A banking information intelligent management method and system based on big data

Abstract

The present invention relates to a bank informationization intelligent management method and system based on big data, belonging to the technical field of bank informationization management. The present invention constructs an information release prediction model according to the maximum information release of the bank informationization management platform, thereby predicting the maximum information release of the bank informationization management platform within a unit time in the current timestamp through the information release prediction model, and finally obtains the storage data to be released according to the data storage analysis result, and formulates a data release strategy according to the maximum information release of the bank informationization management platform within a unit time in the current timestamp and the storage data to be released. The present invention fully considers whether the data storage status of the bank informationization management platform reaches a predetermined standard. When the predetermined standard is reached, the data storage capacity of the bank informationization management platform is released by setting the optimal maximum information release amount, thereby reducing the jamming phenomenon of the bank informationization management platform.

Description

Technical Field

[0001] The present invention relates to the technical field of bank information management, and in particular to a bank information intelligent management method and system based on big data. Background Art

[0002] In the past, the bank's intelligent operation management information system adopted the traditional manual management method, which often took a lot of time to deal with massive data. Big data processing technology has been maturely applied to the operation management information system. The current mature technical framework includes Teradata's dynamic enterprise data warehouse Active EDW, which mainly focuses on the underlying data storage and data processing level; IBM's banking system management solution relies on the SPSClementine data mining platform and Cognos Analytics data visualization analysis tools to develop a data management model. However, as the customer's data increases, the bank's information management platform will cause the data storage volume to continue to increase after a certain period of use, and many data will become useless data after a certain period of time. After the data is released, the platform data will be updated through data synchronization. However, the existing technology does not consider the impact of network fluctuations on data deletion or data release, which leads to the freezing of the bank's information management platform during the deletion or release of data. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method and system for intelligent management of bank informatization based on big data.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a bank information intelligent management method based on big data, comprising the following steps:

[0006] Obtaining data on the amount of data stored on the bank's information management platform, and obtaining data storage analysis results by identifying and analyzing the data on the amount of data stored on the bank's information management platform;

[0007] Obtain the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data through big data, and build an information release amount prediction model according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data;

[0008] Predicting the maximum information release amount of the bank information management platform within a unit time at the current timestamp by using the information release amount prediction model;

[0009] The storage data to be released is obtained according to the data storage volume analysis result, and a data release strategy is formulated according to the maximum information release volume of the bank information management platform within a unit time in the current timestamp and the storage data to be released.

[0010] Furthermore, in this method, the data storage volume data of the bank information management platform is obtained, and the data storage volume analysis results are obtained by identifying and analyzing the data storage volume data of the bank information management platform, which specifically includes:

[0011] Obtaining data on the data storage volume of the bank information management platform, and setting a data storage volume data threshold, and determining whether the data storage volume data of the bank information management platform is greater than the data storage volume data threshold;

[0012] When the data storage capacity of the bank information management platform is greater than the data storage capacity threshold, the current data storage capacity state of the bank information management platform is regarded as an over storage capacity state;

[0013] When the data storage capacity data of the bank information management platform is not greater than the data storage capacity data threshold, the current data storage capacity state of the bank information management platform is regarded as the normal storage capacity state;

[0014] An excess storage state is generated according to the excess storage state or the normal storage state, and the excess storage state is output.

[0015] Furthermore, in this method, the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data is obtained through big data, and an information release amount prediction model is constructed according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data, specifically:

[0016] Obtain the maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data through big data, and input the maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data into the graph neural network;

[0017] The network fluctuation data is used as the first graph node of the graph neural network, and the maximum information release amount of the bank information management platform within a unit time is used as the second graph node to construct a directed description relationship;

[0018] Connecting the first graph node and the second graph node based on the directed description relationship to form a topological structure graph, acquiring a related adjacency matrix based on the topological structure graph, and constructing an information release amount prediction model based on a deep neural network;

[0019] The relevant adjacency matrix is ​​input into the information release amount prediction model, and when the loss function of the information release amount prediction model converges to a preset value, the model parameters of the information release amount prediction model are saved.

[0020] Furthermore, in this method, the maximum information release amount of the bank information management platform within a unit time at the current timestamp is predicted by the information release amount prediction model, specifically:

[0021] Acquire network fluctuation data of the current timestamp, and input the network fluctuation data of the current timestamp into the information release amount prediction model for prediction;

[0022] Through prediction, the maximum information release amount of the bank information management platform within a unit time in the current timestamp is obtained, and the maximum information release amount of the bank information management platform within a unit time in the current timestamp is output.

[0023] Furthermore, in this method, the storage data to be released is obtained according to the data storage amount analysis result, specifically:

[0024] When the data storage capacity analysis result is an overstorage state, the storage time limit data of each stored data in the bank information management platform is obtained, and a storage time limit data threshold is set;

[0025] When the storage time limit data is greater than the storage time limit data threshold, the storage data corresponding to the storage time limit data being greater than the storage time limit data threshold is taken as the storage data to be released, and the storage data to be released is output.

[0026] Furthermore, in this method, a data release strategy is formulated according to the maximum information release amount of the bank information management platform within a unit time in the current timestamp and the stored data to be released, specifically:

[0027] Acquire the storage data to be released in the current timestamp, and determine whether the storage data to be released in the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp;

[0028] When the stored data to be released in the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, the maximum information release amount of the bank information management platform within a unit time in the current timestamp is generated into a first release strategy;

[0029] When the storage data to be released in the current timestamp is not greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, a second release strategy is generated for the storage amount corresponding to the storage data to be released in the current timestamp;

[0030] A data release policy is generated based on the first release policy or the second release policy, and the stored data on the bank information management platform is released according to the data release policy.

[0031] The second aspect of the present invention provides a bank informatization intelligent management system based on big data, including a memory and a processor, wherein the memory includes a bank informatization intelligent management method program based on big data, and when the bank informatization intelligent management method program based on big data is executed by the processor, any step of the bank informatization intelligent management method based on big data is implemented.

[0032] The third aspect of the present invention provides a computer-readable storage medium, characterized in that it includes a program for an intelligent management method for bank informatization based on big data. When the program for an intelligent management method for bank informatization based on big data is executed by a processor, it implements any step of the intelligent management method for bank informatization based on big data.

[0033] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0034] The present invention obtains the data storage capacity data of the bank information management platform, identifies and analyzes the data storage capacity data of the bank information management platform, obtains the data storage capacity analysis results, and then obtains the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data through big data, and constructs an information release amount prediction model according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data, so as to predict the maximum information release amount of the bank information management platform within a unit time in the current timestamp through the information release amount prediction model, and finally obtains the storage data to be released according to the data storage capacity analysis results, and formulates a data release strategy according to the maximum information release amount of the bank information management platform within a unit time in the current timestamp and the storage data to be released. The present invention fully considers whether the data storage state of the bank information management platform reaches the predetermined standard. When the predetermined standard is reached, the data storage capacity of the bank information management platform is released by setting the optimal maximum information release amount, thereby reducing the jamming phenomenon of the bank information management platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention 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 invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0036] Figure 1 The overall flow chart of the bank information intelligent management method based on big data is shown;

[0037] Figure 2 A partial flow chart of the bank information intelligent management method based on big data is shown;

[0038] Figure 3 The system block diagram of the bank information intelligent management system based on big data is shown. DETAILED DESCRIPTION

[0039] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0041] like Figure 1 As shown, the first aspect of the present invention provides a bank information intelligent management method based on big data, comprising the following steps:

[0042] S102: Obtaining data on the data storage volume of the bank's information management platform, and obtaining data storage volume analysis results by identifying and analyzing the data storage volume data of the bank's information management platform;

[0043] S104: obtaining the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data through big data, and constructing an information release amount prediction model according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data;

[0044] S106: Predicting the maximum information release amount of the bank information management platform within a unit time at the current timestamp through the information release amount prediction model;

[0045] S108: Obtain the storage data to be released according to the data storage volume analysis result, and formulate a data release strategy according to the maximum information release volume of the bank information management platform within a unit time at the current timestamp and the storage data to be released.

[0046] It should be noted that the present invention fully considers whether the data storage status of the bank information management platform reaches the predetermined standard. When the predetermined standard is reached, the data storage capacity of the bank information management platform is released by setting the optimal maximum information release amount, thereby reducing the jamming phenomenon of the bank information management platform.

[0047] Furthermore, in this method, the data storage volume data of the bank information management platform is obtained, and the data storage volume data of the bank information management platform is identified and analyzed to obtain the data storage volume analysis results, which specifically include:

[0048] Obtain data on the data storage volume of the bank's information management platform, set a data storage volume data threshold, and determine whether the data storage volume data of the bank's information management platform is greater than the data storage volume data threshold;

[0049] When the data storage capacity of the bank information management platform is greater than the data storage capacity threshold, the current data storage capacity state of the bank information management platform is regarded as an over storage capacity state;

[0050] When the data storage capacity of the bank information management platform is not greater than the data storage capacity threshold, the current data storage capacity state of the bank information management platform is regarded as the normal storage capacity state;

[0051] An excess storage state is generated according to the excess storage state or the normal storage state, and the excess storage state is output.

[0052] It should be noted that this method is used to obtain the data storage status of the bank information management platform. The over-storage status refers to the storage data exceeding the predetermined quantity and size. The storage data includes the user's consumption information, basic information, loan information and other data.

[0053] like Figure 2 As shown, further, in this method, the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data is obtained through big data, and an information release amount prediction model is constructed according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data, specifically:

[0054] S202: obtaining the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data through big data, and inputting the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data into the graph neural network;

[0055] S204: Using the network fluctuation data as the first graph node of the graph neural network and the maximum information release amount of the bank information management platform within a unit time as the second graph node to construct a directed description relationship;

[0056] S206: Connecting the first graph node and the second graph node based on the directed description relationship to form a topological structure graph, obtaining a related adjacency matrix based on the topological structure graph, and constructing an information release amount prediction model based on a deep neural network;

[0057] S208: Input the relevant adjacency matrix into the information release prediction model, and when the loss function of the information release prediction model converges to a preset value, save the model parameters of the information release prediction model.

[0058] It should be noted that since the bank's information management platform is usually a network platform, and secondly due to the influence of network fluctuation data (such as network delay, bit error rate, etc.), the bank's information management platform will have a maximum amount of information released per unit time. This method can be used to construct an information release prediction model to predict the maximum amount of information released under different network fluctuation data (such as 500MB of data that can be released within 1 second).

[0059] Furthermore, in this method, the maximum information release amount of the bank information management platform within a unit time at the current timestamp is predicted by the information release amount prediction model, specifically:

[0060] Obtaining network fluctuation data of the current timestamp, and inputting the network fluctuation data of the current timestamp into the information release amount prediction model for prediction;

[0061] Through prediction, the maximum amount of information released by the bank's information management platform within a unit time at the current timestamp is obtained, and the maximum amount of information released by the bank's information management platform within a unit time at the current timestamp is output.

[0062] Furthermore, in this method, the storage data to be released is obtained according to the data storage amount analysis result, specifically:

[0063] When the data storage capacity analysis result is an overstorage state, the storage time limit data of each stored data in the bank information management platform is obtained, and the storage time limit data threshold is set;

[0064] When the storage time limit data is greater than the storage time limit data threshold, the storage data corresponding to the storage time limit data being greater than the storage time limit data threshold is taken as the storage data to be released, and the storage data to be released is output.

[0065] Furthermore, in this method, a data release strategy is formulated according to the maximum amount of information released by the bank information management platform within a unit time in the current timestamp and the stored data to be released, specifically:

[0066] Obtain the storage data to be released at the current timestamp, and determine whether the storage data to be released at the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time at the current timestamp;

[0067] When the stored data to be released in the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, the maximum information release amount of the bank information management platform within a unit time in the current timestamp is generated into a first release strategy;

[0068] When the storage data to be released in the current timestamp is not greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, a second release strategy is generated for the storage amount corresponding to the storage data to be released in the current timestamp;

[0069] A data release policy is generated based on the first release policy or the second release policy, and the stored data on the bank information management platform is released according to the data release policy.

[0070] It should be noted that this method can release the stored data of the bank information management platform, so that the storage capacity of the bank information management platform is kept within a predetermined standard range, avoiding the lag of the bank information management platform.

[0071] In addition, the method may further include:

[0072] Obtain the maximum information storage capacity of the bank's information management platform and the storage capacity corresponding to the storage data whose storage time limit data is not greater than the storage time limit data threshold;

[0073] Determine whether the storage capacity corresponding to the storage data whose storage time limit data is not greater than the storage time limit data threshold is greater than the maximum information storage capacity of the bank information management platform;

[0074] If the storage time limit data is not greater than the storage time limit data threshold and the storage capacity corresponding to the storage data is not greater than the maximum information storage capacity of the bank information management platform, then a normal storage state is output;

[0075] If the storage capacity corresponding to the storage data whose storage time limit data is not greater than the storage time limit data threshold is greater than the maximum information storage capacity of the bank information management platform, the maximum information storage capacity of the bank information management platform is expanded.

[0076] It should be noted that this method can further improve the rationality of the management of the bank's information management platform.

[0077] Additionally, it includes:

[0078] Acquire the increased data storage volume of the bank information management platform within a preset time, and build a data storage volume prediction model based on LSTM, and input the increased data storage volume of the bank information management platform within the preset time into the data storage volume prediction model for training;

[0079] Through training, a trained data storage volume prediction model is obtained, and the data storage volume preference characteristics increased by the bank information management platform within a preset time are obtained through the trained data storage volume prediction model;

[0080] Initialize the storage capacity that needs to be expanded according to the preference characteristics of the increased data storage capacity of the bank information management platform within the preset time, and calculate the total storage capacity after expansion according to the storage capacity that needs to be expanded;

[0081] Obtain the data storage capacity of the bank information management platform at the current timestamp, and obtain the predicted total storage capacity according to the data storage capacity preference characteristics increased by the bank information management platform within the preset time and the data storage capacity of the bank information management platform at the current timestamp;

[0082] When the predicted total storage capacity is greater than the total storage capacity after expansion, the storage capacity to be expanded is readjusted until the predicted total storage capacity is no greater than the total storage capacity after expansion.

[0083] It should be noted that by predicting the preference characteristics of the increased data storage volume of the bank's information management platform within a preset time, the bank's information management platform can be expanded and optimized to improve the rationality of management.

[0084] like Figure 3 As shown, the second aspect of the present invention provides a bank informationization intelligent management system 4 based on big data, including a memory 41 and a processor 42, wherein the memory includes a bank informationization intelligent management method program based on big data, and when the bank informationization intelligent management method program based on big data is executed by the processor 42, the following steps are implemented:

[0085] Obtain data on the data storage volume of the bank's information management platform, and obtain data storage volume analysis results by identifying and analyzing the data storage volume data of the bank's information management platform;

[0086] The maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data is obtained through big data, and an information release prediction model is constructed based on the maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data;

[0087] The maximum information release amount of the bank information management platform within a unit time at the current timestamp is predicted through the information release amount prediction model;

[0088] The storage data to be released is obtained according to the data storage volume analysis results, and a data release strategy is formulated according to the maximum information release volume of the bank's information management platform within a unit time at the current timestamp and the storage data to be released.

[0089] Furthermore, in this system, the data storage volume data of the bank information management platform is obtained, and the data storage volume data of the bank information management platform is identified and analyzed to obtain the data storage volume analysis results, which specifically include:

[0090] Obtain data on the data storage volume of the bank's information management platform, set a data storage volume data threshold, and determine whether the data storage volume data of the bank's information management platform is greater than the data storage volume data threshold;

[0091] When the data storage capacity of the bank information management platform is greater than the data storage capacity threshold, the current data storage capacity state of the bank information management platform is regarded as an over storage capacity state;

[0092] When the data storage capacity of the bank information management platform is not greater than the data storage capacity threshold, the current data storage capacity state of the bank information management platform is regarded as the normal storage capacity state;

[0093] An excess storage state is generated according to the excess storage state or the normal storage state, and the excess storage state is output.

[0094] Furthermore, in this system, the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data is obtained through big data, and an information release amount prediction model is constructed according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data, specifically:

[0095] The maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data is obtained through big data, and the maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data is input into the graph neural network;

[0096] The network fluctuation data is used as the first graph node of the graph neural network, and the maximum information release of the bank's information management platform within a unit time is used as the second graph node to construct a directed description relationship.

[0097] Connecting the first graph node and the second graph node based on the directed description relationship to form a topological structure graph, obtaining a related adjacency matrix based on the topological structure graph, and building an information release prediction model based on a deep neural network;

[0098] The relevant adjacency matrix is ​​input into the information release prediction model. When the loss function of the information release prediction model converges to a preset value, the model parameters of the information release prediction model are saved.

[0099] Furthermore, in this system, the maximum information release amount of the bank information management platform within a unit time at the current timestamp is predicted by the information release amount prediction model, specifically:

[0100] Obtaining network fluctuation data of the current timestamp, and inputting the network fluctuation data of the current timestamp into the information release amount prediction model for prediction;

[0101] Through prediction, the maximum amount of information released by the bank's information management platform within a unit time at the current timestamp is obtained, and the maximum amount of information released by the bank's information management platform within a unit time at the current timestamp is output.

[0102] Furthermore, in this system, the storage data to be released is obtained according to the data storage amount analysis result, specifically:

[0103] When the data storage capacity analysis result is an overstorage state, the storage time limit data of each stored data in the bank information management platform is obtained, and the storage time limit data threshold is set;

[0104] When the storage time limit data is greater than the storage time limit data threshold, the storage data corresponding to the storage time limit data being greater than the storage time limit data threshold is taken as the storage data to be released, and the storage data to be released is output.

[0105] Furthermore, in this system, a data release strategy is formulated according to the maximum amount of information released by the bank information management platform within a unit time in the current timestamp and the stored data to be released, specifically:

[0106] Obtain the storage data to be released at the current timestamp, and determine whether the storage data to be released at the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time at the current timestamp;

[0107] When the stored data to be released in the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, the maximum information release amount of the bank information management platform within a unit time in the current timestamp is generated into a first release strategy;

[0108] When the storage data to be released in the current timestamp is not greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, a second release strategy is generated for the storage amount corresponding to the storage data to be released in the current timestamp;

[0109] A data release policy is generated based on the first release policy or the second release policy, and the stored data on the bank information management platform is released according to the data release policy.

[0110] The third aspect of the present invention provides a computer-readable storage medium, characterized in that it includes a program for an intelligent management method for bank informatization based on big data. When the program for an intelligent management method for bank informatization based on big data is executed by a processor, it implements any step of the intelligent management method for bank informatization based on big data.

[0111] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0112] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0113] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0114] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0115] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0116] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A bank information intelligent management method based on big data, characterized in that: The following steps are involved: Obtaining data on the amount of data stored on the bank's information management platform, and obtaining data storage analysis results by identifying and analyzing the data on the amount of data stored on the bank's information management platform; Obtain the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data through big data, and build an information release amount prediction model according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data; Predicting the maximum information release amount of the bank information management platform within a unit time at the current timestamp by using the information release amount prediction model; Acquire the storage data to be released according to the data storage volume analysis result, and formulate a data release strategy according to the maximum information release volume of the bank information management platform within a unit time at the current timestamp and the storage data to be released; Also includes: Obtain the increased data storage volume of the bank information management platform within a preset time, and build a data storage volume prediction model based on LSTM, and input the increased data storage volume of the bank information management platform within the preset time into the data storage volume prediction model for training; Through training, a trained data storage volume prediction model is obtained, and the data storage volume preference characteristics increased by the bank information management platform within a preset time are obtained through the trained data storage volume prediction model; Initialize the storage capacity that needs to be expanded according to the data storage capacity preference characteristics increased by the bank information management platform within the preset time, and calculate the total storage capacity after expansion according to the storage capacity that needs to be expanded; Obtain the data storage capacity of the bank information management platform at the current timestamp, and obtain the predicted total storage capacity according to the data storage capacity preference characteristics increased by the bank information management platform within the preset time and the data storage capacity of the bank information management platform at the current timestamp; When the predicted total storage capacity is greater than the total storage capacity after expansion, the storage capacity to be expanded is readjusted until the predicted total storage capacity is no greater than the total storage capacity after expansion.

2. According to the big data-based bank information intelligent management method of claim 1, it is characterized in that: Obtaining data on the amount of data stored on the bank's information management platform, and obtaining data storage analysis results by identifying and analyzing the data on the amount of data stored on the bank's information management platform, specifically including: Obtaining data on the data storage volume of the bank information management platform, and setting a data storage volume data threshold, and determining whether the data storage volume data of the bank information management platform is greater than the data storage volume data threshold; When the data storage capacity of the bank information management platform is greater than the data storage capacity threshold, the current data storage capacity state of the bank information management platform is regarded as an over storage capacity state; When the data storage capacity data of the bank information management platform is not greater than the data storage capacity data threshold, the current data storage capacity state of the bank information management platform is regarded as the normal storage capacity state; An excess storage state is generated according to the excess storage state or the normal storage state, and the excess storage state is output.

3. According to the big data-based bank information intelligent management method of claim 1, it is characterized in that: The maximum information release amount of the bank information management platform within a unit time under each network fluctuation data is obtained through big data, and an information release amount prediction model is constructed according to the maximum information release amount of the bank information management platform within a unit time under each network fluctuation data, specifically: Obtain the maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data through big data, and input the maximum amount of information released by the bank information management platform within a unit time under each network fluctuation data into the graph neural network; The network fluctuation data is used as the first graph node of the graph neural network, and the maximum information release amount of the bank information management platform within a unit time is used as the second graph node to construct a directed description relationship; Connecting the first graph node and the second graph node based on the directed description relationship to form a topological structure graph, acquiring a related adjacency matrix based on the topological structure graph, and constructing an information release amount prediction model based on a deep neural network; The relevant adjacency matrix is ​​input into the information release amount prediction model, and when the loss function of the information release amount prediction model converges to a preset value, the model parameters of the information release amount prediction model are saved.

4. The method for intelligent management of bank informationization based on big data according to claim 1 is characterized in that: The maximum information release amount of the bank information management platform within a unit time at the current timestamp is predicted by the information release amount prediction model, specifically: Acquire network fluctuation data of the current timestamp, and input the network fluctuation data of the current timestamp into the information release amount prediction model for prediction; Through prediction, the maximum information release amount of the bank information management platform within a unit time in the current timestamp is obtained, and the maximum information release amount of the bank information management platform within a unit time in the current timestamp is output.

5. The method for intelligent management of bank informationization based on big data according to claim 1 is characterized in that: Acquiring the storage data to be released according to the data storage amount analysis result is specifically as follows: When the data storage capacity analysis result is an overstorage state, the storage time limit data of each stored data in the bank information management platform is obtained, and a storage time limit data threshold is set; When the storage time limit data is greater than the storage time limit data threshold, the storage data corresponding to the storage time limit data being greater than the storage time limit data threshold is taken as the storage data to be released, and the storage data to be released is output.

6. The method for intelligent management of bank informationization based on big data according to claim 1 is characterized in that: A data release strategy is formulated according to the maximum amount of information released by the bank information management platform within a unit time in the current timestamp and the stored data to be released, specifically: Acquire the stored data to be released in the current timestamp, and determine whether the stored data to be released in the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp; When the stored data to be released in the current timestamp is greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, the maximum information release amount of the bank information management platform within a unit time in the current timestamp is generated into a first release strategy; When the storage data to be released in the current timestamp is not greater than the maximum information release amount of the bank information management platform within a unit time in the current timestamp, a second release strategy is generated for the storage amount corresponding to the storage data to be released in the current timestamp; A data release policy is generated based on the first release policy or the second release policy, and the stored data on the bank information management platform is released according to the data release policy.

7. A bank information intelligent management system based on big data, characterized in that: It comprises a memory and a processor, wherein the memory comprises a program of an intelligent management method for bank informatization based on big data, and when the program of the intelligent management method for bank informatization based on big data is executed by the processor, the steps of the intelligent management method for bank informatization based on big data as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: It comprises a program of a bank informationization intelligent management method based on big data, which, when executed by a processor, implements the steps of the bank informationization intelligent management method based on big data as described in any one of claims 1 to 6.

Images