CN112633742A - Client resource allocation method, device, equipment and storage medium - Google Patents

Client resource allocation method, device, equipment and storage medium Download PDF

Info

Publication number
CN112633742A
CN112633742A CN202011612002.8A CN202011612002A CN112633742A CN 112633742 A CN112633742 A CN 112633742A CN 202011612002 A CN202011612002 A CN 202011612002A CN 112633742 A CN112633742 A CN 112633742A
Authority
CN
China
Prior art keywords
feature vector
customer feature
successful
analyzed
successful customer
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
Application number
CN202011612002.8A
Other languages
Chinese (zh)
Inventor
严杨扬
程克喜
卢显锋
晏湘涛
张政
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Property and Casualty Insurance Company of China Ltd
Original Assignee
Ping An Property and Casualty Insurance Company of China Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Property and Casualty Insurance Company of China Ltd filed Critical Ping An Property and Casualty Insurance Company of China Ltd
Priority to CN202011612002.8A priority Critical patent/CN112633742A/en
Publication of CN112633742A publication Critical patent/CN112633742A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Economics (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Strategic Management (AREA)
  • Evolutionary Computation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application relates to the technical field of artificial intelligence, and discloses a method, a device, equipment and a storage medium for allocating client resources, wherein the method comprises the following steps: determining a plurality of successful customer feature vector cluster sets according to the successful customer feature vector sets of the target personnel; determining a best successful customer feature vector cluster set from the plurality of successful customer feature vector cluster sets; determining a plurality of client characteristic vector cluster sets to be analyzed according to the optimal successful client characteristic vector cluster set and the client characteristic vector sets to be distributed; determining the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, finding out the maximum number of the optimal successful customer feature vectors, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors. Therefore, the matching degree of the marketing abilities of the target customer set and the target personnel is higher, and the selling success rate is favorably improved.

Description

Client resource allocation method, device, equipment and storage medium
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a device, and a storage medium for allocating client resources.
Background
In the prior art, the distribution of potential customers in the sales adopts a random distribution method, so that the matching degree of the marketing ability of a salesman and the distributed potential customers is not high, the success rate of the sales is not high, and the waste of labor cost is caused.
Disclosure of Invention
The application mainly aims to provide a method, a device, equipment and a storage medium for allocating customer resources, and aims to solve the technical problem that in the prior art, a method for randomly allocating potential customers is adopted, so that the matching degree of the marketing ability of a salesman and the allocated potential customers is not high, and the success rate of sales is not high.
In order to achieve the above object, the present application provides a method for allocating client resources, the method including:
acquiring a successful customer feature vector set of a target person;
clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets;
obtaining the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the optimal successful customer feature vector cluster set corresponding to the successful customer feature vector set;
acquiring a client feature vector set to be distributed;
clustering according to the optimal successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed;
respectively carrying out quantity statistics on each to-be-analyzed customer feature vector cluster set in the to-be-analyzed customer feature vector cluster sets to obtain the quantity of the best successful customer feature vectors corresponding to the to-be-analyzed customer feature vector cluster sets;
finding out the maximum number of the optimal successful customer feature vectors from the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors.
Further, the step of clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets includes:
respectively carrying out local density calculation on each successful customer feature vector in the successful customer feature vector set to obtain first to-be-analyzed local densities corresponding to all the successful customer feature vectors in the successful customer feature vector set;
respectively determining high local density and minimum Euclidean distance of the first to-be-analyzed local density corresponding to each successful customer feature vector of the successful customer feature vector set to obtain first high local density minimum Euclidean distances to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set;
respectively multiplying the first to-be-analyzed local density corresponding to each successful customer feature vector of the successful customer feature vector set and the first high local density minimum Euclidean distance to be analyzed to obtain first to-be-analyzed density distances corresponding to all the successful customer feature vectors of the successful customer feature vector set;
acquiring the first density distance to be analyzed from the first density distance to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set by adopting a first preset quantity to obtain a plurality of first target clustering centers corresponding to the successful customer feature vector set;
and clustering according to the plurality of first target clustering centers corresponding to the successful customer feature vector set and the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain the successful customer feature vector clustering sets corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector set.
Further, the step of respectively performing local density calculation on each successful customer feature vector in the successful customer feature vector set to obtain a first local density to be analyzed corresponding to each successful customer feature vector in the successful customer feature vector set includes:
respectively carrying out Euclidean distance calculation between every two successful customer feature vectors in the successful customer feature vector set to obtain a to-be-processed Euclidean distance set corresponding to the successful customer feature vector set;
respectively carrying out local density calculation on each successful customer feature vector in the successful customer feature vector set according to the Euclidean distance set to be processed corresponding to the successful customer feature vector set to obtain the first local density to be analyzed corresponding to all the successful customer feature vectors in the successful customer feature vector set;
calculation formula rho of first local density to be analyzediComprises the following steps:
Figure BDA0002874935980000031
Figure BDA0002874935980000032
where ρ isiIs the first to-be-analyzed local density corresponding to the ith successful customer feature vector of the successful customer feature vector set; m is the number of successful customer feature vectors in the set of successful customer feature vectors; dcIs a preset truncation distance and is a constant; dijIs the pending euclidean distance between the ith and jth successful customer feature vectors of the set of successful customer feature vectors; x is an independent variable, i.e. dij-dc(ii) a When d isij-dcX is determined when less than 0(x)Equal to 1, otherwise determine X(x)Equal to 0.
Further, the step of determining a high local density and a minimum euclidean distance for the first local density to be analyzed corresponding to each successful customer feature vector of the successful customer feature vector set, respectively, to obtain a first high local density minimum euclidean distance to be analyzed corresponding to each successful customer feature vector of the successful customer feature vector set, includes:
obtaining a first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a target first to-be-analyzed local density;
finding out the first to-be-analyzed local density which is greater than the target first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a to-be-analyzed high local density set corresponding to the target first to-be-analyzed local density;
respectively calculating Euclidean distances between the successful customer feature vector corresponding to each first local density to be analyzed in the high local density set to be analyzed and the successful customer feature vector corresponding to the target first local density to be analyzed to obtain a Euclidean distance set to be analyzed corresponding to the target first local density to be analyzed;
obtaining a minimum value from the set of Euclidean distances to be analyzed to obtain a first high local density minimum Euclidean distance to be analyzed of the successful customer feature vector corresponding to the target first local density to be analyzed;
and repeatedly executing the step of obtaining one first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a target first to-be-analyzed local density until determining the minimum Euclidean distance of the first to-be-analyzed local density corresponding to all the successful customer feature vectors of the successful customer feature vector set.
Further, the step of clustering according to the first to-be-analyzed local densities corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector sets and all the successful customer feature vectors of the successful customer feature vector sets to obtain the successful customer feature vector clustering sets corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector sets includes:
respectively carrying out subtraction calculation and absolute value calculation on the first to-be-analyzed local density corresponding to all the successful customer feature vectors of the successful customer feature vector set and each first to-be-analyzed density distance corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector set to obtain a clustering center distance difference value set corresponding to all the successful customer feature vectors of the successful customer feature vector set;
respectively finding out the minimum value in the cluster center distance difference set corresponding to each successful customer feature vector of the successful customer feature vector set to obtain the first target cluster center distance difference value corresponding to each successful customer feature vector of the successful customer feature vector set;
extracting one first target clustering center from a plurality of first target clustering centers corresponding to the successful customer feature vector set as a first target clustering center to be clustered;
classifying the successful customer feature vectors corresponding to the distance difference value of each first target clustering center corresponding to the first target clustering center to be clustered into the same clustering set respectively to obtain the successful customer feature vector clustering set corresponding to the first target clustering center to be clustered;
and repeatedly executing the step of extracting one first target clustering center from a plurality of first target clustering centers corresponding to the successful customer feature vector set to serve as a first target clustering center to be clustered until the successful customer feature vector clustering sets corresponding to the first target clustering centers respectively corresponding to the successful customer feature vector set are determined.
Further, the step of performing cluster clustering according to the best successful customer feature vector cluster set and the customer feature vector set to be allocated to obtain a plurality of customer feature vector cluster sets to be analyzed includes:
marking each successful customer feature vector in the optimal successful customer feature vector cluster set to obtain a marked optimal successful customer feature vector cluster set;
putting the marked optimal successful customer feature vector clustering set and the customer feature vector set to be distributed into a set to obtain a customer feature vector set to be clustered;
and clustering the customer feature vector sets to be clustered to obtain a plurality of customer feature vector cluster sets to be analyzed.
Further, the clustering the to-be-clustered client feature vector sets to obtain the plurality of to-be-analyzed client feature vector cluster sets includes:
respectively carrying out local density calculation on each customer feature vector in the customer feature vector set to be clustered to obtain second local densities to be analyzed, which correspond to all the customer feature vectors in the customer feature vector set to be clustered;
respectively determining high local density and minimum Euclidean distance of the second local density to be analyzed corresponding to each customer feature vector of the customer feature vector set to be clustered to obtain second high local density minimum Euclidean distance to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered;
respectively multiplying the second local density to be analyzed corresponding to each customer feature vector of the customer feature vector set to be clustered and the second high local density minimum Euclidean distance to be analyzed to obtain second density distances to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered;
acquiring second to-be-analyzed density distances from the second to-be-analyzed density distances corresponding to all the client feature vectors of the to-be-clustered client feature vector set by adopting a second preset number to obtain a plurality of second target clustering centers corresponding to the to-be-clustered client feature vector set;
and clustering according to the plurality of second target clustering centers corresponding to the customer feature vector sets to be clustered and the second local densities to be analyzed corresponding to all the customer feature vectors of the customer feature vector sets to be clustered respectively to obtain a plurality of customer feature vector cluster sets to be analyzed.
The present application further proposes a device for allocating client resources, the device comprising:
the first data acquisition module is used for acquiring a successful customer feature vector set of a target person;
the successful customer feature vector cluster set determining module is used for clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets;
the optimal successful customer feature vector cluster set determining module is used for acquiring the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the optimal successful customer feature vector cluster set corresponding to the successful customer feature vector set;
the second data acquisition module is used for acquiring a client feature vector set to be distributed;
a to-be-analyzed client feature vector cluster set determining module, configured to perform cluster clustering according to the optimal successful client feature vector cluster set and the to-be-allocated client feature vector set, so as to obtain a plurality of to-be-analyzed client feature vector cluster sets;
the optimal successful customer feature vector quantity determining module is used for respectively carrying out quantity statistics on each customer feature vector cluster set to be analyzed in the plurality of customer feature vector cluster sets to be analyzed, wherein the quantity statistics belongs to the optimal successful customer feature vector cluster set, and the optimal successful customer feature vector quantity corresponding to each of the plurality of customer feature vector cluster sets to be analyzed is obtained;
and the target customer set determining module is used for finding out the maximum number of the optimal successful customer feature vectors from the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors.
The present application further proposes a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of any of the above methods when executing the computer program.
The present application also proposes a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any of the above.
The method, the device, the equipment and the storage medium for allocating the client resources of the application cluster and cluster the successful client feature vector sets of the target personnel to obtain a plurality of successful client feature vector cluster sets, obtain the successful client feature vector cluster set with the largest number of successful client feature vectors from the successful client feature vector cluster sets to obtain the optimal successful client feature vector cluster set corresponding to the successful client feature vector set, then cluster and cluster according to the optimal successful client feature vector cluster set and the client feature vector set to be allocated to obtain a plurality of client feature vector cluster sets to be analyzed, respectively perform quantity statistics belonging to the optimal successful client feature vector cluster set on each client feature vector cluster set to be analyzed in the plurality of client feature vector cluster sets to be analyzed to obtain the optimal successful client feature vector quantity corresponding to each client feature vector cluster set to be analyzed, and finally, finding the maximum number of the best successful customer feature vectors from the number of the best successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target person according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the best successful customer feature vectors, so that the customer group which is the most adept to sell by the target person is found first, and then potential customers are distributed according to the customer group which is the most adept to sell by the target person, so that the matching degree of the target customer set distributed to the target person and the marketing capacity of the target person is high, the marketing success rate is favorably improved, and the marketing efficiency is improved.
Drawings
Fig. 1 is a schematic flowchart of a method for allocating client resources according to an embodiment of the present application;
fig. 2 is a schematic block diagram illustrating a structure of a client resource allocation apparatus according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The objectives, features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In order to solve the technical problem that the marketing ability of a salesman is not high in matching degree with the distributed potential customers and the success rate of sales is not high by adopting a method for randomly distributing the potential customers in the prior art, the application provides a method for distributing customer resources, and the method is applied to the technical field of artificial intelligence. The distribution method of the customer resources adopts a clustering method to firstly find the customer group which is the best for the target person to sell, and then distributes potential customers according to the customer group which is the best for the target person to sell, so that the matching degree of the target customer set distributed to the target person and the marketing capacity of the target person is higher, the success rate of sales is favorably improved, and the sales efficiency is improved.
Referring to fig. 1, in an embodiment of the present application, a method for allocating client resources is provided, where the method includes:
s1: acquiring a successful customer feature vector set of a target person;
s2: clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets;
s3: obtaining the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the optimal successful customer feature vector cluster set corresponding to the successful customer feature vector set;
s4: acquiring a client feature vector set to be distributed;
s5: clustering according to the optimal successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed;
s6: respectively carrying out quantity statistics on each to-be-analyzed customer feature vector cluster set in the to-be-analyzed customer feature vector cluster sets to obtain the quantity of the best successful customer feature vectors corresponding to the to-be-analyzed customer feature vector cluster sets;
s7: finding out the maximum number of the optimal successful customer feature vectors from the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors.
The embodiment first clusters the successful customer feature vector sets of the target personnel to obtain a plurality of successful customer feature vector cluster sets, obtains the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the best successful customer feature vector cluster set corresponding to the successful customer feature vector set, then clusters and groups the successful customer feature vector cluster sets according to the best successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed, respectively counts the number of the best successful customer feature vector cluster sets to be analyzed in each customer feature vector cluster set to be analyzed to obtain the best successful customer feature vector number corresponding to each customer feature vector cluster set to be analyzed, and finally, finding the maximum number of the best successful customer feature vectors from the number of the best successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target person according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the best successful customer feature vectors, so that the customer group which is the most adept to sell by the target person is found first, and then potential customers are distributed according to the customer group which is the most adept to sell by the target person, so that the matching degree of the target customer set distributed to the target person and the marketing capacity of the target person is high, the marketing success rate is favorably improved, and the marketing efficiency is improved.
For S1, the successful client feature vector set of the target person may be obtained from the database, or the successful client feature vector set of the target person input by the user may be obtained, or the successful client feature vector set of the target person sent by the third-party application system may be obtained.
The target person refers to a business person of the client to be distributed.
The successful customer feature vector set includes a plurality of successful customer feature vectors, each successful customer feature vector corresponding to a customer. The successful customer feature vector refers to the customer feature vector which has been successfully sold.
The vector elements in the customer characteristic vector represent customer characteristics of customers that have historically been successfully sold by the target person. For example, customer characteristics include, but are not limited to: gender, age range, location, one person for multiple cars, car type, number of times of occurrence, driving age, and electricity sales result classification, which are not specifically limited by the examples herein.
Optionally, the step of obtaining a successful customer feature vector set of the target person includes: acquiring historical successful sales data of the target personnel; and extracting the characteristics of each customer from the historical successful sales data to obtain the successful customer characteristic vector set corresponding to the historical successful sales data.
Optionally, when the number of successful customer feature vectors in the successful customer feature vector set of the target person is greater than a preset number of successful customers, steps S2 to S7 are performed. It is understood that, when the number of successful customer feature vectors in the successful customer feature vector set of the target person is greater than the preset number of successful customers, which means that a group of customers that the target person is best in selling can be mined, the target customer set of the target person is determined through the steps S2 to S7, which is beneficial to improving the accuracy of the determined target customer set of the target person and improving the success rate of sales.
Optionally, the preset number of successful customers is set to 100.
And S2, clustering the successful customer feature vector sets by adopting a density peak value clustering algorithm, and taking each set obtained by clustering as a successful customer feature vector cluster set.
For S3, finding the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets, and using the found successful customer feature vector cluster set as the best successful customer feature vector cluster set corresponding to the successful customer feature vector set.
For S4, the set of customer feature vectors to be allocated may be obtained from the database, or may be the set of customer feature vectors to be allocated input by the user, or may be the set of customer feature vectors to be allocated sent by the third-party application system.
The set of customer feature vectors to be distributed, that is, the set of customer feature vectors that need to be distributed to customers for sales by the salesperson.
The set of customer feature vectors to be distributed comprises at least one customer feature vector.
Optionally, obtaining customer data to be distributed; and respectively extracting the characteristics of each client from the client data to be distributed to obtain a client characteristic vector set to be distributed.
For step S5, the best successful customer feature vector cluster set and the customer feature vector set to be allocated are combined into one set, then a density peak clustering algorithm is used to cluster the customer feature vectors in the combined set, and each set obtained by clustering is used as a customer feature vector cluster set to be analyzed.
For step S6, extracting one to-be-analyzed customer feature vector cluster set from the plurality of to-be-analyzed customer feature vector cluster sets as a target to-be-analyzed customer feature vector cluster set; calculating the number of the client characteristic vectors in the client characteristic vector cluster set to be analyzed from the optimal successful client characteristic vector cluster set, and taking the calculated number as the number of the optimal successful client characteristic vectors corresponding to the client characteristic vector cluster set to be analyzed; and repeatedly executing the step of extracting one to-be-analyzed customer feature vector cluster set from the plurality of to-be-analyzed customer feature vector cluster sets as a target to-be-analyzed customer feature vector cluster set until the optimal number of successful customer feature vectors corresponding to each of the plurality of to-be-analyzed customer feature vector cluster sets is determined.
For S7, finding the largest number of the best successful customer feature vectors from the numbers of the best successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and taking the found number of the best successful customer feature vectors as the number of the target best successful customer feature vectors; taking the customer feature vector cluster set to be analyzed corresponding to the number of the target optimal successful customer feature vectors as a target customer feature vector cluster set; and taking all customers corresponding to the target customer feature vector cluster set as the target customer set of the target personnel.
In an embodiment, the clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets includes:
s21: respectively carrying out local density calculation on each successful customer feature vector in the successful customer feature vector set to obtain first to-be-analyzed local densities corresponding to all the successful customer feature vectors in the successful customer feature vector set;
s22: respectively determining high local density and minimum Euclidean distance of the first to-be-analyzed local density corresponding to each successful customer feature vector of the successful customer feature vector set to obtain first high local density minimum Euclidean distances to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set;
s23: respectively multiplying the first to-be-analyzed local density corresponding to each successful customer feature vector of the successful customer feature vector set and the first high local density minimum Euclidean distance to be analyzed to obtain first to-be-analyzed density distances corresponding to all the successful customer feature vectors of the successful customer feature vector set;
s24: acquiring the first density distance to be analyzed from the first density distance to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set by adopting a first preset quantity to obtain a plurality of first target clustering centers corresponding to the successful customer feature vector set;
s25: and clustering according to the plurality of first target clustering centers corresponding to the successful customer feature vector set and the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain the successful customer feature vector clustering sets corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector set.
The embodiment realizes clustering of the successful customer feature vector sets by adopting a density peak clustering algorithm, thereby providing a data basis for determining the customer group which is most adept to sell by target personnel.
For S21, obtaining a successful customer feature vector from the set of successful customer feature vectors as a target successful customer feature vector; according to the successful customer feature vector set, local density calculation is carried out on the target successful customer feature vector to obtain a first to-be-analyzed local density corresponding to the target successful customer feature vector; and repeatedly executing the step of obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector until determining the first to-be-analyzed local density corresponding to each of all the successful customer feature vectors of the successful customer feature vector set.
For S22, obtaining a successful customer feature vector from the set of successful customer feature vectors as a target successful customer feature vector; performing minimum Euclidean distance determination on the first local density to be analyzed corresponding to the target successful customer feature vector to determine high local density and minimum Euclidean distance, and obtaining the minimum Euclidean distance of the first local density to be analyzed corresponding to the target successful customer feature vector; and repeatedly executing the step of obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector until determining the first high local density minimum Euclidean distance to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set.
For S23, obtaining a successful customer feature vector from the set of successful customer feature vectors as a target successful customer feature vector; multiplying the first to-be-analyzed local density corresponding to the target successful customer feature vector and the first high local density minimum Euclidean distance to be analyzed corresponding to the target successful customer feature vector to obtain a first to-be-analyzed density distance corresponding to the target successful customer feature vector; and repeating the step of obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector until determining the first to-be-analyzed density distance corresponding to each of all the successful customer feature vectors of the successful customer feature vector set.
For step S24, the first to-be-analyzed density distances corresponding to all the successful customer feature vectors in the successful customer feature vector set are sorted in a descending order, and are extracted from the beginning from all the sorted first to-be-analyzed density distances, so as to extract a first preset number of first to-be-analyzed density distances, and each extracted first to-be-analyzed density distance is used as a first target cluster center. That is, each of the plurality of first target cluster centers corresponding to the successful client feature vector set corresponds to a first to-be-analyzed density distance.
For S25, clustering successful customer feature vectors in the successful customer feature vector sets to a plurality of first target cluster centers corresponding to the successful customer feature vector sets according to the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector sets, where clustering is completed, and each first target cluster center corresponds to one successful customer feature vector cluster set.
In an embodiment, the step of performing local density calculation on each successful customer feature vector in the successful customer feature vector set to obtain a first local density to be analyzed corresponding to each successful customer feature vector in the successful customer feature vector set includes:
s211: respectively carrying out Euclidean distance calculation between every two successful customer feature vectors in the successful customer feature vector set to obtain a to-be-processed Euclidean distance set corresponding to the successful customer feature vector set;
s212: respectively carrying out local density calculation on each successful customer feature vector in the successful customer feature vector set according to the Euclidean distance set to be processed corresponding to the successful customer feature vector set to obtain the first local density to be analyzed corresponding to all the successful customer feature vectors in the successful customer feature vector set;
calculation formula rho of first local density to be analyzediComprises the following steps:
Figure BDA0002874935980000121
Figure BDA0002874935980000122
where ρ isiIs the first to-be-analyzed local density corresponding to the ith successful customer feature vector of the successful customer feature vector set; m is the number of successful customer feature vectors in the set of successful customer feature vectors; dcIs a preset truncation distance and is a constant; dijIs the pending euclidean distance between the ith and jth successful customer feature vectors of the set of successful customer feature vectors; x is an independent variable, i.e. dij-dc(ii) a When d isij-dcX is determined when less than 0(x)Equal to 1, otherwise determine X(x)Equal to 0.
The embodiment realizes local density calculation based on Euclidean distance, thereby providing a data basis for clustering the successful customer feature vector sets.
For S211, obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector; respectively calculating Euclidean distances between the target successful customer feature vector and each successful customer feature vector in the successful customer feature vector set to obtain a plurality of Euclidean distances to be processed corresponding to the target successful customer feature vector; and repeatedly executing the step of obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector until a plurality of to-be-processed Euclidean distances corresponding to all the successful customer feature vectors in the successful customer feature vector set are determined, and taking all the to-be-processed Euclidean distances as to-be-processed Euclidean distances corresponding to the successful customer feature vector set.
For S212, obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector; according to all to-be-processed Euclidean distances corresponding to the characteristic vectors of the target successful customers, local density calculation is carried out on the characteristic vectors of the target successful customers to obtain the first to-be-analyzed local density corresponding to the characteristic vectors of the target successful customers; and repeatedly executing the step of obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector until the first to-be-analyzed local density corresponding to all the successful customer feature vectors of the successful customer feature vector set is determined.
The preset truncation distance may be input by a user, stored in a database, or transmitted by a third-party application system. It is understood that the preset truncation distance may be written in a program file implementing the application.
In an embodiment, the step of determining a high local density and a minimum euclidean distance for the first local density to be analyzed corresponding to each successful customer feature vector of the successful customer feature vector set to obtain a first high local density minimum euclidean distance to be analyzed corresponding to each successful customer feature vector of the successful customer feature vector set includes:
s221: obtaining a first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a target first to-be-analyzed local density;
s222: finding out the first to-be-analyzed local density which is greater than the target first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a to-be-analyzed high local density set corresponding to the target first to-be-analyzed local density;
s223: respectively calculating Euclidean distances between the successful customer feature vector corresponding to each first local density to be analyzed in the high local density set to be analyzed and the successful customer feature vector corresponding to the target first local density to be analyzed to obtain a Euclidean distance set to be analyzed corresponding to the target first local density to be analyzed;
s224: obtaining a minimum value from the set of Euclidean distances to be analyzed to obtain a first high local density minimum Euclidean distance to be analyzed of the successful customer feature vector corresponding to the target first local density to be analyzed;
s225: and repeatedly executing the step of obtaining one first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a target first to-be-analyzed local density until determining the minimum Euclidean distance of the first to-be-analyzed local density corresponding to all the successful customer feature vectors of the successful customer feature vector set.
The embodiment realizes the determination of the high local density and the determination of the minimum Euclidean distance to obtain the first high local density minimum Euclidean distance to be analyzed, thereby providing a data basis for clustering the successful customer feature vector sets.
For step S221, one first local density to be analyzed is obtained from the first local densities to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set, and the obtained first local density to be analyzed is used as a target first local density to be analyzed.
For step S222, the first local density to be analyzed that is greater than the target first local density to be analyzed is found from the first local densities to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set, and all the found first local densities to be analyzed are used as a high local density set to be analyzed corresponding to the target first local density to be analyzed, so that determination of a high local density is achieved for the target first local density to be analyzed.
For S223, respectively calculating a euclidean distance between the successful customer feature vector corresponding to each first local density to be analyzed in the high local density set to be analyzed and the successful customer feature vector corresponding to the target first local density to be analyzed, thereby achieving determination of a minimum euclidean distance.
For S224, a minimum value is obtained from the set of euclidean distances to be analyzed corresponding to the target first local density to be analyzed, and the obtained euclidean distance to be analyzed is used as the minimum euclidean distance of the first high local density to be analyzed of the successful customer feature vector corresponding to the target first local density to be analyzed.
For S225, the steps S221 to S226 are repeatedly executed until the first high local density minimum euclidean distance to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set is determined.
In an embodiment, the clustering according to the first to-be-analyzed local densities corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector sets and all the successful customer feature vectors of the successful customer feature vector sets to obtain the successful customer feature vector clustering sets corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector sets includes:
s251: respectively carrying out subtraction calculation and absolute value calculation on the first to-be-analyzed local density corresponding to all the successful customer feature vectors of the successful customer feature vector set and each first to-be-analyzed density distance corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector set to obtain a clustering center distance difference value set corresponding to all the successful customer feature vectors of the successful customer feature vector set;
s252: respectively finding out the minimum value in the cluster center distance difference set corresponding to each successful customer feature vector of the successful customer feature vector set to obtain the first target cluster center distance difference value corresponding to each successful customer feature vector of the successful customer feature vector set;
s253: extracting one first target clustering center from a plurality of first target clustering centers corresponding to the successful customer feature vector set as a first target clustering center to be clustered;
s254: classifying the successful customer feature vectors corresponding to the distance difference value of each first target clustering center corresponding to the first target clustering center to be clustered into the same clustering set respectively to obtain the successful customer feature vector clustering set corresponding to the first target clustering center to be clustered;
s255: and repeatedly executing the step of extracting one first target clustering center from a plurality of first target clustering centers corresponding to the successful customer feature vector set to serve as a first target clustering center to be clustered until the successful customer feature vector clustering sets corresponding to the first target clustering centers respectively corresponding to the successful customer feature vector set are determined.
The embodiment realizes clustering of the successful customer feature vector sets by adopting a density peak clustering algorithm, thereby providing a data basis for determining the customer group which is most adept to sell by target personnel.
For S251, a successful customer feature vector is obtained from the successful customer feature vector set as a target successful customer feature vector; subtracting each first to-be-analyzed density distance corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector set from the first to-be-analyzed local density corresponding to the successful customer feature vector set to obtain a plurality of to-be-processed density difference values corresponding to the successful customer feature vector set; respectively carrying out absolute value calculation on each to-be-processed density difference value corresponding to the target successful customer feature vector to obtain a clustering center distance difference value set corresponding to the target successful customer feature vector; and repeating the step of obtaining a successful customer feature vector from the successful customer feature vector set as a target successful customer feature vector until determining the cluster center distance difference value sets corresponding to all the successful customer feature vectors of the successful customer feature vector set.
For step S253, one first target clustering center is sequentially extracted from the plurality of first target clustering centers corresponding to the successful customer feature vector sets as a first target clustering center to be clustered.
For S254, the successful customer feature vectors corresponding to each first target cluster center distance difference value corresponding to the first target cluster center to be clustered are classified into the same cluster set, and the obtained cluster set is used as the successful customer feature vector cluster set corresponding to the first target cluster center to be clustered, that is, the first target cluster center distance difference values corresponding to all the successful customer feature vectors in the successful customer feature vector cluster set are obtained according to the first to-be-analyzed density distance corresponding to the first target cluster center to be clustered.
For S255, the steps S252 to S255 are repeatedly executed until the successful customer feature vector cluster sets corresponding to the plurality of first target cluster centers corresponding to the successful customer feature vector sets are determined.
In an embodiment, the clustering according to the best successful customer feature vector cluster set and the customer feature vector set to be allocated to obtain a plurality of customer feature vector cluster sets to be analyzed includes:
s51: marking each successful customer feature vector in the optimal successful customer feature vector cluster set to obtain a marked optimal successful customer feature vector cluster set;
s52: putting the marked optimal successful customer feature vector clustering set and the customer feature vector set to be distributed into a set to obtain a customer feature vector set to be clustered;
s53: and clustering the customer feature vector sets to be clustered to obtain a plurality of customer feature vector cluster sets to be analyzed.
According to the embodiment, the successful customer feature vectors are marked firstly, then clustering is carried out, and a data basis is provided for the subsequent calculation of the number of the best successful customer feature vectors.
For S51, a marker symbol is used to mark each successful customer feature vector in the best successful customer feature vector cluster set, and all successful customer feature vectors carrying marker symbols are used as the marked best successful customer feature vector cluster set.
And S52, putting the marked optimal successful customer feature vector clustering set and the customer feature vector set to be distributed into a set, and taking the obtained set as the customer feature vector set to be clustered.
And S53, clustering the to-be-clustered customer feature vector sets by adopting a density peak clustering algorithm, and taking each set obtained by clustering as a to-be-analyzed customer feature vector cluster set.
In an embodiment, the clustering the to-be-clustered client feature vector sets to obtain the multiple to-be-analyzed client feature vector cluster sets includes:
s531: respectively carrying out local density calculation on each customer feature vector in the customer feature vector set to be clustered to obtain second local densities to be analyzed, which correspond to all the customer feature vectors in the customer feature vector set to be clustered;
s532: respectively determining high local density and minimum Euclidean distance of the second local density to be analyzed corresponding to each customer feature vector of the customer feature vector set to be clustered to obtain second high local density minimum Euclidean distance to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered;
s533: respectively multiplying the second local density to be analyzed corresponding to each customer feature vector of the customer feature vector set to be clustered and the second high local density minimum Euclidean distance to be analyzed to obtain second density distances to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered;
s534: acquiring second to-be-analyzed density distances from the second to-be-analyzed density distances corresponding to all the client feature vectors of the to-be-clustered client feature vector set by adopting a second preset number to obtain a plurality of second target clustering centers corresponding to the to-be-clustered client feature vector set;
s535: and clustering according to the plurality of second target clustering centers corresponding to the customer feature vector sets to be clustered and the second local densities to be analyzed corresponding to all the customer feature vectors of the customer feature vector sets to be clustered respectively to obtain a plurality of customer feature vector cluster sets to be analyzed.
According to the embodiment, clustering and clustering are carried out on the customer feature vector sets to be clustered by adopting a density peak value clustering algorithm, so that a data basis is provided for distributing potential customers according to a customer group which is most adept to sell by target personnel.
For step S531, a customer feature vector is obtained from the customer feature vector set to be clustered as a target customer feature vector; performing local density calculation on the target customer feature vector according to the customer feature vector set to be clustered to obtain a second local density to be analyzed corresponding to the target customer feature vector; and repeatedly executing the step of obtaining one customer feature vector from the customer feature vector set to be clustered as a target customer feature vector until second local densities to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered are determined.
For S532, a customer feature vector is obtained from the customer feature vector set to be clustered as a target customer feature vector; determining high local density and minimum Euclidean distance of the second local density to be analyzed corresponding to the target customer feature vector to obtain the minimum Euclidean distance of the second local density to be analyzed corresponding to the target customer feature vector; and repeatedly executing the step of obtaining one customer feature vector from the customer feature vector set to be clustered as a target customer feature vector until determining second high local density minimum Euclidean distances to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered.
For step S533, a customer feature vector is obtained from the customer feature vector set to be clustered as a target customer feature vector; multiplying the second local density to be analyzed corresponding to the target customer feature vector by the second high local density minimum Euclidean distance to be analyzed corresponding to the target customer feature vector to obtain a second density distance to be analyzed corresponding to the target customer feature vector; and repeatedly executing the step of obtaining one customer feature vector from the customer feature vector set to be clustered as a target customer feature vector until second density distances to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered are determined.
For step S534, the second density distances to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered are sorted in a descending order, and are extracted from the beginning of all the sorted second density distances to be analyzed, so as to extract a first preset number of the second density distances to be analyzed, and each extracted second density distance to be analyzed is used as a second target clustering center. That is to say, each of the second target cluster centers corresponding to the set of customer feature vectors to be clustered corresponds to a second density distance to be analyzed.
For step S535, clustering the client feature vectors in the client feature vector set to be clustered to a plurality of second target cluster centers corresponding to the client feature vector set to be clustered according to the second local density to be analyzed corresponding to all the client feature vectors in the client feature vector set to be clustered, where clustering is finished and each second target cluster center corresponds to one client feature vector cluster set to be analyzed.
With reference to fig. 2, the present application further proposes an apparatus for allocating client resources, the apparatus including:
a first data obtaining module 100, configured to obtain a successful customer feature vector set of a target person;
a successful customer feature vector cluster set determining module 200, configured to perform cluster clustering on the successful customer feature vector sets to obtain multiple successful customer feature vector cluster sets;
a best successful customer feature vector cluster set determining module 300, configured to obtain, from the successful customer feature vector cluster sets, the successful customer feature vector cluster set with the largest number of successful customer feature vectors, and obtain a best successful customer feature vector cluster set corresponding to the successful customer feature vector set;
a second data obtaining module 400, configured to obtain a set of client feature vectors to be allocated;
a to-be-analyzed client feature vector cluster set determining module 500, configured to perform cluster clustering according to the optimal successful client feature vector cluster set and the to-be-allocated client feature vector set, so as to obtain a plurality of to-be-analyzed client feature vector cluster sets;
a best successful customer feature vector quantity determining module 600, configured to perform quantity statistics on each customer feature vector cluster set to be analyzed in the plurality of customer feature vector cluster sets to be analyzed, where the customer feature vector cluster set to be analyzed belongs to the best successful customer feature vector cluster set, respectively, so as to obtain a quantity of best successful customer feature vectors corresponding to each of the plurality of customer feature vector cluster sets to be analyzed;
a target customer set determining module 700, configured to find the largest number of the best successful customer feature vectors from the number of the best successful customer feature vectors corresponding to each of the plurality of customer feature vector cluster sets to be analyzed, and obtain the target customer set of the target person according to the customer feature vector cluster set to be analyzed corresponding to the largest number of the best successful customer feature vectors.
The embodiment first clusters the successful customer feature vector sets of the target personnel to obtain a plurality of successful customer feature vector cluster sets, obtains the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the best successful customer feature vector cluster set corresponding to the successful customer feature vector set, then clusters and groups the successful customer feature vector cluster sets according to the best successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed, respectively counts the number of the best successful customer feature vector cluster sets to be analyzed in each customer feature vector cluster set to be analyzed to obtain the best successful customer feature vector number corresponding to each customer feature vector cluster set to be analyzed, and finally, finding the maximum number of the best successful customer feature vectors from the number of the best successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target person according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the best successful customer feature vectors, so that the customer group which is the most adept to sell by the target person is found first, and then potential customers are distributed according to the customer group which is the most adept to sell by the target person, so that the matching degree of the target customer set distributed to the target person and the marketing capacity of the target person is high, the marketing success rate is favorably improved, and the marketing efficiency is improved.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for storing data such as the allocation method of the client resource. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of allocating customer resources. The client resource allocation method comprises the following steps: acquiring a successful customer feature vector set of a target person; clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets; obtaining the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the optimal successful customer feature vector cluster set corresponding to the successful customer feature vector set; acquiring a client feature vector set to be distributed; clustering according to the optimal successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed; respectively carrying out quantity statistics on each to-be-analyzed customer feature vector cluster set in the to-be-analyzed customer feature vector cluster sets to obtain the quantity of the best successful customer feature vectors corresponding to the to-be-analyzed customer feature vector cluster sets; finding out the maximum number of the optimal successful customer feature vectors from the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors.
The embodiment first clusters the successful customer feature vector sets of the target personnel to obtain a plurality of successful customer feature vector cluster sets, obtains the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the best successful customer feature vector cluster set corresponding to the successful customer feature vector set, then clusters and groups the successful customer feature vector cluster sets according to the best successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed, respectively counts the number of the best successful customer feature vector cluster sets to be analyzed in each customer feature vector cluster set to be analyzed to obtain the best successful customer feature vector number corresponding to each customer feature vector cluster set to be analyzed, and finally, finding the maximum number of the best successful customer feature vectors from the number of the best successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target person according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the best successful customer feature vectors, so that the customer group which is the most adept to sell by the target person is found first, and then potential customers are distributed according to the customer group which is the most adept to sell by the target person, so that the matching degree of the target customer set distributed to the target person and the marketing capacity of the target person is high, the marketing success rate is favorably improved, and the marketing efficiency is improved.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements a method for allocating client resources, including the steps of: acquiring a successful customer feature vector set of a target person; clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets; obtaining the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the optimal successful customer feature vector cluster set corresponding to the successful customer feature vector set; acquiring a client feature vector set to be distributed; clustering according to the optimal successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed; respectively carrying out quantity statistics on each to-be-analyzed customer feature vector cluster set in the to-be-analyzed customer feature vector cluster sets to obtain the quantity of the best successful customer feature vectors corresponding to the to-be-analyzed customer feature vector cluster sets; finding out the maximum number of the optimal successful customer feature vectors from the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors.
The executed allocation method of the client resources obtains a plurality of successful client characteristic vector cluster sets by clustering successful client characteristic vector sets of target personnel, obtains the successful client characteristic vector cluster set with the largest number of successful client characteristic vectors from the successful client characteristic vector cluster sets to obtain the optimal successful client characteristic vector cluster set corresponding to the successful client characteristic vector set, then carries out clustering and clustering according to the optimal successful client characteristic vector cluster set and the client characteristic sets to be allocated to obtain a plurality of client characteristic vector cluster sets to be analyzed, carries out quantity statistics of each client characteristic vector cluster set to be analyzed belonging to the optimal successful client characteristic vector cluster set in the plurality of client characteristic vector cluster sets to be analyzed respectively to obtain the optimal successful client characteristic vector quantity corresponding to each client characteristic vector cluster set to be analyzed, and finally, finding the maximum number of the best successful customer feature vectors from the number of the best successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target person according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the best successful customer feature vectors, so that the customer group which is the most adept to sell by the target person is found first, and then potential customers are distributed according to the customer group which is the most adept to sell by the target person, so that the matching degree of the target customer set distributed to the target person and the marketing capacity of the target person is high, the marketing success rate is favorably improved, and the marketing efficiency is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
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 an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims (10)

1. A method for allocating customer resources, the method comprising:
acquiring a successful customer feature vector set of a target person;
clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets;
obtaining the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the optimal successful customer feature vector cluster set corresponding to the successful customer feature vector set;
acquiring a client feature vector set to be distributed;
clustering according to the optimal successful customer feature vector cluster set and the customer feature vector sets to be distributed to obtain a plurality of customer feature vector cluster sets to be analyzed;
respectively carrying out quantity statistics on each to-be-analyzed customer feature vector cluster set in the to-be-analyzed customer feature vector cluster sets to obtain the quantity of the best successful customer feature vectors corresponding to the to-be-analyzed customer feature vector cluster sets;
finding out the maximum number of the optimal successful customer feature vectors from the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors.
2. The method according to claim 1, wherein the step of clustering the successful sets of customer feature vectors to obtain a plurality of successful sets of customer feature vector clusters comprises:
respectively carrying out local density calculation on each successful customer feature vector in the successful customer feature vector set to obtain first to-be-analyzed local densities corresponding to all the successful customer feature vectors in the successful customer feature vector set;
respectively determining high local density and minimum Euclidean distance of the first to-be-analyzed local density corresponding to each successful customer feature vector of the successful customer feature vector set to obtain first high local density minimum Euclidean distances to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set;
respectively multiplying the first to-be-analyzed local density corresponding to each successful customer feature vector of the successful customer feature vector set and the first high local density minimum Euclidean distance to be analyzed to obtain first to-be-analyzed density distances corresponding to all the successful customer feature vectors of the successful customer feature vector set;
acquiring the first density distance to be analyzed from the first density distance to be analyzed corresponding to all the successful customer feature vectors of the successful customer feature vector set by adopting a first preset quantity to obtain a plurality of first target clustering centers corresponding to the successful customer feature vector set;
and clustering according to the plurality of first target clustering centers corresponding to the successful customer feature vector set and the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain the successful customer feature vector clustering sets corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector set.
3. The method according to claim 2, wherein the step of performing a local density calculation on each successful client feature vector in the successful client feature vector set to obtain a first to-be-analyzed local density corresponding to each successful client feature vector in the successful client feature vector set comprises:
respectively carrying out Euclidean distance calculation between every two successful customer feature vectors in the successful customer feature vector set to obtain a to-be-processed Euclidean distance set corresponding to the successful customer feature vector set;
respectively carrying out local density calculation on each successful customer feature vector in the successful customer feature vector set according to the Euclidean distance set to be processed corresponding to the successful customer feature vector set to obtain the first local density to be analyzed corresponding to all the successful customer feature vectors in the successful customer feature vector set;
calculation formula rho of first local density to be analyzediComprises the following steps:
Figure FDA0002874935970000021
Figure FDA0002874935970000022
where ρ isiIs the first to-be-analyzed local density corresponding to the ith successful customer feature vector of the successful customer feature vector set; m is the number of successful customer feature vectors in the set of successful customer feature vectors; dcIs a preset truncation distance and is a constant; dijIs the pending euclidean distance between the ith and jth successful customer feature vectors of the set of successful customer feature vectors; x is an independent variable, i.e. dij-dc(ii) a When d isij-dcX is determined when less than 0(x)Equal to 1, otherwise determine X(x)Equal to 0.
4. The method according to claim 2, wherein the step of determining a high local density and a minimum euclidean distance respectively for the first local density to be analyzed corresponding to each successful customer feature vector in the successful customer feature vector set to obtain a first high local density minimum euclidean distance to be analyzed corresponding to each successful customer feature vector in the successful customer feature vector set comprises:
obtaining a first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a target first to-be-analyzed local density;
finding out the first to-be-analyzed local density which is greater than the target first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a to-be-analyzed high local density set corresponding to the target first to-be-analyzed local density;
respectively calculating Euclidean distances between the successful customer feature vector corresponding to each first local density to be analyzed in the high local density set to be analyzed and the successful customer feature vector corresponding to the target first local density to be analyzed to obtain a Euclidean distance set to be analyzed corresponding to the target first local density to be analyzed;
obtaining a minimum value from the set of Euclidean distances to be analyzed to obtain a first high local density minimum Euclidean distance to be analyzed of the successful customer feature vector corresponding to the target first local density to be analyzed;
and repeatedly executing the step of obtaining one first to-be-analyzed local density from the first to-be-analyzed local densities corresponding to all the successful customer feature vectors of the successful customer feature vector set to obtain a target first to-be-analyzed local density until determining the minimum Euclidean distance of the first to-be-analyzed local density corresponding to all the successful customer feature vectors of the successful customer feature vector set.
5. The method according to claim 2, wherein the step of clustering according to the first to-be-analyzed local densities respectively corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector sets and all the successful customer feature vectors of the successful customer feature vector sets to obtain the successful customer feature vector clustering sets respectively corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector sets comprises:
respectively carrying out subtraction calculation and absolute value calculation on the first to-be-analyzed local density corresponding to all the successful customer feature vectors of the successful customer feature vector set and each first to-be-analyzed density distance corresponding to the plurality of first target clustering centers corresponding to the successful customer feature vector set to obtain a clustering center distance difference value set corresponding to all the successful customer feature vectors of the successful customer feature vector set;
respectively finding out the minimum value in the cluster center distance difference set corresponding to each successful customer feature vector of the successful customer feature vector set to obtain the first target cluster center distance difference value corresponding to each successful customer feature vector of the successful customer feature vector set;
extracting one first target clustering center from a plurality of first target clustering centers corresponding to the successful customer feature vector set as a first target clustering center to be clustered;
classifying the successful customer feature vectors corresponding to the distance difference value of each first target clustering center corresponding to the first target clustering center to be clustered into the same clustering set respectively to obtain the successful customer feature vector clustering set corresponding to the first target clustering center to be clustered;
and repeatedly executing the step of extracting one first target clustering center from a plurality of first target clustering centers corresponding to the successful customer feature vector set to serve as a first target clustering center to be clustered until the successful customer feature vector clustering sets corresponding to the first target clustering centers respectively corresponding to the successful customer feature vector set are determined.
6. The method according to claim 1, wherein the step of clustering the clusters according to the best successful customer feature vector cluster and the customer feature vector set to be allocated to obtain a plurality of customer feature vector clusters to be analyzed comprises:
marking each successful customer feature vector in the optimal successful customer feature vector cluster set to obtain a marked optimal successful customer feature vector cluster set;
putting the marked optimal successful customer feature vector clustering set and the customer feature vector set to be distributed into a set to obtain a customer feature vector set to be clustered;
and clustering the customer feature vector sets to be clustered to obtain a plurality of customer feature vector cluster sets to be analyzed.
7. The method according to claim 6, wherein the step of clustering the sets of the client feature vectors to be clustered to obtain the sets of the plurality of sets of the client feature vectors to be analyzed comprises:
respectively carrying out local density calculation on each customer feature vector in the customer feature vector set to be clustered to obtain second local densities to be analyzed, which correspond to all the customer feature vectors in the customer feature vector set to be clustered;
respectively determining high local density and minimum Euclidean distance of the second local density to be analyzed corresponding to each customer feature vector of the customer feature vector set to be clustered to obtain second high local density minimum Euclidean distance to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered;
respectively multiplying the second local density to be analyzed corresponding to each customer feature vector of the customer feature vector set to be clustered and the second high local density minimum Euclidean distance to be analyzed to obtain second density distances to be analyzed corresponding to all the customer feature vectors of the customer feature vector set to be clustered;
acquiring second to-be-analyzed density distances from the second to-be-analyzed density distances corresponding to all the client feature vectors of the to-be-clustered client feature vector set by adopting a second preset number to obtain a plurality of second target clustering centers corresponding to the to-be-clustered client feature vector set;
and clustering according to the plurality of second target clustering centers corresponding to the customer feature vector sets to be clustered and the second local densities to be analyzed corresponding to all the customer feature vectors of the customer feature vector sets to be clustered respectively to obtain a plurality of customer feature vector cluster sets to be analyzed.
8. An apparatus for allocating customer resources, the apparatus comprising:
the first data acquisition module is used for acquiring a successful customer feature vector set of a target person;
the successful customer feature vector cluster set determining module is used for clustering the successful customer feature vector sets to obtain a plurality of successful customer feature vector cluster sets;
the optimal successful customer feature vector cluster set determining module is used for acquiring the successful customer feature vector cluster set with the largest number of successful customer feature vectors from the successful customer feature vector cluster sets to obtain the optimal successful customer feature vector cluster set corresponding to the successful customer feature vector set;
the second data acquisition module is used for acquiring a client feature vector set to be distributed;
a to-be-analyzed client feature vector cluster set determining module, configured to perform cluster clustering according to the optimal successful client feature vector cluster set and the to-be-allocated client feature vector set, so as to obtain a plurality of to-be-analyzed client feature vector cluster sets;
the optimal successful customer feature vector quantity determining module is used for respectively carrying out quantity statistics on each customer feature vector cluster set to be analyzed in the plurality of customer feature vector cluster sets to be analyzed, wherein the quantity statistics belongs to the optimal successful customer feature vector cluster set, and the optimal successful customer feature vector quantity corresponding to each of the plurality of customer feature vector cluster sets to be analyzed is obtained;
and the target customer set determining module is used for finding out the maximum number of the optimal successful customer feature vectors from the number of the optimal successful customer feature vectors corresponding to the plurality of customer feature vector cluster sets to be analyzed, and obtaining the target customer set of the target personnel according to the customer feature vector cluster set to be analyzed corresponding to the maximum number of the optimal successful customer feature vectors.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN202011612002.8A 2020-12-30 2020-12-30 Client resource allocation method, device, equipment and storage medium Pending CN112633742A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011612002.8A CN112633742A (en) 2020-12-30 2020-12-30 Client resource allocation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011612002.8A CN112633742A (en) 2020-12-30 2020-12-30 Client resource allocation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112633742A true CN112633742A (en) 2021-04-09

Family

ID=75286831

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011612002.8A Pending CN112633742A (en) 2020-12-30 2020-12-30 Client resource allocation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112633742A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113469423A (en) * 2021-06-18 2021-10-01 北京明略软件系统有限公司 Resource allocation method, device, storage medium and electronic equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107194815A (en) * 2016-11-15 2017-09-22 平安科技（深圳）有限公司 Client segmentation method and system
CN108537276A (en) * 2018-04-09 2018-09-14 广东工业大学 A kind of choosing method of cluster centre, device and medium
CN111415060A (en) * 2020-01-21 2020-07-14 国网浙江省电力有限公司湖州供电公司 Complaint risk analysis method based on customer label

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107194815A (en) * 2016-11-15 2017-09-22 平安科技（深圳）有限公司 Client segmentation method and system
CN108537276A (en) * 2018-04-09 2018-09-14 广东工业大学 A kind of choosing method of cluster centre, device and medium
CN111415060A (en) * 2020-01-21 2020-07-14 国网浙江省电力有限公司湖州供电公司 Complaint risk analysis method based on customer label

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113469423A (en) * 2021-06-18 2021-10-01 北京明略软件系统有限公司 Resource allocation method, device, storage medium and electronic equipment

Similar Documents

Publication Publication Date Title
CN109871860B (en) Daily load curve dimension reduction clustering method based on kernel principal component analysis
CN111199016A (en) DTW-based improved K-means daily load curve clustering method
CN108241745A (en) The processing method and processing device of sample set, the querying method of sample and device
CN109104731B (en) Method and device for building cell scene category division model and computer equipment
CN109408562B (en) Grouping recommendation method and device based on client characteristics
CN111553390A (en) User classification method and device, computer equipment and storage medium
CN111401642A (en) Method, device and equipment for automatically adjusting predicted value and storage medium
CN113569910A (en) Account type identification method and device, computer equipment and storage medium
CN112907576A (en) Vehicle damage grade detection method and device, computer equipment and storage medium
CN112633742A (en) Client resource allocation method, device, equipment and storage medium
Mousavi et al. Improving customer clustering by optimal selection of cluster centroids in k-means and k-medoids algorithms
CN110097120B (en) Network flow data classification method, equipment and computer storage medium
CN113674425B (en) Point cloud sampling method, device, equipment and computer readable storage medium
CN111210158A (en) Target address determination method and device, computer equipment and storage medium
CN114399367A (en) Insurance product recommendation method, device, equipment and storage medium
CN113920372A (en) Data classification method, device, equipment and storage medium
CN116980824B (en) Lightweight weighting integrated learning indoor CSI positioning method
CN112508363A (en) Deep learning-based power information system state analysis method and device
CN116739186A (en) Service management method based on AI and big data
CN111832631A (en) Feature recognition method and device, computer equipment and storage medium
CN112949885A (en) Method and device for predicting delivery mode, storage medium and electronic equipment
CN115856694A (en) Battery life prediction method and device, computer equipment and storage medium
CN113837319A (en) Clustering-based customer classification method, device, equipment and storage medium
Borges et al. Silhouette-based clustering using an immune network
EP4250190A1 (en) Cost equalization special clustering

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination