Method and device for determining daily cut-off period of business system and identifying data errors

Abstract

The present application provides a method and device for determining the daily cut-off time period and identifying data errors in a business system, which relates to the financial field. The method includes: obtaining the daily cut-off time periods of a business system to be determined within a preset historical number of days; inputting all the daily cut-off time periods into a preset evolutionary prediction model to obtain the current-day cut-off time period. Since the evolutionary prediction model of the present invention is obtained based on an evolutionary algorithm, a daily cut-off delay time prediction model for the business system is trained by combining the self-learning and self-adaptive capabilities of evolutionary computing for the daily cut-off delay characteristics of each business system. The daily cut-off delay time of each business system can be obtained in advance, avoiding the bottleneck effect of the maximum daily cut-off delay on the entire detailed verification mechanism, and at the same time improving the identification efficiency of error transactions.

Description

Technical Field

[0001] The present application relates to the field of information security technology, and particularly relates to a method and device for determining the daily cut-off period of a service system and identifying data errors. Background Art

[0002] In a distributed architecture, a business typically requires multiple business systems to assist each other to achieve. To ensure the consistency of business logic, usually each business system provides business processing details according to the business date in batch at the end of the day, and identifies error business processing through the business processing detail verification mechanism between business systems. At the same time, to avoid the general detail verification mechanism misjudging the cross-day cut-off normal business processing data caused by the inconsistent daily cut-off times of each business system in the distributed architecture as error business processing, calculations are often carried out based on the differences between the daily cut-off time points of each business system and the daily cut-off time point of the reference system, and the general detail verification scope is expanded to eliminate the influence of cross-day cut-off normal business processing data on the identification of real error business processing.

[0003] Existing methods have multiple problems: 1. Expanding the verification detail scope of the general verification mechanism has a large intrusion on the general verification mechanism, increasing the risk of errors in the detail verification system itself, and thus affecting the accuracy of error business processing identification; 2. Cross-day cut-off normal business processing usually only involves some business systems. The existing solutions expand the scope of business processing details included in the verification for the differences between the daily cut-off time points of all business systems and the daily cut-off time point of the reference system, increasing the amount of detail data that is not necessarily involved in the verification, and thus greatly affecting the efficiency of error identification; 3. Determining the expanded scope of business processing details included in the verification depends on the latest daily cut-off time point among all business systems. When this time point is relatively late, it will affect the determination timeliness of the expanded scope of all business systems, and thus seriously affect the error business processing identification and subsequent remedial processing timeliness, and may cause serious economic losses. Therefore, there are many deficiencies. Summary of the Invention

[0004] In view of the problems in the prior art, the present application provides a method and device for determining the daily cut-off period of a service system and identifying data errors.

[0005] In a first aspect, the present invention provides a method for determining the daily cut-off period of a service system, including:

[0006] Obtaining the daily cut-off period of the service system to be determined within a preset historical number of days;

[0007] Inputting all the daily cut-off periods into a preset evolutionary prediction model to obtain the daily cut-off period of the current day; wherein,

[0008] The evolutionary prediction model is obtained based on an evolutionary algorithm.

[0009] In an alternative embodiment, the steps for establishing the evolutionary prediction model include:

[0010] Generating an initial population according to the daily cut-off time periods within a preset historical number of days of the business system to be determined;

[0011] Evolving the initial population to generate a sub-generation population;

[0012] Performing an iterative operation to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than a set threshold or the iteration reaches a set number of times;

[0013] Selecting the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model.

[0014] In an alternative embodiment, the initial population includes multiple individuals, and the steps for generating each individual in the initial population include:

[0015] Generating an individual of the initial population randomly according to the cut-off time difference between the daily cut-off time period and the reference cut-off time period, in combination with selectable operators;

[0016] Repeatedly performing the step of generating an individual of the initial population multiple times to form the initial population.

[0017] In an alternative embodiment, the sub-generation population includes multiple sub-generation individuals, and evolving the initial population to generate a sub-generation population includes:

[0018] For any two individuals in the initial population, exchanging at least one operator at a set position or a random position to form two sub-generation individuals; and / or,

[0019] For each individual in the initial population, randomly transforming at least one operator at a set position or a random position to form the sub-generation individual.

[0020] In a second aspect, the present invention provides a method for identifying data errors in cross-day cut-off business processing across business systems, including:

[0021] Obtaining the daily cut-off time periods within a preset historical number of days for each business system;

[0022] Inputting the daily cut-off time periods within a preset historical number of days for each business system into a preset evolutionary prediction model, and the evolutionary prediction model outputs the daily cut-off time period of the current day;

[0023] Generating possible time periods for cross-day cut-off business processing of each business system according to the daily cut-off time period with the longest duration, the maximum business processing response duration of each business system, and the daily cut-off time period of each business system;

[0024] Identify and eliminate the service processing data generated during the possible occurrence period of the cross-day cut service processing in each business system from all error data; among them,

[0025] The evolutionary prediction model is obtained based on an evolutionary algorithm.

[0026] In an alternative embodiment, the generating the possible occurrence period of the cross-day cut service processing for each business system according to the day cut period of the current day with the longest duration, the maximum service processing response duration of each business system, and the day cut period of the current day of each business system includes:

[0027] Calculate the time difference between each business system and the business system with the longest day cut period of the current day;

[0028] Generate the possible occurrence period of the cross-day cut service processing for each business system according to the maximum service processing response duration of each business system in combination with the corresponding time difference.

[0029] In an alternative embodiment, the steps for establishing the evolutionary prediction model include:

[0030] Generate an initial population according to the day cut periods of each day within the preset historical days of the business system to be determined;

[0031] Evolve the initial population to generate a sub-generation population;

[0032] Perform an iterative operation to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than the set threshold or the iteration reaches the set number of times;

[0033] Select the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model.

[0034] In an alternative embodiment, the initial population includes multiple individuals, and the steps for generating each individual in the initial population include:

[0035] Generate an individual of the initial population randomly according to the day cut time difference between the daily day cut period and the reference day cut period, in combination with the selectable operators;

[0036] Repeat the steps for generating an individual of the initial population multiple times to form the initial population.

[0037] In an alternative embodiment, the sub-generation population includes multiple sub-generation individuals, and the evolving the initial population to generate a sub-generation population includes:

[0038] For any two individuals in the initial population, exchange at least one operator at a set position or a random position to form two sub-generation individuals; and / or,

[0039] For each individual in the initial population, at least one set position or random position operator is randomly transformed to form the sub-generation individual.

[0040] In a third aspect, the present invention provides a daily cut-off time determination device for a service system, including:

[0041] A daily cut-off time acquisition module, which acquires the daily cut-off time of the service system to be determined within a preset historical number of days;

[0042] A model input module, which inputs all the daily cut-off times into a preset evolutionary prediction model to obtain the current day's cut-off time; wherein,

[0043] The evolutionary prediction model is obtained based on an evolutionary algorithm.

[0044] In an optional embodiment, it further includes: a model establishment module; the model establishment module includes:

[0045] An initial population generation unit, which generates an initial population according to the daily cut-off times of the service system to be determined within a preset historical number of days;

[0046] A sub-generation population generation unit, which evolves the initial population to generate a sub-generation population;

[0047] An iteration unit, which performs an iteration operation to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than a set threshold or the iteration reaches a set number of times;

[0048] A model formation unit, which selects the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model.

[0049] In an optional embodiment, the initial population generation unit includes:

[0050] An individual generation unit, which randomly generates an individual of the initial population according to the cut-off time difference between the daily cut-off time and the reference cut-off time, in combination with selectable operators;

[0051] A population generation unit, which repeatedly executes the step of generating an individual of the initial population multiple times to form the initial population.

[0052] In an optional embodiment, the sub-generation population includes multiple sub-generation individuals, and the sub-generation population generation unit includes:

[0053] A crossover unit, which exchanges at least one set position or random position operator for any two individuals in the initial population to form two sub-generation individuals; and / or,

[0054] Mutation unit, for each individual in the initial population, randomly transform at least one set position or random position operator to form the sub-generation individuals.

[0055] Fourthly, the present invention provides a cross-day cut service processing data error identification device for cross-business systems, including:

[0056] Acquisition module, acquiring the daily day cut time periods within a preset historical number of days for each business system;

[0057] Prediction module, inputting the daily day cut time periods within a preset historical number of days for each business system into a preset evolutionary prediction model, and the evolutionary prediction model outputs the day cut time period of the current day;

[0058] Cross-day cut time period generation module, generating the possible cross-day cut service processing time periods for each business system according to the day cut time period of the current day with the longest duration, the maximum service processing response duration of each business system, and the day cut time period of each business system on the current day;

[0059] Error identification module, identifying and removing the service processing data generated within the possible cross-day cut service processing time periods of each business system from all error data; wherein,

[0060] The evolutionary prediction model is obtained based on an evolutionary algorithm.

[0061] In an optional embodiment, the cross-day cut time period generation module includes:

[0062] Time difference calculation unit, calculating the time difference between each business system and the business system with the longest day cut time period on the current day;

[0063] Cross-day cut service processing possible time period generation unit, generating the possible cross-day cut service processing time periods for each business system by combining the maximum service processing response duration of each business system with the corresponding time difference.

[0064] In an optional embodiment, it further includes: a model establishment module; the model establishment module includes:

[0065] Initial population generation unit, generating an initial population according to the daily day cut time periods within a preset historical number of days of the business systems to be determined;

[0066] Sub-generation population generation unit, evolving the initial population to generate a sub-generation population;

[0067] Iteration unit, performing an iteration operation, evolving the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than a set threshold or the iteration reaches a set number of times;

[0068] The model formation unit selects the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model.

[0069] In an optional embodiment, the initial population generation unit includes:

[0070] The individual generation unit randomly generates individuals of the initial population according to the day cut time difference between the daily day cut time period and the reference day cut time period, in combination with selectable operators;

[0071] The population generation unit repeats the step of generating individuals of the initial population multiple times to form the initial population.

[0072] In an optional embodiment, the sub-generation population includes multiple sub-generation individuals, and the sub-generation population generation unit includes:

[0073] The crossover unit exchanges at least one set position or random position operator for any two individuals in the initial population to form two sub-generation individuals; and / or,

[0074] The mutation unit randomly transforms at least one set position or random position operator for each individual in the initial population to form the sub-generation individuals.

[0075] In a fifth aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the day cut time period determination method of the business system described above is implemented.

[0076] In a sixth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the day cut time period determination method of the business system described above is implemented.

[0077] As can be seen from the above technical solutions, the day cut time period determination, data error identification method and device provided by the present application input all daily day cut time periods into a preset evolutionary prediction model, and then predict the day cut time period of the current day. This evolutionary prediction model is obtained based on an evolutionary algorithm. Therefore, for the day cut delay characteristics of each business system, combined with the self-learning and adaptive capabilities of evolutionary computing, a business system day cut delay time prediction model is trained to obtain the day cut delay time of each business system in advance, avoiding the maximum day cut delay from becoming the bottleneck of the entire detailed verification mechanism, and at the same time improving the identification efficiency of error transactions. Description of the Drawings

[0078] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0079] Figure 1 It is a schematic flowchart of the method for determining the daily cut-off time period of the business system in the embodiment of the present application.

[0080] Figure 2 It is a schematic diagram of the daily cut-off time periods of each business system in the embodiment of the present application.

[0081] Figure 3 It is a schematic flowchart of the steps for establishing the evolution prediction model in the embodiment of the present application.

[0082] Figure 4 It is in the embodiment of the present application Figure 3 The specific flowchart of step S01 in

[0083] Figure 5 It is in the embodiment of the present application Figure 3 The specific flowchart of the iterative steps of step S03 in

[0084] Figure 6 It is in the embodiment of the present application Figure 3 The specific flowchart of step S02 in

[0085] Figure 7 It is the overall flowchart of the method for identifying data errors in cross-daily cut-off business processing in the embodiment of the present application.

[0086] Figure 8 It is in the embodiment of the present application Figure 7 The specific flowchart of step S103 in

[0087] Figure 9 It is a schematic diagram of the possible time periods of cross-daily cut-off business data of each business system in the embodiment of the present application.

[0088] Figure 10 It is a schematic diagram of the module structure of the device for determining the daily cut-off time period of the business system in the embodiment of the present application.

[0089] Figure 11 It is a schematic diagram of the module structure of the model establishment model in the embodiment of the present application.

[0090] Figure 12 It is in the embodiment of the present application Figure 11 The specific structure diagram of the initial population generation unit 01 in

[0091] Figure 13 In the embodiments of the present application Figure 11 is a schematic structural diagram of the next-generation population generation unit 02 in the present application.

[0092] Figure 14 is a schematic module structure diagram of the cross-day cut service processing data error identification device in the embodiments of the present application.

[0093] Figure 15 In the embodiments of the present application Figure 14 is a schematic structural diagram of the cross-day cut time period generation module 103 in the present application.

[0094] Figure 16 is a schematic structural diagram of the electronic device in the embodiments of the present application. Detailed implementation manners

[0095] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0096] It should be noted that the method, system, electronic device, and computer-readable storage medium for determining the day cut time period of the service system disclosed in the present application can be used in the field of information security technology, and can also be used in any field other than the field of information security technology. The application fields of the method, system, electronic device, and computer-readable storage medium for determining the day cut time period of the service system disclosed in the present application are not limited.

[0097] The present application also provides a service system group for implementing one or more embodiments of the present application. The service system group includes a plurality of service systems and a reference service system. Each service system has a day cut time period, and the reference service system corresponds to a reference day cut time period. Each service system is communicatively connected to each other, and each service system is communicatively connected to a plurality of service client devices for performing services such as transactions.

[0098] It can be understood that the client devices may include smart phones, tablet electronic devices, portable computers, desktop computers, personal digital assistants (PDAs), etc.

[0099] Any suitable network protocol can be used for communication between the above business system and the client device, including network protocols that have not been developed as of the filing date of this application. The network protocol can, for example, include TCP / IP protocol, UDP / IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol can also include, for example, RPC protocol (Remote Procedure Call Protocol) and REST protocol (Representational State Transfer) used on top of the above protocols.

[0100] A method and apparatus for determining the daily cut-off time period and identifying data errors in a business system provided by this application predicts the daily cut-off time period of the current day by inputting all daily cut-off time periods into a preset evolutionary prediction model. The evolutionary prediction model is obtained based on an evolutionary algorithm. Therefore, in view of the daily cut-off delay characteristics of each business system and combining the self-learning and adaptive capabilities of evolutionary computing, a prediction model for the daily cut-off delay time of the business system is trained, which can obtain the daily cut-off delay time of each business system in advance, avoid the maximum daily cut-off delay from becoming the bottleneck of the entire detailed reconciliation mechanism, and improve the identification efficiency of error transactions at the same time.

[0101] Specifically, it will be described separately through the following multiple embodiments and application examples.

[0102] An embodiment of a method for determining the daily cut-off time period of a business system provided by this application, as Figure 1 shown, is executed by the daily cut-off time period determination node of the business system and includes:

[0103] Step S100: Obtain the daily cut-off time period of the business system to be determined within a preset historical number of days.

[0104] Step S200: Input all daily cut-off time periods into a preset evolutionary prediction model to obtain the daily cut-off time period of the current day.

[0105] Among them, the evolutionary prediction model is obtained based on an evolutionary algorithm.

[0106] From the above description, it can be seen that the method for determining the daily cut-off time period of the business system provided by the embodiment of this application predicts the daily cut-off time period of the current day by inputting all daily cut-off time periods into a preset evolutionary prediction model. The evolutionary prediction model is obtained based on an evolutionary algorithm. Therefore, in view of the daily cut-off delay characteristics of each business system and combining the self-learning and adaptive capabilities of evolutionary computing, a prediction model for the daily cut-off delay time of the business system is trained, which can obtain the daily cut-off delay time of each business system in advance, avoid the maximum daily cut-off delay from becoming the bottleneck of the entire detailed reconciliation mechanism, and improve the identification efficiency of error transactions at the same time.

[0107] In this application, the meaning of the daily cut-off period is the daily time period. For example, in real life, one day is 24 hours, but for a business system, one day may be 25 hours or 23 hours. The daily cut-off periods of each business system may be the same or different.

[0108] As Figure 2 shown, T day is the first day when all business systems provide services externally (the date settings of each business system are the same on the first day). Subsequently, the unified benchmark system triggers the daily cut-off of each business system and provides the standard time by sending a message mechanism to each business system. The difference in message transmission time consumption between the benchmark system and each business system will result in a difference in the daily cut-off time of each business system. The delay time difference between the daily cut-off time of business system 1 and the standard time is t1; the delay time difference between the daily cut-off time of business system n and the standard time is tn. The daily cut-off time difference between business system 1 and business system n is Δt1 = tn - t1. Assuming that s1 is the maximum allowable transaction response time of business system 1, then T1 = Δt1 + s1 is the possible time period for cross-daily cut-off transactions.

[0109] In an embodiment of the method for determining the daily cut-off period of a business system provided in this application, the steps for establishing the evolutionary prediction model are as Figure 3 shown, and include:

[0110] S01: Generate an initial population according to the daily cut-off period of each day within the preset historical days of the business system to be determined;

[0111] S02: Evolve the initial population to generate a sub-generation population;

[0112] S03: Perform an iterative operation to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than the set threshold or the iteration reaches the set number of times;

[0113] S04: Select the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model.

[0114] In the embodiment of this application, the evolutionary prediction model is obtained based on an evolutionary algorithm and is continuously optimized through population reproduction during model establishment. 2) According to Figure 2 shown, each business system sets a daily cut-off time prediction module. According to the delay difference U 1 ~U N between the daily cut-off time and the reference time in the recent N days (the value of N can increase with the number of days the system runs), through evolutionary calculation training, a daily cut-off time delay prediction model for each business system is formed. Each business system can rely on the prediction model to independently predict the daily cut-off time delay value tn before the daily cut-off.

[0115] Specifically, in an embodiment of the method for determining the daily cut-off period of a business system provided in this application, asFigure 4 As shown, step S01 specifically includes:

[0116] S011: According to the day cut time difference between the daily day cut time period and the reference day cut time period, combined with the selectable operators, randomly generate individuals of the initial population;

[0117] S012: Repeat the step of generating individuals of the initial population multiple times to form the initial population.

[0118] The evolutionary algorithm adopted by the present invention is an iterative random search process based on Darwin's theory of evolution, based on fitness, drawing on the selection mechanism of survival of the fittest and elimination of the unfit in nature and the natural genetic mechanism, and realizing the restructuring of the individual structure within the population through the operation of evolutionary operators on the individuals within the population. The evolutionary calculation training process is as Figure 5 shown.

[0119] In this embodiment, the selectable operators may include +, -, *, / , cos, sin, tan, cot, (), power, etc., that is, the general operators in the prior art can be used in the present invention.

[0120] In specific applications, parameter settings are first performed: including the probabilities α ∈ (0, 1) of evolutionary operators (mutation, crossover, etc.), the population size Pop (the number of individuals participating in training), the maximum number of iterations T, and the termination condition (the number of iterations reaches T or the fitness value of the optimal individual in the population is less than a certain threshold Threshold). Each parameter is set according to different scenarios.

[0121] In some embodiments, the population individuals are randomly generated, and each individual is an equation composed of the day cut delay time values U 1 ~U N-1 for the past N - 1 days and the selectable operators (+, -, *, / , cos, sin, tan, cot, (), power, etc.), such as U 1 +7U 2 *sin(U 3 / U 4 )…… / U N-1 3 .

[0122] Furthermore, in an embodiment of the day cut time period determination method for the service system provided in the present application, the next-generation population includes multiple next-generation individuals. As Figure 6 shown, step S02 includes:

[0123] S021: For any two individuals in the initial population, exchange at least one operator at a set position or a random position to form two of the next-generation individuals; and / or,

[0124] S022: For each individual in the initial population, randomly transform at least one set position or random position operator to form the next-generation individual.

[0125] Specifically, the above step S021 belongs to the evolutionary operator crossover operation. As shown in Table 1, for two individuals, exchange at least one set position or random position operator to form the next-generation individual after crossover. In Table 1, for Individual 1 and Individual 2, the operator at the second position is crossed: the * in Individual 1 and the + in Individual 2, to form the new Individual 1 and Individual 2, and the new Individual 1 and Individual 2 are the individuals in the current next-generation population.

[0126] Table 1 Crossover Operator Process

[0127]

[0128] In specific applications, step S022 belongs to the mutation operation of the evolutionary algorithm. As shown in Table 2, for each individual, randomly transform at least one of its operators. In Table 2, the second operator * of the individual is changed to -.

[0129] Table 2 Mutation Operator Process

[0130]

[0131] It can be seen that the individuals in each next-generation population can be obtained by performing the above crossover and mutation on the individuals in the initial population. Then, calculate the fitness value of each individual, and calculate the difference between the delay value obtained from the equation composed of each individual (that is, the daily cut-off delay time values U 1 ~U N-1 and the selectable operators (+, -, *, / , cos, sin, tan, cot, (), power, etc.) and the daily cut-off delay time value U N of the Nth day (the smaller the difference, the better the individual, and the more the training model tends to converge).

[0132] In this embodiment, the termination condition of the iteration is: determine that the number of iterations reaches T or the fitness value of the optimal individual in the population is less than a certain threshold Threshold (both T and Threshold are flexibly set according to specific scenarios during the parameter setting stage).

[0133] The finally formed optimal individual is the evolutionary prediction model.

[0134] It can be understood that in this application, by inputting all the daily cut-off time periods into a preset evolutionary prediction model, the cut-off time period of the current day can be predicted. Since the evolutionary prediction model is obtained based on an evolutionary algorithm, a prediction model for the cut-off delay time of the business system is trained by combining the self-learning and self-adaptive capabilities of evolutionary computing for the cut-off delay characteristics of each business system, so as to obtain the cut-off delay time of each business system in advance, avoiding the maximum cut-off delay from becoming a bottleneck affecting the entire detailed verification mechanism.

[0135] This application provides a method for identifying data errors in cross-day cut-off business processing across business systems, as Figure 7 shown, including:

[0136] S101: Obtain the daily cut-off time period of each business system within a preset historical number of days;

[0137] S102: Input the daily cut-off time period of each business system within a preset historical number of days into a preset evolutionary prediction model, and the evolutionary prediction model outputs the cut-off time period of the current day;

[0138] S103: Generate the possible occurrence time periods of cross-day cut-off business processing for each business system according to the cut-off time period of the current day with the longest duration, the maximum business processing response duration of each business system, and the cut-off time period of each business system;

[0139] S104: Identify and exclude the business processing data generated within the possible occurrence time periods of cross-day cut-off business processing for each business system from all error data; where

[0140] the evolutionary prediction model is obtained based on an evolutionary algorithm.

[0141] A method for identifying data errors across business systems provided by this application predicts the cut-off time period of each business system, combines the cut-off time period of the business system with the longest cut-off time period of the day and the cut-off time period of the reference system, and then compares to obtain the possible transaction time periods for cross-day cut-off. After that, the data generated during this period is excluded from all error data, ensuring the accuracy of error data identification.

[0142] In an optional embodiment, as Figure 8 shown, step S103 includes:

[0143] S1031: Calculate the time difference between each business system and the business system with the longest cut-off time period of the current day;

[0144] S1032: Generate the possible occurrence time periods of cross-day cut-off business processing for each business system according to the maximum business processing response duration of each business system combined with the corresponding time difference.

[0145] In this application, the meaning of the daily cut-off period is the daily time period. For example, in real life, a day is 24 hours, but for a business system, a day may be 25 hours or 23 hours. The daily cut-off periods of each business system may be the same or different.

[0146] As Figure 2 shown, T day is the first day when all business systems provide services externally (the date settings of each business system are the same on the first day). Subsequently, a unified benchmark system triggers the daily cut-off of each business system and provides standard time by sending a message mechanism to each business system. The difference in message transmission time consumption between the benchmark system and each business system will result in a difference in the daily cut-off time of each business system. The delay time difference between the daily cut-off time of business system 1 and the standard time is t1; the delay time difference between the daily cut-off time of business system n and the standard time is tn. The daily cut-off time difference between business system 1 and business system n is Δt1 = tn - t1. Assuming that s1 is the maximum allowable transaction response time of business system 1, then T1 = Δt1 + s1 is the possible time period for cross-daily cut-off transactions.

[0147] In an alternative embodiment, for the steps of establishing the evolutionary prediction model, please continue to refer to Figure 3 , including:

[0148] S01: Generate an initial population according to the daily cut-off period of each business system within the preset historical days to be determined;

[0149] S02: Evolve the initial population to generate a sub-generation population;

[0150] S03: Perform an iterative operation to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than the set threshold or the iteration reaches the set number of times;

[0151] S04: Select the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model.

[0152] In the embodiments of this application, the evolutionary prediction model is obtained based on an evolutionary algorithm and is continuously optimized through population reproduction during model establishment. 2) According to Figure 2 shown, each business system sets a daily cut-off time prediction module. According to the delay difference U 1 ~U N of the daily cut-off time compared with the benchmark time in the recent N days (the value of N can increase with the number of days of system operation), through evolutionary calculation training, a daily cut-off time delay prediction model for each business system is formed. Each business system can rely on the prediction model to independently predict the daily cut-off time delay value tn before the daily cut-off.

[0153] Specifically, in an embodiment of the method for determining the daily cut-off period of a business system provided in this application, please continue to refer to Figure 4As shown, step S01 specifically includes:

[0154] S011: According to the day cut time difference between the daily day cut time period and the reference day cut time period, combined with the selectable operators, randomly generate individuals of the initial population;

[0155] S012: Repeat the step of generating individuals of the initial population multiple times to form the initial population.

[0156] The evolutionary algorithm adopted by the present invention is an iterative random search process based on Darwin's theory of evolution, based on fitness, drawing on the selection mechanism of survival of the fittest and elimination of the unfit in nature and the natural genetic mechanism, and realizing the restructuring of the individual structure within the population through the operation of evolutionary operators on the individuals within the population. The evolutionary calculation training process is as Figure 5 shown.

[0157] In this embodiment, the selectable operators may include +, -, *, / , cos, sin, tan, cot, (), power, etc., that is, the general operators in the prior art can be used in the present invention.

[0158] In specific applications, parameter settings are first performed: including the probabilities α∈(0,1) of evolutionary operators (mutation, crossover, etc.), the population size Pop (the number of individuals participating in training), the maximum number of iterations T, and the termination condition (the number of iterations reaches T or the fitness value of the optimal individual in the population is less than a certain threshold Threshold). Each parameter is set according to different scenarios.

[0159] In some embodiments, the population individuals are randomly generated, and each individual is an equation composed of the day cut delay time values U 1 ~U N-1 for the last N - 1 days and the selectable operators (+, -, *, / , cos, sin, tan, cot, (), power, etc.), such as U 1 +7U 2 *sin(U 3 / U 4 )…… / U N-1 3 .

[0160] Furthermore, in an embodiment of the day cut time period determination method for the service system provided in the present application, the next-generation population includes multiple next-generation individuals. Continuing with Figure 6 as shown, step S02 includes:

[0161] S021: For any two individuals in the initial population, exchange at least one operator at a set position or a random position to form two of the next-generation individuals; and / or,

[0162] S022: For each individual in the initial population, randomly transform at least one set position or random position operator to form the next-generation individual.

[0163] Specifically, the above step S021 belongs to the evolutionary operator crossover operation. As shown in Table 1, for two individuals, exchange at least one set position or random position operator to form the next-generation individual after crossover. In Table 1, for Individual 1 and Individual 2, the operator at the second position is crossed: the * in Individual 1 and the + in Individual 2, forming new Individual 1 and Individual 2, and the new Individual 1 and Individual 2 are the individuals in the current next-generation population.

[0164] In specific applications, step S022 belongs to the mutation operation of the evolutionary algorithm. As shown in Table 2, for each individual, randomly transform at least one of its operators. In Table 2, the second operator * of the individual is changed to -.

[0165] It can be seen that the individuals in each next-generation population can be obtained by performing the above crossover and mutation on the individuals in the initial population. Then, calculate the fitness value of each individual, calculate the difference between the delay value obtained from the equation formed by each individual (i.e., the daily cut delay time values U 1 ~U N-1 and the selectable operators (+, -, *, / , cos, sin, tan, cot, (), power, etc.) and the daily cut delay time value U N on the Nth day (the smaller the difference, the better the individual and the more convergent the training model).

[0166] In this embodiment, the termination condition of the iteration is: determine that the number of iterations reaches T or the fitness value of the optimal individual in the population is less than a certain threshold Threshold (both T and Threshold are flexibly set according to specific scenarios in the parameter setting stage).

[0167] In this way, the finally formed optimal individual is the evolutionary prediction model.

[0168] Then, execute step S104, that is: identify and eliminate the business processing data generated during the possible time periods of cross-day cut business processing in each business system from all error data. Specifically, such as Figure 9As shown, the benchmark system obtains and aggregates the T-day transaction detail files provided by each business system, marks the source business systems of each detail data, and checks the key detail information (such as transaction amount, etc.) according to the transaction detail primary key information (such as transaction serial number) agreed by each business system. For the detail records with consistent checks, a matching process is performed to complete the general detail check. The records that fail to complete the matching are the list LA of identified suspicious error transaction data (including real error transactions and normal transactions across the day cut). At the same time, according to the source of the suspicious error transaction data, the business systems involved in the transaction data can be identified. The benchmark system designs a day cut time queue, aggregates the day cut delay times provided by each business system involved in the suspicious error transaction data, and obtains the maximum day cut delay time t of each business system involved in the suspicious error transaction data by comparing the predicted day cut delay times of each involved business system. max , and further calculates the predicted delay time t of each business system involved in each suspicious error transaction data. n with the maximum value t max The time difference is the T+1 day supplementary detail data time period Δtn of the business system involved in the suspicious error transaction data. The business system involved in the suspicious error transaction data generates the detail data file FA within the time period Δtn, the detail data file FB within the sn time period before the day cut, and the detail data file FC within the 2×sn~sn time period before the day cut (tn is the maximum service response time allowed for business system n) and transmits them to the benchmark system. Based on the daily suspicious error transactions (list LA), the benchmark system sequentially takes the FB, FC, and FA transaction detail data of the opponent business system for the FB transaction detail data of each business system involved in the suspicious error transaction, checks the key detail information (such as transaction amount, etc.) according to the transaction detail primary key information (such as transaction serial number) agreed by each business system, and performs a matching process on the detail records with consistent checks to complete the supplementary detail data check. If it is matched in the FA detail data of the opponent business system, it is a normal transaction across the day cut (list LB), and then the real error transaction list LA-LB is obtained.

[0169] It can be understood that in this application, by predicting the day cut period of each business system, combining the day cut period of the largest business system and the day cut period of the benchmark system, and then comparing to obtain the possible transaction period across the day cut, and then excluding the data generated during this period from all error data, the accuracy of error data identification is guaranteed.

[0170] From the above embodiments, the advantages of the present invention are as follows:

[0171] 1) On the basis of the general detailed verification of each business system within the business date, a mechanism for further identifying cross-day cut normal transactions is added, which avoids intrusion into the general verification mechanism, reduces the impact of the transformation of the verification system itself on the verification results, and further reduces the risk of error identification errors, improving the accuracy of real error transaction identification;

[0172] 2) The cross-day cut normal transaction identification mechanism extracts the minimum range of detailed data as the verification basis within the scope of the business systems involved in the suspicious transactions identified by the general detailed verification, reducing the unnecessary detailed data participating in the verification, improving the processing speed of cross-day cut transaction identification, and further improving the efficiency of real error transaction identification;

[0173] 3) For the day cut delay characteristics of each business system, combined with the self-learning and adaptive capabilities of evolutionary computing, a day cut delay time prediction model for the business system is trained to obtain the day cut delay time of each business system in advance, avoiding the bottleneck effect of the maximum day cut delay on the entire detailed verification mechanism, and further improving the identification efficiency of error transactions.

[0174] From a software perspective, the present invention provides a device for determining the day cut period of a business system, as Figure 10 shown, including:

[0175] A daily day cut period acquisition module 1, which acquires the daily day cut periods of the business system to be determined within a preset historical number of days;

[0176] A model input module 2, which inputs all the daily day cut periods into a preset evolutionary prediction model to obtain the current day cut period; wherein,

[0177] The evolutionary prediction model is obtained based on an evolutionary algorithm.

[0178] The device for determining the day cut period of a business system provided by the present application predicts the current day cut period by inputting all the daily day cut periods into a preset evolutionary prediction model. The evolutionary prediction model is obtained based on an evolutionary algorithm. Therefore, for the day cut delay characteristics of each business system, combined with the self-learning and adaptive capabilities of evolutionary computing, a day cut delay time prediction model for the business system is trained to obtain the day cut delay time of each business system in advance, avoiding the bottleneck effect of the maximum day cut delay on the entire detailed verification mechanism, and at the same time improving the identification efficiency of error transactions.

[0179] In an alternative embodiment, it further includes: a model establishment module; as Figure 11 shown, the model establishment module includes:

[0180] An initial population generation unit 01, which generates an initial population according to the daily day cut periods of the business system to be determined within a preset historical number of days;

[0181] The next-generation population generation unit 02 evolves the initial population to generate a next-generation population;

[0182] The iteration unit 03 performs an iteration operation to evolve the current next-generation population to generate an updated next-generation population until the fitness value of the optimal individual in the current next-generation population is less than a set threshold or the iteration reaches a set number of times;

[0183] The model formation unit 04 selects the optimal individual from the finally updated next-generation population to form the evolutionary prediction model.

[0184] Specifically, in the embodiment of the present application, the evolutionary prediction model is obtained based on an evolutionary algorithm and is continuously optimized through population reproduction during model establishment. 2) As Figure 2 shown, each business system sets a daily cut-off time prediction module, and based on the delay difference U 1 ~U N between the daily cut-off time and the reference time in the past N days (the value of N can increase with the number of days of system operation), through evolutionary calculation training, a daily cut-off time delay prediction model for each business system is formed, and each business system can rely on the prediction model to independently predict the daily cut-off time delay value tn before the daily cut-off.

[0185] In an alternative embodiment, the initial population generation unit 01, as Figure 12 shown, includes:

[0186] The individual generation unit 011 randomly generates individuals of the initial population according to the daily cut-off time difference between the daily cut-off period and the reference daily cut-off period, in combination with selectable operators;

[0187] The population generation unit 012 repeatedly executes the step of generating individuals of the initial population to form the initial population.

[0188] In an alternative embodiment, the next-generation population includes multiple next-generation individuals, and the next-generation population generation unit 02, as Figure 13 shown, includes:

[0189] The crossover unit 021 exchanges at least one operator at a set position or a random position for any two individuals in the initial population to form two of the next-generation individuals; and / or,

[0190] The mutation unit 022 randomly transforms at least one operator at a set position or a random position for each individual in the initial population to form the next-generation individuals.

[0191] In this embodiment, the selectable operators may include +, -, *, / , cos, sin, tan, cot, (), power, etc., that is, general operators in the prior art can be used in the present invention.

[0192] In specific applications, parameter settings are first performed, including the probabilities α ∈ (0, 1) of evolutionary operators (mutation, crossover, etc.), the population size Pop (the number of individuals participating in training), the maximum number of iterations T, and the termination condition (the number of iterations reaches T or the fitness value of the optimal individual in the population is less than a certain threshold Threshold). Each parameter is set according to different scenarios.

[0193] In some embodiments, the population individuals are randomly generated, and each individual is the daily cut-off delay time value U for the last N - 1 days 1 ~U N-1 and an equation composed of selectable operators (+, -, *, / , cos, sin, tan, cot, (), power, etc.), such as U 1 +7U 2 *sin(U 3 / U 4 )…… / U N-1 3 .

[0194] Furthermore, the present invention provides a cross-day cut business processing data error identification device for cross-business systems, as Figure 14 shown, including:

[0195] An acquisition module 101 that acquires the daily cut-off time periods within the preset historical days for each business system;

[0196] A prediction module 102 that inputs the daily cut-off time periods within the preset historical days for each business system into a preset evolutionary prediction model, and the evolutionary prediction model outputs the daily cut-off time period of the current day;

[0197] A cross-day cut time period generation module 103 that generates the possible cross-day cut business processing time periods for each business system based on the daily cut-off time period with the longest duration of the current day, the maximum business processing response duration of each business system, and the daily cut-off time period of each business system;

[0198] An error identification module 104 that identifies and eliminates the business processing data generated within the possible cross-day cut business processing time periods of each business system from all error data; wherein,

[0199] The evolutionary prediction model is obtained based on an evolutionary algorithm.

[0200] A data error identification device for cross-business systems provided by the present application predicts the cut-off time periods of each business system, combines the cut-off time periods of the largest business system and the cut-off time periods of the reference system, and then compares to obtain the possible cross-day cut transaction time periods. After that, the data generated during this time period is eliminated from all error data, ensuring the accuracy of error data identification.

[0201] In an alternative embodiment, the cross-day cut time period generation module, such as Figure 15 includes:

[0202] A time difference calculation unit 1031 that calculates the time difference between each service system and the service system with the longest day cut time period on the current day;

[0203] A cross-day cut service processing possible occurrence time period generation unit 1032 that generates a possible occurrence time period for cross-day cut service processing of each service system according to the maximum service processing response duration of each service system in combination with the corresponding time difference.

[0204] In this application, the meaning of the day cut time period is the daily time period. For example, in real life, it is 24 hours a day. However, for service systems, it may be 25 hours a day or 23 hours a day. The day cut time periods of each service system may be the same or different.

[0205] In an alternative embodiment, it further includes: a model establishment module; please continue to refer to Figure 11 , and the model establishment module includes:

[0206] An initial population generation unit 01 that generates an initial population according to the daily day cut time periods within the preset historical number of days of the service system to be determined;

[0207] A next-generation population generation unit 02 that evolves the initial population to generate a next-generation population;

[0208] An iteration unit 03 that performs an iteration operation to evolve the current next-generation population to generate an updated next-generation population until the fitness value of the optimal individual in the current next-generation population is less than the set threshold or the iteration reaches the set number of times;

[0209] A model formation unit 04 that selects the optimal individual from the finally updated next-generation population to form the evolutionary prediction model.

[0210] Specifically, in the embodiment of this application, the evolutionary prediction model is obtained based on an evolutionary algorithm and is continuously optimized through population reproduction during model establishment. 2) As shown in Figure 2 , a day cut time prediction module is set for each service system, and according to the delay difference U between the day cut time in the recent N days (the value of N can increase with the number of days of system operation) and the reference time 1 ~U N , through evolutionary calculation training, a day cut time delay prediction model for each service system is formed, and each service system can rely on the prediction model to independently predict the day cut time delay value tn on the current day before the day cut.

[0211] In an alternative embodiment, the initial population generation unit 01, as Figure 12 shown, includes:

[0212] The individual generation unit 011 randomly generates individuals of the initial population according to the daily cut-off time difference between the daily cut-off time period and the reference cut-off time period, in combination with selectable operators.

[0213] The population generation unit 012 repeats the step of generating individuals of the initial population multiple times to form the initial population.

[0214] In an optional embodiment, the sub-generation population includes multiple sub-generation individuals, and the sub-generation population generation unit 02, as Figure 13 shown, includes:

[0215] The crossover unit 021 exchanges at least one set position or random position operator for any two individuals in the initial population to form two sub-generation individuals; and / or,

[0216] The mutation unit 022 randomly transforms at least one set position or random position operator for each individual in the initial population to form the sub-generation individuals.

[0217] In this embodiment, the selectable operators may include +, -, *, / , cos, sin, tan, cot, (), power, etc., that is, general operators in the prior art can be used in the present invention.

[0218] In specific applications, parameter settings are first performed: including the probabilities α∈(0,1) of evolutionary operators (mutation, crossover, etc.), the population size Pop (the number of individuals participating in training), the maximum number of iterations T, and the termination condition (the number of iterations reaches T or the fitness value of the optimal individual in the population is less than a certain threshold Threshold). Each parameter is set according to different scenarios.

[0219] In some embodiments, the population individuals are randomly generated, and each individual is an equation composed of the daily cut-off delay time values U 1 ~U N-1 for the last N - 1 days and selectable operators (+, -, *, / , cos, sin, tan, cot, (), power, etc.), such as U 1 +7U 2 *sin(U 3 / U 4 )…… / U N-1 3 .

[0220] It can be understood that a data error identification device for cross-business systems provided by the present application predicts the daily cut-off time period of each business system, combines the daily cut-off time period of the largest business system and the daily cut-off time period of the reference system, and then compares to obtain the possible cross-day cut transaction time period. After that, the data generated during this time period is excluded from all error data, ensuring the accuracy of error data identification.

[0221] At the hardware level, to solve the problem of privacy leakage in the determination of the daily cut-off time of the existing business system, this application provides an embodiment of an electronic device for implementing all or part of the content in the method for determining the daily cut-off time of the business system. The electronic device specifically includes the following content:

[0222] Figure 16 It is a schematic block diagram of the system composition of the electronic device 9600 according to the embodiment of this application. As Figure 16 shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It should be noted that this Figure 16 is exemplary; other types of structures can also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0223] In one embodiment, the function of determining the daily cut-off time of the business system can be integrated into the central processing unit. Among them, the central processing unit can be configured to perform the following controls:

[0224] Step S100: Obtain the daily cut-off time of the business system to be determined within the preset historical number of days;

[0225] Step S200: Input all the daily cut-off times into a preset evolution prediction model to obtain the daily cut-off time of the current day;

[0226] Among them, the evolution prediction model is obtained based on an evolutionary algorithm.

[0227] As can be seen from the above description, the electronic device provided by the embodiment of this application predicts the daily cut-off time of the current day by inputting all the daily cut-off times into a preset evolution prediction model. The evolution prediction model is obtained based on an evolutionary algorithm. Therefore, for the daily cut-off delay characteristics of each business system, combined with the self-learning and adaptive capabilities of evolutionary computing, a prediction model for the daily cut-off delay time of the business system is trained, and the daily cut-off delay time of each business system can be obtained in advance, avoiding the maximum daily cut-off delay from becoming a bottleneck affecting the entire detailed verification mechanism, and at the same time improving the recognition efficiency of error transactions.

[0228] In another embodiment, the system for determining the daily cut-off time of the business system can be separately configured from the central processing unit 9100. For example, the system for determining the daily cut-off time of the business system can be configured as a chip connected to the central processing unit 9100 to implement the blockchain data interaction function through the control of the central processing unit.

[0229] As Figure 16As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It should be noted that the electronic device 9600 does not necessarily have to include Figure 16 all the components shown in; in addition, the electronic device 9600 may further include Figure 16 components not shown in, and reference may be made to the prior art.

[0230] As Figure 16 shown, the central processing unit 9100, sometimes also referred to as a controller or operation control, may include a microprocessor or other processor devices and / or logic devices. The central processing unit 9100 receives inputs and controls the operations of the various components of the electronic device 9600.

[0231] Among them, the memory 9140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices. The above information related to failures can be stored, and in addition, programs for executing relevant information can also be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0232] The input unit 9120 provides inputs to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to supply power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0233] The memory 9140 may be a solid-state memory. For example, a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be such a memory that stores information even when powered off, can be selectively erased and has more data. Examples of such a memory are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, and the application / function storage unit 9142 is used to store application programs and function programs or the processes for operating the electronic device 9600 through the central processing unit 9100.

[0234] The memory 9140 may further include a data storage unit 9143 for storing data such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the communication functions of the electronic device and / or for performing other functions of the electronic device (such as a messaging application, an address book application, etc.).

[0235] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

[0236] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc. The communication module (transmitter / receiver) 9110 is also coupled to the speaker 9131 and the microphone 9132 via the audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby implementing normal telecommunication functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0237] Embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps in the daily cut-off time period determination method of the service system in the above embodiments. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all steps of the daily cut-off time period determination method of the service system with the execution subject being a server or a client in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0238] Step S100: Obtain the daily cut-off time periods within a preset historical number of days of the service system to be determined;

[0239] Step S200: Input all the daily cut-off time periods into a preset evolution prediction model to obtain the current day's cut-off time period;

[0240] Wherein, the evolution prediction model is obtained based on an evolutionary algorithm.

[0241] As can be seen from the above description, the computer-readable medium provided by the embodiments of the present application predicts the daily cut-off time by inputting all daily cut-off time periods into a preset evolutionary prediction model. The evolutionary prediction model is obtained based on an evolutionary algorithm. Therefore, for the daily cut-off delay characteristics of each business system, combined with the self-learning and adaptive capabilities of evolutionary computing, a prediction model for the daily cut-off delay time of the business system is trained, which can obtain the daily cut-off delay time of each business system in advance, avoiding the maximum daily cut-off delay from becoming a bottleneck affecting the entire detailed reconciliation mechanism, and at the same time improving the recognition efficiency of error transactions.

[0242] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, apparatus, or computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.

[0243] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (apparatus), 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 can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0244] These computer program instructions can 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 generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0245] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1Steps of functions specified in one or more boxes.

[0246] In the present invention, specific embodiments are used to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for determining the daily cut-off time period of a business system, characterized in that, it includes: Obtain the daily cut-off time periods within the preset historical days of the business system to be determined; Input all the daily cut-off time periods into a preset evolutionary prediction model to obtain the current day's cut-off time period; wherein, The evolutionary prediction model is obtained based on an evolutionary algorithm; Among them, the steps for establishing the evolutionary prediction model include: Generate an initial population according to the daily cut-off time periods within the preset historical days of the business system to be determined; Evolve the initial population to generate a sub-generation population; Perform iterative operations to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than the set threshold or the iteration reaches the set number of times; Select the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model; Among them, the initial population includes multiple individuals, and the steps for generating each individual in the initial population include: Randomly generate individuals of the initial population according to the cut-off time difference between the daily cut-off time period and the reference cut-off time period, in combination with selectable operators; wherein, the differences in the cut-off times of each business system are caused by the differences in the message transmission time delays between the reference system and each business system; Among them, the sub-generation population includes multiple sub-generation individuals, and the step of evolving the initial population to generate a sub-generation population includes: For any two individuals in the initial population, exchange at least one operator at a set position or a random position to form two sub-generation individuals; and / or, For each individual in the initial population, randomly transform at least one operator at a set position or a random position to form the sub-generation individual.

2. A method for identifying data errors in cross-day cut-off business processing across business systems, characterized in that, it includes: Obtain the daily cut-off time periods within the preset historical days of each business system; Input the daily cut-off time periods within the preset historical days of each business system into a preset evolutionary prediction model, and the evolutionary prediction model outputs the current day's cut-off time period; Generate the possible occurrence time periods of cross-day cut-off business processing for each business system according to the current day's cut-off time period with the longest duration, the maximum business processing response duration of each business system, and the current day's cut-off time period of each business system; Identify and eliminate the business processing data generated within the possible occurrence time periods of cross-day cut-off business processing for each business system from all error data; wherein, The evolutionary prediction model is obtained based on an evolutionary algorithm; Among them, the steps for establishing the evolutionary prediction model include: Generate an initial population according to the daily cut-off time periods within the preset historical days of the business system to be determined; Evolve the initial population to generate a sub-generation population; Perform iterative operations to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than the set threshold or the iteration reaches the set number of times; Select the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model; Among them, the initial population includes multiple individuals, and the steps for generating each individual in the initial population include: Randomly generate individuals of the initial population according to the cut-off time difference between the daily cut-off time period and the reference cut-off time period, in combination with selectable operators; Among them, the differences in the daily cut-off times of each business system are caused by the differences in the message transmission time-consuming between the reference system and each business system.

3. The method for identifying data errors in cross-daily cut-off business processing according to claim 2, characterized in that the generation of the possible occurrence periods of cross-daily cut-off business processing for each business system based on the daily cut-off period with the maximum duration on the current day, the maximum business processing response duration of each business system, and the daily cut-off period of each business system includes: calculating the time difference between each business system and the business system with the longest daily cut-off period on the current day; generating the possible occurrence periods of cross-daily cut-off business processing for each business system by combining the maximum business processing response duration of each business system with the corresponding time difference.

4. The method for identifying data errors in cross-daily cut-off business processing according to claim 2, characterized in that the secondary population includes multiple secondary individuals, and the evolution of the initial population to generate the secondary population includes: for any two individuals in the initial population, exchanging at least one operator at a set position or a random position to form two secondary individuals; and / or, for each individual in the initial population, randomly transforming at least one operator at a set position or a random position to form the secondary individual.

5. A device for determining the daily cut-off period of a business system, characterized in that it includes: a daily cut-off period acquisition module, which acquires the daily cut-off periods of the business system to be determined within a preset number of historical days; a model input module, which inputs all the daily cut-off periods into a preset evolution prediction model to obtain the daily cut-off period on the current day; where the evolution prediction model is obtained based on an evolutionary algorithm; wherein, the device for determining the daily cut-off period of a business system further includes: a model establishment module; the model establishment module includes: an initial population generation unit, which generates an initial population according to the daily cut-off periods of the business system to be determined within a preset number of historical days; a secondary population generation unit, which evolves the initial population to generate a secondary population; an iteration unit, which performs an iteration operation to evolve the current secondary population to generate an updated secondary population until the fitness value of the optimal individual in the current secondary population is less than a set threshold or the iteration reaches a set number of times; a model formation unit, which selects the optimal individual from the finally updated secondary population to form the evolution prediction model; wherein, the initial population generation unit includes: an individual generation unit, which randomly generates individuals of the initial population according to the daily cut-off time difference between the daily cut-off period and the reference daily cut-off period, in combination with the selectable operators; among them, the differences in the daily cut-off times of each business system are caused by the differences in the message transmission time-consuming between the reference system and each business system; wherein, the secondary population generation unit includes: a crossover unit, which exchanges at least one operator at a set position or a random position for any two individuals in the initial population to form two secondary individuals; and / or, a mutation unit, which randomly transforms at least one operator at a set position or a random position for each individual in the initial population to form the secondary individual.

6. A device for identifying data errors in cross-daily cut-off business processing across business systems, characterized in that it includes: An acquisition module that acquires the daily cut-off time periods within a preset historical number of days for each business system; A prediction module that inputs the daily cut-off time periods within a preset historical number of days for each business system into a preset evolutionary prediction model, and the evolutionary prediction model outputs the cut-off time period for the current day; A cross-cut-off time period generation module that generates the possible cross-cut-off business processing time periods for each business system based on the cut-off time period for the current day with the longest duration, the maximum business processing response duration for each business system, and the cut-off time period for the current day of each business system; An error identification module that identifies and eliminates the business processing data generated within the possible cross-cut-off business processing time periods of each business system from all error data; wherein, The evolutionary prediction model is obtained based on an evolutionary algorithm; Among them, the cross-business system cross-cut-off business processing data error identification device further includes: a model establishment module; the model establishment module includes: An initial population generation unit that generates an initial population according to the daily cut-off time periods within a preset historical number of days for the business systems to be determined; A sub-generation population generation unit that evolves the initial population to generate a sub-generation population; An iteration unit that performs an iteration operation to evolve the current sub-generation population to generate an updated sub-generation population until the fitness value of the optimal individual in the current sub-generation population is less than a set threshold or the iteration reaches a set number of times; A model formation unit that selects the optimal individual from the finally updated sub-generation population to form the evolutionary prediction model; Among them, the initial population generation unit includes: An individual generation unit that randomly generates individuals of the initial population according to the cut-off time difference between the daily cut-off time period and the reference cut-off time period, in combination with the selectable operators; Among them, the cut-off time differences of each business system are caused by the message transmission time differences between the reference system and each business system.

7. An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer-readable storage medium, on which a computer program is stored, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images