Method and system for allocating advertising resources at bank outlets
Through data analysis of bank branches and customers, the optimal advertising delivery strategy is determined, which solves the problem of mismatching bank advertising delivery methods and customer needs, and improves conversion rate and operational efficiency.
Patent Information
- Application Number
- CN202210445443.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-26
- Publication Date
- 2024-11-01
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing advertising delivery methods of banks cannot effectively match the needs of different customers, resulting in low matching between pushed advertisements and customers, which seriously affects the conversion rate of bank product promotion.
By analyzing the risk type vector of bank branches and the transaction category vector of customers, performing cluster analysis, dividing bank branches and customer subsets, determining the optimal advertising delivery strategy, and improving the matching degree of advertising delivery.
It improves the conversion rate and operational efficiency of bank product promotion, meets the actual needs of customers, and optimizes advertising delivery under the premise of controllable risks.
Smart Images

Figure CN114820059B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for allocating advertising resources for bank outlets. Background Art
[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.
[0003] The existing advertising method of banks is to push advertisements to customers based on the business needs of the banks. Pushing advertisements based on the business needs of the banks alone makes the pushed advertisements not meet the actual needs of different customers and fails to discover the potential needs of different customers. With the existing advertising method of banks, the matching degree between the advertisements pushed by banks and customers is low, which seriously affects the conversion rate of bank product promotion.
[0004] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects and improve the way of advertising delivery. Summary of the invention
[0005] In order to solve the problems existing in the prior art, the present invention proposes a method and system for allocating advertising resources for bank outlets.
[0006] In a first aspect of an embodiment of the present invention, a method for allocating bank branch advertising resources is proposed, comprising:
[0007] For each bank branch in the bank branch set, determine a risk type vector corresponding to each bank branch;
[0008] Performing cluster analysis on the bank branch set according to the risk type vector to obtain multiple bank branch subsets; storing the corresponding relationship between the bank branch and the bank branch subset to which the bank branch belongs in a database of the bank server;
[0009] Classify the transaction categories of the bank, and divide the transaction category set into multiple transaction category sub-sets;
[0010] For each bank branch subset, obtain a customer set served by each bank branch subset, and for each customer in the customer set, determine a transaction category vector of the customer based on the customer's historical transaction data; wherein the components of the transaction category vector correspond one-to-one to the transaction category subset; cluster the customer set based on the transaction category vector to obtain multiple customer subsets corresponding to the bank branch subset; store the correspondence between the bank branch subset and the multiple customer subsets corresponding to the bank branch subset in a database of a bank server;
[0011] For each bank branch of the bank branch subset, obtain the customer category vector, advertising delivery strategy and advertising effect index in each sampling time period; wherein the components of the customer category vector correspond to the customer subset one by one; determine the optimal advertising delivery strategy corresponding to each customer category vector according to the customer category vector, advertising delivery strategy and advertising effect index, and store the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy in the database of the bank server;
[0012] For the first bank branch, a customer set currently being served is obtained; the first bank branch sends an advertisement delivery strategy acquisition request to a bank server, wherein the acquisition request includes the customer set currently being served;
[0013] The bank server determines the bank branch subset to which the first bank branch belongs based on the correspondence between the bank branch and the bank branch subset to which the bank branch belongs; determines the customer category vector corresponding to the first bank branch at the current moment based on the multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs; the bank server determines the optimal advertising delivery strategy for the first bank branch at the current moment based on the correspondence between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch;
[0014] The first bank branch performs advertisement delivery at the current moment according to the received optimal advertisement delivery strategy.
[0015] In a second aspect of an embodiment of the present invention, a system for allocating advertising resources for bank outlets is provided, comprising:
[0016] A data processing module, used for determining, for each bank branch in the bank branch set, a risk type vector corresponding to each bank branch;
[0017] A bank branch subset analysis module is used to perform cluster analysis on the bank branch set according to the risk type vector to obtain multiple bank branch subsets; and store the corresponding relationship between the bank branch and the bank branch subset to which the bank branch belongs in the database of the bank server;
[0018] A classification module, used to classify the transaction categories of the bank and divide the transaction category set into multiple transaction category sub-sets;
[0019] A transaction category vector processing module is used to obtain, for each bank branch subset, a customer set served by each bank branch subset, and for each customer in the customer set, determine the transaction category vector of the customer based on the customer's historical transaction data; wherein the components of the transaction category vector correspond to the transaction category subset one by one; cluster the customer set based on the transaction category vector to obtain multiple customer subsets corresponding to the bank branch subset; and store the correspondence between the bank branch subset and the multiple customer subsets corresponding to the bank branch subset in a database of a bank server;
[0020] A corresponding relationship processing module is used to obtain the customer category vector, advertising delivery strategy and advertising effect index in each sampling time period for each bank branch of each bank branch subset; wherein the components of the customer category vector correspond to the customer subset one by one; determine the optimal advertising delivery strategy corresponding to each customer category vector according to the customer category vector, advertising delivery strategy and advertising effect index, and store the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy in the database of the bank server;
[0021] A request acquisition module is used to obtain the customer set currently served by the first bank branch; the first bank branch sends an advertisement delivery strategy acquisition request to the bank server, wherein the acquisition request includes the customer set currently served;
[0022] The optimal advertising delivery strategy processing module is used for the bank server to determine the bank branch subset to which the first bank branch belongs according to the corresponding relationship between the bank branch and the bank branch subset to which the bank branch belongs; determine the customer category vector corresponding to the first bank branch at the current moment according to multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs; the bank server determines the optimal advertising delivery strategy for the first bank branch at the current moment according to the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch;
[0023] The advertisement delivery processing module is used for the first bank branch to deliver advertisements at the current moment according to the received optimal advertisement delivery strategy.
[0024] In a third aspect of an embodiment of the present invention, a computer device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method for allocating advertising resources for bank outlets when executing the computer program.
[0025] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for allocating advertising resources for bank outlets is implemented.
[0026] In a fifth aspect of the embodiments of the present invention, a computer program product is proposed. The computer program product includes a computer program. When the computer program is executed by a processor, a method for allocating advertising resources for bank outlets is implemented.
[0027] The method and system for allocating bank branch advertising resources proposed in the present invention analyzes the data of bank branches to determine the risk type vector corresponding to each bank branch; clusters the bank branch set according to the risk type vector to obtain multiple bank branch subsets; classifies the transaction categories of the bank and divides the transaction category set into multiple transaction category subsets; for each bank branch subset, obtains the customer set served by each bank branch subset, and for each customer in the customer set, determines the transaction category vector of the customer according to the historical transaction data of the customer; clusters the customer set according to the transaction category vector to obtain the bank branch. The invention can effectively improve the matching degree between the advertisements pushed by bank branches and bank customers, thereby improving the conversion rate of bank product promotion, improving the operating efficiency of bank branches, and meeting the actual needs of customers under the premise of controllable risks. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0029] Figure 1 The present invention is a flowchart of a method for allocating advertising resources at bank outlets according to an embodiment of the present invention.
[0030] Figure 2 It is a schematic diagram of a specific process of determining a risk type vector corresponding to each bank branch according to an embodiment of the present invention.
[0031] Figure 3It is a schematic diagram of a process of performing cluster analysis on a bank branch set according to a risk type vector according to an embodiment of the present invention.
[0032] Figure 4 It is a flowchart of obtaining a more accurately classified bank branch subset according to an embodiment of the present invention.
[0033] Figure 5 It is a schematic diagram of a specific process of determining a transaction category vector of a customer according to an embodiment of the present invention.
[0034] Figure 6 It is a flowchart of determining the optimal advertisement delivery strategy corresponding to each customer category vector according to an embodiment of the present invention.
[0035] Figure 7 It is a flow chart of determining the optimal advertising delivery strategy of a first bank branch at the current moment according to an embodiment of the present invention.
[0036] Figure 8 It is a flowchart of another embodiment of the present invention for determining the optimal advertising delivery strategy of the first bank branch at the current moment.
[0037] Fig. 9 It is a flowchart of determining multiple maximum corresponding relationships of all the corresponding relationships screened out according to an embodiment of the present invention.
[0038] Fig.10 It is a schematic diagram of the architecture of a bank branch advertising resource allocation system according to an embodiment of the present invention.
[0039] Fig.11 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0040] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.
[0041] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.
[0042] According to an embodiment of the present invention, a method and system for allocating advertising resources for bank outlets are proposed, which relate to the field of data processing technology.
[0043] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.
[0044] Figure 1 FIG. 1 is a flow chart of a method for allocating advertising resources at bank outlets according to an embodiment of the present invention. Figure 1 As shown, the method includes:
[0045] S1, for each bank branch in the bank branch set, determine the risk type vector corresponding to each bank branch;
[0046] S2, performing cluster analysis on the bank branch set according to the risk type vector to obtain multiple bank branch subsets; storing the corresponding relationship between the bank branch and the bank branch subset to which the bank branch belongs in a database of the bank server;
[0047] S3, classifying the transaction categories of the bank, dividing the transaction category set into multiple transaction category sub-sets;
[0048] S4, for each bank branch subset, obtain a customer set served by each bank branch subset, and for each customer in the customer set, determine a transaction category vector of the customer based on the customer's historical transaction data; wherein the components of the transaction category vector correspond one-to-one to the transaction category subset; cluster the customer set based on the transaction category vector to obtain multiple customer subsets corresponding to the bank branch subset; and store the correspondence between the bank branch subset and the multiple customer subsets corresponding to the bank branch subset in a database of a bank server;
[0049] S5, for each bank branch of the bank branch subset, obtain the customer category vector, advertising delivery strategy and advertising effect index in each sampling time period; wherein the components of the customer category vector correspond to the customer subset one by one; determine the optimal advertising delivery strategy corresponding to each customer category vector according to the customer category vector, advertising delivery strategy and advertising effect index, and store the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy in the database of the bank server;
[0050] S6, for the first bank branch, obtaining a set of customers currently served; the first bank branch sends an advertisement delivery strategy acquisition request to a bank server, wherein the acquisition request includes the set of customers currently served;
[0051] S7, the bank server determines the bank branch subset to which the first bank branch belongs based on the correspondence between the bank branch and the bank branch subset to which the bank branch belongs; determines the customer category vector corresponding to the first bank branch at the current moment based on the multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs; the bank server determines the optimal advertising delivery strategy for the first bank branch at the current moment based on the correspondence between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch;
[0052] S8, the first bank branch carries out advertisement delivery at the current moment according to the received optimal advertisement delivery strategy.
[0053] In order to explain the above-mentioned method of allocating bank branch advertising resources more clearly, each step will be described in detail below.
[0054] In S1, ref. Figure 2 , for each bank branch in the bank branch set, the specific process of determining the risk type vector corresponding to each bank branch is:
[0055] S101, determining the risk type of each bank branch and the risk probability corresponding to each risk type based on the historical transaction data of each bank branch;
[0056] S102, taking the risk type with a risk probability greater than a first threshold as the first risk type; setting a risk type vector, the length of which is equal to the number of risk types of the bank, and each component of which corresponds to a risk type; if the corresponding risk type is the first risk type of the bank branch, setting the corresponding component to the risk probability corresponding to the risk type, and if not, setting the corresponding component to 0.
[0057] In one embodiment, (S101) the risk type of each bank branch and the risk probability corresponding to each risk type are determined based on the historical transaction data of each bank branch, specifically:
[0058] Acquire transaction data of the bank branch in period A, and determine the risk type contained in the transaction data as the risk type of the bank branch;
[0059] For each risk type of a bank branch, if the risk type is not the risk type of the bank branch, the risk probability corresponding to the risk type is determined to be 0;
[0060] For each risk type of a bank branch, if the risk type is the risk type of the bank branch, perform the following steps:
[0061] Determine the risk probability of the risk type for each day in period A, and determine the variance σ of the risk probability corresponding to the risk type based on the risk probability of the risk type for all days in period A;
[0062] Select the acceptable probability error threshold ε and the probability P of the acceptable probability error being greater than ε, and determine the day threshold of the risk probability corresponding to the risk type as
[0063] Select period B whose number of days is greater than the day threshold of the risk probability corresponding to the risk type (of course, if the number of days in period A is greater than the day threshold, period A can be selected), and determine the risk probability corresponding to the risk type as the mean of the risk probabilities of the risk type for all days in period B.
[0064] Among them, for each day (period A or period B), the method for determining the risk probability of the risk type on that day is: obtain the historical transaction data of the bank branch on that day, and determine the proportion of historical transaction data involving the risk type in the historical transaction data as the risk probability of the risk type on that day.
[0065] In S2, reference Figure 3 , cluster analysis is performed on the bank branch set according to the risk type vector to obtain multiple bank branch subsets; the specific process of storing the corresponding relationship between the bank branch and the bank branch subset to which the bank branch belongs in the database of the bank server is as follows:
[0066] S201, according to the risk type vector of each bank branch, set the distance function of the bank branch; wherein the independent variable of the distance function is any two bank branches, and the function value is the distance between the risk type vectors of the two bank branches;
[0067] S202: Perform cluster analysis on bank outlets according to the distance function to obtain a plurality of bank outlet subsets.
[0068] In one embodiment, according to the distance function, K-means is used to perform cluster analysis on bank outlets within a region to obtain multiple subsets of bank outlets.
[0069] refer to Figure 4 In order to obtain a more accurately classified subset of bank branches, the following steps can be performed:
[0070] S2021, for each bank branch subset obtained, determine the transaction category with the largest transaction data in the historical transaction data of each branch in the bank branch subset, and determine the transaction category as the maximum transaction category of the branch. For each maximum transaction category corresponding to the bank branch subset, determine the ratio of the number of branches in the bank branch subset corresponding to the maximum transaction category to the number of branches in the bank branch subset, and determine the maximum ratio among all ratios as the consistency index of the bank branch subset;
[0071] S2022, for each bank branch subset obtained, determine whether the bank branch subset satisfies the following condition s: the consistency index of the bank branch subset is greater than the set value. If not, continue to cluster all the branches of the bank branch subset using the clustering algorithm until each newly generated bank branch subset satisfies the condition s.
[0072] In S3, the transaction categories of the bank are classified, and the transaction category set is divided into multiple transaction category sub-sets.
[0073] In this embodiment, for each transaction category of the bank, multi-dimensional data of the transaction category is determined, wherein the transaction dimension includes at least: risk level, main customer category, transaction volume, and main risk type. The risk level refers to the degree of abnormality of the transaction category, and the higher the proportion of abnormality, the higher the risk level; the main customer category is the customer category with the highest proportion among the customers corresponding to the transaction category as the main customer category; the transaction volume refers to the number of transactions; the main risk type is the risk type with the largest difference between the risk probability of the bank branch and the second threshold.
[0074] For each dimension, a corresponding distance function is determined, and the distance between any two values of the dimension can be calculated. Then the distance function corresponding to the transaction is determined, and the two independent variables of the distance function are any two transaction categories. The corresponding function value can be determined as follows: Based on the distance function of each dimension, the distance between the two transaction categories with respect to the two values of the dimension is determined, and then the function value of the two transaction categories is obtained.
[0075] Based on the distance function corresponding to the transaction and taking the main risk type as the identifier, the supervised clustering algorithm is used to perform cluster analysis on the transaction category set to obtain multiple transaction category subsets.
[0076] In S4, ref. Figure 5 For each bank branch subset, the customer set served by each bank branch subset is obtained. For each customer in the customer set, the specific process of determining the transaction category vector of the customer based on the customer's historical transaction data is as follows:
[0077] S401, for each customer, based on the historical transaction data of the customer, determining the transaction data of which the transaction categories in the historical transaction data belong to each transaction category subset;
[0078] S402, set the transaction category vector of the customer, the length of the transaction category vector is equal to the number of transaction category subsets, the components of the transaction category vector correspond one-to-one to the transaction category subsets, and the value of each component is equal to the number of transactions in the historical transaction data of the customer whose transaction category belongs to the transaction category subset corresponding to the component.
[0079] In S5, ref. Figure 6 , for each bank branch subset, obtain the customer category vector, advertising delivery strategy and advertising effect index for each sampling time period; wherein the components of the customer category vector correspond to the customer subset one by one; determine the optimal advertising delivery strategy corresponding to each customer category vector according to the customer category vector, advertising delivery strategy and advertising effect index, and store the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy in the database of the bank server. The specific process is as follows:
[0080] S501, for each sampling time period, obtain the customer set currently served by the bank branch in the sampling time period; for each customer subset, determine the number of customers belonging to the customer subset in the currently served customer set; according to the number of customers, set the customer category vector for the sampling time period, each component of the customer category vector corresponds to each customer subset one by one, and the value of each component is equal to the number of customers belonging to the customer subset corresponding to the component in the currently served customer set;
[0081] S502, for each customer category vector, select a sampling time period with the largest corresponding advertising effect index from multiple sampling time periods corresponding to the customer category vector, and use the advertising delivery strategy corresponding to the sampling time period as the optimal advertising delivery strategy corresponding to the customer category vector; wherein the advertising delivery strategy at least includes the delivery sequence, delivery duration and delivery position of each advertisement; the advertising effect index is the total length of time that all customers served by the bank branch watch the advertisement within the sampling time period, or the proportion of customers who purchase the advertised product after the advertisement is delivered among the set of customers served by the bank branch within the sampling time period.
[0082] In S6, for the first bank branch, the customer set currently served is obtained; the first bank branch sends an advertisement delivery strategy acquisition request to the bank server, wherein the acquisition request includes the customer set currently served.
[0083] In S7, the bank server determines the bank branch subset to which the first bank branch belongs based on the correspondence between bank branches and the bank branch subset to which the bank branch belongs; determines the customer category vector corresponding to the first bank branch at the current moment based on multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs; the bank server determines the optimal advertising delivery strategy for the first bank branch at the current moment based on the correspondence between the bank branch subsets, the customer category vectors and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch.
[0084] In one embodiment, according to the multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs, the specific process of determining the customer category vector corresponding to the first bank branch at the current moment is as follows:
[0085] According to the customer set included in the advertisement delivery strategy acquisition request and multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs, a customer category vector corresponding to the customer set is determined, each component of the customer category vector corresponds one-to-one to each customer subset corresponding to the bank branch subset to which the first bank branch belongs, and each component value of the customer category vector is equal to the number of customers who belong to the customer subset corresponding to the component in the customer set included in the advertisement delivery strategy acquisition request.
[0086] In one embodiment, reference Figure 7 The specific process of the bank server determining the optimal advertising delivery strategy of the first bank branch at the current moment according to the correspondence between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returning the optimal advertising delivery strategy to the first bank branch is as follows:
[0087] S701, from the correspondence between the bank branch subsets, the customer category vectors and the optimal advertisement delivery strategy, select the correspondence between the bank branch subsets to which the first bank branch belongs;
[0088] S702, for each corresponding relationship selected, determine the distance between the customer category vector of the corresponding relationship and the customer category vector corresponding to the first bank branch at the current moment, and use the distance as the distance between the corresponding relationship and the first bank branch at the current moment;
[0089] S703, selecting the corresponding relationship with the shortest distance to the first bank branch at the current moment from the selected multiple corresponding relationships, and determining the optimal advertising delivery strategy of the corresponding relationship as the optimal advertising delivery strategy of the first bank branch at the current moment.
[0090] In one embodiment, reference Figure 8Another method is that the bank server determines the optimal advertising delivery strategy of the first bank branch at the current moment according to the correspondence between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch:
[0091] S711, from the correspondence between the bank branch subsets, the customer category vectors and the optimal advertising delivery strategy, selecting the correspondence between the bank branch subsets to which the first bank branch belongs;
[0092] S712, for any corresponding relationship selected, determine the difference between the customer category vector of the corresponding relationship and the customer category vector corresponding to the first bank branch at the current moment, and determine the difference as the vector difference corresponding to the corresponding relationship;
[0093] S713, determining the partial order of all the corresponding relations selected, wherein, for any two corresponding relations selected, if for any component, the absolute value of the vector difference corresponding to the first corresponding relation of the two corresponding relations in the value of the component is less than or equal to the absolute value of the vector difference corresponding to the second corresponding relation of the two corresponding relations in the value of the component, then it is determined that the first corresponding relation is closer to the second corresponding relation;
[0094] S714, determining multiple maximal corresponding relations of all the selected corresponding relations according to the partial order, wherein the multiple maximal corresponding relations are maximal elements of the partial order;
[0095] S715, determining the optimal advertising delivery strategy for the first bank branch at the current moment based on the optimal advertising delivery strategies of the multiple maximum correspondences.
[0096] It should be noted that the maximum element of the partial order is that in the set corresponding to the partial order, no other element is better than the maximum element. The maximum corresponding relationship of all the corresponding relationships selected specifically means that there is no other corresponding relationship among all the corresponding relationships selected, so that the other corresponding relationship is close to the maximum corresponding relationship.
[0097] Among them, reference Fig. 9 , according to the partial order, the method of determining multiple maximal corresponding relations of all the corresponding relations screened out is as follows:
[0098] S7141, initializing the maximum flag corresponding to each corresponding relationship of all the corresponding relationships screened out to be set as possible;
[0099] S7142, for each corresponding relationship of all the corresponding relationships that have been screened out, if the maximum flag corresponding to the corresponding relationship is not set to possible, then execute step S7142 for the next corresponding relationship; if the maximum flag corresponding to the corresponding relationship is set to possible, then for each other corresponding relationship except the corresponding relationship in all the corresponding relationships that have been screened out, compare the other corresponding relationship with the corresponding relationship, specifically:
[0100] If the other corresponding relationship is closer to the corresponding relationship, the maximum mark corresponding to the corresponding relationship is set to no; if the corresponding relationship is closer to the other corresponding relationship, the maximum mark corresponding to the other corresponding relationship is set to no; otherwise, the maximum mark corresponding to the corresponding relationship and the maximum mark corresponding to the other corresponding relationship remain unchanged;
[0101] If after comparing all other corresponding relationships with the corresponding relationship, the maximum identification of the corresponding relationship is still possible, then the corresponding relationship is determined as the maximum corresponding relationship among all the selected corresponding relationships.
[0102] In S8, the first bank branch performs advertisement delivery at the current moment according to the received optimal advertisement delivery strategy.
[0103] It should be noted that, although the operations of the method of the present invention are described in a specific order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.
[0104] After introducing the method of the exemplary embodiment of the present invention, next, refer to Fig.10 A bank branch advertisement delivery resource allocation system according to an exemplary embodiment of the present invention is introduced.
[0105] The implementation of the allocation system of bank branch advertising resources can refer to the implementation of the above method, and the repetitions will not be repeated. The terms "module" or "unit" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.
[0106] Based on the same inventive concept, the present invention also proposes a bank branch advertising resource allocation system, such as Fig.10 As shown, the system includes:
[0107] The data processing module 1010 is used to determine, for each bank branch in the bank branch set, a risk type vector corresponding to each bank branch;
[0108] The bank branch subset analysis module 1020 is used to perform cluster analysis on the bank branch set according to the risk type vector to obtain multiple bank branch subsets; store the corresponding relationship between the bank branch and the bank branch subset to which the bank branch belongs in the database of the bank server;
[0109] A classification module 1030, for classifying the transaction categories of the bank, and dividing the transaction category set into a plurality of transaction category sub-sets;
[0110] The transaction category vector processing module 1040 is used to obtain, for each bank branch subset, a customer set served by each bank branch subset, and for each customer in the customer set, determine the transaction category vector of the customer based on the customer's historical transaction data; wherein the components of the transaction category vector correspond to the transaction category subset one by one; cluster the customer set based on the transaction category vector to obtain multiple customer subsets corresponding to the bank branch subset; and store the correspondence between the bank branch subset and the multiple customer subsets corresponding to the bank branch subset in a database of a bank server;
[0111] The corresponding relationship processing module 1050 is used to obtain the customer category vector, the advertising delivery strategy and the advertising effect index in each sampling time period for each bank branch of each bank branch subset; wherein the components of the customer category vector correspond to the customer subset one by one; determine the optimal advertising delivery strategy corresponding to each customer category vector according to the customer category vector, the advertising delivery strategy and the advertising effect index, and store the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy in the database of the bank server;
[0112] The request acquisition module 1060 is used to acquire the set of customers currently served by the first bank branch; the first bank branch sends an advertisement delivery strategy acquisition request to the bank server, wherein the acquisition request includes the set of customers currently served;
[0113] The optimal advertisement delivery strategy processing module 1070 is used for the bank server to determine the bank branch subset to which the first bank branch belongs according to the correspondence between the bank branch and the bank branch subset to which the bank branch belongs; determine the customer category vector corresponding to the first bank branch at the current moment according to the multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs; the bank server determines the optimal advertisement delivery strategy for the first bank branch at the current moment according to the correspondence between the bank branch subset, the customer category vector and the optimal advertisement delivery strategy, and returns the optimal advertisement delivery strategy to the first bank branch;
[0114] The advertisement delivery processing module 1080 is used for the first bank branch to deliver advertisements at the current moment according to the received optimal advertisement delivery strategy.
[0115] In one embodiment, the data processing module is specifically used for:
[0116] Based on the historical transaction data of each bank branch, determine the risk type of the bank branch and the risk probability corresponding to each risk type;
[0117] The risk type with a risk probability greater than a first threshold is taken as the first risk type; a risk type vector is set, the length of which is equal to the number of risk types of the bank, and each component of the risk type vector corresponds to a risk type; if the corresponding risk type is the first risk type of the bank branch, the corresponding component is set to the risk probability corresponding to the risk type, if not, the corresponding component is set to 0.
[0118] In one embodiment, the transaction category vector processing module is specifically used to:
[0119] For each customer, based on the customer's historical transaction data, determine the transaction data of each transaction category subset to which the transaction category in the historical transaction data belongs; set the customer's transaction category vector, the length of which is equal to the number of transaction category subsets, the components of which correspond one-to-one to the transaction category subsets, and the value of each component is equal to the number of transactions in the customer's historical transaction data whose transaction category belongs to the transaction category subset corresponding to the component.
[0120] In one embodiment, the correspondence processing module is specifically used to:
[0121] For each sampling time period, obtain the customer set currently served by the bank branch in the sampling time period; for each customer subset, determine the number of customers belonging to the customer subset in the currently served customer set; according to the number of customers, set the customer category vector for the sampling time period, each component of the customer category vector corresponds to each customer subset one by one, and the value of each component is equal to the number of customers belonging to the customer subset corresponding to the component in the currently served customer set;
[0122] For each customer category vector, a sampling time period with the largest corresponding advertising effect index is selected from multiple sampling time periods corresponding to the customer category vector, and the advertising delivery strategy corresponding to the sampling time period is used as the optimal advertising delivery strategy corresponding to the customer category vector; wherein the advertising delivery strategy at least includes the delivery sequence, delivery duration and delivery position of each advertisement; the advertising effect index is the total length of time that all customers served by the bank branch watch the advertisement within the sampling time period, or the proportion of customers who purchase the advertised product after the advertisement is delivered among the set of customers served by the bank branch within the sampling time period.
[0123] In one embodiment, the optimal advertisement delivery strategy processing module is specifically used to:
[0124] According to the customer set included in the advertisement delivery strategy acquisition request and multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs, a customer category vector corresponding to the customer set is determined, each component of the customer category vector corresponds one-to-one to each customer subset corresponding to the bank branch subset to which the first bank branch belongs, and each component value of the customer category vector is equal to the number of customers who belong to the customer subset corresponding to the component in the customer set included in the advertisement delivery strategy acquisition request.
[0125] In one embodiment, the optimal advertisement delivery strategy processing module is specifically used to:
[0126] From the correspondence between the bank branch subsets, the customer category vectors and the optimal advertising delivery strategy, the correspondence between the bank branch subsets to which the first bank branch belongs is selected;
[0127] For each corresponding relationship selected, determine the distance between the customer category vector of the corresponding relationship and the customer category vector corresponding to the first bank branch at the current moment, and use the distance as the distance between the corresponding relationship and the first bank branch at the current moment;
[0128] From the selected multiple corresponding relationships, the corresponding relationship with the shortest distance to the first bank branch at the current moment is selected, and the optimal advertising delivery strategy of the corresponding relationship is determined as the optimal advertising delivery strategy of the first bank branch at the current moment.
[0129] It should be noted that although several modules of the allocation system for bank branch advertising resources are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules described above can be concretized in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules to be concretized.
[0130] Based on the above invention concept, Fig.11 As shown, the present invention also proposes a computer device 1100, including a memory 1110, a processor 1120, and a computer program 1130 stored in the memory 1110 and executable on the processor 1120, wherein the processor 1120 implements the aforementioned method for allocating bank branch advertising resources when executing the computer program 1130.
[0131] Based on the aforementioned inventive concept, the present invention proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the aforementioned method for allocating bank branch advertising resources is implemented.
[0132] Based on the aforementioned inventive concept, the present invention proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, a method for allocating advertising resources for bank outlets is implemented.
[0133] The method and system for allocating bank branch advertising resources proposed in the present invention analyzes the data of bank branches to determine the risk type vector corresponding to each bank branch; clusters the bank branch set according to the risk type vector to obtain multiple bank branch subsets; classifies the transaction categories of the bank and divides the transaction category set into multiple transaction category subsets; for each bank branch subset, obtains the customer set served by each bank branch subset, and for each customer in the customer set, determines the transaction category vector of the customer according to the historical transaction data of the customer; clusters the customer set according to the transaction category vector to obtain the bank branch. The invention can effectively improve the matching degree between the advertisements pushed by bank branches and bank customers, thereby improving the conversion rate of bank product promotion, improving the operating efficiency of bank branches, and meeting the actual needs of customers under the premise of controllable risks.
[0134] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0136] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0138] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims
1. A method for allocating advertising resources for bank outlets, characterized in that: include: For each bank branch in the bank branch set, determine a risk type vector corresponding to each bank branch; Perform cluster analysis on the bank branch set according to the risk type vector to obtain multiple bank branch subsets; The correspondence between the bank branch and the bank branch subset to which the bank branch belongs is stored in a database of the bank server; Classify the transaction categories of the bank and divide the transaction category set into multiple transaction category sub-sets; For each bank branch subset, obtain a customer set served by each bank branch subset, and for each customer in the customer set, determine a transaction category vector of the customer based on the customer's historical transaction data; wherein the components of the transaction category vector correspond one-to-one to the transaction category subset; cluster the customer set based on the transaction category vector to obtain multiple customer subsets corresponding to the bank branch subset; store the correspondence between the bank branch subset and the multiple customer subsets corresponding to the bank branch subset in a database of a bank server; For each bank branch of the bank branch subset, obtain the customer category vector, advertising delivery strategy and advertising effect index in each sampling time period; wherein the components of the customer category vector correspond to the customer subset one by one; determine the optimal advertising delivery strategy corresponding to each customer category vector according to the customer category vector, advertising delivery strategy and advertising effect index, and store the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy in the database of the bank server; For a first bank branch, a customer set currently served by the first bank branch is obtained; the first bank branch sends an advertisement delivery strategy acquisition request to a bank server, wherein the acquisition request includes the customer set currently served by the first bank branch; The bank server determines the bank branch subset to which the first bank branch belongs based on the correspondence between the bank branch and the bank branch subset to which the bank branch belongs; determines the customer category vector corresponding to the first bank branch at the current moment based on the multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs; the bank server determines the optimal advertising delivery strategy for the first bank branch at the current moment based on the correspondence between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch; The first bank branch performs advertisement delivery at the first bank branch at the current moment according to the received optimal advertisement delivery strategy; For each bank branch of each bank branch subset, a customer category vector, an advertisement delivery strategy, and an advertisement effect index in each sampling time period are obtained; wherein the components of the customer category vector correspond to the customer subset one by one; the optimal advertisement delivery strategy corresponding to each customer category vector is determined according to the customer category vector, the advertisement delivery strategy, and the advertisement effect index, and the corresponding relationship between the bank branch subset, the customer category vector, and the optimal advertisement delivery strategy is stored in a database of a bank server, including: For each sampling time period, obtain the customer set currently served by the bank branch in the sampling time period; for each customer subset, determine the number of customers belonging to the customer subset in the currently served customer set; according to the number of customers, set the customer category vector for the sampling time period, each component of the customer category vector corresponds to each customer subset one by one, and the value of each component is equal to the number of customers belonging to the customer subset corresponding to the component in the currently served customer set; For each customer category vector, a sampling time period with the largest corresponding advertising effect index is selected from multiple sampling time periods corresponding to the customer category vector, and the advertising delivery strategy corresponding to the sampling time period is used as the optimal advertising delivery strategy corresponding to the customer category vector; wherein the advertising delivery strategy at least includes the delivery sequence, delivery duration and delivery position of each advertisement; the advertising effect index is the total length of time that all customers served by the bank branch watch the advertisement within the sampling time period, or the proportion of customers who purchase the advertised product after the advertisement is delivered among the set of customers served by the bank branch within the sampling time period.
2. The method according to claim 1, characterized in that For each bank branch in the bank branch set, determine the risk type vector corresponding to each bank branch, including: Based on the historical transaction data of each bank branch, determine the risk type of the bank branch and the risk probability corresponding to each risk type; The risk type with a risk probability greater than a first threshold is taken as the first risk type; a risk type vector is set, the length of which is equal to the number of risk types of the bank, and each component of the risk type vector corresponds to a risk type; if the corresponding risk type is the first risk type of the bank branch, the corresponding component is set to the risk probability corresponding to the risk type, if not, the corresponding component is set to 0.
3. The method according to claim 1, characterized in that For each bank branch subset, a customer set served by each bank branch subset is obtained, and for each customer in the customer set, a transaction category vector of the customer is determined based on the customer's historical transaction data, including: For each customer, based on the customer's historical transaction data, determine the transaction data of each transaction category subset to which the transaction category in the historical transaction data belongs; set the customer's transaction category vector, the length of which is equal to the number of transaction category subsets, the components of which correspond one-to-one to the transaction category subsets, and the value of each component is equal to the number of transactions in the customer's historical transaction data whose transaction category belongs to the transaction category subset corresponding to the component.
4. The method according to claim 1, characterized in that Determining a customer category vector corresponding to the first bank branch at a current moment according to a plurality of customer subsets corresponding to the bank branch subset to which the first bank branch belongs includes: According to the customer set included in the advertisement delivery strategy acquisition request and multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs, a customer category vector corresponding to the customer set is determined, each component of the customer category vector corresponds one-to-one to each customer subset corresponding to the bank branch subset to which the first bank branch belongs, and each component value of the customer category vector is equal to the number of customers who belong to the customer subset corresponding to the component in the customer set included in the advertisement delivery strategy acquisition request.
5. The method according to claim 1, characterized in that The bank server determines the optimal advertising delivery strategy of the first bank branch at the current moment according to the correspondence between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch, including: From the correspondence between the bank branch subsets, the customer category vectors and the optimal advertising delivery strategy, the correspondence between the bank branch subsets to which the first bank branch belongs is selected; For each corresponding relationship selected, determine the distance between the customer category vector of the corresponding relationship and the customer category vector corresponding to the first bank branch at the current moment, and use the distance as the distance between the corresponding relationship and the first bank branch at the current moment; From the selected multiple corresponding relationships, the corresponding relationship with the shortest distance to the first bank branch at the current moment is selected, and the optimal advertising delivery strategy of the corresponding relationship is determined as the optimal advertising delivery strategy of the first bank branch at the current moment.
6. A bank branch advertising resource allocation system, characterized in that: include: A data processing module, used for determining, for each bank branch in the bank branch set, a risk type vector corresponding to each bank branch; A bank branch subset analysis module is used to perform cluster analysis on the bank branch set according to the risk type vector to obtain multiple bank branch subsets; The correspondence between the bank branch and the bank branch subset to which the bank branch belongs is stored in a database of the bank server; A classification module, used to classify the transaction categories of the bank and divide the transaction category set into multiple transaction category sub-sets; A transaction category vector processing module is used to obtain, for each bank branch subset, a customer set served by each bank branch subset, and for each customer in the customer set, determine the transaction category vector of the customer based on the customer's historical transaction data; wherein the components of the transaction category vector correspond to the transaction category subset one by one; cluster the customer set based on the transaction category vector to obtain multiple customer subsets corresponding to the bank branch subset; and store the correspondence between the bank branch subset and the multiple customer subsets corresponding to the bank branch subset in a database of a bank server; A corresponding relationship processing module is used to obtain the customer category vector, advertising delivery strategy and advertising effect index in each sampling time period for each bank branch of each bank branch subset; wherein the components of the customer category vector correspond to the customer subset one by one; determine the optimal advertising delivery strategy corresponding to each customer category vector according to the customer category vector, advertising delivery strategy and advertising effect index, and store the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy in the database of the bank server; A request acquisition module is used to acquire, for a first bank branch, a set of customers served by the first bank branch at the current moment; the first bank branch sends an advertisement delivery strategy acquisition request to a bank server, wherein the acquisition request includes the set of customers served by the first bank branch at the current moment; The optimal advertising delivery strategy processing module is used for the bank server to determine the bank branch subset to which the first bank branch belongs according to the corresponding relationship between the bank branch and the bank branch subset to which the bank branch belongs; determine the customer category vector corresponding to the first bank branch at the current moment according to multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs; the bank server determines the optimal advertising delivery strategy for the first bank branch at the current moment according to the corresponding relationship between the bank branch subset, the customer category vector and the optimal advertising delivery strategy, and returns the optimal advertising delivery strategy to the first bank branch; An advertisement delivery processing module, used for the first bank branch to deliver advertisements at the first bank branch at the current moment according to the received optimal advertisement delivery strategy; Wherein, the corresponding relationship processing module is specifically used for: For each sampling time period, obtain the customer set currently served by the bank branch in the sampling time period; for each customer subset, determine the number of customers belonging to the customer subset in the currently served customer set; according to the number of customers, set the customer category vector for the sampling time period, each component of the customer category vector corresponds to each customer subset one by one, and the value of each component is equal to the number of customers belonging to the customer subset corresponding to the component in the currently served customer set; For each customer category vector, a sampling time period with the largest corresponding advertising effect index is selected from multiple sampling time periods corresponding to the customer category vector, and the advertising delivery strategy corresponding to the sampling time period is used as the optimal advertising delivery strategy corresponding to the customer category vector; wherein the advertising delivery strategy at least includes the delivery sequence, delivery duration and delivery position of each advertisement; the advertising effect index is the total length of time that all customers served by the bank branch watch the advertisement within the sampling time period, or the proportion of customers who purchase the advertised product after the advertisement is delivered among the set of customers served by the bank branch within the sampling time period.
7. The system according to claim 6, characterized in that The data processing module is specifically used for: Based on the historical transaction data of each bank branch, determine the risk type of the bank branch and the risk probability corresponding to each risk type; The risk type with a risk probability greater than a first threshold is regarded as a first risk type; Set a risk type vector, the length of which is equal to the number of risk types of the bank, and each component of which corresponds to a risk type; If the corresponding risk type is the first risk type of the bank branch, the corresponding component is set to the risk probability corresponding to the risk type; if not, the corresponding component is set to 0.
8. The system according to claim 6, characterized in that The transaction category vector processing module is specifically used for: For each customer, based on the customer's historical transaction data, determine the transaction data of each transaction category subset to which the transaction category in the historical transaction data belongs; set the customer's transaction category vector, the length of which is equal to the number of transaction category subsets, the components of which correspond one-to-one to the transaction category subsets, and the value of each component is equal to the number of transactions in the customer's historical transaction data whose transaction category belongs to the transaction category subset corresponding to the component.
9. The system according to claim 6, characterized in that The optimal advertisement delivery strategy processing module is specifically used for: According to the customer set included in the advertisement delivery strategy acquisition request and multiple customer subsets corresponding to the bank branch subset to which the first bank branch belongs, a customer category vector corresponding to the customer set is determined, each component of the customer category vector corresponds one-to-one to each customer subset corresponding to the bank branch subset to which the first bank branch belongs, and each component value of the customer category vector is equal to the number of customers who belong to the customer subset corresponding to the component in the customer set included in the advertisement delivery strategy acquisition request.
10. The system according to claim 6, characterized in that The optimal advertisement delivery strategy processing module is specifically used for: From the correspondence between the bank branch subsets, the customer category vectors and the optimal advertising delivery strategy, the correspondence between the bank branch subsets to which the first bank branch belongs is selected; For each corresponding relationship selected, determine the distance between the customer category vector of the corresponding relationship and the customer category vector corresponding to the first bank branch at the current moment, and use the distance as the distance between the corresponding relationship and the first bank branch at the current moment; From the selected multiple corresponding relationships, the corresponding relationship with the shortest distance to the first bank branch at the current moment is selected, and the optimal advertising delivery strategy of the corresponding relationship is determined as the optimal advertising delivery strategy of the first bank branch at the current moment.
11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.
12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
