Data processing method, device, equipment and readable storage medium
By dividing cash circulation data into a storage data set according to preset business attributes and coding rules in the banking system, and storing only the target information, the resource waste problem caused by storing full data is solved, and efficient data storage and crown font size are achieved. Traceability.
Patent Information
- Application Number
- CN202110551024.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-05-20
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When storing cash circulation data in the banking system, the existing technology requires storing all the data, resulting in waste of storage resources and high space demand.
By obtaining cash flow data within the preset time period, the data is divided into a storage data set according to the preset business attributes and encoding rules, and only the target information of each stored data set is stored, including business attributes and encoding rules, and the neural network model is used. Training the classification model to determine the optimal coding rules and reduce duplicate storage.
It effectively reduces storage space requirements, avoids waste of storage resources, and realizes traceability of the crown font size.
Smart Images

Figure CN113129143B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, device, equipment and readable storage medium. Background Art
[0002] In the field of cash circulation and banking system in my country, the legal identification and circulation tracking of banknotes are powerful means to combat illegal and criminal acts such as counterfeiting and altering national currency, and are also an important guarantee for maintaining financial security. In order to achieve the traceability of circulating banknotes, the cash circulation data generated by all bank branches every day are usually stored in the branch databases of bank branches at all levels. It can be seen that each level of branch database needs to store a large amount of cash circulation data, which requires a huge storage space, and the repeated storage of the full amount of cash circulation data causes a waste of storage resources. Summary of the invention
[0003] The present application provides a data processing method, apparatus, device and readable storage medium for reducing the amount of stored data to avoid waste of storage resources, as follows:
[0004] A data processing method, comprising:
[0005] Obtain cash flow data within a preset time period, each piece of cash flow data including a prefix number and preset business attributes;
[0006] Obtaining a preset coding rule to which each of the serial numbers belongs;
[0007] According to the preset business attributes and the preset coding rules to which the serial number belongs, the cash circulation data is divided into a plurality of storage data sets, each of the storage data sets including cash circulation data having the same preset coding rules to which the serial number belongs and the same preset business attributes to which the serial number belongs;
[0008] The target information of any one cash circulation data of each stored data set is stored, wherein the target information includes a preset business attribute of the any one cash circulation data and a preset coding rule to which the prefix number of the any one cash circulation data belongs.
[0009] Optionally, before obtaining the preset coding rule to which each of the serial numbers belongs, the method further includes:
[0010] Constructing a preset rule library, wherein the preset rule library includes a correspondence between a plurality of preset coding rules and preset rule levels;
[0011] A neural network model is trained according to preset sample data to obtain a classification model, wherein the classification model is used to output a preset coding rule to which a serial number as input data belongs, wherein the preset sample data includes: a historical serial number as input sample data, and an optimal coding rule to which the historical serial number belongs as target output data; the optimal coding rule is a preset coding rule in the preset rule library that meets preset conditions, wherein the preset conditions include: the corresponding preset rule has the highest level.
[0012] Optionally, the preset sample data further includes: a preset capacity as input sample data;
[0013] The preset condition also includes: the number of optimal encoding rules included in the target output data is less than a preset number threshold, and the difference with the preset number threshold is less than a preset difference threshold, and the preset number threshold is the maximum storage quantity determined according to the preset capacity.
[0014] Optionally, obtaining a preset coding rule to which each of the serial numbers belongs includes:
[0015] The serial number is input into the classification model, and the output of the classification model is used as the preset coding rule to which the serial number belongs.
[0016] Optionally, it also includes:
[0017] The quantity information and time information of each stored data set are stored, wherein the quantity information is the quantity of cash circulation data included in the stored data set, and the time information indicates the preset time period.
[0018] Optionally, the preset business attributes include: at least one of a business type, a branch number, and a business processing party number.
[0019] A data processing device, comprising:
[0020] A data acquisition unit, used to acquire cash circulation data within a preset time period, each piece of cash circulation data including a serial number and a preset business attribute;
[0021] A rule acquisition unit, used for acquiring a preset coding rule to which each of the serial numbers belongs;
[0022] a set division unit, dividing the cash circulation data into a plurality of storage data sets according to the preset business attributes and the preset coding rules to which the serial number belongs, each of the storage data sets including cash circulation data having the same preset coding rules to which the serial number belongs and the same preset business attributes to which the serial number belongs;
[0023] The data storage unit is used to store target information of any cash circulation data of each stored data set, wherein the target information includes a preset business attribute of the any cash circulation data and a preset coding rule to which the prefix number of the any cash circulation data belongs.
[0024] Optionally, the method further comprises: a model building unit, which is used, before obtaining the preset coding rule to which each of the serial numbers belongs:
[0025] Constructing a preset rule library, the preset rule library including a correspondence between a plurality of preset coding rules and preset rule levels of the preset coding rules;
[0026] A neural network model is trained according to preset sample data to obtain a classification model, wherein the classification model is used to output a preset coding rule to which a serial number as input data belongs, wherein the preset sample data includes: a historical serial number as input sample data, and an optimal coding rule to which the historical serial number belongs as target output data; the optimal coding rule is a preset coding rule in the preset rule library that meets preset conditions, wherein the preset conditions include: the corresponding preset rule has the highest level.
[0027] A data processing device, comprising: a memory and a processor;
[0028] The memory is used to store programs;
[0029] The processor is used to execute the program to implement each step of the data processing method.
[0030] A readable storage medium stores a computer program, which implements various steps of a data processing method when executed by a processor.
[0031] It can be seen from the above technical solutions that the data processing method, device, equipment and readable storage medium provided in the embodiments of the present application obtain cash circulation data within a preset time period, obtain the preset coding rules to which each serial number belongs, and divide the cash circulation data into multiple storage data sets according to the preset business attributes and the preset coding rules to which the serial number belongs, and store the target information of any cash circulation data in each storage data set. Since each storage data set includes cash circulation data with the same preset coding rules and preset business attributes to which the serial number belongs, and the target information includes the preset business attributes of any cash circulation data and the preset coding rules to which the serial number of any cash circulation data belongs, therefore, compared with the prior art that stores the full amount of cash circulation data, the present application only needs to store the target information of one cash circulation data for each storage data set, thereby avoiding the waste of storage resources caused by repeated storage of the full amount of cash circulation data and reducing the requirements for storage space. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0033] Figure 1 A flowchart of a specific implementation method of a data processing method provided in an embodiment of the present application;
[0034] Figure 2 A flowchart of a data processing method provided in an embodiment of the present application;
[0035] Figure 3 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;
[0036] Figure 4 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0038] The data processing method provided in the embodiment of the present application is applied to but not limited to the scenario of storing the cash flow data generated every day, and is specifically applied to each data processor of a preset level. It should be noted that the data processor is preset in a bank branch of a preset level, and is used to execute the data processing method to obtain storage data and store the storage data in the database of the bank branch of the preset level.
[0039] In actual applications, in order to achieve serial number traceability, after all preset-level outlets complete the cash circulation data of the day, the full amount of cash circulation data will be stored in the counting device server, and then reported to the memory of each preset-level bank outlet for full storage. Each piece of cash circulation data indicates the business handling information of a banknote. Obviously, if the memory of each preset-level bank outlet stores the full amount of cash circulation data, the storage space requirement is high and it is easy to cause a waste of storage resources. Therefore, this embodiment provides a data processing method, the purpose of which is to reduce the storage space requirement and avoid the waste of storage resources.
[0040] Figure 1 A specific implementation of a data processing method provided in an embodiment of the present application is as follows: Figure 1 As shown, the method includes:
[0041] S101. Obtain data to be processed.
[0042] In this embodiment, the data to be processed includes cash flow data within a preset time period.
[0043] As mentioned above, cash circulation data includes but is not limited to serial numbers and preset business attributes, wherein the preset business attributes include: business type and branch number. The serial number is the serial number printed on the banknote, the business type includes deposit and withdrawal, and the branch number indicates the branch that handles deposit or withdrawal.
[0044] It should be noted that the triggering timing of the present method includes the data processing time indicated by the preset data processing cycle. For example, the preset data processing cycle is one day (24 hours), and the data processing time is 9 o'clock every night for data processing, then the preset time period is the time period indicated by the preset data processing cycle.
[0045] It should be further explained that the method for obtaining the data to be processed is to receive the full amount of cash flow data sent by the counting device server. For details, please refer to the prior art.
[0046] S102: Build a preset rule library.
[0047] In this embodiment, the preset rule library includes a plurality of preset coding rules and a correspondence between each preset coding rule and a preset rule level. Each preset coding rule is obtained by processing the historical prefix number. Each preset coding rule indicates the coding attribute of a type of prefix number. For example, the coding attribute of the prefix number belonging to the first preset coding rule is: the third digit of the prefix number is any number from 1 to 9, and the coding attribute of the prefix number belonging to the second preset coding rule is: the sum of all digits of the prefix number is 20.
[0048] In this embodiment, the preset rule level corresponding to the preset coding rule is a level set at least according to the number of historical serial numbers belonging to the preset coding rule. For example, the more preset coding rules there are, the higher the preset rule level corresponding to the preset coding rule.
[0049] It should be noted that the serial number stored in the server is obtained as the historical serial number, and the method for processing the historical serial number may be a tree model method or a clustering method. For details, please refer to the prior art.
[0050] S103: Train a neural network model based on preset sample data to obtain a classification model.
[0051] In this embodiment, the classification model is used to output the optimal coding rule to which the crown number as input data belongs, and the preset sample data includes the historical crown number and the optimal coding rule to which the historical crown number belongs. Among them, the optimal coding rule to which the historical crown number belongs is the preset coding rule with the highest corresponding preset rule level among the multiple preset coding rules to which the historical crown number belongs. It can be understood that if the historical crown number belongs to only one preset coding rule, the preset coding rule to which the historical crown number belongs can be used as the optimal coding rule. For the method of obtaining the historical crown number and the preset coding rule to which the historical crown number belongs, refer to the above S102. It will not be elaborated here.
[0052] In this embodiment, the historical serial number is used as input, and the optimal encoding rule to which the historical serial number belongs is used as the target output to train the neural network model. It should be noted that the specific training method can refer to the prior art, and this embodiment will not be repeated.
[0053] S104, inputting the prefix number in the data to be processed into the classification model, and using the output of the classification model as the optimal encoding rule to which the prefix number belongs.
[0054] It should be noted that since a large number of serial numbers will be generated in actual applications, using a pre-trained classification model to classify the serial numbers and obtain the optimal coding rules for the serial numbers can improve the efficiency of data processing. Moreover, since the classification model is trained based on objective data (that is, historical serial numbers and the optimal coding rules belonging to the historical serial numbers), the output of the classification model is used as the optimal coding rule for the serial numbers with high accuracy.
[0055] S105. Divide the cash flow data into multiple storage data sets according to the optimal coding rule of the prefix number and the preset business attributes.
[0056] Specifically, the optimal coding rule of the serial number in each cash circulation data is used as the first classification information, the preset business attribute of the cash circulation data is used as the second classification information, and multiple cash circulation data corresponding to the same first classification information and second classification information are used as the same group of storage data to obtain a storage data set.
[0057] In this embodiment, the first classification information and the second classification information of the plurality of cash circulation data correspond to each other in the same manner, which means that the first classification information of the plurality of cash circulation data is the same, and the second classification information of the plurality of cash circulation data is also the same.
[0058] It can be understood that the serial numbers of various cash circulation data in the stored data set have the same optimal coding rules and the same preset business attributes.
[0059] S106: store the rule information, quantity information, and time information of each stored data set in a preset memory accordingly.
[0060] In this embodiment, the first classification information and the second classification information of any cash circulation data in the storage data set are used as the rule information of the storage data set. The quantity information indicates the quantity of cash circulation data included in the storage data set, and the time information indicates the time of data processing.
[0061] It can be seen from the above technical scheme that a data processing method provided by an embodiment of the present application, compared with the prior art that stores the full amount of cash circulation data, the present application only needs to store the rule information, quantity information, and time information of each stored data set. Since the stored data set includes multiple cash circulation data, the rule information of the stored data set is the optimal coding rule and preset business attribute of the serial number of any cash circulation data. Therefore, the amount of rule information, quantity information, and time information of the stored data set stored in the present application is small. Therefore, the present application can avoid the waste of storage resources caused by repeated storage of the full amount of cash circulation data and reduce the requirement for storage space.
[0062] Furthermore, since the rule information, quantity information, and time information of the multiple cash flow data in each stored data set are the same, the retrieval information of the serial number can be retrieved based on the time information and any preset attribute item, thereby achieving traceability of the serial number.
[0063] For example, an embodiment of the present application also provides a method for obtaining serial number retrieval information. This method is applied to each preset level of data processor, and the purpose is to achieve traceability of the serial number. Specifically including: 1. Obtaining query information, the query information includes the target serial number, target time and target attributes. It should be noted that the query information can be obtained by receiving user query instructions. 2. Obtaining the target rule, the target rule is the optimal encoding rule to which the target serial number belongs. 3. Determine whether there is a corresponding relationship between the target time, target attribute, and target rule in the storage data of the preset storage space. If not, output the first retrieval information. The first retrieval information indicates the circulation information of the banknote printed with the target serial number, and the circulation information includes all information corresponding to the stored target rule.
[0064] It should be noted that Figure 1 This is only a specific implementation of a data processing method provided in the embodiment of the present application. In other application scenarios, other specific implementations are also included. For example, the preset business attribute may also include: a business processing party number, where the business processing party number indicates the processing party for depositing or withdrawing cash, including the deposit and withdrawal machine number and the teller account number. For another example, the triggering timing of this method also includes: in response to receiving a preset data processing instruction.
[0065] For another example, in an optional application scenario, the preset sample data also includes the capacity or preset level of the preset memory. Then the optimal coding rule to which the historical serial number belongs is the preset coding rule that meets the preset capacity condition among the multiple preset coding rules to which the historical serial number belongs. Optionally, the preset capacity condition includes: the number of optimal coding rules to which all serial numbers belong is within a preset number interval, wherein the preset number interval is determined according to the capacity or preset level of the preset memory.
[0066] It is understandable that the storage period of the cash flow data stored in the preset storage is the preset period, and it will be cleared after the preset period. The preset principle of the preset capacity condition is that the capacity of the data stored within the preset period is close to the capacity of the preset storage. The purpose is to store as much data as possible without adding additional storage space and making full use of the storage space.
[0067] In summary, the data processing method provided in the embodiment of the present application is summarized as follows: Figure 2 As shown in the process. Figure 2 As shown, the method includes:
[0068] S201. Obtain cash flow data within a preset time period.
[0069] In this embodiment, each cash flow data includes a prefix number and a preset business attribute, wherein the preset business attribute includes at least one of a business type, a branch number, and a business processing party number, and the content of each of the items can refer to the introduction of the above embodiment.
[0070] S202: Obtain the preset coding rule to which each serial number belongs.
[0071] In this embodiment, there are multiple methods for obtaining the preset coding rules to which each serial number belongs. An optional method is: according to a pre-built classification model, the preset coding rules to which each serial number belongs are obtained. Specifically, the serial number is input into the classification model, and the output of the classification model is used as the preset coding rule to which the serial number belongs. The classification model is a neural network model pre-trained according to preset sample data. The specific training process includes multiple methods. For details, refer to the above embodiment.
[0072] S203: Divide the cash flow data into a plurality of storage data sets according to preset business attributes and preset coding rules to which the prefix number belongs.
[0073] In this embodiment, each stored data set includes cash circulation data to which the preset coding rule and the preset business attribute of the prefix number are the same.
[0074] S204: Storing target information of any cash flow data in each stored data set.
[0075] In this embodiment, the target information includes a preset business attribute of any piece of cash circulation data and a preset coding rule to which the prefix number of any piece of cash circulation data belongs.
[0076] It can be seen from the above technical scheme that a data processing method provided by an embodiment of the present application obtains cash circulation data within a preset time period, obtains the preset coding rules to which each serial number belongs, divides the cash circulation data into multiple storage data sets according to the preset business attributes and the preset coding rules to which the serial number belongs, and stores the target information of any cash circulation data in each storage data set. Since each storage data set includes cash circulation data with the same preset coding rules and preset business attributes to which the serial number belongs, and the target information includes the preset business attributes of any cash circulation data and the preset coding rules to which the serial number of any cash circulation data belongs, therefore, compared with the prior art that stores the full amount of cash circulation data, the present application only needs to store the target information of one cash circulation data for each storage data set, thereby avoiding the waste of storage resources caused by repeated storage of the full amount of cash circulation data and reducing the requirements for storage space.
[0077] Figure 3 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application is shown. Figure 3 As shown, the device may include:
[0078] The data acquisition unit 301 is used to acquire cash circulation data within a preset time period, each piece of the cash circulation data includes a serial number and a preset business attribute;
[0079] A rule acquisition unit 302, used to acquire a preset coding rule to which each of the serial numbers belongs;
[0080] The set division unit 303 divides the cash circulation data into a plurality of storage data sets according to the preset business attributes and the preset coding rules to which the serial number belongs, each of which has the same preset coding rules and the same preset business attributes to which the serial number belongs, and includes cash circulation data having the same preset coding rules and the same preset business attributes to which the serial number belongs;
[0081] The data storage unit 304 is used to store target information of any cash circulation data in each of the stored data sets, wherein the target information includes a preset business attribute of the any cash circulation data and a preset coding rule to which the prefix number of the any cash circulation data belongs.
[0082] Optionally, the method further comprises: a model building unit, which is used, before obtaining the preset coding rule to which each of the serial numbers belongs:
[0083] Constructing a preset rule library, the preset rule library including a correspondence between a plurality of preset coding rules and preset rule levels of the preset coding rules;
[0084] A neural network model is trained according to preset sample data to obtain a classification model, wherein the classification model is used to output a preset coding rule to which a serial number as input data belongs, wherein the preset sample data includes: a historical serial number as input sample data, and an optimal coding rule to which the historical serial number belongs as target output data; the optimal coding rule is a preset coding rule in the preset rule library that meets preset conditions, wherein the preset conditions include: the corresponding preset rule has the highest level.
[0085] Optionally, the preset sample data further includes: a preset capacity as input sample data;
[0086] The preset condition also includes: the number of optimal encoding rules included in the target output data is less than a preset number threshold, and the difference with the preset number threshold is less than a preset difference threshold, and the preset number threshold is the maximum storage quantity determined according to the preset capacity.
[0087] Optionally, the rule acquisition unit is used to acquire the preset coding rule to which each of the serial numbers belongs, including: the rule acquisition unit is specifically used to:
[0088] The serial number is input into the classification model, and the output of the classification model is used as the preset coding rule to which the serial number belongs.
[0089] Optionally, the data storage unit is further used to: store quantity information and time information of each of the stored data sets, the quantity information being the quantity of cash circulation data included in the stored data set, and the time information indicating the preset time period.
[0090] Optionally, the preset business attributes include: at least one of a business type, a branch number, and a business processing party number.
[0091] Figure 4 A schematic diagram of the structure of the device is shown, and the device may include: at least one processor 401, at least one communication interface 402, at least one memory 403 and at least one communication bus 404;
[0092] In the embodiment of the present application, the number of the processor 401, the communication interface 402, the memory 403, and the communication bus 404 is at least one, and the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404;
[0093] The processor 401 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention;
[0094] The memory 403 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;
[0095] The memory stores a program, and the processor can execute the program stored in the memory to implement various steps of a data processing method provided in an embodiment of the present application, as follows:
[0096] A data processing method, comprising:
[0097] Obtain cash flow data within a preset time period, each piece of cash flow data including a prefix number and preset business attributes;
[0098] Obtaining a preset coding rule to which each of the serial numbers belongs;
[0099] According to the preset business attributes and the preset coding rules to which the serial number belongs, the cash circulation data is divided into a plurality of storage data sets, each of which has the same preset coding rules and the same preset business attributes to which the serial number belongs, and includes cash circulation data having the same preset coding rules and the same preset business attributes to which the serial number belongs;
[0100] The target information of any one cash circulation data of each stored data set is stored, wherein the target information includes a preset business attribute of the any one cash circulation data and a preset coding rule to which the prefix number of the any one cash circulation data belongs.
[0101] Optionally, before obtaining the preset coding rule to which each of the serial numbers belongs, the method further includes:
[0102] Constructing a preset rule library, wherein the preset rule library includes a correspondence between a plurality of preset coding rules and preset rule levels;
[0103] A neural network model is trained according to preset sample data to obtain a classification model, wherein the classification model is used to output a preset coding rule to which a serial number as input data belongs, wherein the preset sample data includes: a historical serial number as input sample data, and an optimal coding rule to which the historical serial number belongs as target output data; the optimal coding rule is a preset coding rule in the preset rule library that meets preset conditions, wherein the preset conditions include: the corresponding preset rule has the highest level.
[0104] Optionally, the preset sample data further includes: a preset capacity as input sample data;
[0105] The preset condition also includes: the number of optimal encoding rules included in the target output data is less than a preset number threshold, and the difference with the preset number threshold is less than a preset difference threshold, and the preset number threshold is the maximum storage quantity determined according to the preset capacity.
[0106] Optionally, obtaining a preset coding rule to which each of the serial numbers belongs includes:
[0107] The serial number is input into the classification model, and the output of the classification model is used as the preset coding rule to which the serial number belongs.
[0108] Optionally, it also includes:
[0109] The quantity information and time information of each stored data set are stored, wherein the quantity information is the quantity of cash circulation data included in the stored data set, and the time information indicates the preset time period.
[0110] Optionally, the preset service attribute includes: at least one of a service type, a branch number, and a service processing party number.
[0111] The embodiment of the present application further provides a readable storage medium, which can store a computer program suitable for execution by a processor. When the computer program is executed by the processor, the steps of a data processing method provided in the embodiment of the present application are implemented as follows:
[0112] A data processing method, comprising:
[0113] Obtain cash flow data within a preset time period, each piece of cash flow data including a prefix number and preset business attributes;
[0114] Obtaining a preset coding rule to which each of the serial numbers belongs;
[0115] According to the preset business attributes and the preset coding rules to which the serial number belongs, the cash circulation data is divided into a plurality of storage data sets, each of which has the same preset coding rules and the same preset business attributes to which the serial number belongs, and includes cash circulation data having the same preset coding rules and the same preset business attributes to which the serial number belongs;
[0116] The target information of any one cash circulation data of each stored data set is stored, wherein the target information includes a preset business attribute of the any one cash circulation data and a preset coding rule to which the prefix number of the any one cash circulation data belongs.
[0117] Optionally, before obtaining the preset coding rule to which each of the serial numbers belongs, the method further includes:
[0118] Constructing a preset rule library, wherein the preset rule library includes a correspondence between a plurality of preset coding rules and preset rule levels;
[0119] A neural network model is trained according to preset sample data to obtain a classification model, wherein the classification model is used to output a preset coding rule to which a serial number as input data belongs, wherein the preset sample data includes: a historical serial number as input sample data, and an optimal coding rule to which the historical serial number belongs as target output data; the optimal coding rule is a preset coding rule in the preset rule library that meets preset conditions, wherein the preset conditions include: the corresponding preset rule has the highest level.
[0120] Optionally, the preset sample data further includes: a preset capacity as input sample data;
[0121] The preset condition also includes: the number of optimal encoding rules included in the target output data is less than a preset number threshold, and the difference with the preset number threshold is less than a preset difference threshold, and the preset number threshold is the maximum storage quantity determined according to the preset capacity.
[0122] Optionally, obtaining a preset coding rule to which each of the serial numbers belongs includes:
[0123] The serial number is input into the classification model, and the output of the classification model is used as the preset coding rule to which the serial number belongs.
[0124] Optionally, it also includes:
[0125] The quantity information and time information of each stored data set are stored, wherein the quantity information is the quantity of cash circulation data included in the stored data set, and the time information indicates the preset time period.
[0126] Optionally, the preset service attribute includes: at least one of a service type, a branch number, and a service processing party number.
[0127] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0128] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0129] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A data processing method, characterized in that: include: Obtain cash flow data within a preset time period, each piece of cash flow data including a prefix number and preset business attributes; Obtaining a preset coding rule to which each of the serial numbers belongs; According to the preset business attributes and the preset coding rules to which the serial number belongs, the cash circulation data is divided into a plurality of storage data sets, each of which has the same preset coding rules and the same preset business attributes to which the serial number belongs, and includes cash circulation data having the same preset coding rules and the same preset business attributes to which the serial number belongs; Storing target information of any one of the cash circulation data in each of the stored data sets, the target information includes a preset business attribute of the any one of the cash circulation data and a preset coding rule to which the prefix number of the any one of the cash circulation data belongs; Before obtaining the preset coding rule to which each serial number belongs, the method further includes: Constructing a preset rule library, wherein the preset rule library includes a correspondence between a plurality of preset coding rules and preset rule levels; A neural network model is trained according to preset sample data to obtain a classification model, wherein the classification model is used to output a preset coding rule to which a serial number as input data belongs, wherein the preset sample data includes: a historical serial number as input sample data, and an optimal coding rule to which the historical serial number belongs as target output data; the optimal coding rule is a preset coding rule in the preset rule library that meets preset conditions, wherein the preset conditions include: the corresponding preset rule has the highest level; The preset sample data also includes: a preset capacity as input sample data; The preset condition also includes: the number of optimal encoding rules included in the target output data is less than a preset number threshold, and the difference with the preset number threshold is less than a preset difference threshold, and the preset number threshold is a maximum storage number determined according to the preset capacity; The obtaining of the preset coding rule to which each of the serial numbers belongs includes: The serial number is input into the classification model, and the output of the classification model is used as the preset coding rule to which the serial number belongs.
2. The method according to claim 1, characterized in that Also includes: The quantity information and time information of each stored data set are stored, wherein the quantity information is the quantity of cash circulation data included in the stored data set, and the time information indicates the preset time period.
3. The method according to claim 1, characterized in that The preset service attributes include: at least one of a service type, a branch number, and a service processing party number.
4. A data processing device, characterized in that: include: A data acquisition unit, used to acquire cash circulation data within a preset time period, each piece of cash circulation data including a serial number and a preset business attribute; A rule acquisition unit, used to acquire a preset coding rule to which each of the serial numbers belongs; a set division unit, dividing the cash circulation data into a plurality of storage data sets according to the preset business attributes and the preset coding rules to which the serial number belongs, each of the storage data sets having the same preset coding rules and the same preset business attributes to which the serial number belongs, and including cash circulation data having the same preset coding rules and the same preset business attributes to which the serial number belongs; A data storage unit, used for storing target information of any cash circulation data of each of the stored data sets, wherein the target information includes a preset business attribute of the any cash circulation data and a preset coding rule to which the prefix number of the any cash circulation data belongs; The model building unit is used for, before obtaining the preset coding rule to which each of the serial numbers belongs: Constructing a preset rule library, the preset rule library including a correspondence between a plurality of preset coding rules and preset rule levels of the preset coding rules; A neural network model is trained according to preset sample data to obtain a classification model, wherein the classification model is used to output a preset coding rule to which a serial number as input data belongs, wherein the preset sample data includes: a historical serial number as input sample data, and an optimal coding rule to which the historical serial number belongs as target output data; the optimal coding rule is a preset coding rule in the preset rule library that meets preset conditions, wherein the preset conditions include: the corresponding preset rule has the highest level; The preset sample data also includes: a preset capacity as input sample data; The preset condition also includes: the number of optimal encoding rules included in the target output data is less than a preset number threshold, and the difference with the preset number threshold is less than a preset difference threshold, and the preset number threshold is a maximum storage number determined according to the preset capacity; The obtaining of the preset coding rule to which each of the serial numbers belongs includes: The serial number is input into the classification model, and the output of the classification model is used as the preset coding rule to which the serial number belongs.
5. A data processing device, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the data processing method according to any one of claims 1 to 3.
6. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the data processing method according to any one of claims 1 to 3 is implemented.
