comments: An emotional correlation analysis-based clustering method;Jia Ke;Computers and Electrical Engineering;20240102;第113卷;全文 * |
| 基于RFAT模型的加油站客户分类定价营销策略;王永祺;;化工管理;20200201(第04期);全文 * |
| 基于客户价值分析的客户策略在财务管理中的应用;王冬梅;;航天工业管理;20110515(第05期);全文 * |
| 基于社会认同理论的微博群体用户画像;林燕霞;谢湘生;;情报理论与实践;20171129(第03期);全文 * |
| 浅谈大数据在商业银行中的应用;庄道通;;劳动保障世界;20170815(第23期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117911085A (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117911085B (en) | User management system, method and terminal based on enterprise marketing | |
| US8260921B2 (en) | Demand forecasting system for data center, demand forecasting method and recording medium with a demand forecasting program recorded thereon | |
| CN111127105A (en) | User hierarchical model construction method and system, and operation analysis method and system | |
| CN103744928B (en) | A kind of network video classification method based on history access record | |
| CN115577152B (en) | Online book borrowing management system based on data analysis | |
| CN109636128A (en) | A kind of optimization method of dot number and structure based on business hall measures of effectiveness | |
| Aggrawal et al. | Modeling and characterizing viewers of You Tube videos | |
| CN111597443A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN111062564A (en) | Method for calculating power customer appeal sensitive value | |
| CN109428760B (en) | User credit evaluation method based on operator data | |
| CN111858245A (en) | Abnormal data analysis method and device, electronic equipment and storage medium | |
| CN117271905B (en) | Crowd image-based lateral demand analysis method and system | |
| CN115063035A (en) | Customer evaluation method, system, equipment and storage medium based on neural network | |
| CN114493686A (en) | Operation content generation and pushing method and device | |
| Wang | Research on bank marketing behavior based on machine learning | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN112308419A (en) | Data processing method, device, equipment and computer storage medium | |
| CN112132689A (en) | Recommendation method and device based on time sequence factor event | |
| CN117726360B (en) | Client behavior driven industrial product sales analysis method and related components | |
| Liu et al. | Profile-based traffic characterization of commercial web sites | |
| CN117236801B (en) | Data processing method, device, electronic equipment and readable storage medium | |
| CN116739752A (en) | Message reminding method and device, electronic equipment and storage medium | |
| CN113222760A (en) | User data processing method and related device | |
| CN117114820A (en) | Method and system for calculating optimal push index of offline user and online user | |
| CN116797097A (en) | Data asset value assessment 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |