Cash business processing method, device and system
By calling the scheduling model and cash prediction model on the backend server of the bank branch, the amount of cash in cash storage devices and tellers is reasonably dispatched, which solves the problems of cash security risks and low business efficiency, and realizes efficient cash business deal with.
Patent Information
- Application Number
- CN202110849291.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-07-27
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When bank branches handle cash business, cash safety risks are high and business processing efficiency is low. Cash storage equipment requirements are high. Tellers need to frequently operate cash storage equipment to increase labor intensity and may cause excessive or too little cash. .
By calling pre-built scheduling models on the backend server, the amount of cash at the cash storage device and the teller is reasonably dispatched, ensuring that the cash storage device and teller efficiently complete cash business processing, avoid frequent operation of the cash storage device, and pass the cash through The banknote prediction model predicts the cash demand for the next day and optimizes the initial configuration.
While ensuring the safety of cash in bank branches, it can improve the efficiency of cash business processing, reduce the frequency of tellers' operation, avoid excessive or too little cash, and improve business processing efficiency.
Smart Images

Figure CN113487419B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and more specifically, to a cash business processing method, device and system. Background Art
[0002] At present, when bank branches handle cash transactions, the cash is always with the tellers, posing a risk to the safety of the cash.
[0003] In order to improve the cash safety of bank branches, some bank branches consider deploying cash storage devices at the counter, and the cash storage devices will be used to issue cash every time a cash transaction is handled. However, if all cash in the bank branch is stored in the cash storage device, it is necessary to store cash of all currencies in the cash storage device, which places high requirements on the cash storage device. In addition, the teller needs to frequently operate the cash storage device to issue cash or hand in the cash in his hand, which makes the business handling efficiency very low. Summary of the invention
[0004] In view of this, the present invention provides a cash business processing method, device and system, which improve the processing efficiency of cash business while ensuring the safety of cash in bank branches.
[0005] In order to achieve the above-mentioned invention object, the specific technical solution provided by the present invention is as follows:
[0006] A cash business processing method, applied to a backend server, comprising:
[0007] When receiving a cash business processing request, parsing the cash business processing request to obtain the currency, currency type and amount corresponding to the business to be processed;
[0008] Obtaining the amount of cash in various currencies in the cash storage device and the amount of cash in various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller;
[0009] The current time, the currency, currency type and amount corresponding to the pending business, the cash quantity of various currencies of the cash storage device and the cash quantity of various currencies at the teller are input into a pre-constructed scheduling model to obtain the cash quantity of the currency to be issued by the cash storage device and the cash quantity of the currency to be issued at the teller.
[0010] Optionally, the method further includes:
[0011] In response to the cash forecast instruction, a pre-built cash forecast model is called to forecast the currency type and cash quantity of the bank branch the next day.
[0012] Optionally, after predicting the currency type and the amount of cash at the bank branch on the next day, the method further includes:
[0013] Calling the expert system to predict the currency, currency type and cash quantity of the cash storage device in the bank branch the next day;
[0014] The currency type, currency type and cash amount at the teller in the bank branch are determined according to the currency type, currency type and cash amount of the bank branch on the next day and the currency type, currency type and cash amount of the cash storage device.
[0015] Optionally, the initial currency type and cash amount of the cash storage device in the bank branch and the initial currency type and cash amount at the teller are pre-configured based on the forecast result of the previous day.
[0016] Optionally, the calling of the expert system to predict the currency type, currency type and amount of the cash storage device in the bank branch the next day includes:
[0017] Obtain the characteristic elements of the next day;
[0018] Invoke the inference engine in the expert system to match the rules corresponding to the characteristic elements of the next day from the knowledge base;
[0019] According to the rules corresponding to the characteristic elements of the next day, the currency type, currency type and cash quantity of the cash storage device in the bank branch on the next day are determined.
[0020] Optionally, the inference engine is obtained by training a neural network model using training samples marked with rule identifiers, and the training samples marked with rule identifiers include various feature elements.
[0021] Optionally, the method for constructing the scheduling model includes:
[0022] Get sample data marked with scheduling results;
[0023] Divide the sample data marked with scheduling results into a training set and a validation set;
[0024] Using the training set to train the neural network model;
[0025] The trained neural network model is verified using the verification set, and the scheduling model is obtained when the verification result meets the preset accuracy requirement.
[0026] Optionally, the obtaining of sample data marked with the scheduling result includes:
[0027] Obtain cash business processing data including scheduling results during historical cash business processing;
[0028] When the scheduling result meets the preset scheduling requirements, the cash business processing data is used as sample data marked with the scheduling result.
[0029] A cash business processing device, applied to a backend server, comprising:
[0030] A request parsing unit, configured to parse the cash business processing request upon receiving the cash business processing request, and obtain the currency, currency type and amount corresponding to the business to be processed;
[0031] A data acquisition unit, used to acquire the amount of cash of various currencies in the cash storage device and the amount of cash of various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller;
[0032] The cash scheduling unit is used to input the current time, the currency, currency type and amount corresponding to the business to be processed, the cash quantity of various currencies and currencies of the cash storage device and the cash quantity of various currencies and currencies at the teller into a pre-built scheduling model to obtain the cash quantity of the currency and currency to be issued by the cash storage device and the cash quantity of the currency and currency to be issued by the teller.
[0033] Optionally, the device further comprises:
[0034] The branch cash forecasting unit is used to respond to the cash forecasting instruction, call the pre-built cash forecasting model, and predict the currency type and cash quantity of the bank branch on the next day.
[0035] Optionally, the device further comprises:
[0036] The equipment cash prediction unit is used to call the expert system to predict the currency, currency type and cash amount of the cash storage device in the bank branch the next day after predicting the currency type and cash amount of the bank branch the next day;
[0037] The teller cash determination unit is used to determine the currency, currency type and cash amount of the teller in the bank branch according to the currency type, currency type and cash amount of the bank branch the next day and the currency type, currency type and cash amount of the cash storage device.
[0038] Optionally, the initial currency type and cash amount of the cash storage device in the bank branch and the initial currency type and cash amount at the teller are pre-configured based on the forecast result of the previous day.
[0039] Optionally, the device cash prediction unit is specifically used for:
[0040] Obtain the characteristic elements of the next day;
[0041] Invoke the inference engine in the expert system to match the rules corresponding to the characteristic elements of the next day from the knowledge base;
[0042] According to the rules corresponding to the characteristic elements of the next day, the currency type, currency type and cash quantity of the cash storage device in the bank branch on the next day are determined.
[0043] Optionally, the inference engine is obtained by training a neural network model using training samples marked with rule identifiers, and the training samples marked with rule identifiers include various feature elements.
[0044] Optionally, the device further includes a scheduling model building unit, which is specifically used to:
[0045] Get sample data marked with scheduling results;
[0046] Divide the sample data marked with scheduling results into a training set and a validation set;
[0047] Using the training set to train the neural network model;
[0048] The trained neural network model is verified using the verification set, and the scheduling model is obtained when the verification result meets the preset accuracy requirement.
[0049] A cash business processing system comprises: a backend server and at least one cash storage device, wherein the cash storage device is communicatively connected with the backend server;
[0050] The backend server is used to execute the cash business processing method disclosed in the above embodiment;
[0051] The cash storage device is used to deposit or withdraw cash under the control of the background server, automatically count the current cash quantities of various currencies after depositing or withdrawing cash, and send the current cash quantities of various currencies to the background server.
[0052] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0053] The present invention discloses a cash business processing method, which configures cash of various currencies in a cash storage device and a teller in a bank branch respectively, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller, thereby ensuring the safety of cash in the bank branch. When a cash business processing request is received, the amount of cash in the cash storage device and the amount of cash in the cash storage device and the amount of cash in the teller are reasonably scheduled by calling a scheduling model, so that the cash storage device cooperates with the teller to efficiently complete the cash business processing, and the teller is prevented from frequently operating the cash storage device to issue cash or hand in the cash in his hand, thereby improving the processing efficiency of the cash business while ensuring the safety of the cash in the bank branch. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] 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 embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0055] Figure 1 A schematic diagram of a cash business processing method disclosed in an embodiment of the present invention;
[0056] Figure 2 A schematic diagram of a flow chart of a method for constructing a scheduling model disclosed in an embodiment of the present invention;
[0057] Figure 3 A schematic diagram of a flow chart of a method for initial cash configuration at a bank branch disclosed in an embodiment of the present invention;
[0058] Figure 4 A schematic diagram of the structure of a cash business processing device disclosed in an embodiment of the present invention;
[0059] Figure 5 A schematic diagram of the structure of a cash business processing system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION
[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0061] The inventor has found through research that if all the cash in a bank branch is stored in a cash storage device, it is necessary to store cash of all currencies in the cash storage device, which places high requirements on the cash storage device. In addition, the teller needs to frequently operate the cash storage device to take out cash or hand in the cash in his hand, and the business handling efficiency is very low. If most of the cash in the bank branch is stored in the cash storage device in the initial state, and a small amount of cash is at the teller, the teller needs to manually operate the cash storage device to take out cash based on experience, which increases the teller's labor intensity, and there may be too much or too little cash at the teller.
[0062] In order to solve the above technical problems, the present invention provides a cash business processing method, which is applied to a background server, and the background server is communicated with a cash storage device in a bank branch. When the background server receives a cash business processing request, it calls a scheduling model to reasonably schedule the amount of cash in the currency type to be issued by the cash storage device and the amount of cash in the currency type to be issued at the teller, so that the cash storage device cooperates with the teller to efficiently complete the cash business processing, avoids the teller frequently operating the cash storage device to issue cash or hand in the cash in his hand, and avoids the situation where there is too much or too little cash at the teller, thereby improving the processing efficiency of cash business while ensuring the cash safety of the bank branch.
[0063] For details, please refer to Figure 1 A cash business processing method disclosed in this embodiment specifically includes the following steps:
[0064] S101: When a cash business processing request is received, the cash business processing request is parsed to obtain the currency, currency type and amount corresponding to the business to be processed;
[0065] Currencies include: RMB, USD, JPY, etc.
[0066] The currency indicates the amount of cash. Taking RMB as an example, the currencies include 100 yuan, 50 yuan, 10 yuan, 1 yuan, etc.
[0067] The amount is the amount corresponding to the currency.
[0068] For example, if the cash business is a withdrawal business and the withdrawal amount is RMB 1,050, it includes 10 RMB 100 banknotes and 1 RMB 50 banknote.
[0069] S102: Acquire the amount of cash in various currencies in the cash storage device and the amount of cash in various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller;
[0070] Specifically, the automatic inventory function of the cash storage device is used to obtain the amount of cash of various currencies in the cash storage device.
[0071] Since the initial amount of cash in the teller's currency is fixed, the background server will record the latest amount of cash in the teller's currency after each cash business is processed. Therefore, the background server can also obtain the amount of cash in various currencies at the teller.
[0072] In order to ensure the safety of cash in bank branches and improve the efficiency of cash business processing, the amount of cash in cash storage devices is much greater than the amount of cash at the teller. Ideally, as cash business is continuously processed, the amount of cash in cash storage devices and at the teller decreases or increases in the same proportion.
[0073] S103: Input the current time, the currency, currency type and amount corresponding to the business to be processed, the cash quantity of various currencies in the cash storage device and the cash quantity of various currencies at the teller into a pre-built scheduling model to obtain the cash quantity of the currency to be issued in the cash storage device and the cash quantity of the currency to be issued at the teller.
[0074] The input data of the scheduling model are the current time, the currency, currency type and amount corresponding to the business to be processed, the amount of cash in various currencies in the cash storage device and the amount of cash in various currencies at the teller. The output data are the amount of cash in various currencies to be issued by the cash storage device and the amount of cash in various currencies to be issued at the teller for this cash business.
[0075] It should be noted that each window in a bank branch corresponds to a cash storage device, that is, the cash storage device corresponds to the teller one by one, and the backend server simultaneously controls the cash business processing of all windows in the bank branch.
[0076] See also Figure 2 This embodiment discloses a method for constructing a scheduling model, which specifically includes the following steps:
[0077] S201: Acquire sample data marked with scheduling results;
[0078] Specifically, first, the cash business processing data including the scheduling results in the historical cash business processing process is obtained. The historical cash business can be the cash business processing data of the teller manually scheduling the cash storage device and the cash in the teller's own hands. The historical cash business can be the cash business processing data using the cash business processing method disclosed in this embodiment, which is not specifically limited here.
[0079] Then, the historical cash business processing data whose scheduling results meet the preset scheduling requirements are screened from the historical cash business processing data as sample data marked with the scheduling results.
[0080] Scheduling requirements can be set based on actual needs, such as the amount of cash in cash storage devices and at tellers decreasing or increasing in the same proportion.
[0081] S202: Divide the sample data marked with the scheduling results into a training set and a validation set;
[0082] S203: Training the neural network model using the training set;
[0083] S204: Use the verification set to verify the trained neural network model, and obtain the scheduling model when the verification result meets the preset accuracy requirement.
[0084] The accuracy requirements here can be mean absolute error, mean square error, root mean square error, etc.
[0085] The present embodiment discloses a cash business processing method, which configures cash of various currencies in the cash storage device and the teller in the bank branch respectively, and the amount of cash in the cash storage device is much greater than the amount of cash at the teller, so as to ensure the safety of cash in the bank branch. When a cash business processing request is received, the amount of cash in the currency of the cash storage device to be issued and the amount of cash in the currency of the teller to be issued are reasonably scheduled by calling the scheduling model, so that the cash storage device cooperates with the teller to efficiently complete the cash business processing, and avoids the teller from frequently operating the cash storage device to issue or hand in the cash in his hand, so as to improve the processing efficiency of cash business while ensuring the safety of cash in the bank branch.
[0086] In order to ensure the reasonable allocation of cash between cash storage devices and tellers in the initial state before bank branches open for business every day, it is necessary to accurately predict the total amount of cash in bank branches and the amount of cash in cash storage devices. On this basis, please refer to Figure 3 The bank branch initial cash configuration method disclosed in this embodiment includes the following steps:
[0087] S301: In response to the cash forecast instruction, a pre-built cash forecast model is called to forecast the currency type and cash quantity of the bank branch the next day;
[0088] Specifically, the cash prediction model is obtained by pre-training the neural network model using the historical transaction data of bank outlets. The input data of the cash prediction model is the prediction date, holiday characteristics, week characteristics, and weather characteristics of the prediction date. The output data is the currency type and cash amount of the bank outlet on the prediction date, that is, the cash amount corresponding to each currency type.
[0089] S302: calling the expert system to predict the currency type, currency type and cash quantity of the cash storage device in the bank branch the next day;
[0090] The expert system includes an inference engine and a knowledge base, in which multiple rules are pre-stored, such as US dollars are used more often the day before holidays, and 100-yuan RMB is used more often on rainy days.
[0091] Specifically, characteristic elements of the next day are obtained, such as holiday characteristics, week characteristics, weather characteristics, etc., and then the inference engine in the expert system is called to match the rules corresponding to the characteristic elements of the next day from the knowledge base. The rule here is at least one rule. Finally, according to the rules corresponding to the characteristic elements of the next day, the currency, currency type and cash quantity of the cash storage devices in the bank branches on the next day are determined.
[0092] The inference engine is obtained by training a neural network model using training samples marked with rule identifiers, and the training samples marked with rule identifiers include various feature elements.
[0093] S303: Determine the currency, currency type and cash amount at the teller in the bank branch according to the currency type, currency type and cash amount of the bank branch and the currency, currency type and cash amount of the cash storage device on the next day.
[0094] For example, if a bank branch has only one business window, the currency type and cash amount of the bank branch the next day minus the currency type, currency type and cash amount of the cash storage device is the currency type, currency type and cash amount of the teller in the bank branch. If the bank branch has more than one business window, the currency type and cash amount of the bank branch the next day minus the currency type, currency type and cash amount of all cash storage devices, and the remaining cash is distributed to each teller in equal proportion.
[0095] It is understandable that the initial currency type and cash amount of the cash storage device in the bank branch and the initial currency type and cash amount at the teller are pre-configured based on the forecast results of the previous day.
[0096] After the initial currency type and cash amount of the cash storage device in the bank branch and the initial currency type and cash amount at the teller are configured, the following cash business processing method can be executed after the business hours arrive:
[0097] When receiving a cash business processing request, parsing the cash business processing request to obtain the currency, currency type and amount corresponding to the business to be processed;
[0098] Obtaining the amount of cash in various currencies in the cash storage device and the amount of cash in various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller;
[0099] The current time, the currency, currency type and amount corresponding to the pending business, the cash quantity of various currencies of the cash storage device and the cash quantity of various currencies at the teller are input into a pre-constructed scheduling model to obtain the cash quantity of the currency to be issued by the cash storage device and the cash quantity of the currency to be issued at the teller.
[0100] Based on the cash business processing method disclosed in the above embodiment, this embodiment correspondingly discloses a cash business processing device, see Figure 4 , the device comprises:
[0101] The request parsing unit 100 is used to parse the cash business processing request when receiving the cash business processing request, and obtain the currency, currency type and amount corresponding to the business to be processed;
[0102] The data acquisition unit 200 is used to acquire the amount of cash of various currencies in the cash storage device and the amount of cash of various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller;
[0103] The cash scheduling unit 300 is used to input the current time, the currency, currency type and amount corresponding to the business to be processed, the cash quantity of various currencies of the cash storage device and the cash quantity of various currencies at the teller into a pre-built scheduling model to obtain the cash quantity of the currency to be issued by the cash storage device and the cash quantity of the currency to be issued at the teller.
[0104] Optionally, the device further comprises:
[0105] The branch cash forecasting unit is used to respond to the cash forecasting instruction, call the pre-built cash forecasting model, and predict the currency type and cash quantity of the bank branch on the next day.
[0106] Optionally, the device further comprises:
[0107] The equipment cash prediction unit is used to call the expert system to predict the currency, currency type and cash amount of the cash storage device in the bank branch the next day after predicting the currency type and cash amount of the bank branch the next day;
[0108] The teller cash determination unit is used to determine the currency, currency type and cash amount of the teller in the bank branch according to the currency type, currency type and cash amount of the bank branch the next day and the currency type, currency type and cash amount of the cash storage device.
[0109] Optionally, the initial currency type and cash amount of the cash storage device in the bank branch and the initial currency type and cash amount at the teller are pre-configured based on the forecast result of the previous day.
[0110] Optionally, the device cash prediction unit is specifically used for:
[0111] Obtain the characteristic elements of the next day;
[0112] Invoke the inference engine in the expert system to match the rules corresponding to the characteristic elements of the next day from the knowledge base;
[0113] According to the rules corresponding to the characteristic elements of the next day, the currency type, currency type and cash quantity of the cash storage device in the bank branch on the next day are determined.
[0114] Optionally, the inference engine is obtained by training a neural network model using training samples marked with rule identifiers, and the training samples marked with rule identifiers include various feature elements.
[0115] Optionally, the device further includes a scheduling model building unit, which is specifically used to:
[0116] Get sample data marked with scheduling results;
[0117] Divide the sample data marked with scheduling results into a training set and a validation set;
[0118] Using the training set to train the neural network model;
[0119] The trained neural network model is verified using the verification set, and the scheduling model is obtained when the verification result meets the preset accuracy requirement.
[0120] The present embodiment discloses a cash business processing device, which respectively configures cash of various currencies in the cash storage device and the teller in the bank branch. The amount of cash in the cash storage device is much greater than the amount of cash at the teller, so as to ensure the safety of cash in the bank branch. When a cash business processing request is received, the amount of cash in the currency of the cash storage device to be issued and the amount of cash in the currency of the teller to be issued are reasonably scheduled by calling the scheduling model, so that the cash storage device cooperates with the teller to efficiently complete the cash business processing, and avoids the teller from frequently operating the cash storage device to issue or hand in the cash in his hand, so as to improve the processing efficiency of cash business while ensuring the safety of cash in the bank branch.
[0121] This embodiment also discloses a cash business processing system. Figure 5 , the cash business processing system includes: a backend server and at least one cash storage device, the cash storage device is communicatively connected with the backend server;
[0122] The cash storage device is used to deposit or withdraw cash under the control of the backend server, automatically count the current amount of cash in various currencies after depositing or withdrawing cash, and send the current amount of cash in various currencies to the backend server;
[0123] The backend server is used to execute the following cash business processing method:
[0124] When receiving a cash business processing request, parsing the cash business processing request to obtain the currency, currency type and amount corresponding to the business to be processed;
[0125] Obtaining the amount of cash in various currencies in the cash storage device and the amount of cash in various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller;
[0126] The current time, the currency, currency type and amount corresponding to the pending business, the cash quantity of various currencies of the cash storage device and the cash quantity of various currencies at the teller are input into a pre-constructed scheduling model to obtain the cash quantity of the currency to be issued by the cash storage device and the cash quantity of the currency to be issued at the teller.
[0127] Furthermore, the method further comprises:
[0128] In response to the cash forecast instruction, a pre-built cash forecast model is called to forecast the currency type and cash quantity of the bank branch the next day.
[0129] Further, after predicting the currency type and the amount of cash at the bank branch on the next day, the method further includes:
[0130] Calling the expert system to predict the currency, currency type and cash quantity of the cash storage device in the bank branch the next day;
[0131] The currency type, currency type and cash amount at the teller in the bank branch are determined according to the currency type, currency type and cash amount of the bank branch on the next day and the currency type, currency type and cash amount of the cash storage device.
[0132] Furthermore, the initial currency type and the amount of cash in the cash storage device in the bank branch and the initial currency type and the amount of cash at the teller are pre-configured based on the forecast result of the previous day.
[0133] Furthermore, the calling of the expert system to predict the currency type, currency type and amount of the cash storage device in the bank branch the next day includes:
[0134] Obtain the characteristic elements of the next day;
[0135] Invoke the inference engine in the expert system to match the rules corresponding to the characteristic elements of the next day from the knowledge base;
[0136] According to the rules corresponding to the characteristic elements of the next day, the currency type, currency type and cash quantity of the cash storage device in the bank branch on the next day are determined.
[0137] Furthermore, the inference engine is obtained by training a neural network model using training samples marked with rule identifiers, and the training samples marked with rule identifiers include various feature elements.
[0138] Furthermore, the method for constructing the scheduling model includes:
[0139] Get sample data marked with scheduling results;
[0140] Divide the sample data marked with scheduling results into a training set and a validation set;
[0141] Using the training set to train the neural network model;
[0142] The trained neural network model is verified using the verification set, and the scheduling model is obtained when the verification result meets the preset accuracy requirement.
[0143] Further, the obtaining of sample data marked with the scheduling result includes:
[0144] Obtain cash business processing data including scheduling results during historical cash business processing;
[0145] When the scheduling result meets the preset scheduling requirements, the cash business processing data is used as sample data marked with the scheduling result.
[0146] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0147] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0148] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0149] The above-mentioned embodiments may be combined arbitrarily. For the above description of the disclosed embodiments, the features recorded in the embodiments in this specification may be replaced or combined with each other, so that professional and technical personnel in this field can implement or use the present application.
[0150] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A cash business processing method, characterized in that: Applied to a backend server, the method comprises: When receiving a cash business processing request, parsing the cash business processing request to obtain the currency, currency type and amount corresponding to the business to be processed; Obtaining the amount of cash in various currencies in the cash storage device and the amount of cash in various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller; Input the current time, the currency, currency type and amount corresponding to the pending business, the amount of cash in various currencies of the cash storage device and the amount of cash in various currencies at the teller into a pre-built scheduling model, and obtain the amount of cash in the currency to be issued by the cash storage device and the amount of cash in the currency to be issued by the teller; The method further comprises: In response to the cash forecast instruction, a pre-built cash forecast model is called to forecast the currency type and cash quantity of the bank branch the next day; After predicting the currency type and cash amount of the bank branch the next day, calling the expert system to predict the currency type, currency type and cash amount of the cash storage device in the bank branch the next day; Determine the currency, currency and cash amount at the teller in the bank branch according to the currency, currency type and cash amount of the bank branch on the next day and the currency, currency type and cash amount of the cash storage device; The calling of the expert system to predict the currency type, currency type and amount of the cash storage device in the bank branch the next day includes: Obtain the characteristic elements of the next day; Invoke the inference engine in the expert system to match the rules corresponding to the characteristic elements of the next day from the knowledge base; According to the rules corresponding to the characteristic elements of the next day, determine the currency type, currency type and cash quantity of the cash storage device in the bank branch on the next day; The method for constructing the scheduling model includes: Get sample data marked with scheduling results; Divide the sample data marked with scheduling results into a training set and a validation set; Using the training set to train the neural network model; The trained neural network model is verified using the verification set, and the scheduling model is obtained when the verification result meets the preset accuracy requirement.
2. The method according to claim 1, characterized in that: The initial currency type and cash amount of the cash storage device in the bank branch and the initial currency type and cash amount at the teller are pre-configured based on the forecast results of the previous day.
3. The method according to claim 1, characterized in that The inference engine is obtained by training a neural network model using training samples marked with rule identifiers, and the training samples marked with rule identifiers include various feature elements.
4. The method according to claim 1, characterized in that: The obtaining of sample data marked with the scheduling result includes: Obtain cash business processing data including scheduling results during historical cash business processing; When the scheduling result meets the preset scheduling requirements, the cash business processing data is used as sample data marked with the scheduling result.
5. A cash business processing device, characterized in that: Applied to a backend server, the device comprises: A request parsing unit, configured to parse the cash business processing request upon receiving the cash business processing request, and obtain the currency, currency type and amount corresponding to the business to be processed; A data acquisition unit, used to acquire the amount of cash of various currencies in the cash storage device and the amount of cash of various currencies at the teller, wherein the amount of cash in the cash storage device is much greater than the amount of cash at the teller; A cash dispatching unit is used to input the current time, the currency, currency type and amount corresponding to the business to be handled, the cash quantity of various currencies and currencies of the cash storage device and the cash quantity of various currencies and currencies at the teller into a pre-built dispatching model, and obtain the cash quantity of the currency and currency to be issued by the cash storage device and the cash quantity of the currency and currency to be issued by the teller; A scheduling model building unit, used to obtain sample data marked with scheduling results, divide the sample data marked with scheduling results into a training set and a verification set, train the neural network model using the training set, verify the trained neural network model using the verification set, and obtain the scheduling model when the verification result meets the preset accuracy requirement; The branch cash forecasting unit is used to respond to the cash forecasting instruction, call the pre-built cash forecasting model, and forecast the currency type and cash quantity of the bank branch the next day; The equipment cash prediction unit is used to call the expert system to predict the currency, currency type and cash amount of the cash storage device in the bank branch the next day after predicting the currency type and cash amount of the bank branch the next day; A teller cash determination unit, used to determine the currency type, currency type and cash amount of the teller in the bank branch according to the currency type, currency type and cash amount of the bank branch on the next day and the currency type, currency type and cash amount of the cash storage device; The device cash prediction unit is specifically used to obtain the characteristic elements of the next day; call the inference engine in the expert system to match the rules corresponding to the characteristic elements of the next day from the knowledge base; and determine the currency, currency type and cash quantity of the cash storage device in the bank branch on the next day based on the rules corresponding to the characteristic elements of the next day.
6. A cash business processing system, characterized in that: include: A backend server and at least one cash storage device, wherein the cash storage device is communicatively connected to the backend server; The backend server is used to execute the cash business processing method according to any one of claims 1 to 4; The cash storage device is used to deposit or withdraw cash under the control of the background server, automatically count the current cash quantities of various currencies after depositing or withdrawing cash, and send the current cash quantities of various currencies to the background server.
