CN117493979A - Customer classification method based on data processing - Google Patents
Customer classification method based on data processing Download PDFInfo
- Publication number
- CN117493979A CN117493979A CN202311841473.XA CN202311841473A CN117493979A CN 117493979 A CN117493979 A CN 117493979A CN 202311841473 A CN202311841473 A CN 202311841473A CN 117493979 A CN117493979 A CN 117493979A
- Authority
- CN
- China
- Prior art keywords
- particle
- fitness
- value
- particles
- calculating
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000002245 particle Substances 0.000 claims abstract description 113
- 239000011159 matrix material Substances 0.000 claims abstract description 6
- 238000010606 normalization Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 6
- 239000011164 primary particle Substances 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
Abstract
The invention discloses a client classification method based on data processing, which relates to the technical field of data processing, and comprises the following steps: establishing a classification index system, and storing client data aiming at a plurality of clients in a matrix mode; and (3) carrying out standardized processing on the client data, and classifying by combining a K-means algorithm and a particle swarm algorithm. The clustering algorithm combining the K-means and the particle swarm is utilized, the defect of the K-means algorithm is overcome, the processed client data is clustered, the clustering accuracy is improved, and the clients are effectively classified according to the client data, so that the clients of different types can be clearly divided by an electronic business enterprise.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a client classification method based on data processing.
Background
In the context of online shopping popularity, more e-commerce enterprises can select for clients, and the business information of the clients can be obtained with low cost and high efficiency for the e-commerce enterprises. Therefore, how to effectively mine the value of the clients through data analysis, classify and manage the clients, and reduce the loss of the clients to be the core management task of the electronic commerce enterprise. The method for classifying the K-means algorithm in the related technology has the problems that the number of clusters is difficult to estimate, the selection of the initial class center can cause a plurality of uncertainties and the like of the clustering result.
Disclosure of Invention
The invention provides a client classification method based on data processing, which solves the technical problems by combining a K-means algorithm and a particle swarm algorithm for classification.
According to an aspect of the present disclosure, there is provided a data processing-based client classification method, the method comprising:
establishing a classification index system, wherein the classification index system comprises a first layer of classification indexes and a second layer of classification indexes, and the first layer of classification indexes comprise: the second-layer classification indexes comprise average purchase quantity and average transaction amount related to the current value, the number of purchased commodity types related to the potential value, customer stay time, purchase frequency and comment airing number;
acquiring client data of an electronic commerce enterprise; the customer data includes: average purchase amount, average transaction amount, type of goods purchased, customer residence time, comment on the sun number, frequency of purchase;
storing client data for a plurality of clients in a matrix manner;
the standardized processing of the customer data comprises the following steps: processing the client data to enable the value to be in the range of the [0,1] interval; wherein the data set formed by the client data comprises N samples;
then k sample cluster centers are selected, the positions of the sample cluster centers are used as initial values of the particle individual positions and the group optimal positions, the speed of the particle individual is initialized, the positions of the sample cluster centers are used as the particle individual optimal positions, and the particle individual optimal position fitness is calculated; wherein the particles are samples in the dataset;
calculating the fitness value of each particle according to a particle swarm algorithm, for each particle, taking the current position as a new individual optimal position if the fitness value of the current position of the particle is smaller than that of the individual optimal position, and taking the current position as a new global optimal position if the fitness value of the current position of the particle is smaller than that of the group optimal position;
calculating the fitness value of the optimal position of the group;
updating the speed and the position of the particles according to a particle swarm algorithm; the velocity and position of the particles are vectors;
calculating a population fitness variance, wherein the population fitness variance reflects the degree of particle convergence in the particle swarm;
terminating the particle swarm algorithm iteration when the population fitness variance is smaller than a threshold value;
taking the global best position as a clustering center, calculating the distance from the rest particles to the clustering center, classifying according to the distance, and determining a new clustering center;
if the maximum iteration number is reached, comparing the fitness of the new clustering center with the fitness of the previous particle, and if the fitness of the new clustering center is better, updating the particle with the position of the new clustering center and ending the operation to obtain a clustering result;
wherein the result of the clustering comprises the average purchase amount, the average transaction amount, the customer residence time, the comment count, the purchase frequency, the purchase commodity type and the number of customers contained in the current class of each clustering center.
In one possible implementation manner, the calculating the fitness value of each particle according to the particle swarm algorithm includes:
and calculating the sum of the distances between the sample data and each cluster center to obtain the fitness value.
In one possible implementation, the updating the speed and the position of the particles according to the particle swarm algorithm includes: updating the velocity of the particles by equation (1), and updating the particle position by equation (2):
（1）；
（2）；
wherein t is the current iteration number, V i (t) represents the current velocity of the particle, ω is an inertial weight, the inertial weight represents the influence of the primary particle velocity on the current velocity, l 1 And l 2 As a learning factor, the sub-table represents the influence degree of the optimal positions of individuals and groups on speed updating;
rand () is a function that generates random numbers within the range 0, 1;
P besti for the optimal position of particle i, P si Is the population optimal position for particle i.
In one possible implementation, the calculating the population fitness variance includes: calculating the population fitness variance of the particle swarm through a formula (3):
（3）；
wherein Q represents the number of particles, f i Fitness f for the ith particle avg For an average fitness of a population of particles, f represents a normalization factor, and determining the normalization factor comprises:
determining the difference value between the fitness of each particle and the average fitness of the particle swarm, and selecting the maximum value of the difference values;
comparing the maximum value with 1, selecting the maximum value as the normalization factor if the maximum value is larger than 1, and selecting 1 as the normalization factor if the maximum value is smaller than 1.
According to another aspect of the present disclosure, there is provided an electronic device, wherein the electronic device includes: a processor and a memory storing computer executable instructions that, when executed, cause the processor to perform a data processing based customer classification method.
According to another aspect of the present disclosure, there is provided a computer readable storage medium storing one or more instructions, wherein the one or more instructions, when executed by a processor, implement a method of customer classification based on data processing.
Compared with the prior art, the invention has the beneficial effects that:
according to the client classification method based on data processing, client data of an electronic commerce industry are obtained by establishing a classification index system, and client data of a plurality of clients are stored in a matrix mode; the client data is subjected to standardized processing, the defects of the K-means algorithm are overcome by utilizing the clustering algorithm combining the K-means and the particle swarm, the clustering accuracy is improved, the clients are effectively classified according to the client data, different types of clients can be clearly divided by an electronic business enterprise, service strategies are adopted for the different types of clients in a targeted manner, the old clients are kept, new clients are developed, and the management efficiency of enterprises is improved.
Drawings
FIG. 1 illustrates a flow chart of a method of customer classification based on data processing according to an embodiment of the present disclosure.
Description of the embodiments
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
According to an aspect of the present disclosure, there is provided a data processing-based client classification method, the method comprising:
establishing a classification index system, wherein the classification index system comprises a first layer of classification indexes and a second layer of classification indexes, and the first layer of classification indexes comprise: the second-layer classification indexes comprise average purchase quantity and average transaction amount related to the current value, the number of purchased commodity types related to the potential value, customer stay time, purchase frequency and comment airing number;
the potential value of a customer refers to the value that the customer may have, and needs to be judged by long-term eyes. The current customer value refers to the accumulated contribution of the transaction behaviors of the current customer and the enterprise, and reflects the contribution degree of the customer to the enterprise.
Acquiring client data of an electronic commerce enterprise; the customer data includes: average purchase amount, average transaction amount, type of goods purchased, customer residence time, comment on the sun number, frequency of purchase;
for example, the purchase frequency refers to the number of transactions between the customer and the enterprise in a period of time, the average transaction amount reflects the average amount of goods purchased by the customer once, the average transaction amount refers to the average number of goods purchased by the customer once, the average purchase power of the customer is reflected, the customer residence time refers to the sum of the time spent by the customer browsing the product pages in a period of time, the comment airing number of the customer refers to the number of goods evaluated after the customer purchases the goods, the quality and service problems of the product are fed back through the comment and airing list, the number of communication between the customer and the enterprise and the other customers is reflected, the number of the purchased goods refers to the number of the product categories of the enterprise, the enterprise departments can divide the products into major categories, collect the types of the products purchased by the customer for grasping sales situations of various products, and count the types of the products purchased by the customer.
Storing client data for a plurality of clients in a matrix manner;
the standardized processing of the customer data comprises the following steps: processing the client data to enable the value to be in the range of the [0,1] interval; wherein the data set formed by the client data comprises N samples;
for example, the average purchase amount, average transaction amount, customer residence time, comment count, purchase frequency, and size of six index data of the purchased commodity category are different, such as units above thousand yuan of the average purchase amount, and the comment count is mostly unit digits. An index with an excessively high value may affect the effect of an index with an excessively low value in comprehensive analysis, and in order to ensure that the indexes can be compared in a common range and eliminate the influence of units on a clustering result, sample data with different dimensions need to be subjected to standardization processing. For example, the normalized data is obtained by subtracting the minimum value of a certain index from the value of the index, and dividing the difference by the difference between the maximum value and the minimum value of the index.
Then k sample cluster centers are selected, the positions of the sample cluster centers are used as initial values of the particle individual positions and the group optimal positions, the speed of the particle individual is initialized, the positions of the sample cluster centers are used as the particle individual optimal positions, and the particle individual optimal position fitness is calculated; wherein the particles are samples in the dataset;
calculating the fitness value of each particle according to a particle swarm algorithm, for each particle, taking the current position as a new individual optimal position if the fitness value of the current position of the particle is smaller than that of the individual optimal position, and taking the current position as a new global optimal position if the fitness value of the current position of the particle is smaller than that of the group optimal position;
calculating the fitness value of the optimal position of the group;
updating the speed and the position of the particles according to a particle swarm algorithm; the velocity and position of the particles are vectors;
calculating a population fitness variance, wherein the population fitness variance reflects the degree of particle convergence in the particle swarm;
terminating the particle swarm algorithm iteration when the population fitness variance is smaller than a threshold value; for example, the threshold may be 0.1.
Taking the global best position as a clustering center, calculating the distance from the rest particles to the clustering center, classifying according to the distance, and determining a new clustering center;
if the maximum iteration number is reached, comparing the fitness of the new clustering center with the fitness of the previous particle, and if the fitness of the new clustering center is better, updating the particle with the position of the new clustering center and ending the operation to obtain a clustering result;
wherein the result of the clustering comprises the average purchase amount, the average transaction amount, the customer residence time, the comment count, the purchase frequency, the purchase commodity type and the number of customers contained in the current class of each clustering center.
For example, the classification management of the class duty ratio clients of the current class is calculated through the number of clients of the current cluster center, enterprise resources are reasonably allocated, different clients are treated differently, and different service strategies are adopted.
For example, the important relation of the classification indexes can be obtained through a questionnaire form, different indexes are given different weight values according to importance, the average purchase amount and the average transaction amount in the classified results are weighted and summed to obtain the score of the current value, the data of the class center of the classified results are analyzed, the number of the purchased commodity types, the customer stay time, the purchase frequency and the comment sun number are weighted and summed to obtain the score of the potential value. And classifying the data according to the scores, classifying the clients with low current value and low potential value as first class clients, classifying the clients with low current value and high potential value as second class clients, classifying the clients with high current value and low potential value as third class clients, and classifying the clients with high current value and high potential value as fourth class clients.
According to the analysis result, enterprises can make some strategies, and when the first-class clients cannot bring higher profits to the enterprises, enterprise resources are wasted, and meanwhile, the basic requirements of the clients are met, and excessive resources are not needed to be input. For the second class of clients, the company needs to take necessary strategies to promote the current value. For a third class of customers, the enterprise should take measures to maintain the current value of that class of customers to develop potential value. For the fourth type of clients, the clients have higher current value and higher future potential value, and enterprises should service the clients in an important way.
According to the client classification method based on data processing, client data of an electronic commerce industry are obtained by establishing a classification index system, and client data of a plurality of clients are stored in a matrix mode; the client data is subjected to standardized processing, the defects of the K-means algorithm are overcome by utilizing the clustering algorithm combining the K-means and the particle swarm, the clustering accuracy is improved, the clients are effectively classified according to the client data, different types of clients can be clearly divided by an electronic business enterprise, service strategies are adopted for the different types of clients in a targeted manner, the old clients are kept, new clients are developed, and the management efficiency of enterprises is improved.
In one possible implementation manner, the calculating the fitness value of each particle according to the particle swarm algorithm includes:
and calculating the sum of the distances between the sample data and each cluster center to obtain the fitness value.
In one possible implementation, the updating the speed and the position of the particles according to the particle swarm algorithm includes: updating the velocity of the particles by equation (1), and updating the particle position by equation (2):
（1）；
（2）；
wherein t is the current iteration number, V i (t) represents the current velocity of the particle, ω is an inertial weight, the inertial weight represents the influence of the primary particle velocity on the current velocity, l 1 And l 2 For learning factors, separate tablesIndicating the influence degree of the optimal positions of individuals and groups on the speed update; to achieve a balance of local and global search capabilities, one needs to go through constant adjustment of l 1 And l 2 . If l 1 And l 2 If the value of the solution is too large, the particles possibly fly out of the effective area of the population in the flight process, and if the value is too small, the running speed of the particles is slow, and a long time is required to search the optimal solution, so that the operation efficiency of the whole particle swarm algorithm is affected. In general l 1 And/l 2 Has the same value and the experience range of [0,4 ]]Between them.
For example, learning may thus take on values of 0.3 inertia weights, respectively, may take on values of 0.4-0.9; the maximum number of iterations may be 100;
rand () is a function that generates random numbers within the range 0, 1;
P besti for the optimal position of particle i, P si Is the population optimal position for particle i.
The inertial weight represents the influence of the velocity of the primary particles on the current velocity, and the value of the inertial weight needs to be adjusted according to the actual problem. If the inertia weight is larger, the particle swarm algorithm has stronger global searching capability, and is more beneficial to searching a swarm optimal solution; if the inertia weight value is smaller, the particle swarm algorithm has stronger local searching capability, and is more beneficial to searching the optimal solution of the particles. Therefore, the inertia weight needs to be adaptively adjusted to improve the performance of the algorithm, and an inertia weight adaptive adjustment formula is shown in a formula (4):
（4）；
wherein ω represents inertial weight, ω max Representing the maximum weight omega min Represents the minimum weight, t max The maximum number of iterations is represented, and t represents the current number of iterations.
In one possible implementation, the calculating the population fitness variance includes: calculating the population fitness variance of the particle swarm through a formula (3):
（3）；
wherein Q represents the number of particles, f i Fitness f for the ith particle avg For an average fitness of a population of particles, f represents a normalization factor, and determining the normalization factor comprises:
determining the difference value between the fitness of each particle and the average fitness of the particle swarm, and selecting the maximum value of the difference values;
comparing the maximum value with 1, selecting the maximum value as the normalization factor if the maximum value is larger than 1, and selecting 1 as the normalization factor if the maximum value is smaller than 1.
According to another aspect of the present disclosure, there is provided an electronic device, wherein the electronic device includes: a processor and a memory storing computer executable instructions that, when executed, cause the processor to perform a data processing based customer classification method.
According to another aspect of the present disclosure, there is provided a computer readable storage medium storing one or more instructions, wherein the one or more instructions, when executed by a processor, implement a method of customer classification based on data processing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvements in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (6)
1. A method of classifying clients based on data processing, the method comprising:
establishing a classification index system, wherein the classification index system comprises a first layer of classification indexes and a second layer of classification indexes, and the first layer of classification indexes comprise: the second-layer classification indexes comprise average purchase quantity and average transaction amount related to the current value, the number of purchased commodity types related to the potential value, customer stay time, purchase frequency and comment airing number;
acquiring client data of an electronic commerce enterprise; the customer data includes: average purchase amount, average transaction amount, type of goods purchased, customer residence time, comment on the sun number, frequency of purchase;
storing client data for a plurality of clients in a matrix manner;
the standardized processing of the customer data comprises the following steps: processing the client data to enable the value to be in the range of the [0,1] interval; wherein the data set formed by the client data comprises N samples;
then k sample cluster centers are selected, the positions of the sample cluster centers are used as initial values of the particle individual positions and the group optimal positions, the speed of the particle individual is initialized, the positions of the sample cluster centers are used as the particle individual optimal positions, and the particle individual optimal position fitness is calculated; wherein the particles are samples in the dataset;
calculating the fitness value of each particle according to a particle swarm algorithm, for each particle, taking the current position as a new individual optimal position if the fitness value of the current position of the particle is smaller than that of the individual optimal position, and taking the current position as a new global optimal position if the fitness value of the current position of the particle is smaller than that of the group optimal position;
calculating the fitness value of the optimal position of the group;
updating the speed and the position of the particles according to a particle swarm algorithm; the velocity and position of the particles are vectors;
calculating a population fitness variance, wherein the population fitness variance reflects the degree of particle convergence in the particle swarm;
terminating the particle swarm algorithm iteration when the population fitness variance is smaller than a threshold value;
taking the global best position as a clustering center, calculating the distance from the rest particles to the clustering center, classifying according to the distance, and determining a new clustering center;
if the maximum iteration number is reached, comparing the fitness of the new clustering center with the fitness of the previous particle, and if the fitness of the new clustering center is better, updating the particle with the position of the new clustering center and ending the operation to obtain a clustering result;
wherein the result of the clustering comprises the average purchase amount, the average transaction amount, the customer residence time, the comment count, the purchase frequency, the purchase commodity type and the number of customers contained in the current class of each clustering center.
2. A method of classifying clients based on data processing according to claim 1, wherein said calculating the fitness value of each particle according to the particle swarm algorithm comprises:
and calculating the sum of the distances between the sample data and each cluster center to obtain the fitness value.
3. A method of classifying clients based on data processing according to claim 1, wherein updating the speed and position of particles according to a particle swarm algorithm comprises: updating the velocity of the particles by equation (1), and updating the particle position by equation (2):
（1）；
（2）；
wherein t is the current iteration number, V i (t) represents the current velocity of the particle, ω is an inertial weight, the inertial weight represents the influence of the primary particle velocity on the current velocity, l 1 And l 2 As a learning factor, the sub-table represents the influence degree of the optimal positions of individuals and groups on speed updating;
rand () is a function that generates random numbers within the range 0, 1;
P besti for the optimal position of particle i, P si Is the population optimal position for particle i.
4. A method of classifying clients based on data processing according to claim 2, wherein said calculating a population fitness variance comprises: calculating the population fitness variance of the particle swarm through a formula (3):
（3）；
wherein Q represents the number of particles, f i Fitness f for the ith particle avg For an average fitness of a population of particles, f represents a normalization factor, and determining the normalization factor comprises:
determining the difference value between the fitness of each particle and the average fitness of the particle swarm, and selecting the maximum value of the difference values;
comparing the maximum value with 1, selecting the maximum value as the normalization factor if the maximum value is larger than 1, and selecting 1 as the normalization factor if the maximum value is smaller than 1.
5. An electronic device, wherein the electronic device comprises: a processor and a memory storing computer executable instructions which, when executed, cause the processor to perform the method of any of claims 1-4.
6. A computer readable storage medium storing one or more instructions which, when executed by a processor, implement the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311841473.XA CN117493979A (en) | 2023-12-29 | 2023-12-29 | Customer classification method based on data processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311841473.XA CN117493979A (en) | 2023-12-29 | 2023-12-29 | Customer classification method based on data processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117493979A true CN117493979A (en) | 2024-02-02 |
Family
ID=89676766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311841473.XA Pending CN117493979A (en) | 2023-12-29 | 2023-12-29 | Customer classification method based on data processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117493979A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295969A (en) * | 2016-08-02 | 2017-01-04 | 贵州电网有限责任公司信息中心 | Power customer is worth a kind of weighting K means method hived off |
| CN107220841A (en) * | 2016-03-22 | 2017-09-29 | 上海市玻森数据科技有限公司 | A kind of clustering system based on business data |
| CN108230029A (en) * | 2017-12-29 | 2018-06-29 | 西南大学 | Client trading behavior analysis method |
| CN110866782A (en) * | 2019-11-06 | 2020-03-06 | 中国农业大学 | Customer classification method and system and electronic equipment |
| CN110909773A (en) * | 2019-11-08 | 2020-03-24 | 中国农业大学 | Client classification method and system based on adaptive particle swarm |
| CN111967723A (en) * | 2020-07-24 | 2020-11-20 | 南昌大学 | User peak regulation potential analysis method based on data mining |
| CN115170294A (en) * | 2022-07-22 | 2022-10-11 | 中国工商银行股份有限公司 | Client classification method and device and server |
-
2023
- 2023-12-29 CN CN202311841473.XA patent/CN117493979A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220841A (en) * | 2016-03-22 | 2017-09-29 | 上海市玻森数据科技有限公司 | A kind of clustering system based on business data |
| CN106295969A (en) * | 2016-08-02 | 2017-01-04 | 贵州电网有限责任公司信息中心 | Power customer is worth a kind of weighting K means method hived off |
| CN108230029A (en) * | 2017-12-29 | 2018-06-29 | 西南大学 | Client trading behavior analysis method |
| CN110866782A (en) * | 2019-11-06 | 2020-03-06 | 中国农业大学 | Customer classification method and system and electronic equipment |
| CN110909773A (en) * | 2019-11-08 | 2020-03-24 | 中国农业大学 | Client classification method and system based on adaptive particle swarm |
| CN111967723A (en) * | 2020-07-24 | 2020-11-20 | 南昌大学 | User peak regulation potential analysis method based on data mining |
| CN115170294A (en) * | 2022-07-22 | 2022-10-11 | 中国工商银行股份有限公司 | Client classification method and device and server |
Non-Patent Citations (2)
| Title |
|---|
| 毛清华等: "《矿用带式输送机智能监测及防护技术》", 31 May 2020, 华中科技大学出版社, pages: 95 * |
| 王巧玉: "基于客户价值的B2C电商企业客户分类研究", 中国优秀硕士学位论文全文数据库信息科技辑, vol. 2021, no. 2, 15 February 2021 (2021-02-15), pages 140 - 289 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220335501A1 (en) | Item recommendations using convolutions on weighted graphs | |
| Li et al. | Unsupervised streaming feature selection in social media | |
| Thorleuchter et al. | Analyzing existing customers’ websites to improve the customer acquisition process as well as the profitability prediction in B-to-B marketing | |
| US20170364933A1 (en) | User maintenance system and method | |
| US11468471B2 (en) | Audience expansion according to user behaviors | |
| US8296182B2 (en) | Computer-implemented marketing optimization systems and methods | |
| CN109033101B (en) | Label recommendation method and device | |
| US20200394658A1 (en) | Determining subsets of accounts using a model of transactions | |
| CN108320171A (en) | Hot item prediction technique, system and device | |
| CN111931055B (en) | Object recommendation method, object recommendation device and electronic equipment | |
| WO2023103527A1 (en) | Access frequency prediction method and device | |
| CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
| Anwar et al. | Optimization of many objective pickup and delivery problem with delay time of vehicle using memetic decomposition based evolutionary algorithm | |
| US20220044244A1 (en) | Incremental addition to an augmented graph model | |
| CN111754287A (en) | Article screening method, apparatus, device and storage medium | |
| CN111612499A (en) | Information pushing method and device, storage medium and terminal | |
| CN110427545B (en) | Information pushing method and system | |
| CA3069987A1 (en) | System and method for detecting and responding to transaction patterns | |
| CN113424207B (en) | System and method for efficiently training understandable models | |
| CN113159213A (en) | Service distribution method, device and equipment | |
| CN113688906A (en) | Customer segmentation method and system based on quantum K-means algorithm | |
| US11829921B2 (en) | System and method for recommending demand-supply agent combination pairs for transactions using machine learning | |
| CN108804520A (en) | A kind of visitor's behavior sorting technique and system | |
| CN117493979A (en) | Customer classification method based on data processing | |
| Xu et al. | aDMSCN: a novel perspective for user intent prediction in customer service bots |
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 |