Hotspot account identification method and device

Abstract

The present invention discloses a hotspot account identification method and device, and relates to the field of artificial intelligence technology, wherein the method comprises: inputting a transaction account in a current time period and transaction feature data corresponding to the transaction account into a transaction volume prediction model to obtain the transaction volume of the transaction account in the next time period; judging whether the transaction account is a hotspot account according to the transaction volume of the transaction account in the next time period and the system performance of the banking system; and when the transaction account is a hotspot account, adding the transaction account to a hotspot account list. The present invention can autonomously identify hotspot accounts when the transaction frequency of a transaction account in a certain time period is greater than a preset transaction frequency and will become a hotspot account, thereby ensuring the stable and efficient operation of the banking system and the user experience.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a hotspot account identification method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] In the banking system, in order to make transactions less affected by hot accounts, it is necessary to accurately identify hot accounts. In the existing hot account identification methods, the data to determine whether an ordinary account is a hot account (whether an ordinary account is a hot account means that the transaction volume of the transaction account surges in a certain period of time, exceeds the preset value and is about to become a hot account) are all pre-buried data or manually added data, but manual judgment is likely to be delayed or wrong. If an ordinary account becomes a hot account with a huge transaction volume without being set as a hot account, it may cause the banking system to bear huge transaction pressure and fail to provide services, affecting customer experience. Summary of the invention

[0004] The embodiment of the present invention provides a hot account identification method, which is used to autonomously identify hot accounts when the transaction frequency of a transaction account in a certain time period is greater than a preset transaction frequency and will become a hot account, thereby ensuring the stable and efficient operation of a banking business system and ensuring user experience. The method includes:

[0005] Inputting the transaction accounts in the current time period and the transaction feature data corresponding to the transaction accounts into the transaction volume prediction model to obtain the transaction volume of the transaction accounts in the next time period, wherein the current time period is the time period from the preset start time to the current time, and the transaction volume prediction model is obtained by training the neural network model based on the historical transaction accounts in the banking business system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume of the historical transaction accounts in the next time period;

[0006] Determine whether the trading account is a hot account based on the trading volume of the trading account in the next time period and the system performance of the banking system;

[0007] When the trading account is a hot account, add the trading account to the hot account list.

[0008] The embodiment of the present invention also provides a hot account identification device, which is used to autonomously identify hot accounts when the transaction frequency of a transaction account in a certain time period is greater than a preset transaction frequency and will become a hot account, thereby ensuring the stable and efficient operation of the banking system and the user experience. The device includes:

[0009] A prediction module, used to input the transaction accounts and transaction feature data corresponding to the transaction accounts in the current time period into a transaction volume prediction model to obtain the transaction volume of the transaction accounts in the next time period, wherein the current time period is the time period from a preset start time to the current time, and the transaction volume prediction model is obtained by training a neural network model based on historical transaction accounts in the banking business system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume of the historical transaction accounts in the next time period;

[0010] A judgment module, used to judge whether a trading account is a hot account according to the trading volume of the trading account in the next time period and the system performance of the banking system;

[0011] Add a module to add a trading account to the hot account list when the trading account is a hot account.

[0012] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned hotspot account identification method when executing the computer program.

[0013] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program for executing the above-mentioned hotspot account identification method.

[0014] In an embodiment of the present invention, the transaction account in the current time period and the transaction feature data corresponding to the transaction account are input into the transaction volume prediction model to obtain the transaction volume of the transaction account in the next time period, wherein the current time period is the time period from the preset start time to the current time, and the transaction volume prediction model is obtained by training the neural network model based on the historical transaction accounts in the banking system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume in the next time period of the historical transaction accounts; according to the transaction volume of the transaction account in the next time period and the system performance of the banking system, it is judged whether the transaction account is a hot account; when the transaction account is a hot account, the transaction account is added to the hot account list. Compared with the existing method of manually judging hot accounts, the present invention predicts the transaction volume of the transaction account in the next time period based on the transaction data in the current time period, and then according to the transaction volume of the transaction account in the next time period and the system performance of the banking system, it can autonomously judge whether the transaction account is a hot account, thereby ensuring the stable and efficient operation of the banking system and the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0016] Figure 1 A hotspot account identification method provided in an embodiment of the present invention Figure 1 ;

[0017] Figure 2 A flow chart of a method for training a transaction volume prediction model provided in an embodiment of the present invention;

[0018] Figure 3 A hotspot account identification method provided in an embodiment of the present invention Figure 2 ;

[0019] Figure 4 A hotspot account identification method provided in an embodiment of the present invention Figure 3 ;

[0020] Figure 5 A hotspot account identification method provided in an embodiment of the present invention Figure 4 ;

[0021] Figure 6 A flow chart of a method for updating a transaction volume prediction model provided in an embodiment of the present invention;

[0022] Figure 7 A schematic diagram of a hotspot account identification device provided in an embodiment of the present invention Figure 1 ;

[0023] Figure 8 A schematic diagram of a hotspot account identification device provided in an embodiment of the present invention Figure 2 ;

[0024] Fig. 9 A schematic diagram of a hotspot account identification device provided in an embodiment of the present invention Figure 3 . DETAILED DESCRIPTION

[0025] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0026] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be appropriately adjusted as needed.

[0027] Terminology explanation:

[0028] Hot Accounts: refers to accounts with a high transaction frequency within a certain period of time during the transaction process. During the transaction process, the account balance data corresponding to the hot accounts will be updated frequently, causing the bank system to encounter database processing bottlenecks and transaction pressure to increase sharply.

[0029] In order to solve the problem that an ordinary account becomes a hotspot account with a huge transaction volume without being set as a hotspot account, which may cause the banking system to be under great transaction pressure and unable to provide services, an embodiment of the present invention provides a hotspot account identification method, such as Figure 1 As shown, the method comprises the following steps:

[0030] Step 101, inputting the transaction accounts in the current time period and the transaction feature data corresponding to the transaction accounts into the transaction volume prediction model to obtain the transaction volume of the transaction accounts in the next time period, wherein the current time period is the time period from the preset start time to the current time, and the transaction volume prediction model is obtained by training the neural network model based on the historical transaction accounts in the banking business system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume of the historical transaction accounts in the next time period;

[0031] Step 102, judging whether the transaction account is a hot account according to the transaction volume of the transaction account in the next time period and the system performance of the banking system;

[0032] Step 103: When the transaction account is a hot account, the transaction account is added to a hot account list.

[0033] In the embodiment of the present invention, compared with the existing method of manually determining hot accounts, the present invention uses a transaction volume prediction model to predict the transaction volume of a transaction account in the next time period based on the transaction data in the current time period, and then independently determines whether the transaction account is a hot account based on the transaction volume of the transaction account in the next time period and the system performance of the banking business system, thereby ensuring the stability and efficiency of the banking business system and the user experience.

[0034] In the above step 101, the transaction information of the banking system can be monitored by the daily operation and maintenance monitoring module, and the transaction accounts in the banking system in the current time period and the transaction feature data corresponding to the transaction accounts in the current time period can be obtained.

[0035] Specifically, a starting time can be preset, and the transaction data within the time period from the starting time to the current time (i.e., the current time period) can be obtained. The current time period can be an integer number of minutes. Then, the transaction accounts in the transaction data within the current time period and the transaction feature data corresponding to the transaction accounts are extracted. Among them, the transaction feature data may include product type, transaction type, transaction channel, and transaction lending direction.

[0036] The extracted trading accounts and the trading feature data corresponding to the trading accounts are input into the trading volume prediction model to obtain the trading volume of the trading accounts in the next time period.

[0037] Before step 101, a transaction volume prediction model obtained by training a neural network model may be constructed based on historical transaction accounts in the banking system, transaction feature data corresponding to the historical transaction accounts, and transaction volumes of the historical transaction accounts in the next time period.

[0038] like Figure 2 As shown, an embodiment of the present invention provides a flow chart of a training method for a transaction volume prediction model, which may include the following steps:

[0039] Step 201, obtaining historical transaction accounts in a banking system, transaction feature data corresponding to the historical transaction accounts, and transaction volumes of the historical transaction accounts in the next time period as sample data, and constructing a training set and a test set, wherein the historical transaction data includes transaction accounts and historical transaction feature data corresponding to the transaction accounts;

[0040] Step 202, using the training set to train the neural network model to obtain a transaction volume prediction model;

[0041] Step 203: Test the transaction volume prediction model using the test set.

[0042] In one embodiment of the present invention, the above step 201 may specifically include:

[0043] The historical trading accounts, the transaction feature data corresponding to the historical trading accounts and the transaction volume of the historical trading accounts in the next time period are desensitized and used as sample data; the preset fixed time length is used as the size of the sliding window, and the sample data is divided according to the sliding window algorithm to obtain multiple sample data sets; and the training set and the test set are constructed based on the multiple sample data sets.

[0044] In the specific implementation, the historical transaction accounts in the banking business system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume of the transaction accounts of the historical transaction accounts in the next time period are obtained. In order to make the sample data meet the data security standards, the historical transaction data and the transaction volume of the corresponding transaction accounts in the next time period are desensitized, cleaned, etc., and then used as sample data. Then, a fixed time length T is preset, T is used as the sliding window size, and the sample data is divided according to the sliding window algorithm to obtain multiple sample data sets with a time length of T. The sample data in each sample data set is counted, and the transaction accounts in the sample data and the historical transaction feature data corresponding to the transaction accounts are extracted and the historical transaction feature data are standardized. Then, the sample data is divided into a training set and a test set according to a preset ratio.

[0045] For example, if T is 5 minutes, after dividing the sample data, 10 sample data sets with 5 minutes as the unit are obtained, 8 sample data sets are used as training sets, and 2 sample data sets are used as test sets.

[0046] In addition, the above-mentioned neural network model can be a long short-term memory network (Long Short-Term Memory, LSTM). By training the LSTM with a training set, a recurrent neural network model for predicting the trading volume of a trading account in the next time period, namely, a trading volume prediction model, can be obtained.

[0047] In this way, by desensitizing, cleaning, extracting features and standardizing the historical transaction data in the banking business system and the transaction volume of the corresponding transaction accounts in the next time period, the selected historical transaction data is more representative, and the prediction results of the transaction volume prediction model finally trained are more accurate.

[0048] It should be noted that the next time period in the above step 101 is the same length as the current time period, and the next time period starts at the current time.

[0049] In the above step 102, it is determined whether the transaction account is a hot account based on the transaction volume of the transaction account predicted in step 101 in the next time period and the system performance of the banking system.

[0050] It should be noted that different banking systems have different conditions for determining hot accounts. When the banking system has good system performance, the efficiency of processing transactions is also high, and the requirements for hot accounts in a certain period of time are also high.

[0051] In one embodiment of the present invention, Figure 3 As shown, the above step 102 may specifically include:

[0052] Step 301, obtaining the historical transaction volume of the trading account in the current time period and multiple time periods before the current time period.

[0053] Here, the duration of the multiple time periods before the current time period is the same as the duration of the current time period, and the multiple time periods are multiple time periods that are continuous with the current time period. For example, the current time period is 10:00-11:00, and the three time periods before 10:00 can be: 9:00-10:00, 8:00-9:00, and 7:00-8:00. Then, the historical trading volume of trading account A is 10:00-11:00: N1; 9:00-10:00: N2; 8:00-9: N3; 7:00-8: N4.

[0054] Step 302: construct a transaction volume set according to the transaction volume and historical transaction volume of the transaction account in the next time period.

[0055] Here, based on the description of step 301 above, for example, the next time period is 11:00-12:00, and the predicted value of the transaction volume of trading account A from 11:00 to 12:00 is R. Then, the obtained transaction volume set is Y={R, N1, N2, N3, N4}.

[0056] Step 303: Determine whether the transaction account is a hotspot account based on the system performance and transaction volume set of the banking system.

[0057] Here, in one embodiment of the present invention, Figure 4 As shown, step 303 may specifically include:

[0058] Step 401, obtain performance parameters of system performance, the performance parameters including the number of transactions processed concurrently by the banking system, the highest threshold percentage of the number of transactions processed concurrently, the lowest threshold percentage of the number of transactions processed concurrently, the highest threshold percentage of the average number of transactions processed concurrently, and the lowest threshold percentage of the average number of transactions processed concurrently.

[0059] Among them, the number of transactions processed concurrently by the banking system refers to the number of transactions that can be successfully processed by a single account per second.

[0060] It should be noted that the number of transactions processed concurrently by the banking system is not fixed. Depending on the specific application scenario, the number of transactions processed concurrently may increase or decrease to a certain extent. Therefore, the performance parameters of the system performance also include the highest threshold percentage of concurrently processed transactions, the lowest threshold percentage of concurrently processed transactions, the highest threshold percentage of the average number of concurrently processed transactions, and the lowest threshold percentage of the average number of concurrently processed transactions.

[0061] Step 402: If the transaction volume of the transaction account in the next time period is greater than or equal to the product of the number of concurrently processed transactions and the highest threshold percentage of the concurrently processed transaction number, and the mean of the transaction volume set is greater than the product of the number of concurrently processed transactions and the highest threshold percentage of the average of the concurrently processed transaction number, the transaction account is determined to be a hot account.

[0062] In the above step 103, when the transaction account is a hot account, the transaction account is added to the hot account list.

[0063] After a transaction account is added to the hot account list, when the transaction account has a transaction again, the hot account processing branch can be used to process the transaction of the transaction account, which can reduce the risk that an ordinary account becomes a hot account with a huge transaction volume without being set as a hot account, causing the banking business system to be unable to provide services due to the huge transaction pressure.

[0064] In another embodiment of the present invention, Figure 5 As shown, after step 401, the following steps may also be included:

[0065] Step 501: if the transaction volume of the transaction account in the next time period is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the number of concurrently processed transactions, and the mean of the transaction volume set is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the average of the number of concurrently processed transactions, and the transaction account is in the hot account list, determine that the transaction account is a non-hot account;

[0066] Step 502: Delete the transaction account from the hot account list.

[0067] After the transaction account is deleted from the hot account list, when the transaction account has another transaction, the transaction of the transaction account is processed by using the common account processing branch of the banking system.

[0068] For example, let the transaction volume of the transaction account in the next time period be R; the number of transactions processed concurrently by the banking system may be X, the highest threshold percentage P1 of the number of transactions processed concurrently is 120%; the lowest threshold percentage P2 of the number of transactions processed concurrently is 50%; the highest threshold percentage P3 of the average number of transactions processed concurrently is 90%; the lowest threshold percentage P4 of the average number of transactions processed concurrently is 60%; then:

[0069] When R≥X*120% and MEAN(Y)>X*90%, A is identified as a hotspot account;

[0070] When R<X*50% and MEAN(Y)<X*60% and A is in the hot account list, A is determined to be a non-hot account.

[0071] Among them, MEAN(Y) is the mean of the transaction volume set Y.

[0072] In this way, based on the transaction volume of the transaction account in the next time period, combined with the historical transaction volume of the transaction account in the current time period and multiple time periods before the current time period, and the system performance of the banking business system, it is possible to accurately determine whether the transaction account will change from an ordinary account to a hot account, or from a hot account to an ordinary account in the next time period, and then configure the corresponding processing method for the transaction of the transaction account based on the judgment result, thereby ensuring the stable and efficient operation of the banking business system and the user experience.

[0073] In addition, in one embodiment of the present invention, the transaction accounts in the hot account list of the day, the transaction feature data corresponding to the transaction accounts, and the transaction volumes corresponding to the transaction accounts in each time period of the day can be added to the sample data, and the transaction volume prediction model can continue to be trained and tuned to ensure that the generated prediction results are more accurate.

[0074] like Figure 6 As shown, it is a flow chart of the method for updating the transaction volume prediction model provided by an embodiment of the present invention. When the transaction account is a hot account, after adding the transaction account to the hot account list, the following steps may also be included:

[0075] Step 601, updating sample data with the transaction accounts in the hot account list of the day, the transaction feature data corresponding to the transaction accounts, and the transaction volume corresponding to the transaction accounts in each time period of the day;

[0076] Step 602, using the updated sample data, update the training set and the test set, and continue to train and test the transaction volume prediction model.

[0077] The present invention also provides a hotspot account identification device, as described in the following embodiments. Since the principle of solving the problem by the device is similar to that of the hotspot account identification method, the implementation of the device can refer to the implementation of the hotspot account identification method, and the repeated parts will not be repeated.

[0078] like Figure 7 FIG. 1 is a schematic diagram of a hotspot account identification device provided by an embodiment of the present invention, wherein the device includes:

[0079] The prediction module 701 is used to input the transaction accounts and the transaction feature data corresponding to the transaction accounts in the current time period into the transaction volume prediction model to obtain the transaction volume of the transaction accounts in the next time period, wherein the current time period is the time period from the preset start time to the current time, and the transaction volume prediction model is obtained by training the neural network model based on the historical transaction accounts in the banking business system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume of the historical transaction accounts in the next time period;

[0080] A determination module 702, configured to determine whether the transaction account is a hotspot account according to the transaction volume of the transaction account in the next time period and the system performance of the banking system;

[0081] The adding module 703 is used to add the transaction account to the hot account list when the transaction account is a hot account.

[0082] In one embodiment of the present invention, the judgment module is specifically used to:

[0083] Get the historical trading volume of the trading account in the current time period and multiple time periods before the current time period;

[0084] Build a volume set based on the trading account's trading volume and historical trading volume in the next time period;

[0085] Based on the system performance and transaction volume of the banking system, determine whether the transaction account is a hot account.

[0086] In one embodiment of the present invention, the judgment module is further used to:

[0087] Obtaining performance parameters of system performance, the performance parameters including the number of transactions processed concurrently by the banking system, the highest threshold percentage of the number of transactions processed concurrently, the lowest threshold percentage of the number of transactions processed concurrently, the highest threshold percentage of the average number of transactions processed concurrently, and the lowest threshold percentage of the average number of transactions processed concurrently;

[0088] If the transaction volume of the transaction account in the next time period is greater than or equal to the product of the number of concurrently processed transactions and the highest threshold percentage of the concurrently processed transaction number, and the mean of the transaction volume set is greater than the product of the number of concurrently processed transactions and the highest threshold percentage of the average of the concurrently processed transaction number, the transaction account is determined to be a hot account.

[0089] In one embodiment of the present invention, the judgment module is further used to:

[0090] If the transaction volume of the transaction account in the next time period is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the number of concurrently processed transactions, and the mean of the transaction volume set is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the average of the number of concurrently processed transactions, and the transaction account is in the hot account list, the transaction account is determined to be a non-hot account;

[0091] Delete the trading account from the hot account list.

[0092] In one embodiment of the present invention, Figure 8 As shown, it also includes a model training and testing module 801, which is used to input the transaction accounts and transaction feature data corresponding to the transaction accounts in the current time period into the transaction volume prediction model in the prediction module:

[0093] Acquire historical transaction accounts in a banking business system, transaction feature data corresponding to the historical transaction accounts, and transaction volumes of the historical transaction accounts in a next time period as sample data, and construct training sets and test sets, wherein the historical transaction data includes transaction accounts and historical transaction feature data corresponding to the transaction accounts;

[0094] Use the training set to train the neural network model and obtain the transaction volume prediction model;

[0095] The trading volume prediction model is tested using the test set.

[0096] In one embodiment of the present invention, Figure 8 The model training and testing modules shown are also used to:

[0097] The historical trading accounts, the transaction feature data corresponding to the historical trading accounts, and the transaction volume of the historical trading accounts in the next time period are desensitized and used as sample data;

[0098] Using a preset fixed time length as the size of the sliding window, the sample data is divided according to the sliding window algorithm to obtain multiple sample data sets;

[0099] Construct training and test sets based on multiple sample datasets.

[0100] In one embodiment of the present invention, Fig. 9As shown, it also includes a model optimization module 901, which is specifically used for:

[0101] Update sample data with the transaction accounts in the hot account list of the day, the transaction feature data corresponding to the transaction accounts, and the transaction volume corresponding to the transaction accounts in each time period of the day;

[0102] Using the updated sample data, the training set and test set are updated, and the trading volume prediction model is continued to be trained and tested.

[0103] In one embodiment of the present invention, the transaction characteristic data includes product type, transaction type, transaction channel and transaction lending direction.

[0104] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned hotspot account identification method when executing the computer program.

[0105] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program for executing the above-mentioned hotspot account identification method.

[0106] In an embodiment of the present invention, the transaction account in the current time period and the transaction feature data corresponding to the transaction account are input into the transaction volume prediction model to obtain the transaction volume of the transaction account in the next time period, wherein the current time period is the time period from the preset start time to the current time, and the transaction volume prediction model is obtained by training the neural network model based on the historical transaction accounts in the banking system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume in the next time period of the historical transaction accounts; according to the transaction volume of the transaction account in the next time period and the system performance of the banking system, it is judged whether the transaction account is a hot account; when the transaction account is a hot account, the transaction account is added to the hot account list. Compared with the existing method of manually judging hot accounts, the present invention predicts the transaction volume of the transaction account in the next time period based on the transaction data in the current time period, and then according to the transaction volume of the transaction account in the next time period and the system performance of the banking system, it can autonomously judge whether the transaction account is a hot account, thereby ensuring the stable and efficient operation of the banking system and the user experience.

[0107] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to 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 flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A hotspot account identification method, characterized in that: include: Inputting the transaction accounts in the current time period and the transaction feature data corresponding to the transaction accounts into the transaction volume prediction model to obtain the transaction volume of the transaction accounts in the next time period, wherein the current time period is the time period from the preset start time to the current time, and the transaction volume prediction model is obtained by training the neural network model based on the historical transaction accounts in the banking business system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume of the historical transaction accounts in the next time period; Determine whether the trading account is a hot account based on the trading volume of the trading account in the next time period and the system performance of the banking system; When the trading account is a hot account, add the trading account to the hot account list; Judging whether the trading account is a hot account according to the trading volume of the trading account in the next time period and the system performance of the banking system, including: obtaining the historical trading volume of the trading account in the current time period and multiple time periods before the current time period; constructing a trading volume set according to the trading volume of the trading account in the next time period and the historical trading volume; judging whether the trading account is a hot account according to the system performance of the banking system and the trading volume set; Judging whether a transaction account is a hot account based on the system performance and transaction volume set of the banking system includes: obtaining performance parameters of the system performance, the performance parameters including the number of transactions processed concurrently by the banking system, the highest threshold percentage of the number of transactions processed concurrently, the lowest threshold percentage of the number of transactions processed concurrently, the highest threshold percentage of the average number of transactions processed concurrently, and the lowest threshold percentage of the average number of transactions processed concurrently; determining that the transaction account is a hot account when the transaction volume of the transaction account in a next time period is greater than or equal to the product of the number of transactions processed concurrently and the highest threshold percentage of the number of transactions processed concurrently, and the mean of the transaction volume set is greater than the product of the number of transactions processed concurrently and the highest threshold percentage of the average number of transactions processed concurrently.

2. The method according to claim 1, characterized in that After obtaining the performance parameters of the system performance, it also includes: If the transaction volume of the transaction account in the next time period is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the number of concurrently processed transactions, and the mean of the transaction volume set is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the average of the number of concurrently processed transactions, and the transaction account is in the hot account list, the transaction account is determined to be a non-hot account; Delete the trading account from the hot account list.

3. The method according to claim 1, characterized in that Before inputting the transaction accounts and transaction feature data corresponding to the transaction accounts in the current time period into the transaction volume prediction model, it also includes: Obtain historical transaction accounts in the banking business system, transaction feature data corresponding to the historical transaction accounts, and transaction volumes in the next time period of the historical transaction accounts as sample data to construct training sets and test sets; Use the training set to train the neural network model and obtain the transaction volume prediction model; The trading volume prediction model is tested using the test set.

4. The method according to claim 3, characterized in that Obtain historical transaction accounts in the banking system, transaction feature data corresponding to the historical transaction accounts, and transaction volumes in the next time period of the historical transaction accounts as sample data, and construct training sets and test sets, including: The historical trading accounts, the transaction feature data corresponding to the historical trading accounts, and the transaction volume of the historical trading accounts in the next time period are desensitized and used as sample data; Using a preset fixed time length as the size of the sliding window, the sample data is divided according to the sliding window algorithm to obtain multiple sample data sets; Construct training and test sets based on multiple sample datasets.

5. The method according to claim 3, characterized in that Also includes: Update sample data with the transaction accounts in the hot account list of the day, the transaction feature data corresponding to the transaction accounts, and the transaction volume corresponding to the transaction accounts in each time period of the day; Using the updated sample data, the training set and test set are updated, and the trading volume prediction model is continued to be trained and tested.

6. The method according to claim 1, characterized in that The transaction characteristic data includes product type, transaction type, transaction channel and transaction lending direction.

7. A hotspot account identification device, characterized in that: include: A prediction module, used to input the transaction accounts and transaction feature data corresponding to the transaction accounts in the current time period into a transaction volume prediction model to obtain the transaction volume of the transaction accounts in the next time period, wherein the current time period is the time period from a preset start time to the current time, and the transaction volume prediction model is obtained by training a neural network model based on historical transaction accounts in the banking business system, the transaction feature data corresponding to the historical transaction accounts, and the transaction volume of the historical transaction accounts in the next time period; A judgment module, used to judge whether a trading account is a hot account according to the trading volume of the trading account in the next time period and the system performance of the banking system; Add a module to add a trading account to the hot account list when the trading account is a hot account; The judgment module is specifically used to: obtain the historical transaction volume of the transaction account in the current time period and multiple time periods before the current time period; construct a transaction volume set based on the transaction volume and historical transaction volume of the transaction account in the next time period; and judge whether the transaction account is a hot account based on the system performance of the banking business system and the transaction volume set; The judgment module is further specifically used to: obtain performance parameters of system performance, the performance parameters including the number of transactions processed concurrently by the banking system, the highest threshold percentage of the number of transactions processed concurrently, the lowest threshold percentage of the number of transactions processed concurrently, the highest threshold percentage of the average number of transactions processed concurrently, and the lowest threshold percentage of the average number of transactions processed concurrently; determine that the transaction account is a hot account when the transaction volume of the transaction account in the next time period is greater than or equal to the product of the number of concurrently processed transactions and the highest threshold percentage of the number of concurrently processed transactions, and the mean of the transaction volume set is greater than the product of the number of concurrently processed transactions and the highest threshold percentage of the average number of concurrently processed transactions.

8. The device according to claim 7, characterized in that The judgment module is also used for: If the transaction volume of the transaction account in the next time period is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the number of concurrently processed transactions, and the mean of the transaction volume set is less than the product of the number of concurrently processed transactions and the minimum threshold percentage of the average of the number of concurrently processed transactions, and the transaction account is in the hot account list, the transaction account is determined to be a non-hot account; Delete the trading account from the hot account list.

9. The device according to claim 7, characterized in that It also includes a model training and testing module, which is used to input the transaction account and transaction feature data corresponding to the transaction account in the current time period into the transaction volume prediction model in the prediction module: Obtain historical transaction accounts in the banking business system, transaction feature data corresponding to the historical transaction accounts, and transaction volumes in the next time period of the historical transaction accounts as sample data to construct training sets and test sets; Use the training set to train the neural network model and obtain the transaction volume prediction model; The trading volume prediction model is tested using the test set.

10. The device according to claim 9, characterized in that Model training and testing modules are also used for: The historical trading accounts, the transaction feature data corresponding to the historical trading accounts, and the transaction volume of the historical trading accounts in the next time period are desensitized and used as sample data; Using a preset fixed time length as the size of the sliding window, the sample data is divided according to the sliding window algorithm to obtain multiple sample data sets; Construct training and test sets based on multiple sample datasets.

11. The device according to claim 9, characterized in that It also includes a model optimization module, which is specifically used to: Update sample data with the transaction accounts in the hot account list of the day, the transaction feature data corresponding to the transaction accounts, and the transaction volume corresponding to the transaction accounts in each time period of the day; Using the updated sample data, the training set and test set are updated, and the trading volume prediction model is continued to be trained and tested.

12. The device according to claim 7, characterized in that The transaction characteristic data includes product type, transaction type, transaction channel and transaction lending direction.

13. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

14. 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 6 is implemented.

Images