CN114971021A - Transaction tab prediction method and device - Google Patents
Transaction tab prediction method and device Download PDFInfo
- Publication number
- CN114971021A CN114971021A CN202210586557.2A CN202210586557A CN114971021A CN 114971021 A CN114971021 A CN 114971021A CN 202210586557 A CN202210586557 A CN 202210586557A CN 114971021 A CN114971021 A CN 114971021A
- Authority
- CN
- China
- Prior art keywords
- transaction
- transactions
- customer
- current
- client
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004590 computer program Methods 0.000 claims description 29
- 238000004891 communication Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a transaction tab prediction method and a device, which relate to the technical field of artificial intelligence, and the method comprises the following steps: acquiring historical transaction data of bank customers in a designated area, and clustering the customers according to the historical transaction data to obtain a plurality of customer subsets; according to the historical transaction data, a transaction graph corresponding to each customer subset is constructed; when receiving current transaction data operated by a customer on a bank self-service terminal, determining the current transaction in progress by the customer; determining a target transaction graph corresponding to a customer subset where the customer is; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed after the client according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; and after the customer completes the current transaction, displaying the transaction option card of the alternative transaction on the bank self-service terminal. The invention can facilitate the customer to quickly find the next transaction to be completed.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a transaction tab prediction method and a device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
At present, a bank self-service terminal can provide a variety of transactions, correspondingly, a plurality of transaction tabs are provided, the interface structure is complex, a customer needs to spend a long time to check each transaction tab, and the transaction tab corresponding to the transaction which the customer wants to complete is selected, so that the customer experience is low.
Disclosure of Invention
The embodiment of the invention provides a transaction option prediction method, which is used for predicting the next transaction which is possibly performed after the current transaction of a client, and is convenient for the client to quickly search the next transaction to be completed, thereby improving the experience of the client, and the method comprises the following steps:
acquiring historical transaction data of bank customers in a designated area, and clustering the customers according to the historical transaction data to obtain a plurality of customer subsets;
according to the historical transaction data, constructing a transaction graph corresponding to each customer subset, wherein the transaction graph comprises occurrence conditions and occurrence probability of a subsequent transaction after the previous transaction is completed in the associated transactions with a sequential execution order relationship;
when receiving current transaction data operated by a customer on a bank self-service terminal, determining the current transaction performed by the customer; determining a target transaction graph corresponding to a customer subset where a customer is located; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; and after the customer completes the current transaction, displaying the transaction option card of the alternative transaction on the bank self-service terminal.
The embodiment of the present invention further provides a transaction tab prediction device, configured to predict a next transaction that may be performed after a current transaction of a client, so that the client can conveniently and quickly find the next transaction to be completed, and the experience of the client is improved, where the device includes:
the clustering module is used for acquiring historical transaction data of bank customers in a designated area, and clustering the customers according to the historical transaction data to obtain a plurality of customer subsets;
the construction module is used for constructing a transaction graph corresponding to each customer subset according to the historical transaction data, wherein the transaction graph comprises the occurrence conditions and the occurrence probability of the next transaction after the previous transaction is completed in the associated transactions with the sequential execution order relationship;
the system comprises a determining module, a processing module and a processing module, wherein the determining module is used for determining the current transaction of a customer when receiving the current transaction data operated by the customer on a bank self-service terminal; determining a target transaction graph corresponding to a customer subset where the customer is; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; when the customer completes the current transaction, the display module displays the transaction option card of the alternative transaction on the bank self-service terminal
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the transaction option prediction method.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for predicting a transaction tab is implemented.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the method for predicting a transaction tab is implemented.
In the embodiment of the invention, considering that the transaction behaviors of the customers in a certain area have certain similarity, historical transaction data of bank customers in a specified area are obtained, and then the customers are clustered according to the historical transaction data to obtain a plurality of customer subsets, so that the customers in each customer subset can consider that the transaction behaviors have higher similarity, and the transaction behaviors to be generated by the customers in the customer subset can be predicted according to the historical transaction data of all the customers in the customer subset. During specific prediction, due to the fact that relevance exists among a plurality of transactions continuously selected by a customer, a transaction graph corresponding to each customer subset can be constructed according to historical transaction data, wherein the transaction graph comprises occurrence conditions and occurrence probability of a subsequent transaction after the former transaction is completed in the associated transactions with a sequential execution sequence relation. When receiving current transaction data operated by a customer on a bank self-service terminal, determining the current transaction performed by the customer; determining a target transaction graph corresponding to a customer subset where a customer is located; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction, the transaction option card of the alternative transaction is displayed on the bank self-service terminal, so that the customer can conveniently and quickly find the next transaction to be completed, the time of the customer is saved, and the customer experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flow chart of a transaction tab prediction method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another transaction tab prediction method in accordance with an embodiment of the present invention;
FIG. 3 is a flow chart of another transaction tab prediction method in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of a transaction tab prediction apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
It is first stated that the data acquisition, storage, use, processing, etc. in the technical solution of the present application all comply with the relevant regulations of the national laws and regulations.
An embodiment of the present invention provides a method for predicting a transaction tab, as shown in fig. 1, the method includes steps 101 to 103:
In the embodiment of the invention, the client subset with similar behaviors can be obtained through clustering. Specifically, the following method may be used to cluster the customers using historical transaction data:
1. determining values for a plurality of customer dimensions of a customer, wherein the plurality of customer dimensions may include: risk index, number of businesses in each business category.
And counting the number of risk transactions in the historical transaction data of each client, and determining the risk index of the client as the ratio of the number of the risk transactions to the transaction number contained in the historical transaction data of the client.
When the bank processes (real-time or post-processing) the transaction data of the customer, it is determined by a program algorithm or a human whether there is a risk such as illegal transaction, transaction fraud, suspected fraud, etc. in the transaction data. And if the judgment result is that the risk exists, setting the transaction data as risk data, and carrying out risk identification.
2. And determining a distance function of the bank customer based on the plurality of customer dimensions.
Specifically, firstly, for each customer dimension, a distance function of the customer dimension and an argument of the distance function are setIs any two bank customers, and the corresponding function value is the distance between two values (such as the difference between the two values) of the two bank customers in the customer dimension; determining the distance function of the bank customer according to the distance function corresponding to each customer dimension, for example, setting as
Where f is the distance function of the bank customer, f i Is a distance function of the ith customer dimension, w i Is the weight corresponding to the distance function for the ith customer dimension.
3. And clustering all customers of the bank based on the distance function of the bank customers to obtain a plurality of customer subsets.
Specifically, on the basis of obtaining the distance function of the bank customers, an unsupervised clustering algorithm (such as K-means) is adopted to cluster all the customers of the bank, and the transaction categories of the customers can also be used as category identifiers, and a supervised clustering algorithm is adopted to cluster all the customers of the bank, so that a plurality of customer subsets are obtained.
4. In order to obtain a more accurate clustering result, for each client subset obtained above, determining a risk level of each client in the client subset, and determining a maximum value of the client number ratio corresponding to each risk level in the client subset. And determining whether the client subset meets a condition e, wherein the condition e is that the maximum value of the client number ratio corresponding to each risk level in the client subset is greater than a specified ratio, and if the client number ratio is not met (namely is less than the specified ratio), continuing to cluster the client subset (by adopting the clustering algorithm in the steps) until each generated new client subset meets the condition e.
And 102, constructing a transaction graph corresponding to each customer subset according to historical transaction data, wherein the transaction graph comprises the occurrence conditions and the occurrence probability of the next transaction after the previous transaction is completed in the associated transactions with the sequential execution order relation.
In the embodiment of the present invention, the transaction graph is a graph formed by transactions and their sequential execution relations, for example, it is assumed that a directed edge in the transaction graph is from one transaction a to another transaction b (b is a subsequent transaction of a), the corresponding occurrence condition table includes a piece of data, the condition of the data is c and d, and the corresponding occurrence probability is 0.6, which indicates that the current client is making transaction a, and when the transactions c and d have been completed in sequence before, the probability of the client selecting transaction d is 0.6.
Specifically, as shown in fig. 2, for each customer subset, a transaction graph corresponding to the customer subset is constructed according to historical transaction data, and the following steps 201 to 204 may be executed:
and step 204, determining all the associated transactions, the occurrence condition of each group of associated transactions and the occurrence probability corresponding to each group of occurrence conditions as the transaction graph corresponding to the customer subset.
For example, in the historical transaction data of the customers in each customer subset, the same customer completes two transactions b and c in sequence in the operation process of a bank self-service terminal, and if the transaction a is completed before the transactions b and c, the transactions b and c are determined to be related transactions.
And when the statistics shows that a transaction is carried out by some customers, d transaction is carried out by some customers, and e transaction and f transaction are carried out by some customers, the transaction a is used as a group of front transactions of the transaction b and the transaction c, the transaction d is used as a group of front transactions, and the transaction e and the transaction f are used as a group of front transactions.
Counting first historical transaction quantities of continuously executing the transactions a and b in historical transaction data according to the occurrence condition a of the transactions b and c, and recording the first historical transaction quantities as m; then, counting a second historical transaction quantity for continuously executing the transactions a, b and c, and taking n/m as the occurrence probability of the occurrence condition a if the second historical transaction quantity is recorded as n; and (4) calculating the occurrence probability of other occurrence conditions, such as the d transaction and the e and f transactions, in the same way, obtaining all associated transactions and all occurrence conditions of the associated transactions, namely the corresponding occurrence probabilities, wherein the associated transactions, the occurrence conditions and the occurrence probabilities form a transaction graph.
In another possible implementation, the occurrence probability may be calculated as follows:
for historical transaction data of all customers of the customer subset, dividing the historical transaction data into a plurality of data subsets according to a sequence (time sequence);
counting third historical transaction quantity of transactions in the continuous execution occurrence condition and prior transactions in the associated transactions and fourth historical transaction quantity of two transactions in the continuous execution occurrence condition and the associated transactions in each data subset according to each group of associated transactions and each group of occurrence conditions of the group of associated transactions, and determining the ratio of the fourth historical transaction quantity to the third historical transaction quantity as an occurrence probability sample of the group of associated transactions about the group of occurrence conditions;
thirdly, aiming at each group of associated transactions and each group of occurrence conditions of the group of associated transactions, determining the variance corresponding to the occurrence probability of the group of associated transactions relative to the group of occurrence conditions and the number of corresponding samples based on the occurrence probability samples of the group of associated transactions relative to the group of occurrence conditions;
calculating the quotient of the square of the variance corresponding to the occurrence probability of the group of associated transactions relative to the group of occurrence conditions and the corresponding sample number aiming at each group of associated transactions and each group of occurrence conditions of the group of associated transactions, and taking the quotient as the upper error bound of the group of associated transactions relative to the group of occurrence conditions;
if the upper error bound of the group of the associated transactions about the group of the occurrence conditions is determined to be larger than the error threshold, circularly executing the following steps until the upper error bound of the group of the associated transactions about the group of the occurrence conditions is smaller than or equal to the error threshold:
acquiring new historical transaction data of the client subset (or historical transaction data of similar client subsets of the client subset), and dividing the new historical transaction data into a plurality of new data subsets according to a sequence (time sequence); then, sequentially executing the steps II, III and IV according to the group of associated transactions and the group of occurrence conditions;
and determining the occurrence probability of the set of occurrence conditions as the mean value of the occurrence probability samples of the set of associated transactions about the set of occurrence conditions aiming at each set of associated transactions and each set of occurrence conditions of the set of associated transactions.
Wherein the error threshold is determined according to the theorem of majorities.
In one possible implementation, after step 203 is executed to determine the ratio of the second historical transaction amount to the first historical transaction amount as the occurrence probability of the set of occurrence conditions, as shown in fig. 3, the following method may also be executed:
In order to save time of a customer, in the embodiment of the invention, a preset threshold value is used for screening occurrence conditions, preferred occurrence conditions with high occurrence probability are reserved, and occurrence conditions with low occurrence probability are screened out.
In the embodiment of the invention, the incidence relation among the transactions can be obtained through the construction of the transaction graph, and the next transaction which is required by the customer is predicted through the incidence relation.
103, when current transaction data operated by a customer on the bank self-service terminal is received, determining the current transaction carried out by the customer; determining a target transaction graph corresponding to a customer subset where the customer is; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; and after the customer completes the current transaction, displaying the transaction option card of the alternative transaction on the bank self-service terminal.
In the embodiment of the present invention, before step 103 is executed, for each client, each transaction completed when the client operates the mobile terminal may be counted from historical transaction data of the client, and the transactions are arranged according to the order of execution of the client to form a transaction chain; and taking other transactions except the first transaction in the transaction chain as predicted prior transactions in the predicted related transactions, and taking the first 1, the first 2 to the first M transactions which are performed before the predicted prior transactions as occurrence conditions of the predicted online transactions, wherein M is the number of all transactions which are completed before the predicted prior transactions in the transaction chain. Then, for each predicted occurrence condition, all subsequent transactions and occurrence probabilities that occur after the same predicted occurrence condition and the same predicted prior transaction are read from the transaction map as predicted subsequent transactions and predicted occurrence probabilities.
After receiving the current transaction data operated by the customer on the bank self-service terminal, the incidence relation among the predicted prior transaction, the predicted subsequent transaction, the predicted occurrence condition and the corresponding predicted occurrence probability of the customer can be issued to the bank self-service terminal operated by the customer, so that the bank self-service terminal can predict the alternative transaction which is possibly completed by the customer after the current transaction according to the incidence relation, and the transaction option card of the alternative transaction is displayed after the customer completes the current transaction. Therefore, when the network condition between the bank self-service terminal and the bank system is good or bad, the transaction option cards of alternative transactions can be rapidly displayed, and the waiting time of customers is reduced.
In another possible implementation manner, when an unpredicted success message sent by a bank self-service terminal is received, a target transaction graph corresponding to a customer subset where a customer is located is determined; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction, displaying a transaction option card of the alternative transaction in the bank self-service terminal; and when the predicted prior transaction in the association does not contain the current transaction in progress of the customer, the bank self-service terminal sends an unpredicted success message.
In the embodiment of the invention, after receiving the current transaction data operated by a customer on the bank self-service terminal, when all the customer subsets do not contain the customer by searching, the appointed historical transaction data of the customer can be obtained from other areas outside the appointed area, the customer subset to which the customer belongs is determined according to the appointed historical transaction data, and the transaction graph of the customer subset of the customer is determined as the target transaction graph; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; and after the customer completes the current transaction, displaying the transaction option card of the alternative transaction in the bank self-service terminal.
Specifically, when all the client subsets are searched and do not include the client, the client subset to which the client belongs may be determined according to the following method:
determining the dimension value of the customer in each customer dimension according to the specified historical transaction data of the customer;
calculating the distance value of the customer dimension corresponding to the customers of the customer and each customer subset according to the distance function of each customer dimension, and taking the minimum value of the distance values as the distance value of the customer dimension corresponding to the customer of the customer and each customer subset;
selecting a plurality of client subsets from all the client subsets, wherein each selected client subset satisfies that no other client subsets exist, so that for each client dimension, the distance value of the client corresponding to the client dimension from the other client subsets is smaller than or equal to the distance value of the client corresponding to the client dimension from the selected client subset;
and determining the client subset to which the client belongs according to the selected plurality of client subsets.
The customer dimensions comprise risk indexes, business quantity of each business category and the like, and the dimension value of each customer dimension can be obtained from appointed historical transaction data.
In the embodiment of the invention, considering that the transaction behaviors of the customers in a certain area have certain similarity, historical transaction data of bank customers in a specified area are obtained, and then the customers are clustered according to the historical transaction data to obtain a plurality of customer subsets, so that the customers in each customer subset can consider that the transaction behaviors have higher similarity, and the transaction behaviors to be generated by the customers in the customer subset can be predicted according to the historical transaction data of all the customers in the customer subset. During specific prediction, due to the fact that relevance exists among a plurality of transactions continuously selected by a customer, a transaction graph corresponding to each customer subset can be constructed according to historical transaction data, wherein the transaction graph comprises occurrence conditions and occurrence probability of a subsequent transaction after the former transaction is completed in the associated transactions with a sequential execution sequence relation. When receiving current transaction data operated by a customer on a bank self-service terminal, determining the current transaction in progress by the customer; determining a target transaction graph corresponding to a customer subset where a customer is located; if the current transaction is not the first transaction carried out by the client in the current operation, predicting alternative transactions which are possibly finished by the client after the current transaction according to the transaction which is finished before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction, the transaction option card of the alternative transaction is displayed on the bank self-service terminal, so that the customer can conveniently and quickly find the next transaction to be completed, the time of the customer is saved, and the customer experience is improved.
Embodiments of the present invention further provide a transaction tab prediction apparatus, as described in the following embodiments. Because the principle of the device for solving the problems is similar to the transaction option prediction method, the implementation of the device can refer to the implementation of the transaction option prediction method, and repeated parts are not repeated.
As shown in fig. 4, the apparatus 400 includes:
the clustering module 401 is configured to obtain historical transaction data of bank customers in a specified area, and cluster the customers according to the historical transaction data to obtain a plurality of customer subsets;
a building module 402, configured to build a transaction graph corresponding to each customer subset according to historical transaction data, where the transaction graph includes occurrence conditions and occurrence probabilities of a previous transaction and a subsequent transaction after the previous transaction is completed in associated transactions having a sequential execution order relationship;
a determining module 403, configured to determine, when current transaction data operated by a customer on a bank self-service terminal is received, a current transaction being performed by the customer; determining a target transaction graph corresponding to a customer subset where the customer is; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; when the customer completes the current transaction, the transaction tab for the alternate transaction is displayed on the bank self-service terminal by the display module 404.
In an implementation manner of the embodiment of the present invention, the building module is configured to:
extracting associated transactions from historical transaction data of the customers in the customer subset, wherein two transactions which are successively and continuously completed by the same customer in the operation process of a bank self-service terminal are determined as associated transactions, and the two transactions which have completed at least 1 other transaction before the two transactions are determined as associated transactions;
according to historical transaction data of the customers in the customer subset, counting the pre-transactions completed before each group of associated transactions to obtain multiple groups of pre-transactions, and determining each group of pre-transactions as a generation condition of the group of associated transactions, wherein the pre-transactions comprise the first 1 transaction, the first 2 transactions and the first N transactions of the associated transactions, and N is the number of all transactions generated before the associated transactions;
for each group of associated transactions and each group of occurrence conditions of the group of associated transactions, counting a first historical transaction quantity of transactions in the occurrence conditions and prior transactions in the associated transactions and a second historical transaction quantity of two transactions in the occurrence conditions and the associated transactions in the historical transaction data, and determining the ratio of the second historical transaction quantity to the first historical transaction quantity as the occurrence probability of the group of occurrence conditions;
and determining all the associated transactions, the occurrence conditions of each group of associated transactions and the occurrence probability corresponding to each group of occurrence conditions as the transaction graph corresponding to the customer subset.
In an implementation manner of the embodiment of the present invention, the apparatus further includes:
the rejecting module is used for rejecting the occurrence condition of which the occurrence probability is smaller than a preset threshold value aiming at each group of associated transactions to obtain an optimal occurrence condition;
a determination module to:
and determining all the associated transactions, the preferred occurrence conditions of each group of associated transactions and the occurrence probability corresponding to each group of preferred occurrence conditions as the transaction graph corresponding to the customer subset.
In an implementation manner of the embodiment of the present invention, the apparatus further includes a prediction module, configured to:
counting various transactions completed by the client each time the client operates the mobile terminal from historical transaction data of the client aiming at each client, and arranging the various transactions according to the sequence of the execution of the client to form a transaction chain;
taking other transactions except the first transaction in the transaction chain as predicted prior transactions in the predicted related transactions, and taking the first 1, the first 2 to the first M transactions which are performed before the predicted prior transactions as occurrence conditions of the predicted online transactions, wherein M is the number of all transactions which are completed before the predicted prior transactions in the transaction chain;
reading all subsequent transactions and occurrence probabilities which occur after the same predicted occurrence condition and the same predicted prior transaction from the transaction graph as predicted subsequent transactions and predicted occurrence probabilities aiming at each predicted occurrence condition;
the device still includes:
and the communication module is used for issuing the incidence relation among the predicted prior transaction, the predicted subsequent transaction, the predicted occurrence condition and the corresponding predicted occurrence probability of the customer to the bank self-service terminal operated by the customer, so that the bank self-service terminal can predict the alternative transaction possibly completed by the customer after the current transaction according to the incidence relation, and display the transaction option card of the alternative transaction after the customer completes the current transaction.
In an implementation manner of the embodiment of the present invention, the prediction module is further configured to:
when an unpredicted success message sent by a bank self-service terminal is received, determining a target transaction graph corresponding to a customer subset where a customer is located; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction, displaying a transaction option card of an alternative transaction in the bank self-service terminal; and when the predicted prior transaction in the association does not contain the current transaction in progress of the customer, the bank self-service terminal sends an unpredicted success message.
In an implementation manner of the embodiment of the present invention, the apparatus further includes:
the acquisition module is used for acquiring appointed historical transaction data of the client from other areas outside the appointed area, determining a client subset to which the client belongs according to the appointed historical transaction data, and determining a transaction graph of the client subset of the client as a target transaction graph;
the determining module is further used for predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph when the current transaction is not the first transaction performed by the client in the current operation; and after the customer completes the current transaction, the display module displays the transaction option cards of the alternative transactions in the bank self-service terminal.
In the embodiment of the invention, considering that the transaction behaviors of customers in a certain area have certain similarity, historical transaction data of bank customers in a specified area are obtained, and then the customers are clustered according to the historical transaction data to obtain a plurality of customer subsets. During specific prediction, due to the fact that relevance exists among a plurality of transactions continuously selected by a customer, a transaction graph corresponding to each customer subset can be constructed according to historical transaction data, wherein the transaction graph comprises occurrence conditions and occurrence probability of a subsequent transaction after the former transaction is completed in the associated transactions with a sequential execution sequence relation. When receiving current transaction data operated by a customer on a bank self-service terminal, determining the current transaction in progress by the customer; determining a target transaction graph corresponding to a customer subset where the customer is; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction, the transaction option card of the alternative transaction is displayed on the bank self-service terminal, so that the customer can conveniently and quickly find the next transaction to be completed, the time of the customer is saved, and the customer experience is improved.
An embodiment of the present invention further provides a computer device, and fig. 5 is a schematic diagram of a computer device in an embodiment of the present invention, where the computer device is capable of implementing all steps in the transaction tab prediction method in the foregoing embodiment, and the computer device specifically includes the following contents:
a processor (processor)501, a memory (memory)502, a communication Interface (Communications Interface)503, and a communication bus 504;
the processor 501, the memory 502 and the communication interface 503 complete mutual communication through the communication bus 504; the communication interface 503 is used for implementing information transmission between related devices;
the processor 501 is used to call the computer program in the memory 502, and when the processor executes the computer program, the transaction tab prediction method in the above embodiment is implemented.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for predicting a transaction tab is implemented.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the method for predicting a transaction tab is implemented.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (15)
1. A transaction tab prediction method, the method comprising:
acquiring historical transaction data of bank customers in a designated area, and clustering the customers according to the historical transaction data to obtain a plurality of customer subsets;
according to the historical transaction data, constructing a transaction graph corresponding to each customer subset, wherein the transaction graph comprises occurrence conditions and occurrence probability of a subsequent transaction after the previous transaction is completed in the associated transactions with a sequential execution order relationship;
when receiving current transaction data operated by a customer on a bank self-service terminal, determining the current transaction in progress by the customer; determining a target transaction graph corresponding to a customer subset where the customer is; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; and after the customer completes the current transaction, displaying the transaction option card of the alternative transaction on the bank self-service terminal.
2. The method of claim 1, wherein for each subset of customers, constructing a transaction graph corresponding to the subset of customers according to the historical transaction data comprises:
extracting associated transactions from historical transaction data of the customers in the customer subset, wherein two transactions which are successively and continuously completed by the same customer in the operation process of a bank self-service terminal are determined as associated transactions, and the two transactions which have completed at least 1 other transaction before the two transactions are determined as associated transactions;
according to historical transaction data of the customers in the customer subset, counting the pre-transactions completed before each group of associated transactions to obtain multiple groups of pre-transactions, and determining each group of pre-transactions as a generation condition of the group of associated transactions, wherein the pre-transactions comprise the first 1 transaction, the first 2 transactions and the first N transactions of the associated transactions, and N is the number of all transactions generated before the associated transactions;
for each group of associated transactions and each group of occurrence conditions of the group of associated transactions, counting a first historical transaction quantity of transactions in the occurrence conditions and prior transactions in the associated transactions and a second historical transaction quantity of two transactions in the occurrence conditions and the associated transactions in the historical transaction data, and determining the ratio of the second historical transaction quantity to the first historical transaction quantity as the occurrence probability of the group of occurrence conditions;
and determining all the associated transactions, the occurrence conditions of each group of associated transactions and the occurrence probability corresponding to each group of occurrence conditions as the transaction graph corresponding to the customer subset.
3. The method of claim 2, wherein after determining a ratio of the second historical transaction amount to the first historical transaction amount as a probability of occurrence of the set of occurrence conditions, the method further comprises:
for each group of associated transactions, rejecting occurrence conditions with occurrence probability smaller than a preset threshold value to obtain preferred occurrence conditions;
determining all the associated transactions, the occurrence condition of each group of associated transactions and the occurrence probability corresponding to each group of occurrence conditions as a transaction graph corresponding to the customer subset, wherein the steps of:
and determining all the associated transactions, the preferred occurrence conditions of each group of associated transactions and the occurrence probability corresponding to each group of preferred occurrence conditions as the transaction graph corresponding to the customer subset.
4. The method according to any one of claims 1 to 3, wherein the target trading map corresponding to the subset of customers where the customer is located is determined; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction and before the transaction tab of the alternative transaction is displayed in the bank self-service terminal, the method further comprises the following steps:
counting various transactions completed by the client each time the client operates the mobile terminal from historical transaction data of the client aiming at each client, and arranging the various transactions according to the sequence of the execution of the client to form a transaction chain;
taking other transactions except the first transaction in the transaction chain as predicted prior transactions in the predicted related transactions, and taking the first 1, the first 2 to the first M transactions which are performed before the predicted prior transactions as occurrence conditions of the predicted online transactions, wherein M is the number of all transactions which are completed before the predicted prior transactions in the transaction chain;
for each predicted occurrence condition, reading all subsequent transactions and occurrence probabilities which occur after the same predicted occurrence condition and the same predicted prior transaction from the transaction graph as predicted subsequent transactions and predicted occurrence probabilities;
after receiving current transaction data operated by the customer on the bank self-service terminal, the method further comprises the following steps:
and issuing the incidence relation among the predicted prior transaction, the predicted subsequent transaction, the predicted occurrence condition and the corresponding predicted occurrence probability of the customer to the bank self-service terminal operated by the customer, so that the bank self-service terminal can predict the alternative transaction which is possibly completed by the customer after the current transaction according to the incidence relation, and displaying the transaction option card of the alternative transaction after the customer completes the current transaction.
5. The method of claim 4, further comprising:
when an unpredicted success message sent by a bank self-service terminal is received, determining a target transaction graph corresponding to a customer subset where a customer is located; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction, displaying a transaction option card of the alternative transaction in the bank self-service terminal; and when the predicted prior transaction in the incidence relation does not contain the current transaction in progress of the customer, the bank self-service terminal sends an unpredicted success message.
6. The method of claim 1, wherein when the current transaction data of the customer operating on the bank self-service terminal is received and the customer is not found in all the customer subsets, the method further comprises:
acquiring appointed historical transaction data of the client from other areas outside the appointed area, determining a client subset to which the client belongs according to the appointed historical transaction data, and determining a transaction graph of the client subset of the client as a target transaction graph;
if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; and when the customer completes the current transaction, displaying the transaction option card of the alternative transaction in the bank self-service terminal.
7. A transaction tab prediction apparatus, the apparatus comprising:
the clustering module is used for acquiring historical transaction data of bank customers in a designated area, and clustering the customers according to the historical transaction data to obtain a plurality of customer subsets;
the construction module is used for constructing a transaction graph corresponding to each customer subset according to the historical transaction data, wherein the transaction graph comprises the occurrence conditions and the occurrence probability of the next transaction after the previous transaction is completed in the associated transactions with the sequential execution order relationship;
the system comprises a determining module, a processing module and a processing module, wherein the determining module is used for determining the current transaction of a customer when receiving the current transaction data operated by the customer on a bank self-service terminal; determining a target transaction graph corresponding to a customer subset where the customer is; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; and after the customer completes the current transaction, the display module displays the transaction option card of the alternative transaction on the bank self-service terminal.
8. The apparatus of claim 7, wherein the means for constructing is configured to:
extracting associated transactions from historical transaction data of the customers in the customer subset, wherein two transactions which are successively and continuously completed by the same customer in the operation process of a bank self-service terminal are determined as associated transactions, and the two transactions which have completed at least 1 other transaction before the two transactions are determined as associated transactions;
according to historical transaction data of the customers in the customer subset, counting the pre-transactions completed before each group of associated transactions to obtain multiple groups of pre-transactions, and determining each group of pre-transactions as a generation condition of the group of associated transactions, wherein the pre-transactions comprise the first 1 transaction, the first 2 transactions and the first N transactions of the associated transactions, and N is the number of all transactions generated before the associated transactions;
for each group of associated transactions and each group of occurrence conditions of the group of associated transactions, counting a first historical transaction quantity of transactions in the continuously executed occurrence conditions and prior transactions in the associated transactions and a second historical transaction quantity of transactions in the continuously executed occurrence conditions and two transactions in the associated transactions in the historical transaction data, and determining the ratio of the second historical transaction quantity to the first historical transaction quantity as the occurrence probability of the group of occurrence conditions;
and determining all the associated transactions, the occurrence conditions of each group of associated transactions and the occurrence probability corresponding to each group of occurrence conditions as the transaction graph corresponding to the customer subset.
9. The apparatus of claim 8, further comprising:
the rejecting module is used for rejecting the occurrence condition of which the occurrence probability is smaller than a preset threshold value aiming at each group of associated transactions to obtain an optimal occurrence condition;
a determination module to:
and determining all the associated transactions, the preferred occurrence conditions of each group of associated transactions and the occurrence probability corresponding to each group of preferred occurrence conditions as the transaction graph corresponding to the customer subset.
10. The apparatus of any one of claims 7 to 9, further comprising a prediction module configured to:
counting various transactions completed by the client each time the client operates the mobile terminal from historical transaction data of the client aiming at each client, and arranging the various transactions according to the sequence of the execution of the client to form a transaction chain;
taking other transactions except the first transaction in the transaction chain as predicted prior transactions in the predicted related transactions, and taking the first 1, the first 2 to the first M transactions which are performed before the predicted prior transactions as occurrence conditions of the predicted online transactions, wherein M is the number of all transactions which are completed before the predicted prior transactions in the transaction chain;
reading all subsequent transactions and occurrence probabilities which occur after the same predicted occurrence condition and the same predicted prior transaction from the transaction graph as predicted subsequent transactions and predicted occurrence probabilities aiming at each predicted occurrence condition;
the device further comprises:
and the communication module is used for issuing the incidence relation among the predicted prior transaction, the predicted subsequent transaction, the predicted occurrence condition and the corresponding predicted occurrence probability of the customer to the bank self-service terminal operated by the customer, so that the bank self-service terminal can predict the alternative transaction which is possibly completed by the customer after the current transaction according to the incidence relation, and display the transaction option card of the alternative transaction after the customer completes the current transaction.
11. The apparatus of claim 10, wherein the prediction module is further configured to:
when an unpredicted success message sent by a bank self-service terminal is received, determining a target transaction graph corresponding to a customer subset where a customer is located; if the current transaction is not the first transaction performed by the client in the current operation, predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph; after the customer completes the current transaction, displaying a transaction option card of the alternative transaction in the bank self-service terminal; and when the predicted prior transaction in the incidence relation does not contain the current transaction in progress of the customer, the bank self-service terminal sends an unpredicted success message.
12. The apparatus of claim 7, further comprising:
the acquisition module is used for acquiring appointed historical transaction data of the client from other areas outside the appointed area, determining a client subset to which the client belongs according to the appointed historical transaction data, and determining a transaction graph of the client subset of the client as a target transaction graph;
the determining module is also used for predicting alternative transactions which are possibly completed by the client after the current transaction according to the transaction completed before the current transaction in the current operation, the current transaction and the target transaction graph when the current transaction is not the first transaction performed by the client in the current operation; and after the customer completes the current transaction, the display module displays the transaction option cards of the alternative transactions in the bank self-service terminal.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 6 when executing the computer program.
14. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 6.
15. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210586557.2A CN114971021A (en) | 2022-05-27 | 2022-05-27 | Transaction tab prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210586557.2A CN114971021A (en) | 2022-05-27 | 2022-05-27 | Transaction tab prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114971021A true CN114971021A (en) | 2022-08-30 |
Family
ID=82955421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210586557.2A Pending CN114971021A (en) | 2022-05-27 | 2022-05-27 | Transaction tab prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114971021A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210900A (en) * | 2019-05-23 | 2019-09-06 | 中国银行股份有限公司 | Method, apparatus and equipment are determined based on the reference product of transaction association |
| CN111158837A (en) * | 2019-12-31 | 2020-05-15 | 中国银行股份有限公司 | Bank software function interface generation method and device |
| US20200211065A1 (en) * | 2018-12-28 | 2020-07-02 | Paypal, Inc. | Intelligent interface displays based on past data correlations |
| CN112258260A (en) * | 2020-08-14 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Page display method, device, medium and electronic equipment based on user characteristics |
| CN113177671A (en) * | 2021-05-27 | 2021-07-27 | 中国银行股份有限公司 | Data processing method, device and equipment and readable storage medium |
-
2022
- 2022-05-27 CN CN202210586557.2A patent/CN114971021A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200211065A1 (en) * | 2018-12-28 | 2020-07-02 | Paypal, Inc. | Intelligent interface displays based on past data correlations |
| CN110210900A (en) * | 2019-05-23 | 2019-09-06 | 中国银行股份有限公司 | Method, apparatus and equipment are determined based on the reference product of transaction association |
| CN111158837A (en) * | 2019-12-31 | 2020-05-15 | 中国银行股份有限公司 | Bank software function interface generation method and device |
| CN112258260A (en) * | 2020-08-14 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Page display method, device, medium and electronic equipment based on user characteristics |
| CN113177671A (en) * | 2021-05-27 | 2021-07-27 | 中国银行股份有限公司 | Data processing method, device and equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106156092B (en) | Data processing method and device | |
| CN109389321B (en) | Item list classification method and device | |
| CN107203866A (en) | The processing method and device of order | |
| CN112463859B (en) | User data processing method and server based on big data and business analysis | |
| CN112765230B (en) | Payment big data analysis method and big data analysis system based on internet finance | |
| CN111160329A (en) | Root cause analysis method and device | |
| CN112200644B (en) | Method and device for identifying fraudulent user, computer equipment and storage medium | |
| CN111311276B (en) | Identification method and device for abnormal user group and readable storage medium | |
| CN110991241B (en) | Abnormality recognition method, apparatus, and computer-readable medium | |
| CN112529319A (en) | Grading method and device based on multi-dimensional features, computer equipment and storage medium | |
| CN116610821A (en) | Knowledge graph-based enterprise risk analysis method, system and storage medium | |
| CN114971021A (en) | Transaction tab prediction method and device | |
| CN115965468A (en) | Transaction data-based abnormal behavior detection method, device, equipment and medium | |
| CN115527610A (en) | Cluster analysis method of unicellular omics data | |
| CN113177671A (en) | Data processing method, device and equipment and readable storage medium | |
| CN110111131A (en) | The determination method and device of false visitor's standing breath | |
| Yeh et al. | Predicting failure of P2P lending platforms through machine learning: The case in China | |
| CN112396513B (en) | Data processing method and device | |
| CN114942877A (en) | Method and device for determining user interface of bank system | |
| CN114881764A (en) | Transaction interface display method and device | |
| CN117974276A (en) | Commodity recommendation model training method, commodity recommendation method and electronic equipment | |
| CN116881333A (en) | Method and device for mining potential guests, electronic equipment and readable storage medium | |
| CN116012011A (en) | Method, device, terminal equipment and storage medium for anti-fraud of group partner transaction based on high-density subgraph mining | |
| CN116739752A (en) | Message reminding method and device, electronic equipment and storage medium | |
| CN114881699A (en) | Bank product delivery processing method and device based on regional 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 |