CN112581183A - Intelligent client classification system for enterprise service - Google Patents
Intelligent client classification system for enterprise service Download PDFInfo
- Publication number
- CN112581183A CN112581183A CN202011576638.1A CN202011576638A CN112581183A CN 112581183 A CN112581183 A CN 112581183A CN 202011576638 A CN202011576638 A CN 202011576638A CN 112581183 A CN112581183 A CN 112581183A
- Authority
- CN
- China
- Prior art keywords
- clients
- client
- zone
- transaction
- customers
- 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
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000012795 verification Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 5
- 101000878595 Arabidopsis thaliana Squalene synthase 1 Proteins 0.000 claims description 3
- 101000713575 Homo sapiens Tubulin beta-3 chain Proteins 0.000 claims description 3
- 101000713585 Homo sapiens Tubulin beta-4A chain Proteins 0.000 claims description 3
- 102100036790 Tubulin beta-3 chain Human genes 0.000 claims description 3
- 102100036788 Tubulin beta-4A chain Human genes 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 description 11
- 238000005457 optimization Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0204—Market segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/45—Structures or tools for the administration of authentication
- G06F21/46—Structures or tools for the administration of authentication by designing passwords or checking the strength of passwords
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- General Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent client classification system for enterprise service, which comprises a user collection unit, a key data sorting unit, an association collection unit, a self-classification unit, a processor, a user side, an identity verification end, a database, a self-encryption unit and a management unit, wherein the user collection unit is used for collecting key data; the user collecting unit is used for collecting all the clients transacted with the company and collecting corresponding transaction information, and the transaction information comprises transaction time, transaction amount and transaction cost; the invention collects all the clients transacted with the company by the user collecting unit and collects the corresponding transaction information, wherein the transaction information comprises transaction time, transaction amount and transaction cost; and then carrying out base processing on the transaction information by using a key data sorting unit to obtain a first zone client Sj, a second zone client Eo, a second zone client Cu and a last zone client Ma.
Description
Technical Field
The invention belongs to the field of customer classification, relates to an intelligent enterprise service technology, and particularly relates to an intelligent customer classification system for enterprise service.
Background
Publication number CN110909773A provides a client classification method and system based on adaptive particle swarm, the method includes: dynamically adjusting the inertia weight of the standard particle swarm optimization according to the search state change characteristics of particles in the particle swarm to obtain an improved particle swarm optimization algorithm; updating the positions of the particles according to the improved particle swarm optimization algorithm, and performing border crossing processing on the positions of the particles to obtain a plurality of clustering centers; taking the plurality of clustering centers as initial clustering centers of a K-Means clustering algorithm to obtain a client classification model of the self-adaptive particle swarm; and clustering the purchasing behavior characteristic data set of the target customer group according to the customer classification model of the self-adaptive particle swarm to obtain a customer classification result of the target customer group. The embodiment of the invention improves the convergence precision and efficiency of the particle swarm algorithm, avoids the problem of local minimum value, and can effectively and accurately divide the consumers.
However, for enterprises, the inability to classify customers more accurately generally involves only the analysis of premium customers, and does not involve some customer analysis that has been lost; in order to solve this technical drawback, a solution is now provided.
Disclosure of Invention
The invention aims to provide an intelligent client classification system for enterprise service.
The purpose of the invention can be realized by the following technical scheme:
an intelligent client classification system for enterprise service comprises a user collecting unit, a key data sorting unit, an association collecting unit, a self-classification unit, a processor, a user side, an identity verification side, a database, a self-encryption unit and a management unit;
the user collecting unit is used for collecting all the clients transacted with the company and collecting corresponding transaction information, wherein the transaction information comprises transaction time, transaction amount and transaction cost;
the user collecting unit is used for transmitting transaction information to the key data sorting unit, the key data sorting unit receives the transaction information transmitted by the user collecting unit and carries out base division processing on the transaction information, and a first zone client Sj, a second zone client Eo, a second zone client Cu and a last zone client Ma are obtained;
the key data sorting unit is used for transmitting the secondary area client Cu and the final area client Ma to the association searching unit;
the key data sorting unit is used for transmitting first zone clients, second zone clients, secondary zone clients and last zone clients to the self-classifying unit, and the self-classifying unit receives the first zone clients, the second zone clients, the secondary zone clients and the last zone clients transmitted by the key data sorting unit;
the association collection unit is used for performing association data collection processing on the secondary region client and the last region client to obtain loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma;
the association collection unit is used for transmitting the loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma to the self-classification unit, and the self-classification unit receives the loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma which are transmitted by the association collection unit;
the self-classification unit is used for performing customer analysis steps on first zone customers, second zone customers, secondary zone customers and last zone customers, and comprises the following specific steps:
SS 1: acquiring a first area client and a second area client;
SS 2: acquiring corresponding transaction information, and marking single-time values according to first-zone customers and second-zone customers;
SS 3: marking the single-value of the first area client as 1.5, and marking the single-value of the second area client as 1;
SS 4: acquiring a first zone client and a second zone client, and marking the fusion of the first zone client and the second zone client as a zone evaluation client Esj, wherein j is 1.. X1+ X2; its single value is marked as Dsj; acquiring the transaction time, the transaction amount and the transaction cost corresponding to the evaluation area client Esj;
SS 5: obtaining the transaction times corresponding to all the appraisal area clients Esj according to the transaction time, and marking the transaction times as the number Wsj of the coming and going times, wherein j is 1.. X1+ X2;
SS 6: automatically calculating profit points of all the clients in the assessment area according to the transaction amount and the transaction cost in the transaction information of the clients Esj in the assessment area, and marking the profit points as Lsj, wherein j is 1.. X1+ X2; wherein Lsj, Wsj and Esj are in one-to-one correspondence;
SS 7: and (3) calculating the merit Ysj of all the clients in the assessment area by using a formula, wherein the specific calculation formula is as follows:
Ysj=Dsj*(0.537*Wsj+0.463*Lsj);
wherein the calculation is performed on the basis of the removed dimension; 0.537 and 0.463 are both preset weights;
SS 8: sorting according to the order of the merit Ysj from big to small, marking the corresponding client in the assessment area with the top B1 as a high-quality sticky client, and marking the rest as a recent client; b1 is a preset value;
SS 9: acquiring loss amounts Lu and Lma corresponding to a secondary area client Cu and a last area client Ma;
SS 10: acquiring the transaction times of a secondary area client Cu and a final area client Ma, and respectively marking the transaction times as Hu and Ha;
SS 11: automatically calculating the pull values Whu and Wha of the client Cu in the secondary district and the client Ma in the last district, wherein the specific calculation formula is as follows:
Whu=1.35*(0.732*Lu+0.268*1/Hu);
Wha=1*(0.732*Lma+0.268*1/Ha);
wherein, 0.732 and 0.268 are preset weights;
SS 12: mixing the secondary zone clients and the last zone clients, and sequencing the secondary zone clients and the last zone clients according to the sequence from large to small in the rank order;
SS 13: marking the first B2 ranking as potential rebooting clients and the rest as attrition clients;
SS 14: potential reopening customers, churning customers, high-quality sticky customers and near-term customers are obtained;
the management unit is in communication connection with the processor.
Further, the basic processing comprises the following specific steps:
the method comprises the following steps: acquiring all customers, and marking the customers as Ki, i 1.. n;
step two: then, transaction time in all transaction information of the user is obtained, the last transaction of each customer is obtained, the last transaction is marked as end-loading time, and the end-loading time is marked as Zi, i is 1.. n;
step three: acquiring all terminal loading time Zi; acquiring the current earliest load end time, acquiring the current time interval and marking the current time interval as G;
step four: calculating the interval period by using a formula, wherein the specific calculation formula is that the interval period is G/4;
step five: dividing one carrier interval at intervals from the carrier end time to the current time to obtain four carrier intervals;
step six: dividing all clients into four intervals according to the last-zone time Zi to obtain first-zone clients, second-zone clients and last-zone clients, wherein the first-zone clients refer to the clients closest to the current last-zone interval, and the second-zone clients, the second-zone clients and the last-zone clients are analogized backwards in sequence;
step seven: sequentially marking a first area client, a second area client and an end area client as Sj, j is 1.. X1, Eo, o is 1.. X2 and Cu, u is 1.. X3 and Ma, a is 1.. X4; wherein X1+ X2+ X3+ X4 is n.
Further, the data collection processing comprises the following specific steps:
s1: acquiring all secondary area client Cu, u ═ 1.. X3;
s2: obtaining a corresponding secondary area customer, which is a trade product of the company, and marking the secondary area customer as a class product;
s3: acquiring the expenditure amount of the similar products, and marking the expenditure amount as the loss amount L1;
s4: repeating the steps S2-S4 by making u equal to u +1, and marking the loss amount of the customer Cu in all secondary areas as Lu, u equal to 1.. X3; lu corresponds to Cu one by one;
s5: then all end area clients Ma, a 1.. X4 are obtained;
s6: according to the same principle of steps S2-S4, the attrition amount of the end zone customer Ma is obtained, which is marked as Lma, a 1.. X4;
s7: and obtaining loss amounts Lu and Lma corresponding to the secondary area customer Cu and the final area customer Ma.
Further, the self-classifying unit is used for transmitting potential reopening clients, attrition clients, quality sticky clients and recent clients to the processor, and the processor is used for transmitting the potential reopening clients, the attrition clients, the quality sticky clients and the recent clients to the database;
the database receives potential reopening clients, lost clients, high-quality sticky clients and recent clients transmitted by the processor and stores the potential reopening clients, lost clients, high-quality sticky clients and recent clients in real time; the self-encryption unit is used for giving authority to potential reopening clients, lost clients, high-quality sticky clients and recent clients stored in the database, and the specific giving process is as follows:
s01: marking potential reopening users and high-quality sticky clients as primary rights;
s02: marking the recent clients as secondary rights;
s03: marking lost clients as three-level permissions;
the user side is used for a user to log in the user by combining with the identity verification side, and the specific operation steps are as follows:
SS 01: a user inputs a password and an account through a user side;
SS 02: the authority level of the corresponding account is automatically acquired by means of the account and the standard password thereof stored by the identity verification terminal; the permission level comprises a primary permission, a secondary permission and a tertiary permission; the authority level is initially input by an administrator;
SS 03: when the password is successfully verified, automatically acquiring the authority level of the user;
SS 04: and accessing the corresponding content in the database through the processor by virtue of the identity verification terminal according to the authority level of the user.
Further, the management unit is used for recording all preset values.
The invention has the beneficial effects that:
the invention collects all the clients transacted with the company by the user collecting unit and collects the corresponding transaction information, wherein the transaction information comprises transaction time, transaction amount and transaction cost; then, carrying out base processing on the transaction information by using a key data sorting unit to obtain a first zone client Sj, a second zone client Eo, a second zone client Cu and a last zone client Ma;
then, the key data sorting unit is used for transmitting the first zone clients, the second zone clients, the secondary zone clients and the last zone clients to the self-classifying unit, and then the self-classifying unit is used for receiving the first zone clients, the second zone clients, the secondary zone clients and the last zone clients transmitted by the key data sorting unit; then, the association collection unit is used for performing association data collection processing on the secondary region client and the last region client to obtain loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma; then, performing a customer analysis step on first-region customers, second-region customers and last-region customers by means of a self-classification unit to obtain potential reopening customers, lost customers, high-quality sticky customers and recent customers; therefore, the accurate classification of the clients is realized, the existing high-quality clients and the overlooked clients excavated from the past clients are fully considered; the invention is simple, effective and easy to use.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is a block diagram of the system of the present invention.
Detailed Description
As shown in fig. 1, an intelligent client classification system for enterprise services includes a user collection unit, a key data sorting unit, an association collection unit, a self-classification unit, a processor, a user side, an identity verification side, a database, a self-encryption unit, and a management unit;
the user collecting unit is used for collecting all the clients transacted with the company and collecting corresponding transaction information, wherein the transaction information comprises transaction time, transaction amount and transaction cost;
the user collecting unit is used for transmitting the transaction information to the key data sorting unit, the key data sorting unit receives the transaction information transmitted by the user collecting unit and carries out base processing on the transaction information, and the specific base processing steps are as follows:
the method comprises the following steps: acquiring all customers, and marking the customers as Ki, i 1.. n;
step two: then, transaction time in all transaction information of the user is obtained, the last transaction of each customer is obtained, the last transaction is marked as end-loading time, and the end-loading time is marked as Zi, i is 1.. n;
step three: acquiring all terminal loading time Zi; acquiring the current earliest load end time, acquiring the current time interval and marking the current time interval as G;
step four: calculating the interval period by using a formula, wherein the specific calculation formula is that the interval period is G/4;
step five: dividing one carrier interval at intervals from the carrier end time to the current time to obtain four carrier intervals;
step six: dividing all clients into four intervals according to the last-zone time Zi to obtain first-zone clients, second-zone clients and last-zone clients, wherein the first-zone clients refer to the clients closest to the current last-zone interval, and the second-zone clients, the second-zone clients and the last-zone clients are analogized backwards in sequence;
step seven: sequentially marking a first area client, a second area client and an end area client as Sj, j is 1.. X1, Eo, o is 1.. X2 and Cu, u is 1.. X3 and Ma, a is 1.. X4; wherein X1+ X2+ X3+ X4 ═ n;
the key data sorting unit is used for transmitting the secondary area client Cu and the final area client Ma to the association searching unit;
the key data sorting unit is used for transmitting first zone clients, second zone clients, secondary zone clients and last zone clients to the self-classifying unit, and the self-classifying unit receives the first zone clients, the second zone clients, the secondary zone clients and the last zone clients transmitted by the key data sorting unit;
the association gathering unit is used for performing association data gathering processing on the secondary area client and the last area client, and the specific processing steps are as follows:
s1: acquiring all secondary area client Cu, u ═ 1.. X3;
s2: obtaining a corresponding secondary area customer, which is a trade product of the company, and marking the secondary area customer as a class product;
s3: acquiring the expenditure amount of the similar products, and marking the expenditure amount as the loss amount L1;
s4: repeating the steps S2-S4 by making u equal to u +1, and marking the loss amount of the customer Cu in all secondary areas as Lu, u equal to 1.. X3; lu corresponds to Cu one by one;
s5: then all end area clients Ma, a 1.. X4 are obtained;
s6: according to the same principle of steps S2-S4, the attrition amount of the end zone customer Ma is obtained, which is marked as Lma, a 1.. X4;
s7: obtaining loss amounts Lu and Lma corresponding to the secondary area customer Cu and the last area customer Ma;
the association collection unit is used for transmitting the loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma to the self-classification unit, and the self-classification unit receives the loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma which are transmitted by the association collection unit;
the self-classification unit is used for performing customer analysis steps on first zone customers, second zone customers, secondary zone customers and last zone customers, and comprises the following specific steps:
SS 1: acquiring a first area client and a second area client;
SS 2: acquiring corresponding transaction information, and marking single-time values according to first-zone customers and second-zone customers;
SS 3: marking the single-value of the first area client as 1.5, and marking the single-value of the second area client as 1;
SS 4: acquiring a first zone client and a second zone client, and marking the fusion of the first zone client and the second zone client as a zone evaluation client Esj, wherein j is 1.. X1+ X2; its single value is marked as Dsj; acquiring the transaction time, the transaction amount and the transaction cost corresponding to the evaluation area client Esj;
SS 5: obtaining the transaction times corresponding to all the appraisal area clients Esj according to the transaction time, and marking the transaction times as the number Wsj of the coming and going times, wherein j is 1.. X1+ X2;
SS 6: automatically calculating profit points of all the clients in the assessment area according to the transaction amount and the transaction cost in the transaction information of the clients Esj in the assessment area, and marking the profit points as Lsj, wherein j is 1.. X1+ X2; wherein Lsj, Wsj and Esj are in one-to-one correspondence;
SS 7: and (3) calculating the merit Ysj of all the clients in the assessment area by using a formula, wherein the specific calculation formula is as follows:
Ysj=Dsj*(0.537*Wsj+0.463*Lsj);
wherein the calculation is performed on the basis of the removed dimension; 0.537 and 0.463 are both preset weights, because different factors have different influences on the final result, and in order to highlight the influences, the weights are introduced, and specific values are obtained by a plurality of test modes;
SS 8: sorting according to the order of the merit Ysj from big to small, marking the corresponding client in the assessment area with the top B1 as a high-quality sticky client, and marking the rest as a recent client; b1 is a predetermined value, and particularly preferably 30 or more;
SS 9: acquiring loss amounts Lu and Lma corresponding to a secondary area client Cu and a last area client Ma;
SS 10: acquiring the transaction times of a secondary area client Cu and a final area client Ma, and respectively marking the transaction times as Hu and Ha;
SS 11: automatically calculating the pull values Whu and Wha of the client Cu in the secondary district and the client Ma in the last district, wherein the specific calculation formula is as follows:
Whu=1.35*(0.732*Lu+0.268*1/Hu);
Wha=1*(0.732*Lma+0.268*1/Ha);
in the formula, 0.732 and 0.268 are preset weights and are introduced to highlight different influences of different factors; 1.35 and 1 are added values introduced by corresponding secondary zone clients and final zone clients due to different time;
SS 12: mixing the secondary zone clients and the last zone clients, and sequencing the secondary zone clients and the last zone clients according to the sequence from large to small in the rank order;
SS 13: marking the first B2 ranking as potential rebooting clients and the rest as attrition clients;
SS 14: potential reopening customers, churning customers, high-quality sticky customers and near-term customers are obtained;
the self-classification unit is used for transmitting potential reopening clients, attrition clients, high-quality sticky clients and recent clients to the processor, and the processor is used for transmitting the potential reopening clients, the attrition clients, the high-quality sticky clients and the recent clients to the database;
the database receives potential reopening clients, lost clients, high-quality sticky clients and recent clients transmitted by the processor and stores the potential reopening clients, lost clients, high-quality sticky clients and recent clients in real time; the self-encryption unit is used for giving authority to potential reopening clients, lost clients, high-quality sticky clients and recent clients stored in the database, and the specific giving process is as follows:
s01: marking potential reopening users and high-quality sticky clients as primary rights;
s02: marking the recent clients as secondary rights;
s03: marking lost clients as three-level permissions;
the user side is used for a user to log in the user by combining with the identity verification side, and the specific operation steps are as follows:
SS 01: a user inputs a password and an account through a user side;
SS 02: the authority level of the corresponding account is automatically acquired by means of the account and the standard password thereof stored by the identity verification terminal; the permission level comprises a primary permission, a secondary permission and a tertiary permission; the authority level is initially input by an administrator;
SS 03: when the password is successfully verified, automatically acquiring the authority level of the user;
SS 04: accessing corresponding contents in the database through the processor by means of the identity verification terminal according to the authority level of the user;
the management unit is in communication connection with the processor and is used for recording all preset values.
An intelligent customer classification system for enterprise service is disclosed, wherein when in work, a user collection unit is used for collecting all customers transacted with a company and collecting corresponding transaction information, wherein the transaction information comprises transaction time, transaction amount and transaction cost; then, carrying out base processing on the transaction information by using a key data sorting unit to obtain a first zone client Sj, a second zone client Eo, a second zone client Cu and a last zone client Ma;
then, the key data sorting unit is used for transmitting the first zone clients, the second zone clients, the secondary zone clients and the last zone clients to the self-classifying unit, and then the self-classifying unit is used for receiving the first zone clients, the second zone clients, the secondary zone clients and the last zone clients transmitted by the key data sorting unit; then, the association collection unit is used for performing association data collection processing on the secondary region client and the last region client to obtain loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma; then, performing a customer analysis step on first-region customers, second-region customers and last-region customers by means of a self-classification unit to obtain potential reopening customers, lost customers, high-quality sticky customers and recent customers; therefore, the accurate classification of the clients is realized, the existing high-quality clients and the overlooked clients excavated from the past clients are fully considered; the invention is simple, effective and easy to use.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (5)
1. An intelligent client classification system for enterprise service is characterized by comprising a user collection unit, a key data sorting unit, an association collection unit, a self-classification unit, a processor, a user side, an identity verification end, a database, a self-encryption unit and a management unit;
the user collecting unit is used for collecting all the clients transacted with the company and collecting corresponding transaction information, wherein the transaction information comprises transaction time, transaction amount and transaction cost;
the user collecting unit is used for transmitting transaction information to the key data sorting unit, the key data sorting unit receives the transaction information transmitted by the user collecting unit and carries out base division processing on the transaction information, and a first zone client Sj, a second zone client Eo, a second zone client Cu and a last zone client Ma are obtained;
the key data sorting unit is used for transmitting the secondary area client Cu and the final area client Ma to the association searching unit;
the key data sorting unit is used for transmitting first zone clients, second zone clients, secondary zone clients and last zone clients to the self-classifying unit, and the self-classifying unit receives the first zone clients, the second zone clients, the secondary zone clients and the last zone clients transmitted by the key data sorting unit;
the association collection unit is used for performing association data collection processing on the secondary region client and the last region client to obtain loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma;
the association collection unit is used for transmitting the loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma to the self-classification unit, and the self-classification unit receives the loss amounts Lu and Lma corresponding to the secondary region client Cu and the last region client Ma which are transmitted by the association collection unit;
the self-classification unit is used for performing customer analysis steps on first zone customers, second zone customers, secondary zone customers and last zone customers, and comprises the following specific steps:
SS 1: acquiring a first area client and a second area client;
SS 2: acquiring corresponding transaction information, and marking single-time values according to first-zone customers and second-zone customers;
SS 3: marking the single-value of the first area client as 1.5, and marking the single-value of the second area client as 1;
SS 4: acquiring a first zone client and a second zone client, and marking the fusion of the first zone client and the second zone client as a zone evaluation client Esj, wherein j is 1.. X1+ X2; its single value is marked as Dsj; acquiring the transaction time, the transaction amount and the transaction cost corresponding to the evaluation area client Esj;
SS 5: obtaining the transaction times corresponding to all the appraisal area clients Esj according to the transaction time, and marking the transaction times as the number Wsj of the coming and going times, wherein j is 1.. X1+ X2;
SS 6: automatically calculating profit points of all the clients in the assessment area according to the transaction amount and the transaction cost in the transaction information of the clients Esj in the assessment area, and marking the profit points as Lsj, wherein j is 1.. X1+ X2; wherein Lsj, Wsj and Esj are in one-to-one correspondence;
SS 7: and (3) calculating the merit Ysj of all the clients in the assessment area by using a formula, wherein the specific calculation formula is as follows:
Ysj=Dsj*(0.537*Wsj+0.463*Lsj);
wherein the calculation is performed on the basis of the removed dimension; 0.537 and 0.463 are both preset weights;
SS 8: sorting according to the order of the merit Ysj from big to small, marking the corresponding client in the assessment area with the top B1 as a high-quality sticky client, and marking the rest as a recent client; b1 is a preset value;
SS 9: acquiring loss amounts Lu and Lma corresponding to a secondary area client Cu and a last area client Ma;
SS 10: acquiring the transaction times of a secondary area client Cu and a final area client Ma, and respectively marking the transaction times as Hu and Ha;
SS 11: automatically calculating the pull values Whu and Wha of the client Cu in the secondary district and the client Ma in the last district, wherein the specific calculation formula is as follows:
Whu=1.35*(0.732*Lu+0.268*1/Hu);
Wha=1*(0.732*Lma+0.268*1/Ha);
wherein, 0.732 and 0.268 are preset weights;
SS 12: mixing the secondary zone clients and the last zone clients, and sequencing the secondary zone clients and the last zone clients according to the sequence from large to small in the rank order;
SS 13: marking the first B2 ranking as potential rebooting clients and the rest as attrition clients;
SS 14: potential reopening customers, churning customers, high-quality sticky customers and near-term customers are obtained;
the management unit is in communication connection with the processor.
2. The intelligent client classification system for enterprise services as claimed in claim 1, wherein the base processing comprises the following steps:
the method comprises the following steps: acquiring all customers, and marking the customers as Ki, i 1.. n;
step two: then, transaction time in all transaction information of the user is obtained, the last transaction of each customer is obtained, the last transaction is marked as end-loading time, and the end-loading time is marked as Zi, i is 1.. n;
step three: acquiring all terminal loading time Zi; acquiring the current earliest load end time, acquiring the current time interval and marking the current time interval as G;
step four: calculating the interval period by using a formula, wherein the specific calculation formula is that the interval period is G/4;
step five: dividing one carrier interval at intervals from the carrier end time to the current time to obtain four carrier intervals;
step six: dividing all clients into four intervals according to the last-zone time Zi to obtain first-zone clients, second-zone clients and last-zone clients, wherein the first-zone clients refer to the clients closest to the current last-zone interval, and the second-zone clients, the second-zone clients and the last-zone clients are analogized backwards in sequence;
step seven: sequentially marking a first area client, a second area client and an end area client as Sj, j is 1.. X1, Eo, o is 1.. X2 and Cu, u is 1.. X3 and Ma, a is 1.. X4; wherein X1+ X2+ X3+ X4 is n.
3. The intelligent client classification system for enterprise services as claimed in claim 1, wherein the data gathering process comprises the following steps:
s1: acquiring all secondary area client Cu, u ═ 1.. X3;
s2: obtaining a corresponding secondary area customer, which is a trade product of the company, and marking the secondary area customer as a class product;
s3: acquiring the expenditure amount of the similar products, and marking the expenditure amount as the loss amount L1;
s4: repeating the steps S2-S4 by making u equal to u +1, and marking the loss amount of the customer Cu in all secondary areas as Lu, u equal to 1.. X3; lu corresponds to Cu one by one;
s5: then all end area clients Ma, a 1.. X4 are obtained;
s6: according to the same principle of steps S2-S4, the attrition amount of the end zone customer Ma is obtained, which is marked as Lma, a 1.. X4;
s7: and obtaining loss amounts Lu and Lma corresponding to the secondary area customer Cu and the final area customer Ma.
4. The intelligent customer classification system for enterprise services as claimed in claim 1, wherein the self-classification unit is configured to transmit potential reopening customers, attrition customers, premium sticky customers and recent customers to the processor, and the processor is configured to transmit the potential reopening customers, the attrition customers, the premium sticky customers and the recent customers to the database;
the database receives potential reopening clients, lost clients, high-quality sticky clients and recent clients transmitted by the processor and stores the potential reopening clients, lost clients, high-quality sticky clients and recent clients in real time; the self-encryption unit is used for giving authority to potential reopening clients, lost clients, high-quality sticky clients and recent clients stored in the database, and the specific giving process is as follows:
s01: marking potential reopening users and high-quality sticky clients as primary rights;
s02: marking the recent clients as secondary rights;
s03: marking lost clients as three-level permissions;
the user side is used for a user to log in the user by combining with the identity verification side, and the specific operation steps are as follows:
SS 01: a user inputs a password and an account through a user side;
SS 02: the authority level of the corresponding account is automatically acquired by means of the account and the standard password thereof stored by the identity verification terminal; the permission level comprises a primary permission, a secondary permission and a tertiary permission; the authority level is initially input by an administrator;
SS 03: when the password is successfully verified, automatically acquiring the authority level of the user;
SS 04: and accessing the corresponding content in the database through the processor by virtue of the identity verification terminal according to the authority level of the user.
5. The intelligent client classification system for enterprise services as claimed in claim 1, wherein said management unit is configured to enter all default values.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011576638.1A CN112581183A (en) | 2020-12-28 | 2020-12-28 | Intelligent client classification system for enterprise service |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011576638.1A CN112581183A (en) | 2020-12-28 | 2020-12-28 | Intelligent client classification system for enterprise service |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112581183A true CN112581183A (en) | 2021-03-30 |
Family
ID=75140048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011576638.1A Pending CN112581183A (en) | 2020-12-28 | 2020-12-28 | Intelligent client classification system for enterprise service |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112581183A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116227969A (en) * | 2022-12-14 | 2023-06-06 | 广州永兆网络科技有限公司 | Cloud computing-based enterprise client marketing intelligent management system |
-
2020
- 2020-12-28 CN CN202011576638.1A patent/CN112581183A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116227969A (en) * | 2022-12-14 | 2023-06-06 | 广州永兆网络科技有限公司 | Cloud computing-based enterprise client marketing intelligent management system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Simon | A formal theory of the employment relationship | |
SubbaNarasimha et al. | Technological knowledge and firm performance of pharmaceutical firms | |
US20040267553A1 (en) | Evaluating storage options | |
CN113051291A (en) | Work order information processing method, device, equipment and storage medium | |
CN112907305A (en) | Customer full-period management system based on big data analysis | |
KR20160056304A (en) | A Computer Apparatus for Providing Customized Consulting | |
CN115577152A (en) | Online book borrowing management system based on data analysis | |
CN112581183A (en) | Intelligent client classification system for enterprise service | |
CN114037504A (en) | Collection, recruitment and bidding system based on Internet | |
US20020147596A1 (en) | On-line laboratory services brokerage system | |
Schlegelmilch | Can export performance be explained by attitudinal differences? | |
ali Khan et al. | An evaluation of requirement prioritization techniques with ANP | |
Triantis | Fuzzy non-radial data envelopment analysis (DEA) measures of technical efficiency in support of an integrated performance measurement system | |
CN116976492A (en) | Wind control strategy comparison optimization management system and method | |
Hopenhayn et al. | Optimal simple ratings | |
Behdani et al. | An alternative approach to rank efficient DMUs in DEA via cross-efficiency evaluation, Gini coefficient, and Bonferroni mean | |
CN114049213A (en) | Informatization financial data analysis system and analysis method | |
Otoiu et al. | Analysing Labour-Based Estimates of Automation and Their Implications. A Comparative Approach from an Economic Competitiveness Perspective. | |
Chen et al. | on revenue management with strategic customers choosing when and what to buy | |
de Moraes et al. | An Efficiency Frontier based Model for Cloud Computing Provider Selection and Ranking. | |
CN113191857A (en) | Cloud platform e-commerce data processing method and system based on big data | |
Astuti et al. | Public Service Community Satisfaction Survey And Evaluation: A State Health Center Perspective | |
Ohsato et al. | Construction of an Input-Output Table Considering Business-to-Consumer Transactions by using Private Data | |
Merkas | Digital Transformation Index Based On The Digital Maturity Model: Case Study Of Croatia | |
Danesh et al. | Requirements prioritization in on-line banking systems: using value-oriented framework |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210330 |