Method and device for evaluating transaction interface of self-service terminal

Abstract

The present invention proposes a transaction interface evaluation method and device for a self-service terminal, which relates to the technical field of computer data processing. The method comprises: classifying the bank's self-service terminals based on customer data and transaction data of the bank's self-service terminals to obtain multiple terminal categories; for each terminal category, determining the interval time corresponding to the transaction interface of the terminal category based on the transaction data of each transaction interface corresponding to the terminal category; determining the prediction accuracy of the transaction interface corresponding to the terminal category based on the interface recommendation data corresponding to the transaction interface of the terminal category; determining the partial order of the transaction interfaces corresponding to the terminal category based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface of any two transaction interfaces is better than the second transaction interface; and determining the preferred transaction interface of each self-service terminal of the terminal category based on the partial order of the transaction interfaces corresponding to the terminal category.

Description

Technical Field

[0001] The present invention relates to the technical field of computer data processing, and in particular to a transaction interface evaluation method and device for a self-service terminal. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Currently, banks have launched a variety of transaction interfaces for self-service terminals to facilitate customers' operations at the self-service terminals. However, no relevant evaluation method has been proposed in the prior art to evaluate the actual effects of these new transaction interfaces.

[0004] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects and evaluate the transaction interface of the self-service terminal. Summary of the Invention

[0005] In order to solve the problems existing in the prior art, the present invention proposes a transaction interface evaluation method and device for a self-service terminal.

[0006] In a first aspect of an embodiment of the present invention, a method for evaluating a transaction interface of a self-service terminal is provided, comprising:

[0007] Based on the customer data and transaction data of the bank's self-service terminals, the bank's self-service terminals are classified to obtain multiple terminal categories;

[0008] For each terminal category, based on the transaction data of each transaction interface corresponding to the terminal category, the interval time corresponding to the transaction interface of the terminal category is determined; based on the interface recommendation data corresponding to the transaction interface of the terminal category, the prediction accuracy rate of the transaction interface corresponding to the terminal category is determined;

[0009] Determining a partial order of the transaction interfaces corresponding to the terminal category based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface is superior to the second transaction interface among any two transaction interfaces;

[0010] According to the partial order of the transaction interfaces corresponding to the terminal category, the preferred transaction interface of each self-service terminal of the terminal category is determined.

[0011] In a second aspect of an embodiment of the present invention, a transaction interface evaluation device for a self-service terminal is provided, comprising:

[0012] A self-service terminal classification module is used to classify the bank's self-service terminals based on their customer data and transaction data to obtain multiple terminal categories;

[0013] A data processing module is configured to determine, for each terminal category, based on the transaction data of each transaction interface corresponding to the terminal category, the interval time for the transaction interface corresponding to the terminal category; and to determine, based on the interface recommendation data corresponding to the transaction interface, the prediction accuracy rate for the transaction interface corresponding to the terminal category;

[0014] a partial order determination module, configured to determine a partial order of the transaction interfaces corresponding to the terminal category based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface is superior to the second transaction interface among any two transaction interfaces;

[0015] The transaction interface evaluation module is used to determine the preferred transaction interface of each self-service terminal of the terminal category according to the partial order of the transaction interfaces corresponding to the terminal category.

[0016] 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 transaction interface evaluation method for a self-service terminal when executing the computer program.

[0017] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, a transaction interface evaluation method for a self-service terminal is implemented.

[0018] 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 transaction interface evaluation method for a self-service terminal is implemented.

[0019] The transaction interface evaluation method and device of the self-service terminal proposed in the present invention classify the bank's self-service terminals based on the customer data and transaction data of the bank's self-service terminals to obtain multiple terminal categories; for each terminal category, the interval time of the terminal category corresponding to the transaction interface is determined based on the transaction data of each transaction interface corresponding to the terminal category; the prediction accuracy of the terminal category corresponding to the transaction interface is determined based on the interface recommendation data of the terminal category corresponding to the transaction interface; the partial order of the transaction interfaces corresponding to the terminal category is determined based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface is better than the second transaction interface in any two transaction interfaces; the preferred transaction interface of each self-service terminal of the terminal category is determined based on the partial order of the transaction interfaces corresponding to the terminal category. The overall solution can analyze and evaluate the transaction interface of the self-service terminal, so as to determine the transaction interface with better effect, so as to improve the customer experience when using the self-service terminal and provide strong technical support for improving the operating efficiency of the bank. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. 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 any creative work.

[0021] Figure 1 The figure is a flow chart of a transaction interface evaluation method for a self-service terminal according to an embodiment of the present invention.

[0022] Figure 2 The figure is a flow chart of classifying bank self-service terminals according to an embodiment of the present invention.

[0023] Figure 3 The figure is a flowchart of determining the interval time of the transaction interface corresponding to the terminal category according to an embodiment of the present invention.

[0024] Figure 4 It is a flowchart of determining the prediction accuracy of the transaction interface corresponding to the terminal category according to an embodiment of the present invention.

[0025] Figure 5 This is a schematic diagram of a process for determining a preferred transaction interface for each self-service terminal of a terminal type according to an embodiment of the present invention.

[0026] Figure 6 2 is a schematic diagram of the architecture of a transaction interface evaluation device for a self-service terminal according to an embodiment of the present invention.

[0027] Figure 7 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] 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 solely 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. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0029] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0030] According to an embodiment of the present invention, a method and device for evaluating a transaction interface of a self-service terminal are proposed, which relate to the technical field of computer data processing.

[0031] The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0032] Figure 1 FIG. 1 is a flow chart of a transaction interface evaluation method for a self-service terminal according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0033] S1, classifying the bank's self-service terminals based on customer data and transaction data of the bank's self-service terminals to obtain multiple terminal categories;

[0034] S2, for each terminal category, based on the transaction data of each transaction interface corresponding to the terminal category, determining the interval time corresponding to the transaction interface for the terminal category; based on the interface recommendation data corresponding to the transaction interface for the terminal category, determining the prediction accuracy rate for the transaction interface for the terminal category;

[0035] S3, determining a partial order of the transaction interfaces corresponding to the terminal category based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether a first transaction interface is superior to a second transaction interface among any two transaction interfaces;

[0036] S4: Determine the preferred transaction interface for each self-service terminal of the terminal category according to the partial order of the transaction interfaces corresponding to the terminal category.

[0037] In order to explain the transaction interface evaluation method of the self-service terminal more clearly, each step is described in detail below.

[0038] In S1, ref. Figure 2 ,Based on the customer data and transaction data of the bank's self-service terminals, the bank's self-service terminals are classified to obtain multiple terminal categories, including:

[0039] S11, constructing a customer space and a business space, wherein the dimensions of the customer space correspond one-to-one with the customer categories, and the dimensions of the business space correspond one-to-one with the business categories;

[0040] S12. For each self-service terminal of the bank, determine the coordinates of the self-service terminal in the customer space and the business space based on the customer data and business data of the self-service terminal; wherein the coordinate value of each dimension of the self-service terminal in the customer space is equal to the number of customers corresponding to the customer category corresponding to the dimension among the customers included in the customer data of the self-service terminal, and the coordinate value of each dimension of the self-service terminal in the business space is equal to the number of services corresponding to the business category corresponding to the dimension among the services included in the business data of the self-service terminal;

[0041] S13, determining the customer distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the customer space, and determining the business distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the business space;

[0042] S14, classifying the bank's self-service terminals according to the customer distances corresponding to the self-service terminals and the business distances corresponding to the self-service terminals to obtain a plurality of terminal categories.

[0043] In one embodiment, (S14) the bank's self-service terminals are classified according to the customer distance corresponding to the self-service terminals and the business distance corresponding to the self-service terminals to obtain multiple terminal categories, including:

[0044] S141, clustering the bank's self-service terminals based on the customer distances corresponding to the self-service terminals to obtain multiple terminal categories;

[0045] S142: For each terminal category obtained, determine the most important customer category corresponding to each self-service terminal in the terminal category; for each customer category, use the proportion of all self-service terminals in the terminal category whose most important customer category is the customer category as the proportion of the terminal category corresponding to the customer category;

[0046] S143, determining whether each terminal category satisfies condition t: the maximum value of the proportion of the terminal category corresponding to each customer category is greater than a set proportion threshold;

[0047] S144: If there is a terminal category that does not meet condition t, the following steps are executed in a loop until all terminal categories meet condition t:

[0048] Select a terminal category that does not meet condition t;

[0049] Clustering all self-service terminals of the selected terminal category according to the service distance corresponding to the self-service terminal, and replacing the terminal category with multiple new terminal categories obtained;

[0050] For each new terminal category, determine the most important customer category corresponding to each self-service terminal in the new terminal category; for each customer category, the proportion of all self-service terminals in the new terminal category whose most important customer category is the customer category in the new terminal category is used as the proportion of the new terminal category corresponding to the customer category.

[0051] In S2, reference Figure 3 , based on the transaction data of each transaction interface corresponding to the terminal category, determine the interval time of the transaction interface corresponding to the terminal category, including:

[0052] S211, for each transaction interface, determining a plurality of interval time samples corresponding to each transaction category of the transaction interface based on the transaction data of the terminal category corresponding to the transaction interface;

[0053] S212: Determine the interval time of the terminal category corresponding to the transaction interface based on a plurality of interval time samples of the transaction interface corresponding to each transaction category.

[0054] In one embodiment, the primary transaction category of the terminal category is determined as follows:

[0055] S001, determining the transaction volume of each transaction category of the terminal category based on the transaction data of each transaction category of the terminal category;

[0056] S002, sorting the transaction categories of the terminal category according to the transaction volume;

[0057] S003, determining the ratio of the sum of the transaction volumes of the top N transaction categories in the ranking to the sum of the transaction volumes of all transaction categories of the terminal category;

[0058] S004, if the ratio is greater than the set ratio threshold, the top N transaction categories in the ranking are used as the main transaction categories of the terminal category;

[0059] Furthermore, (S22) determining the interval time corresponding to the transaction interface for the terminal category based on the plurality of interval time samples corresponding to each transaction category of the transaction interface includes:

[0060] The interval time corresponding to the transaction interface of the terminal category is determined based on a plurality of interval time samples of each main transaction category of the terminal category corresponding to the transaction interface.

[0061] In S2, reference Figure 4 , based on the interface recommendation data of the terminal category corresponding to the transaction interface, determining the prediction accuracy of the terminal category corresponding to the transaction interface, including:

[0062] S221, dividing the interface recommendation data corresponding to each transaction interface of the terminal category into a plurality of interface recommendation data subsets corresponding to the transaction interface of the terminal category;

[0063] S222, taking the proportion of the recommended data for each transaction interface selected by the customer in the recommended data subset corresponding to the transaction interface for the terminal category as the predicted accurate sample for the transaction interface for the terminal category;

[0064] S223 , determining the prediction accuracy rate of the terminal category corresponding to the transaction interface as the average of the accurate prediction samples of the terminal category corresponding to the transaction interface.

[0065] In S3, based on the waiting time and prediction accuracy, the partial order of the transaction interface corresponding to the terminal category is determined, including:

[0066] For any two transaction interfaces, if the interval time for the terminal category corresponding to the first of the two transaction interfaces is less than or equal to the interval time for the terminal category corresponding to the second of the two transaction interfaces, and the prediction accuracy rate for the terminal category corresponding to the first transaction interface is greater than or equal to the prediction accuracy rate for the terminal category corresponding to the second transaction interface, then the partial order determines that the first transaction interface is better than the second transaction interface.

[0067] In S4, ref. Figure 5 , according to the partial order of the transaction interfaces corresponding to the terminal category, determining the preferred transaction interface of each self-service terminal of the terminal category, including:

[0068] S41, determining a potential preferred transaction interface for the terminal category based on the partial order of the transaction interfaces corresponding to the terminal category;

[0069] For example, the maximum element of the partial order of the transaction interface corresponding to the terminal category is used as the potential preferred transaction interface of the terminal category.

[0070] S42 , determining the preferred transaction interface of each self-service terminal of the terminal category according to the interval time and prediction accuracy of each potential preferred transaction interface of the terminal category corresponding to the terminal category.

[0071] In one embodiment, the maximum element of the partial order of the transaction interfaces corresponding to the terminal category is selected as the potential preferred transaction interface for the terminal category, including:

[0072] Initialize the pending transaction interface and the comparison transaction interface to all transaction interfaces;

[0073] Repeat the following three steps until the pending transaction interface is empty:

[0074] Select the transaction interface A with the highest prediction accuracy from the pending transaction interfaces, and compare the transaction interface A with each transaction interface B in the comparison transaction interfaces except for the transaction interface A based on the partial order of the transaction interfaces corresponding to the terminal category;

[0075] If trading interface B is better than trading interface A, trading interface A will be deleted from the pending trading interface list; if trading interface A is better than trading interface B, trading interface B will be deleted from the pending trading interface list and trading interface B will be made the secondary trading interface of trading interface A.

[0076] If it is confirmed that each transaction interface except transaction interface A in the comparison transaction interface is not superior to transaction interface A based on the partial order of the transaction interfaces corresponding to the terminal category, then transaction interface A will be regarded as the potential preferred transaction interface for the terminal category, and all secondary transaction interfaces of transaction interface A will be deleted from the comparison transaction interfaces.

[0077] In one embodiment, (S41) determining a potential preferred transaction interface for the terminal category based on the partial order of the transaction interfaces corresponding to the terminal category includes:

[0078] S411, determining the upper bound of the prediction error for each transaction interface corresponding to the terminal category as the ratio of the square of the variance of the accurate prediction samples for the terminal category corresponding to the transaction interface to the number of accurate prediction samples for the terminal category corresponding to the transaction interface;

[0079] S412, for each transaction interface, if the upper bound of the prediction error for each transaction interface corresponding to the terminal category is less than the set error threshold, then the transaction interface is selected as an optional transaction interface;

[0080] S413, a set consisting of all optional transaction interfaces is used as an optional transaction interface set;

[0081] S414: The maximum element of the set of optional transaction interfaces corresponding to the partial order of the transaction interfaces corresponding to the terminal category is used as the potential preferred transaction interface for the terminal category.

[0082] In one embodiment, (S414) determining the maximum element of the set of optional transaction interfaces corresponding to the partial order of the transaction interfaces corresponding to the terminal category as the potential preferred transaction interface for the terminal category includes:

[0083] S414-1, initializing the pending transaction interface and the comparison transaction interface as a set of optional transaction interfaces;

[0084] S414-2, loop through the following three steps until the pending transaction interface is empty:

[0085] Select the transaction interface S with the smallest corresponding interval from the pending transaction interfaces, and compare the transaction interface S with each transaction interface T in the comparison transaction interfaces except for the transaction interface S according to the partial order of the transaction interfaces corresponding to the terminal category;

[0086] If transaction interface T is better than transaction interface S, then transaction interface S is deleted from the pending transaction interface list; if transaction interface S is better than transaction interface T, then transaction interface T is deleted from the pending transaction interface list and transaction interface T is made the secondary transaction interface of transaction interface S;

[0087] If it is confirmed that each transaction interface except the transaction interface S in the comparison transaction interface is not superior to the transaction interface S based on the partial order of the transaction interfaces corresponding to the terminal category, then the transaction interface S will be regarded as the potential preferred transaction interface for the terminal category, and all secondary transaction interfaces of the transaction interface S will be deleted from the comparison transaction interfaces.

[0088] In one embodiment, (S42) determining the preferred transaction interface for each self-service terminal of the terminal category based on the interval time and prediction accuracy of each potential preferred transaction interface for the terminal category includes:

[0089] S421, sorting the potential preferred transaction interfaces of the terminal category;

[0090] S422: Determine the priority left endpoint of each potential preferred transaction interface of the terminal category.

[0091] Specifically, the priority left endpoint of each potential preferred transaction interface of the terminal category is determined according to the following formula:

[0092]

[0093] Among them, l i is the preferred left endpoint of the ith potential preferred trading interface of the terminal category, r k and r j are the intervals between the kth and jth potential preferred trading interfaces of the terminal category, s k and s j are the prediction accuracy of the kth and jth potential preferred trading interfaces of the terminal category, respectively. f>0 is a real-valued function whose partial derivative with respect to the first independent variable is less than 0 and whose partial derivative with respect to the second independent variable is greater than 0.

[0094] S423, selecting a random number generator, wherein the generator conforms to a uniform distribution with a range of [0, 1];

[0095] S424, for each self-service terminal of the terminal category, generate a random number according to the selected random number generator, and use the random number as the random number corresponding to the self-service terminal;

[0096] S425, selecting the maximum priority left endpoint that is smaller than the random number corresponding to the self-service terminal from the priority left endpoints of each potential preferred transaction interface of the terminal category;

[0097] S426: Use the potential preferred transaction interface corresponding to the maximum priority left endpoint as the preferred transaction interface of the self-service terminal.

[0098] 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 drawings, this does not require or imply that these operations must be performed in this specific order, or that all illustrated operations must be performed to achieve the desired results. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0099] After introducing the method of the exemplary embodiment of the present invention, next, reference is made to Figure 6 A transaction interface evaluation device for a self-service terminal according to an exemplary embodiment of the present invention is introduced.

[0100] The implementation of the transaction interface evaluation device for the self-service terminal can be referenced to the implementation of the above-mentioned method, and any repetitions will not be repeated here. The terms "module" or "unit" used below may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0101] Based on the same inventive concept, the present invention also proposes a transaction interface evaluation device for a self-service terminal, such as Figure 6 As shown, the device includes:

[0102] The self-service terminal classification module 610 is used to classify the bank's self-service terminals based on the customer data and transaction data of the bank's self-service terminals to obtain multiple terminal categories;

[0103] The data processing module 620 is configured to determine, for each terminal category, the interval time for each transaction interface corresponding to the terminal category based on the transaction data corresponding to the transaction interface; and determine the prediction accuracy rate for the transaction interface corresponding to the terminal category based on the interface recommendation data corresponding to the transaction interface;

[0104] A partial order determination module 630 is configured to determine a partial order of the transaction interfaces corresponding to the terminal category based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface is superior to the second transaction interface among any two transaction interfaces;

[0105] The transaction interface evaluation module 640 is configured to determine the preferred transaction interface for each self-service terminal of the terminal category according to the partial order of the transaction interfaces corresponding to the terminal category.

[0106] In one embodiment, the self-service terminal classification module is specifically used to:

[0107] Build customer space and business space, where the dimensions of the customer space correspond one-to-one with customer categories, and the dimensions of the business space correspond one-to-one with business categories;

[0108] For each self-service terminal of the bank, the coordinates of the self-service terminal in the customer space and the business space are determined based on the customer data and business data of the self-service terminal; wherein the coordinate value of each dimension of the self-service terminal in the customer space is equal to the number of customers corresponding to the customer category corresponding to the dimension among the customers included in the customer data of the self-service terminal, and the coordinate value of each dimension of the self-service terminal in the business space is equal to the number of services corresponding to the business category corresponding to the dimension among the services included in the business data of the self-service terminal;

[0109] Determine the customer distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the customer space, and determine the business distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the business space;

[0110] The bank's self-service terminals are classified according to the customer distance corresponding to the self-service terminals and the business distance corresponding to the self-service terminals to obtain multiple terminal categories.

[0111] In one embodiment, the self-service terminal classification module is specifically used to:

[0112] Cluster the bank's self-service terminals based on their corresponding customer distances to obtain multiple terminal categories.

[0113] For each terminal category obtained, determine the most important customer category corresponding to each self-service terminal in the terminal category; for each customer category, use the proportion of all self-service terminals in the terminal category whose most important customer category is the customer category as the proportion of the terminal category corresponding to the customer category;

[0114] Determine whether each terminal category meets condition t: the maximum value of the proportion of each customer category corresponding to the terminal category is greater than a set proportion threshold;

[0115] If there is a terminal category that does not meet condition t, the following steps are executed repeatedly until all terminal categories meet condition t:

[0116] Select a terminal category that does not meet condition t;

[0117] Clustering all self-service terminals of the selected terminal category according to the service distance corresponding to the self-service terminal, and replacing the terminal category with multiple new terminal categories obtained;

[0118] For each new terminal category, determine the most important customer category corresponding to each self-service terminal in the new terminal category; for each customer category, the proportion of all self-service terminals in the new terminal category whose most important customer category is the customer category in the new terminal category is used as the proportion of the new terminal category corresponding to the customer category.

[0119] In one embodiment, the data processing module is specifically configured to:

[0120] For each transaction interface, based on the transaction data of the terminal category corresponding to the transaction interface, multiple interval time samples corresponding to each transaction category of the transaction interface are determined;

[0121] The interval time corresponding to the transaction interface of the terminal category is determined based on a plurality of interval time samples corresponding to each transaction category of the transaction interface.

[0122] In one embodiment, the data processing module is specifically configured to:

[0123] Dividing the interface recommendation data corresponding to each transaction interface of the terminal category into multiple interface recommendation data subsets corresponding to the transaction interface of the terminal category;

[0124] The proportion of the recommended data of each interface recommendation data subset corresponding to the transaction interface of the terminal category in which the customer selects the corresponding transaction interface is used as the predicted accurate sample of the transaction interface corresponding to the terminal category;

[0125] The prediction accuracy rate of the terminal category corresponding to the transaction interface is determined as the average of the accurate prediction samples of the terminal category corresponding to the transaction interface.

[0126] In one embodiment, the partial order determination module is specifically configured to:

[0127] For any two transaction interfaces, if the interval time for the terminal category corresponding to the first of the two transaction interfaces is less than or equal to the interval time for the terminal category corresponding to the second of the two transaction interfaces, and the prediction accuracy rate for the terminal category corresponding to the first transaction interface is greater than or equal to the prediction accuracy rate for the terminal category corresponding to the second transaction interface, then the partial order determines that the first transaction interface is better than the second transaction interface.

[0128] In one embodiment, the transaction interface evaluation module is specifically used to:

[0129] Determine the potential preferred trading interface for the terminal category based on the partial order of the trading interfaces corresponding to the terminal category;

[0130] The preferred transaction interface of each self-service terminal of the terminal category is determined according to the interval time and prediction accuracy of each potential preferred transaction interface of the terminal category corresponding to the terminal category.

[0131] In one embodiment, the transaction interface evaluation module is specifically used to:

[0132] The upper bound of the prediction error for each transaction interface corresponding to the terminal category is determined as the ratio of the square of the variance of the accurate prediction samples for the terminal category corresponding to the transaction interface to the number of accurate prediction samples for the terminal category corresponding to the transaction interface;

[0133] For each trading interface, if the upper bound of the prediction error for each trading interface of the terminal category is less than the set error threshold, the trading interface will be selected as an optional trading interface;

[0134] The set of all optional trading interfaces is defined as the optional trading interface set;

[0135] The maximum element of the set of optional trading interfaces corresponding to the partial order of the trading interfaces of the terminal category is used as the potential preferred trading interface of the terminal category.

[0136] It should be noted that while the above detailed description mentions several modules of the transaction interface evaluation device for a self-service terminal, this division is merely exemplary and not mandatory. In practice, according to embodiments of the present invention, the features and functions of two or more modules described above may be embodied in a single module. Conversely, the features and functions of a single module described above may be further divided and embodied by multiple modules.

[0137] Based on the above invention concept, Figure 7 As shown, the present invention also proposes a computer device 700, including a memory 710, a processor 720 and a computer program 730 stored in the memory 710 and executable on the processor 720, wherein the processor 720 implements the aforementioned transaction interface evaluation method of the self-service terminal when executing the computer program 730.

[0138] 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 transaction interface evaluation method of the self-service terminal is implemented.

[0139] 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 transaction interface evaluation method for a self-service terminal is implemented.

[0140] The transaction interface evaluation method and device of the self-service terminal proposed in the present invention classify the bank's self-service terminals based on the customer data and transaction data of the bank's self-service terminals to obtain multiple terminal categories; for each terminal category, the interval time of the terminal category corresponding to the transaction interface is determined based on the transaction data of each transaction interface corresponding to the terminal category; the prediction accuracy of the terminal category corresponding to the transaction interface is determined based on the interface recommendation data of the terminal category corresponding to the transaction interface; the partial order of the transaction interfaces corresponding to the terminal category is determined based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface is better than the second transaction interface in any two transaction interfaces; the preferred transaction interface of each self-service terminal of the terminal category is determined based on the partial order of the transaction interfaces corresponding to the terminal category. The overall solution can analyze and evaluate the transaction interface of the self-service terminal, so as to determine the transaction interface with better effect, so as to improve the customer experience when using the self-service terminal and provide strong technical support for improving the operating efficiency of the bank.

[0141] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0142] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, 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 implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. 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.

[0144] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 1a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0146] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for evaluating a transaction interface of a self-service terminal, characterized in that: include: Based on the customer data and transaction data of the bank's self-service terminals, the bank's self-service terminals are classified to obtain multiple terminal categories; For each terminal category, based on the transaction data of each transaction interface corresponding to the terminal category, determine the interval time corresponding to the transaction interface of the terminal category; Determine the prediction accuracy of the transaction interface corresponding to the terminal category based on the interface recommendation data corresponding to the transaction interface of the terminal category; Determining a partial order of the transaction interfaces corresponding to the terminal category based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface is superior to the second transaction interface among any two transaction interfaces; Determining the preferred transaction interface for each self-service terminal of the terminal category based on the partial order of the transaction interfaces corresponding to the terminal category; The step of determining the interval time for each transaction interface corresponding to the terminal category based on the transaction data of each transaction interface corresponding to the terminal category includes: For each transaction interface, based on the transaction data of the terminal category corresponding to the transaction interface, multiple interval time samples corresponding to each transaction category of the transaction interface are determined; Determine the interval time corresponding to the transaction interface for the terminal category based on multiple interval time samples corresponding to each transaction category of the transaction interface; Determining the prediction accuracy of the transaction interface corresponding to the terminal category based on the interface recommendation data corresponding to the transaction interface of the terminal category includes: Dividing the interface recommendation data corresponding to each transaction interface of the terminal category into multiple interface recommendation data subsets corresponding to the transaction interface of the terminal category; The proportion of the recommended data of each interface recommendation data subset corresponding to the transaction interface of the terminal category in which the customer selects the corresponding transaction interface is used as the predicted accurate sample of the transaction interface corresponding to the terminal category; The prediction accuracy rate of the terminal category corresponding to the transaction interface is determined as the average of the accurate prediction samples of the terminal category corresponding to the transaction interface.

2. The method according to claim 1, wherein Based on the customer data and transaction data of the bank's self-service terminals, the bank's self-service terminals are classified into multiple terminal categories, including: Build customer space and business space, where the dimensions of the customer space correspond one-to-one with customer categories, and the dimensions of the business space correspond one-to-one with business categories; For each self-service terminal of the bank, the coordinates of the self-service terminal in the customer space and the business space are determined based on the customer data and business data of the self-service terminal; wherein the coordinate value of each dimension of the self-service terminal in the customer space is equal to the number of customers corresponding to the customer category corresponding to the dimension among the customers included in the customer data of the self-service terminal, and the coordinate value of each dimension of the self-service terminal in the business space is equal to the number of services corresponding to the business category corresponding to the dimension among the services included in the business data of the self-service terminal; Determine the customer distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the customer space, and determine the business distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the business space; The bank's self-service terminals are classified according to the customer distance corresponding to the self-service terminals and the business distance corresponding to the self-service terminals to obtain multiple terminal categories.

3. The method according to claim 2, wherein Based on the customer distance and business distance corresponding to the self-service terminals, the bank's self-service terminals are classified to obtain multiple terminal categories, including: Cluster the bank's self-service terminals based on their corresponding customer distances to obtain multiple terminal categories. For each terminal category obtained, determine the most important customer category corresponding to each self-service terminal in the terminal category; for each customer category, use the proportion of all self-service terminals in the terminal category whose most important customer category is the customer category as the proportion of the terminal category corresponding to the customer category; Determine whether each terminal category meets condition t: the maximum value of the proportion of each customer category corresponding to the terminal category is greater than a set proportion threshold; If there is a terminal category that does not meet condition t, the following steps are executed repeatedly until all terminal categories meet condition t: Select a terminal category that does not meet condition t; Clustering all self-service terminals of the selected terminal category according to the service distance corresponding to the self-service terminal, and replacing the terminal category with multiple new terminal categories obtained; For each new terminal category, determine the most important customer category corresponding to each self-service terminal in the new terminal category; for each customer category, the proportion of all self-service terminals in the new terminal category whose most important customer category is the customer category in the new terminal category is used as the proportion of the new terminal category corresponding to the customer category.

4. The method according to claim 1, wherein Based on the waiting time and prediction accuracy, the partial order of the trading interface corresponding to the terminal category is determined, including: For any two transaction interfaces, if the interval time for the terminal category corresponding to the first of the two transaction interfaces is less than or equal to the interval time for the terminal category corresponding to the second of the two transaction interfaces, and the prediction accuracy rate for the terminal category corresponding to the first transaction interface is greater than or equal to the prediction accuracy rate for the terminal category corresponding to the second transaction interface, then the partial order determines that the first transaction interface is better than the second transaction interface.

5. The method according to claim 1, wherein Determining the preferred transaction interface for each self-service terminal of the terminal category based on the partial order of the transaction interfaces corresponding to the terminal category includes: Determine the potential preferred trading interface for the terminal category based on the partial order of the trading interfaces corresponding to the terminal category; The preferred transaction interface of each self-service terminal of the terminal category is determined according to the interval time and prediction accuracy of each potential preferred transaction interface of the terminal category corresponding to the terminal category.

6. A transaction interface evaluation device for a self-service terminal, characterized in that: include: A self-service terminal classification module is used to classify the bank's self-service terminals based on their customer data and transaction data to obtain multiple terminal categories; A data processing module is used to determine, for each terminal category, the interval time corresponding to each transaction interface of the terminal category based on the transaction data of each transaction interface corresponding to the terminal category; Determine the prediction accuracy of the transaction interface corresponding to the terminal category based on the interface recommendation data corresponding to the transaction interface of the terminal category; a partial order determination module, configured to determine a partial order of the transaction interfaces corresponding to the terminal category based on the waiting time and the prediction accuracy, wherein the partial order is used to determine whether the first transaction interface is superior to the second transaction interface among any two transaction interfaces; A transaction interface evaluation module is used to determine the preferred transaction interface of each self-service terminal of the terminal category based on the partial order of the transaction interfaces corresponding to the terminal category; The data processing module is specifically used for: For each transaction interface, based on the transaction data of the terminal category corresponding to the transaction interface, multiple interval time samples corresponding to each transaction category of the transaction interface are determined; Determine the interval time corresponding to the transaction interface for the terminal category based on multiple interval time samples corresponding to each transaction category of the transaction interface; Dividing the interface recommendation data corresponding to each transaction interface of the terminal category into multiple interface recommendation data subsets corresponding to the transaction interface of the terminal category; The proportion of the recommended data of each interface recommendation data subset corresponding to the transaction interface of the terminal category in which the customer selects the corresponding transaction interface is used as the predicted accurate sample of the transaction interface corresponding to the terminal category; The prediction accuracy rate of the terminal category corresponding to the transaction interface is determined as the average of the accurate prediction samples of the terminal category corresponding to the transaction interface.

7. The device according to claim 6, characterized in that The self-service terminal classification module is specifically used for: Build customer space and business space, where the dimensions of the customer space correspond one-to-one with customer categories, and the dimensions of the business space correspond one-to-one with business categories; For each self-service terminal of the bank, the coordinates of the self-service terminal in the customer space and the business space are determined based on the customer data and business data of the self-service terminal; wherein the coordinate value of each dimension of the self-service terminal in the customer space is equal to the number of customers corresponding to the customer category corresponding to the dimension among the customers included in the customer data of the self-service terminal, and the coordinate value of each dimension of the self-service terminal in the business space is equal to the number of services corresponding to the business category corresponding to the dimension among the services included in the business data of the self-service terminal; Determine the customer distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the customer space, and determine the business distance corresponding to the self-service terminal based on the coordinates of the self-service terminal in the business space; The bank's self-service terminals are classified according to the customer distance corresponding to the self-service terminals and the business distance corresponding to the self-service terminals to obtain multiple terminal categories.

8. The device according to claim 7, wherein The self-service terminal classification module is specifically used for: Cluster the bank's self-service terminals based on their corresponding customer distances to obtain multiple terminal categories. For each terminal category obtained, determine the most important customer category corresponding to each self-service terminal in the terminal category; for each customer category, use the proportion of all self-service terminals in the terminal category whose most important customer category is the customer category as the proportion of the terminal category corresponding to the customer category; Determine whether each terminal category meets condition t: the maximum value of the proportion of each customer category corresponding to the terminal category is greater than a set proportion threshold; If there is a terminal category that does not meet condition t, the following steps are executed repeatedly until all terminal categories meet condition t: Select a terminal category that does not meet condition t; Clustering all self-service terminals of the selected terminal category according to the service distance corresponding to the self-service terminal, and replacing the terminal category with multiple new terminal categories obtained; For each new terminal category, determine the most important customer category corresponding to each self-service terminal in the new terminal category; for each customer category, the proportion of all self-service terminals in the new terminal category whose most important customer category is the customer category in the new terminal category is used as the proportion of the new terminal category corresponding to the customer category.

9. The device according to claim 6, wherein The partial order determination module is specifically used for: For any two transaction interfaces, if the interval time for the terminal category corresponding to the first of the two transaction interfaces is less than or equal to the interval time for the terminal category corresponding to the second of the two transaction interfaces, and the prediction accuracy rate for the terminal category corresponding to the first transaction interface is greater than or equal to the prediction accuracy rate for the terminal category corresponding to the second transaction interface, then the partial order determines that the first transaction interface is better than the second transaction interface.

10. The device according to claim 6, wherein The transaction interface evaluation module is specifically used to: Determine the potential preferred trading interface for the terminal category based on the partial order of the trading interfaces corresponding to the terminal category; The preferred transaction interface of each self-service terminal of the terminal category is determined according to the interval time and prediction accuracy of each potential preferred transaction interface of the terminal category corresponding to the terminal category.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: 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.

Images