A method, device and medium for bank data scheduling

Abstract

The application discloses a bank data scheduling method, device and medium, the method comprises the following steps: a data platform determines original data obtained in advance by a third-party institution with corresponding qualifications; a pre-stored preprocessing instruction is obtained through a rule configuration module, and first data related to the preprocessing instruction is obtained from the original data according to the preprocessing instruction; the first data is preprocessed through the preprocessing instruction, and second data after preprocessing is obtained; a bank service instruction sent by a bank is received, and third data required is determined according to the bank service instruction; and bank service data corresponding to the bank service instruction is obtained through a pre-trained analysis model and the third data. The following beneficial effects can be brought: the bank can obtain required service data in time and accurately, data confusion and data failure are avoided, the efficiency of bank data management is improved, and the risk of service handling is reduced.

Description

Technical Field

[0001] This application relates to the field of data scheduling, specifically to a method, device, and medium for bank data scheduling. Background Technology

[0002] As the socio-economic level continues to grow, the types of business that banks are involved in are constantly increasing, and their systems are continuously expanding, resulting in increasingly complex platform architectures. Within these systems, disordered data organization and information silos are common problems.

[0003] Furthermore, with the establishment of various types of online banking such as mobile banking, WeChat banking, and online banking, the methods of big data processing in banking systems have gradually become outdated. Timely data is constantly being lost, and important data is difficult to retrieve in a timely manner. As a result, banking systems are experiencing problems that urgently need to be addressed, such as long business processing times and inaccurate business data evaluation. Summary of the Invention

[0004] To address the aforementioned problems, namely the difficulty for banks to promptly retrieve important data, leading to excessively long processing times and inaccurate data evaluation, this application proposes a method, device, and medium for bank data scheduling, including:

[0005] In a first aspect, this application proposes a method for bank data scheduling, comprising: a data platform determining raw data pre-obtained through a qualified third-party institution; obtaining pre-stored preprocessing instructions through a rule configuration module, and obtaining first data related to the preprocessing instructions from the raw data according to the preprocessing instructions; preprocessing the first data according to the preprocessing instructions to obtain preprocessed second data; receiving a banking business instruction sent by a bank, and determining the required third data according to the banking business instruction; selecting a portion of the raw data that cannot be preprocessed by the pre-stored preprocessing instructions, and / or a portion of the second data, as the third data; and obtaining the banking business data corresponding to the banking business instruction through a pre-trained analysis model and the third data.

[0006] In one example, the number of banking business instructions is multiple; after receiving the banking business instructions sent by the bank and determining the required data according to the banking business instructions, the method further includes: establishing a resource consumption prediction model for any one of the multiple banking business instructions, the resource consumption model including multiple sub-models, the sub-models being used to reflect the computing resources occupied by any one of the indicators included in the banking business instructions; and allocating resources to the multiple banking business instructions according to a preset matching algorithm and the resource consumption prediction model.

[0007] In one example, resource allocation is performed on multiple banking business instructions according to a preset matching algorithm and the resource consumption estimation model. Specifically, this includes: for any one of the multiple banking business instructions, obtaining the expected time contained in the banking business instruction; according to the resource consumption estimation model corresponding to the banking business instruction, retrieving the computing resources corresponding to the resource consumption estimation model, and generating the estimated completion time of the banking business instruction; if the estimated time is greater than the expected time, then more computing resources are allocated for the banking business instruction.

[0008] In one example, after receiving a banking instruction from a bank and determining the required data based on the banking instruction, the method further includes: obtaining a similarity value between the banking instruction and the preprocessing instruction; if the similarity value is greater than a first preset threshold, increasing the weight ratio of the second data in the third data and decreasing the weight ratio of the original data in the third data; if the similarity value is not greater than the first preset threshold, decreasing the weight ratio of the second data in the third data and increasing the weight ratio of the original data in the third data.

[0009] In one example, if the similarity value is not greater than the first preset threshold, then after reducing the weight ratio of the second data in the third data and increasing the weight ratio of the original data in the third data, the method further includes: analyzing the banking business instruction through a pre-trained indicator analysis model, removing the marked special indicators contained in the banking business instruction, and obtaining the processed banking business instruction; obtaining the similarity value between the processed banking business instruction and the pre-processed instruction, and if the similarity value is not less than the first preset threshold, then adding the processed banking business instruction to the rule configuration module.

[0010] In one example, preprocessing the first data using the preprocessing instruction to obtain preprocessed second data specifically includes: acquiring multiple first indicators included in the preprocessing instruction; based on the first indicators, removing data in the second data whose correlation value with the first indicators is less than a second preset threshold to obtain removed second data; for any one of the removed second data, obtaining the difference between the data and a preset standard value; if the difference is greater than a third preset threshold, correcting the data to obtain corrected second data; and using the corrected second data as the preprocessed data.

[0011] In one example, the banking business data corresponding to the banking business instruction is obtained through a pre-trained analysis model and the third data. Specifically, this includes: acquiring multiple second indicators included in the banking business instruction; based on the second indicators and the analysis model, removing data in the third data whose correlation value with the second indicators is less than a fourth preset threshold to obtain the removed third data; for any one of the removed third data, obtaining the difference between the data and a preset standard value; if the difference is greater than a fifth preset threshold, correcting the data to obtain the corrected third data; and using the corrected third data as the banking business data.

[0012] In one example, before selecting a portion of the original data that cannot be preprocessed by the pre-stored preprocessing instructions, and / or a portion of the second data, as the third data, the method further includes: storing the original data and the second data in a database table, and establishing a global data index and / or a local data index for the database table.

[0013] On the other hand, this application proposes a bank data scheduling device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the following instructions: A data platform determines raw data pre-obtained through a qualified third-party institution; obtains pre-stored preprocessing instructions through a rule configuration module, and obtains first data related to the preprocessing instructions from the raw data according to the preprocessing instructions; preprocesses the first data according to the preprocessing instructions to obtain preprocessed second data; receives a banking business instruction sent by a bank, and determines the required third data according to the banking business instruction; selects a portion of the raw data that cannot be preprocessed by the pre-stored preprocessing instructions, and / or a portion of the second data, as the third data; and obtains the banking business data corresponding to the banking business instruction through a pre-trained analysis model and the third data.

[0014] On the other hand, this application proposes a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows: a data platform determines raw data obtained in advance through a qualified third-party institution; obtains pre-stored preprocessing instructions through a rule configuration module, and obtains first data related to the preprocessing instructions from the raw data according to the preprocessing instructions; preprocesses the first data according to the preprocessing instructions to obtain preprocessed second data; receives a banking business instruction sent by a bank, and determines the required third data according to the banking business instruction; selects a portion of the raw data that cannot be preprocessed by the pre-stored preprocessing instructions, and / or a portion of the second data, as the third data; and obtains banking business data corresponding to the banking business instruction through a pre-trained analysis model and the third data.

[0015] The bank data scheduling method, device, and medium proposed in this application can bring the following beneficial effects: it can help banks obtain the business data they need in a timely and accurate manner, avoid data chaos and data failure, improve the efficiency of bank data management, and reduce the risk of business processing. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 This is a flowchart illustrating a method for bank data scheduling in an embodiment of this application;

[0018] Figure 2 This is a schematic diagram illustrating the framework of a bank data scheduling method in an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of a bank data scheduling device according to an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The method for mobilizing bank data described in this application embodiment is stored in a corresponding system or server. Users can log in through a terminal to access the system or server, thereby enabling the bank to schedule data. The terminal can be a hardware device with corresponding functions, such as a smartphone, tablet, or personal computer. The terminal is pre-installed with a corresponding system or APP and can log in to the system or server where this bank data scheduling method is located.

[0022] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0023] like Figure 1 and Figure 2 As shown in the figure, this application provides a method for bank data scheduling, including:

[0024] S101. The data platform determines the original data obtained in advance through a qualified third-party organization.

[0025] Specifically, raw data is obtained from qualified third-party institutions through a pre-built data platform. These qualified third-party institutions can be relevant government platforms or other relevant platforms that can provide various data for banking business processing.

[0026] The data platform can acquire raw data from third-party institutions in real time, and can also perform real-time rule-based operations, storage, and analysis on the raw data. Furthermore, the data platform can integrate with the bank's internal general file transfer platform and unified scheduling platform to achieve real-time communication with the bank's systems.

[0027] It's important to note that the data platform can utilize the mature Akka microserver architecture combined with Docker container cloud technology as the foundational technical architecture for its stream computing and data service components. The Akka microserver architecture avoids lock conflicts on internal shared resources through a messaging mechanism, reducing thread resource requirements. Furthermore, the Akka microserver architecture enables rapid data failure recovery at all levels of the internal architecture, flexible packaging and deployment of overall functions and services, and the construction of a location-transparent cluster service system. In addition, a data platform built using the Akka microserver architecture can achieve elastic scaling, increasing its data processing capacity at any time, and allows for differentiated hardware resource configurations. Moreover, when designing the Akka microserver architecture using the Actor model, it's possible to implement a multi-level qualification supervision mechanism within the Akka microserver, build secure firewalls and sandboxes, achieve microsecond-level fault recovery speeds, support elastic deployment of multiple cluster deployment modes, transparent remote service access, and various configurable load balancing strategies.

[0028] S102. Obtain the pre-stored preprocessing instructions through the rule configuration module, and obtain the first data related to the preprocessing instructions from the original data according to the preprocessing instructions.

[0029] Specifically, pre-stored preprocessing instructions can be obtained through a pre-configured rule configuration module in the data platform. This module stores multiple preprocessing instructions, which refer to various banking business types. These instructions include, but are not limited to, personal loans, investment transactions, fund disbursements, fund settlements, fund guarantees, and fund custody. In this embodiment, personal loans are used as an example for explanation.

[0030] Preprocessing instructions can include multiple indicators. When the preprocessing instruction is for personal credit, these indicators include, but are not limited to, personal movable property status, personal immovable property status, and personal loan amount status. Furthermore, a rule configuration module can be built using a rule engine and a Streaming SQL engine. The built rule configuration module provides a visual rule configuration page and drag-and-drop indicator configuration. Business personnel can drag and drop multiple indicators from the pre-stored indicators on the rule configuration page to generate preprocessing instructions. When business personnel drag and drop multiple indicators through the rule configuration page, they can operate directly via touch screen, mouse clicks, or keyboard commands, without needing to perform further programming development. The built rule configuration module supports complex rule logic, supports elastic scaling, and the logic processing time based on streaming data—that is, the time for dragging and dropping multiple instructions—can be within 100ms, improving running speed and work efficiency.

[0031] Furthermore, first data related to the preprocessing instruction can be obtained from the raw data according to the preprocessing instruction. The first data includes, but is not limited to: the value of the individual's movable property, the value of the individual's immovable property, the purchase time of the movable and immovable property, the current amount of personal loans, and the current amount of loans of immediate family members.

[0032] S103. The first data is preprocessed using the preprocessing instructions to obtain the preprocessed second data.

[0033] Specifically, the first step is to obtain multiple first indicators contained in the preprocessing instructions. In this embodiment, the multiple first indicators can be set as: personal movable property status, personal immovable property status, and personal loan amount status. The first data can be set as: the value of all personal movable property, the value of all personal immovable property, the purchase time of movable and immovable property, the current personal loan amount, and the current loan amount of immediate family members.

[0034] Furthermore, based on the aforementioned first indicator, data in the second data whose correlation value with the first indicator is less than a second preset threshold can be removed to obtain the removed second data. In this embodiment, a pre-trained analysis model can be used to analyze the correlation value between the first indicator and the second data. This analysis model can be any existing neural network model, and no particular limitation is made here. In addition, the second preset threshold can be set according to the actual situation, and its specific value is not particularly limited here. In this embodiment, the correlation value between the current loan amount of immediate family members in the second data and the first indicator may be less than the second preset threshold, so this data can be removed to obtain the removed second data.

[0035] Furthermore, for any one of the removed second data points, the difference between that data and a preset standard value is obtained. If the difference is greater than a third preset threshold, the data is corrected to obtain corrected second data, which is then used as preprocessed data. In this embodiment, each data point has a corresponding preset standard value. This standard value is used to evaluate the authenticity of the data. If the difference between the data and the corresponding standard value is greater than the third preset threshold, it indicates that the authenticity of the data is low, and there may be data errors or false data. For such data, a preset correction algorithm can be used to correct the data to make it more authentic. It should be noted that the standard value corresponding to each data point can be set differently according to the actual situation, and its specific value is not specifically limited here. The correction algorithm can use any existing correction algorithm, and it is not specifically limited here either.

[0036] It should be noted that the data processing rules described above for preprocessing the second data are just one type of multiple processing rules, and these rules can be redesigned or modified according to actual circumstances. During the preprocessing of the second data, to address the variations in data processing rules caused by different types of second data and to reduce the workload of hard-coding stream computing components, the open-source Drools rule engine can be introduced. The Drools rule engine is fast, efficient, and has powerful rule conflict capabilities. It is also completely open-source, written in Java, and easy to use for development.

[0037] S104. Receive banking business instructions sent by the bank, and determine the required third data according to the banking business instructions.

[0038] Specifically, the system receives banking business instructions sent by the bank through a communication channel between the data platform and the bank, and determines the third-party data required for the banking business instruction based on the instruction. Banking business instructions include, but are not limited to, personal loans, investment transactions, fund disbursements, fund settlements, fund guarantees, and fund custody. In this embodiment, the example of setting a personal loan as the banking business instruction is used for explanation.

[0039] S105. Select a portion of the original data that cannot be preprocessed by the pre-stored preprocessing instructions, and / or a portion of the second data, as the third data.

[0040] Specifically, since the banking transaction instruction pertains to personal loans, and the data platform has already preprocessed the relevant data for personal loans, the indicators included in the banking transaction instruction may not be entirely the same as those included in the preprocessed instruction. Therefore, directly using the preprocessed data as the third set of data may result in incomplete data. Thus, it is possible to select data from the unprocessed raw data and / or from the second set of data, combining the two sets of data to form the third set of data.

[0041] Before selecting the third data, the original data and the second data storage value table can be created, and global and / or local indexes can be established for the data table. Specifically, standard SQL can be used directly through the JDBC driver to perform database table operations on the Hyperbase table, creating a data table that supports global and local indexes.

[0042] S106. Using the pre-trained analysis model and the third data, obtain the banking business data corresponding to the banking business instruction.

[0043] Specifically, the first step is to obtain multiple second indicators contained in the banking business instruction. In this embodiment, the multiple second indicators can be set as: personal movable property status, personal immovable property status, personal loan amount status, and immediate family member loan amount status. The third data can be set as: the value of personal movable property, the value of personal immovable property, the purchase time of movable and immovable property, the current personal loan amount, the current loan amount of immediate family members, and the value of movable and immovable property owned by immediate family members.

[0044] Furthermore, based on the aforementioned second indicator, data in the third data whose correlation value with the second indicator is less than a fourth preset threshold can be removed to obtain the removed third data. In this embodiment, a pre-trained analysis model can be used to analyze the correlation value between the second indicator and the third data. This analysis model can be any existing neural network model, and no further limitations are imposed here. Additionally, the fourth preset threshold can be set according to actual circumstances, and its specific value is not limited here. In this embodiment, the correlation value between the value of movable and immovable property owned by immediate family members in the third data and the second indicator may be less than the fourth preset threshold; therefore, this data can be removed to obtain the removed third data.

[0045] Furthermore, for any one of the removed third data items, the difference between that data and a preset standard value is obtained. If the difference is greater than a fifth preset threshold, the data is corrected to obtain corrected third data, which is then used as banking business data. In this embodiment, each data item has a preset standard value. This standard value is used to evaluate the authenticity of the data. If the difference between the data and the corresponding standard value is greater than the fifth preset threshold, it indicates that the authenticity of the data is low, and there may be data errors or false data. For such data, a preset correction algorithm can be used to correct the data to make it more authentic. It should be noted that the standard value corresponding to each data item can be set differently according to the actual situation, and its specific value is not specifically limited here. The correction algorithm can use any existing correction algorithm, and it is not specifically limited here either.

[0046] It should be noted that the data platform provides a Scala language interface for developing data mining and deep learning models, enabling distributed mining and model training of third-party data.

[0047] In one embodiment, if there are multiple banking instructions, after receiving the banking instructions sent by the bank and determining the required data based on the instructions, a resource consumption prediction model can be established for any one of the multiple banking instructions. This resource consumption prediction model includes multiple sub-models, which can be used to reflect the computing resources occupied by any indicator included in the banking instruction. Then, resources can be allocated to the multiple banking instructions according to a preset matching algorithm and the resource consumption prediction model.

[0048] Specifically, for any one of the banking business instructions, the expected time included in the banking business instruction can be obtained. It should be noted that this expected time is filled in by bank staff and represents the urgency of their data requirements. According to the resource consumption estimation model corresponding to the banking business instruction, the computing resources corresponding to the resource consumption estimation model are retrieved, and the estimated completion time of the banking business instruction is generated. The estimated completion time can be completed using any time estimation algorithm, and the specific algorithm is not specifically limited here. If the estimated time is greater than the above-mentioned expected time, more computing resources are retrieved for the banking business instruction to try to meet the expected time as much as possible.

[0049] It should be noted that for a stable system, the time for data processing to complete depends on the number of nodes and the average processing volume. In time priority control, according to the principle of maximum throughput rate, the priority will increase rapidly with time. However, for a system, if the proportion of the current banking business instruction occupying the system's computing resources is not considered, the time wasted by nodes will be relatively serious, resulting in uneven load. Therefore, the nodes processed each time can be combined with the path of the nodes occupied by the banking business instruction and the current load situation of the system, and the system's balanced load can be achieved through parameter control to ensure the processing time of each banking business instruction.

[0050] The load situation calculation model includes: when the time for the banking business instruction to completely consume the current node B+ tree + the time for the current node resource Hash queue to be completely consumed > the node Buffer update time, and the Buffer length < the maximum volume of the B+ tree + the Hash queue length, the system can ensure normal operation.

[0051] In one embodiment, after receiving the banking business instruction sent by the bank and determining the required data according to the banking business instruction, the similarity value between the banking business instruction and the preprocessing instruction can also be obtained. The similarity value can be analyzed and obtained using any neural network model. The comparison principle is to analyze the differences in the indicators included in the banking business instruction and the preprocessing instruction respectively. If the similarity value is greater than the first preset threshold, it means that the banking business instruction and the preprocessing instruction are similar enough. Then, the weight ratio of the above-mentioned second data occupying the third data is increased, and the weight ratio of the original data occupying the third data is decreased, which can improve the data processing time and save the computing resources of the system.

[0052] If the similarity value is not greater than the first preset threshold, it indicates a significant difference between the banking instruction and the preprocessed instruction. Therefore, the weight of the second data in the third data set is reduced, while the weight of the original data in the third data set is increased. This ensures improved data accuracy while maximizing the saving of system computing resources. Furthermore, a pre-trained indicator analysis model can be used to analyze the banking instructions. Based on the analysis results, it can be determined whether the banking instructions contain any marked special indicators. These special indicators can be marked by banking personnel, indicating that the indicator was added specifically for the particular nature of the business and does not reflect normal indicators for this type of business. For example, in personal loan instructions, banking personnel can add special indicators such as proof of electricity bills for the residence within the past three months. Due to the special nature of these indicators, they can be removed, resulting in the processed banking instruction.

[0053] Furthermore, the similarity value between the processed banking instruction and the preprocessed instruction is obtained. If the similarity value is still not less than the first preset threshold, it indicates that there is still a significant difference between the banking instruction that proposes the special indicator and the preprocessed instruction. In this case, the processed banking instruction can be added to the rule configuration module as a brand new preprocessed instruction.

[0054] In one embodiment, this application provides a device for bank data scheduling, such as... Figure 3 As shown, it includes:

[0055] At least one processor; and,

[0056] A memory communicatively connected to the at least one processor; wherein,

[0057] The memory stores instructions that can be executed by the at least one processor, and the instructions, when executed by the at least one processor, enable the at least one processor to execute the following instructions:

[0058] The data platform determines the raw data obtained in advance through qualified third-party institutions;

[0059] The pre-stored preprocessing instructions are obtained through the rule configuration module, and the first data related to the preprocessing instructions is obtained from the original data according to the preprocessing instructions.

[0060] The first data is preprocessed using the preprocessing instructions to obtain the preprocessed second data;

[0061] Receive banking instructions from the bank and determine the required third data based on the banking instructions;

[0062] Select a portion of the original data that cannot be preprocessed using the pre-stored preprocessing instructions, and / or a portion of the second data, as the third data;

[0063] The banking business data corresponding to the banking business instruction is obtained through the pre-trained analysis model and the third data.

[0064] In one embodiment, this application provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0065] The data platform determines the raw data obtained in advance through qualified third-party institutions;

[0066] The pre-stored preprocessing instructions are obtained through the rule configuration module, and the first data related to the preprocessing instructions is obtained from the original data according to the preprocessing instructions.

[0067] The first data is preprocessed using the preprocessing instructions to obtain the preprocessed second data;

[0068] Receive banking instructions from the bank and determine the required third data based on the banking instructions;

[0069] Select a portion of the original data that cannot be preprocessed using the pre-stored preprocessing instructions, and / or a portion of the second data, as the third data;

[0070] The banking business data corresponding to the banking business instruction is obtained through the pre-trained analysis model and the third data.

[0071] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0072] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0073] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0075] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0076] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0079] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0081] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for bank data scheduling, characterized in that, include: The data platform determines the raw data obtained in advance through qualified third-party institutions; The pre-stored preprocessing instructions are obtained through the rule configuration module, and the first data related to the preprocessing instructions is obtained from the original data according to the preprocessing instructions. The first data is preprocessed using the preprocessing instructions to obtain the preprocessed second data; Receive banking instructions from the bank and determine the required third data based on the banking instructions; Select a portion of the original data and a portion of the second data that cannot be preprocessed using the pre-stored preprocessing instructions, and use them as the third data; The banking business data corresponding to the banking business instruction is obtained through the pre-trained analysis model and the third data. After receiving a banking instruction from a bank and determining the required data based on the banking instruction, the method further includes: Obtain the similarity value between the banking transaction instruction and the preprocessing instruction; If the similarity value is greater than a first preset threshold, then the weight ratio of the second data in the third data is increased, and the weight ratio of the original data in the third data is decreased. If the similarity value is not greater than the first preset threshold, then the weight ratio of the second data in the third data is reduced, and the weight ratio of the original data in the third data is increased.

2. The method for bank data scheduling according to claim 1, characterized in that, The number of banking business instructions is multiple; After receiving a banking instruction from a bank and determining the required data based on the banking instruction, the method further includes: A resource consumption prediction model is established for any one of the multiple banking business instructions. The resource consumption model includes multiple sub-models, which are used to reflect the computing resources occupied by any one of the indicators contained in the banking business instruction. Based on the preset matching algorithm and the resource consumption prediction model, resources are allocated to multiple banking business instructions.

3. The method for bank data scheduling according to claim 2, characterized in that, Based on a preset matching algorithm and the resource consumption prediction model, resources are allocated to multiple banking business instructions, specifically including: For any one of the multiple banking business instructions, obtain the expected time contained in that banking business instruction; Based on the resource consumption estimation model corresponding to the banking business instruction, the computing resources corresponding to the resource consumption estimation model are retrieved, and the estimated completion time of the banking business instruction is generated. If the estimated completion time is longer than the expected time, then more computing resources will be allocated for the banking business instruction.

4. The method for bank data scheduling according to claim 1, characterized in that, If the similarity value is not greater than the first preset threshold, then after reducing the weight ratio of the second data in the third data and increasing the weight ratio of the original data in the third data, the method further includes: The banking business instruction is analyzed by a pre-trained indicator analysis model, and special indicators with tags are removed from the banking business instruction to obtain the processed banking business instruction. Obtain the similarity value between the processed banking instruction and the preprocessed instruction. If the similarity value is not less than the first preset threshold, add the processed banking instruction to the rule configuration module.

5. The method for bank data scheduling according to claim 1, characterized in that, The first data is preprocessed using the preprocessing instructions to obtain the preprocessed second data, specifically including: Obtain multiple first indicators contained in the preprocessing instructions; Based on the first indicator, data in the second data whose correlation value with the first indicator is less than the second preset threshold are removed to obtain the removed second data. For any one of the second data after the removal, the difference between the data and the preset standard value is obtained. If the difference is greater than the third preset threshold, the data is corrected to obtain the corrected second data. The corrected second data is used as the preprocessed data.

6. The method for bank data scheduling according to claim 1, characterized in that, Using a pre-trained analysis model and the third data, the banking business data corresponding to the banking business instruction is obtained, specifically including: Obtain multiple second indicators contained in the banking business instruction; Based on the second indicator and the analysis model, data in the third data whose correlation value with the second indicator is less than the fourth preset threshold are removed to obtain the removed third data. For any one of the removed third data, the difference between the data and the preset standard value is obtained. If the difference is greater than the fifth preset threshold, the data is corrected to obtain the corrected third data. The revised third data will be used as banking business data.

7. The method for bank data scheduling according to claim 1, characterized in that, Before selecting a portion of the original data and a portion of the second data that cannot be preprocessed using the pre-stored preprocessing instructions as the third data, the method further includes: The original data and the second data are stored in a database table, and a global index and / or a local index are created for the database table.

8. A device for bank data scheduling, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the following instructions: The data platform determines the raw data obtained in advance through qualified third-party institutions; The pre-stored preprocessing instructions are obtained through the rule configuration module, and the first data related to the preprocessing instructions is obtained from the original data according to the preprocessing instructions. The first data is preprocessed using the preprocessing instructions to obtain the preprocessed second data; Receive banking instructions from the bank and determine the required third data based on the banking instructions; Select a portion of the original data and a portion of the second data that cannot be preprocessed using the pre-stored preprocessing instructions, and use them as the third data; The banking business data corresponding to the banking business instruction is obtained through the pre-trained analysis model and the third data. After receiving a banking service instruction from the bank and determining the required data based on the instruction, the process also includes: Obtain the similarity value between the banking transaction instruction and the preprocessing instruction; If the similarity value is greater than a first preset threshold, then the weight ratio of the second data in the third data is increased, and the weight ratio of the original data in the third data is decreased. If the similarity value is not greater than the first preset threshold, then the weight ratio of the second data in the third data is reduced, and the weight ratio of the original data in the third data is increased.

9. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: The data platform determines the raw data obtained in advance through qualified third-party institutions; The pre-stored preprocessing instructions are obtained through the rule configuration module, and the first data related to the preprocessing instructions is obtained from the original data according to the preprocessing instructions. The first data is preprocessed using the preprocessing instructions to obtain the preprocessed second data; Receive banking instructions from the bank and determine the required third data based on the banking instructions; Select a portion of the original data and a portion of the second data that cannot be preprocessed using the pre-stored preprocessing instructions, and use them as the third data; The banking business data corresponding to the banking business instruction is obtained through the pre-trained analysis model and the third data. After receiving a banking service instruction from the bank and determining the required data based on the instruction, the process also includes: Obtain the similarity value between the banking transaction instruction and the preprocessing instruction; If the similarity value is greater than a first preset threshold, then the weight ratio of the second data in the third data is increased, and the weight ratio of the original data in the third data is decreased. If the similarity value is not greater than the first preset threshold, then the weight ratio of the second data in the third data is reduced, and the weight ratio of the original data in the third data is increased.

Images