Method, device, equipment, medium and product for predicting cash deposit amount of ATM

Abstract

The present invention discloses a method, device, equipment, medium, and product for predicting the cash deposit amount of an ATM, relating to the field of artificial intelligence technology. The method comprises: generating a target time enhancement feature based on a target time feature and a target static feature; determining a spatial correlation coefficient between the other ATMs and the target ATM based on the target initial spatiotemporal features corresponding to the target ATM and other initial spatiotemporal features corresponding to other ATMs; determining a target spatiotemporal fusion feature corresponding to the target ATM based on the spatial correlation coefficient and other initial spatiotemporal features, and predicting a target cash deposit amount corresponding to the target ATM at the current time point based on the target spatiotemporal fusion feature. The present invention combines the temporal features, spatial features, and static features that affect the cash deposit amount of an ATM, and uses these features together to predict the cash deposit amount of the ATM, thereby ensuring the accuracy and reliability of the cash deposit amount prediction, which is beneficial for banks to rationally allocate cash resources and effectively prevent risks.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, medium and product for predicting the cash deposit amount of an ATM. Background Art

[0002] With the continuous improvement of people's living standards in recent years, deposit and withdrawal transactions at ATMs have become more frequent, leading to a rapid growth in the ATM market. To ensure that users can access cash in real time, banks predict the cash level at ATMs and allocate cash to them accordingly.

[0003] Existing technologies typically predict future cash levels by analyzing historical cash deposit trends at ATMs. However, the cash levels at ATMs are subject to numerous uncertainties, and relying solely on historical cash deposit trends to predict cash levels cannot guarantee accuracy and reliability. Summary of the Invention

[0004] The present invention provides a method, device, equipment, medium and product for predicting the cash deposit amount of an ATM, so as to solve the problem that the existing technology relies on historical cash deposit amount trends to predict the cash deposit amount, and cannot ensure the accuracy and reliability of the cash deposit amount prediction.

[0005] According to one aspect of the present invention, a method for predicting the amount of cash deposited in an ATM is provided, the method comprising:

[0006] Obtaining at least one target time feature and at least one target static feature corresponding to the current time point, and generating a target time enhancement feature based on the target time feature and the target static feature; wherein the target static feature includes at least one of a user behavior feature, a payment method feature, and a withdrawal fee feature;

[0007] Determine, based on the target initial spatiotemporal features corresponding to the target ATM and other initial spatiotemporal features corresponding to at least one other ATM, the spatial correlation coefficients between each of the other ATMs and the target ATM; wherein the target initial spatiotemporal features are determined based on at least one target spatial feature and the target time enhancement feature corresponding to the target ATM, and the other initial spatiotemporal features are determined based on at least one other spatial feature and the target time enhancement feature corresponding to the other ATM;

[0008] According to each of the spatial correlation coefficients and each of the other initial spatiotemporal features, the target spatiotemporal fusion features corresponding to the target ATM are determined, and the target cash deposit amount corresponding to the target ATM at the current time point is predicted based on the target spatiotemporal fusion features.

[0009] According to another aspect of the present invention, there is provided a device for predicting the amount of cash deposited in a cash dispenser, the device comprising:

[0010] a time-enhanced feature generation module, configured to obtain at least one target time feature and at least one target static feature corresponding to a current time point, and generate a target time-enhanced feature based on the target time feature and the target static feature; wherein the target static feature includes at least one of a user behavior feature, a payment method feature, and a withdrawal fee feature;

[0011] A spatial correlation coefficient determination module is configured to determine the spatial correlation coefficient between each of the other cash dispensers and the target cash dispenser based on the target initial spatiotemporal characteristics corresponding to the target cash dispenser and other initial spatiotemporal characteristics corresponding to at least one other cash dispenser; wherein the target initial spatiotemporal characteristics are determined based on at least one target spatial characteristic corresponding to the target cash dispenser and the target time enhancement characteristic, and the other initial spatiotemporal characteristics are determined based on at least one other spatial characteristic corresponding to the other cash dispenser and the target time enhancement characteristic;

[0012] The cash deposit amount prediction module is used to determine the target spatiotemporal fusion features corresponding to the target ATM based on each of the spatial correlation coefficients and each of the other initial spatiotemporal features, and predict the target cash deposit amount corresponding to the target ATM at the current time point based on the target spatiotemporal fusion features.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the cash deposit amount of an ATM according to any one of the present inventions.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the cash deposit amount of an ATM according to any one of the present inventions when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for predicting the cash deposit amount of an ATM according to any one of the present inventions.

[0019] The present invention combines the time characteristics, spatial characteristics and static characteristics that affect the cash storage amount of the ATM, and uses them together to predict the cash storage amount of the ATM, thereby ensuring the accuracy and reliability of the cash storage amount prediction of the ATM, which is beneficial for the bank to rationally allocate cash resources and effectively prevent risks.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flowchart of a method for predicting the amount of cash deposited in an ATM provided in Example 1 of the present invention;

[0023] Figure 2 A flowchart of a method for predicting the amount of cash deposited in an ATM provided in Example 2 of the present invention;

[0024] Figure 3 A flowchart of a method for generating initial spatiotemporal features of a target provided in Example 3 of the present invention;

[0025] Figure 4 A flowchart of a method for generating target spatiotemporal fusion features provided in the fourth embodiment of the present invention;

[0026] Figure 5 A schematic diagram of the structure of a device for predicting the amount of cash deposited in an ATM provided in a fifth embodiment of the present invention;

[0027] Figure 6 The present invention is a schematic structural diagram of an electronic device for implementing the method for predicting the cash deposit amount of an ATM according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "candidate", "target", "first", "second", "third", "current", "future", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a method for predicting the amount of cash stored in an ATM provided in the first embodiment of the present invention. This embodiment can be applied to predict the amount of cash stored in an ATM using three feature dimensions: time feature, spatial feature, and static feature. This method can be executed by a device for predicting the amount of cash stored in an ATM. The device for predicting the amount of cash stored in an ATM can be implemented in the form of hardware and / or software. Figure 1 As shown, the method includes:

[0032] S101: Acquire at least one target time feature and at least one target static feature corresponding to the current time point, and generate a target time enhancement feature based on the target time feature and the target static feature.

[0033] The current time point refers to the current real-time time point, i.e., the time point corresponding to the cash level at the ATM to be predicted. The target time features refer to relevant time features that may affect the cash level at the ATM (also known as cash demand), including but not limited to seasonal, economic, and weather factors.

[0034] Seasonal factors include, but are not limited to, whether it's a holiday, weekend, or peak travel season during winter or summer vacations. It's understandable that different seasonal factors will lead to different cash usage demands from consumers, which will directly affect the amount of cash held at ATMs. Economic factors include, but are not limited to, changes in financial policies, exchange rates, and price levels. It's understandable that different economic factors will lead to different levels of consumer withdrawal demand, which will directly affect the amount of cash held at ATMs. Weather factors include, but are not limited to, temperature, wind speed, precipitation, and air pollution index. It's understandable that different weather factors will lead to different frequencies of consumer outings, further affecting ATM usage and thus the amount of cash held at ATMs. For example, severe weather such as heavy snow and typhoons may cause people to go out less, reducing ATM usage. Conversely, improved weather may lead to a concentrated rebound in demand.

[0035] The target static features include at least one of user behavior features, payment method features, and withdrawal fee features. User behavior features include, but are not limited to, cash usage habits, consumption types, salary payment dates, etc. It is understandable that different user behavior features will affect consumers' usage rate of ATMs, thereby directly affecting the amount of cash stored in ATMs. Payment method features include, but are not limited to the popularity of electronic payments, etc. It is understandable that different payment method features will affect consumers' reliance on cash, thereby directly affecting the amount of cash stored in ATMs. For example, the popularity of electronic payments has reduced people's reliance on cash, and the amount of cash stored in ATMs has decreased. Withdrawal fee features include, but are not limited to, withdrawal fees, inter-bank fees, withdrawal limits, etc. It is understandable that withdrawal fee features will affect consumers' cash withdrawal habits, thereby directly affecting the amount of cash stored in ATMs.

[0036] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with relevant laws, regulations and standards in the relevant regions.

[0037] In one embodiment, at least one target time feature and at least one target static feature corresponding to the current time point are obtained. Further, the target static feature is input into a static feature encoder, and the static feature encoder is used to encode the target static feature to generate a context feature, wherein the static feature encoder is constructed according to a gated residual network (GRN). Further, the target time feature and the context feature are input into a pre-generated gated residual network, and the gated residual network is used to process the target time feature and the context feature, and output a target time enhanced feature. It is understandable that since there is a significant influence between the target static feature and the target time feature, the target time feature is enhanced by using the target static feature to ensure that the generated target time enhanced feature contains richer feature information.

[0038] S102. Determine the spatial correlation coefficient between each of the other ATMs and the target ATM based on the target initial spatiotemporal characteristics corresponding to the target ATM and other initial spatiotemporal characteristics corresponding to at least one other ATM.

[0039] Among them, the target ATM refers to an ATM (Automated Teller Machine) with a predicted cash storage demand. Other ATMs refer to ATMs other than the target ATM. The target initial spatiotemporal features refer to the features obtained by combining the time features and the spatial features of the target ATM, and the other initial spatiotemporal features refer to the features obtained by combining the time features and the spatial features of other ATMs. Specifically, the target initial spatiotemporal features are determined based on at least one target spatial feature and target time enhancement feature corresponding to the target ATM, and the other initial spatiotemporal features are determined based on at least one other spatial feature and target time enhancement feature corresponding to other ATMs.

[0040] Spatial characteristics include but are not limited to geographical location characteristics and traffic condition characteristics. It is understandable that different geographical location characteristics will lead to different usage frequencies and cash demands of ATMs, which will directly affect the cash storage capacity of ATMs. For example, in areas with large traffic flow, such as commercial centers and tourist attractions, the frequency of ATM usage is high, and the demand for cash will also increase accordingly; while in some residential areas or rural areas, the frequency of ATM usage may be closely related to daily life, and the cash demand is relatively stable. It is understandable that different traffic condition characteristics will lead to different usage frequencies of ATMs, which will directly affect the cash storage capacity of ATMs. For example, ATMs located in convenient transportation locations, especially in subway stations, bus stations, airports and other places, usually have a high frequency of usage.

[0041] The spatial correlation coefficient reflects the topological relationship between each other ATM and the target ATM. For example, the larger the spatial correlation coefficient between any other ATM and the target ATM, the greater the importance of the other ATM to the target ATM, that is, the closer the topological relationship.

[0042] In one embodiment, feature splicing is performed based on at least one target spatial feature and target time enhancement feature corresponding to the target ATM to generate the target initial spatiotemporal feature corresponding to the target ATM; and feature splicing is performed based on at least one other spatial feature and target time enhancement feature corresponding to each other ATM to generate other initial spatiotemporal features corresponding to each other ATM.

[0043] Feature splicing is performed based on the target initial spatiotemporal features and other initial spatiotemporal features, and the feature splicing results are input into the graph attention network. The output results of the graph attention network are further processed using an activation function to determine the spatial correlation coefficients between each other ATM and the target ATM.

[0044] S103. Determine the target spatiotemporal fusion features corresponding to the target ATM based on the spatial correlation coefficients and other initial spatiotemporal features, and predict the target cash deposit amount corresponding to the target ATM at the current time point based on the target spatiotemporal fusion features.

[0045] In one embodiment, a weighted summation is performed based on the spatial correlation coefficients and other initial spatiotemporal features, and a target spatiotemporal fusion feature corresponding to the target ATM is determined based on the weighted summation result. Furthermore, a pre-trained prediction model is used to predict the cash holding amount based on the target spatiotemporal fusion feature to determine the target cash holding amount corresponding to the target ATM at the current time point.

[0046] Optionally, since the cash deposit amount of the ATM fluctuates greatly, a conformal prediction method is introduced to predict the fluctuation range of the cash deposit amount.

[0047] During the training phase, a conditional distribution is constructed using training samples with known labels, and confidence intervals are then calculated based on this distribution. During the prediction phase, confidence intervals are calculated for each new sample, and the sample is labeled as either "conforms to the training distribution" or "does not conform to the training distribution" based on the confidence level. In time series applications, additional calibration sets and base models are often introduced, resulting in a new approach called Inductive Conformal Prediction (ICP).

[0048] Specifically, the ICP method operates by splitting the training set into a proper training set of size n and a calibration set of size m. The proper training set is used to train the base model M, while the calibration set is used to calculate the unacceptability score, which measures how abnormal a given sample is compared to previously observed data.

[0049] The resulting empirical failure score distribution is used to calculate the key failure score ε, which corresponds to the [(m+1)(1+α)]th minimum residual. For the target spatiotemporal fusion feature x i+1 , target cash deposit amount y i+1 The prediction interval is [y i+1 -ε,y i+1 +ε].

[0050] The embodiment of the present invention combines the temporal characteristics, spatial characteristics and static characteristics that affect the cash storage amount of the ATM, and uses them together to predict the cash storage amount of the ATM, thereby ensuring the accuracy and reliability of the cash storage amount prediction of the ATM, which is beneficial for the bank to rationally allocate cash resources and effectively prevent risks.

[0051] Example 2

[0052] Figure 2 This is a flowchart of a method for predicting the amount of cash deposited in an ATM provided by the second embodiment of the present invention. This embodiment further optimizes and expands the above embodiment and can be combined with the above optional implementations. Figure 2 As shown, the method includes:

[0053] S201: Input at least one candidate static feature into a first gated residual network, and determine first selection weight values ​​corresponding to each candidate static feature according to an output result of the first gated residual network.

[0054] The candidate static features refer to a set of all static features that may affect the cash balance prediction. The first selection weight reflects the degree of influence of the candidate static features on the cash balance prediction. It is understood that the larger the first selection weight corresponding to a candidate static feature, the greater the influence of the candidate static feature on the cash balance prediction.

[0055] In one embodiment, the first selection weight value is determined using the following formula:

[0056] v1=Softmax(GRN1(x1,c1))

[0057] Here, x1 represents any candidate static feature, GRN1 represents the first gated residual network, v1 represents the first selection weight corresponding to the candidate static feature, and Softmax is used to normalize the output of GRN1. Since the calculation of the first selection weight depends only on the candidate static feature, the context feature c1 is zero at this time.

[0058] S202: Input each candidate static feature into a second gated residual network, and determine a first feature variable value corresponding to each candidate static feature according to an output result of the second gated residual network.

[0059] In one embodiment, the following formula is used to determine the value of the first characteristic variable:

[0060] X1=GRN2(x1,c2)

[0061] Where x1 represents any candidate static feature, GRN2 represents the second gated residual network, and X1 represents the first feature variable value corresponding to the candidate static feature. Since the calculation of the first feature variable value depends only on the candidate static feature, the context feature c2 is zero at this time.

[0062] S203: Determine first weighted feature variable values ​​corresponding to respective candidate static features according to respective first feature variable values ​​and respective first selection weight values, and determine a target static feature from the candidate static features according to respective first weighted feature variable values.

[0063] In one embodiment, the following formula is used to determine the value of the first weighted characteristic variable:

[0064] A1=v1X1

[0065] Among them, v1 represents the first selection weight value corresponding to any candidate static feature, X1 represents the first feature variable value corresponding to the candidate static feature, and A1 represents the first weighted feature variable value corresponding to the candidate static feature.

[0066] After determining the first weighted feature variable values ​​corresponding to each candidate static feature, a target number of candidate static features having larger first weighted feature variable values ​​are selected as target static features based on the ranking results of the first weighted feature variable values. For example, the top five candidate static features ranked by first weighted feature variable values ​​are selected as target static features.

[0067] By inputting at least one candidate static feature into a first gated residual network, and determining the first selection weight value corresponding to each candidate static feature according to the output result of the first gated residual network; inputting each candidate static feature into a second gated residual network, and determining the first feature variable value corresponding to each candidate static feature according to the output result of the second gated residual network; determining the first weighted feature variable value corresponding to each candidate static feature according to each first feature variable value and each first selection weight value, and determining the target static feature from each candidate static feature according to each first weighted feature variable value, the candidate static features that are not important for the prediction of the cash deposit amount can be eliminated, that is, the candidate static features that generate unnecessary noise for the prediction of the cash deposit amount can be eliminated, thereby improving the accuracy and efficiency of the cash deposit amount prediction.

[0068] S204: Input at least one candidate time feature and the first context feature into a first gated residual network, and determine a second selection weight value corresponding to each candidate time feature according to an output result of the first gated residual network.

[0069] The first context feature is determined according to the target static feature.

[0070] In one embodiment, the second selection weight value is determined using the following formula:

[0071] v2=Softmax(GRN1(x2,c3))

[0072] Where x2 represents any candidate temporal feature, GRN1 represents the first gated residual network, v2 represents the second selection weight corresponding to the candidate temporal feature, Softmax is used to normalize the output of GRN1, and c3 represents the target static feature.

[0073] S205: Input each candidate time feature into a third gated residual network, and determine a second feature variable value corresponding to each candidate time feature according to an output result of the third gated residual network.

[0074] In one embodiment, the second characteristic variable value is determined using the following formula:

[0075] X2=GRN3(x2,c4)

[0076] Where x2 represents any candidate temporal feature, GRN3 represents the third gated residual network, and X2 represents the second feature variable value corresponding to the candidate temporal feature. Since the calculation of the second feature variable value depends only on the candidate temporal feature, the context feature c4 is zero at this time.

[0077] S206: Determine the second weighted feature variable value corresponding to each candidate time feature according to each second feature variable value and each second selection weight value, and determine the target time feature from each candidate time feature according to each second weighted feature variable value.

[0078] In one embodiment, the second weighted characteristic variable value is determined using the following formula:

[0079] A2=v2X2

[0080] Among them, v2 represents the second weighted feature variable value corresponding to any candidate time feature, X2 represents the second feature variable value corresponding to the candidate time feature, and A2 represents the second weighted feature variable value corresponding to the candidate time feature.

[0081] After determining the second weighted feature variable values ​​corresponding to each candidate time feature, a target number of candidate time features having larger second weighted feature variable values ​​are selected as target time features based on the ranking results of the second weighted feature variable values. For example, the top five candidate time features ranked by second weighted feature variable values ​​are selected as target time features.

[0082] By inputting at least one candidate time feature and a first context feature into a first gated residual network, and determining the second selection weight value corresponding to each candidate time feature according to the output result of the first gated residual network; wherein the first context feature is determined according to the target static feature; inputting each candidate time feature into a third gated residual network, and determining the second feature variable value corresponding to each candidate time feature according to the output result of the third gated residual network; determining the second weighted feature variable value corresponding to each candidate time feature according to each second feature variable value and each second selection weight value, and determining the target time feature from each candidate time feature according to each second weighted feature variable value, the candidate time features that are not important for the prediction of the cash deposit amount can be eliminated, that is, the candidate time features that generate unnecessary noise for the prediction of the cash deposit amount can be eliminated, thereby improving the accuracy and efficiency of the cash deposit amount prediction.

[0083] S207. Generate target time enhancement features based on the target time features and target static features, and determine the spatial correlation coefficients between each other ATM and the target ATM based on the target initial time-space features corresponding to the target ATM and other initial time-space features corresponding to at least one other ATM.

[0084] Optionally, a target time enhancement feature is generated based on the target time feature and the target static feature, including:

[0085] A1. Perform position encoding on each target time feature to generate a first encoding feature, and perform timestamp encoding on each target time feature to generate a second encoding feature.

[0086] Among them, Positional Encoding (PE) is used to obtain the sequential relationship of temporal features, and Timestamp Encoding (TE) is used to capture the impact of temporal features at a specific time point.

[0087] B1. Generate a target coding feature based on the first coding feature and the second coding feature, input the target coding feature and the second context feature into a fourth gated residual network, and determine the target temporal enhancement feature based on the output result of the fourth gated residual network.

[0088] The second context feature is generated according to the target static feature.

[0089] In one embodiment, the target time enhancement feature is determined using the following formula:

[0090] θ(t)=GRN4(x t ,c ep ,c ek )

[0091] Among them, x t represents the target encoding feature; c ep ,c ek represents the second context feature, which is generated based on the target static feature; GRN4 represents the fourth gated residual network, and GRN4 shares weights within the entire layer; θ(t) represents the target time enhancement feature.

[0092] By performing position encoding on each target time feature to generate a first encoding feature, and performing timestamp encoding on each target time feature to generate a second encoding feature, the sequential relationship of the time features is obtained, and the effect of capturing the influence of the time features at a specific time point is achieved, thereby achieving the effect of obtaining the time characteristics of the target time features, which is conducive to improving the accuracy of cash deposit prediction.

[0093] Since there is an influence between static features and time features, the target coding features are generated based on the first coding features and the second coding features, and the target coding features and the second context features are input into the fourth gated residual network. According to the output results of the fourth gated residual network, the target time enhancement features are determined, so that the target time enhancement features contain both time feature information and static feature information, which enhances the feature information expression of the target time enhancement features and is conducive to improving the accuracy of cash deposit prediction.

[0094] Optionally, determining the spatial correlation coefficient between each of the other ATMs and the target ATM based on the target initial spatiotemporal characteristics corresponding to the target ATM and other initial spatiotemporal characteristics corresponding to at least one other ATM includes:

[0095] A2. Generate a first spatiotemporal weighted feature based on the target ATM weight value corresponding to the target ATM and the target initial spatiotemporal feature, and generate a second spatiotemporal weighted feature based on the other ATM weight values ​​corresponding to each other ATM and each other initial spatiotemporal feature.

[0096] For example, assuming that the target ATM weight value corresponding to the target ATM i is W i , the target initial spatiotemporal feature is x t,i The weight value of other ATMs corresponding to other ATMs j is W j , other initial space-time features are x t,j The first spatiotemporal weighted feature is W i x t,i , the second spatiotemporal weighted feature is W j x t,j .

[0097] B2. Input the feature splicing results of the first spatiotemporal weighted feature and the second spatiotemporal weighted feature into the graph attention network, and determine the spatial correlation coefficient based on the output result of the graph attention network.

[0098] In one embodiment, the spatial correlation coefficient is determined using the following formula:

[0099]

[0100] Among them, W i x t,i is the first spatiotemporal weighted feature, W j x t,j is the second spatiotemporal weighted feature, LeakyReLU is the activation function that enables the model to obtain nonlinear information. t,i,j Represents the spatial correlation coefficient between the target ATM i and other ATMs j.

[0101] A first spatiotemporal weighted feature is generated based on the target ATM weight value corresponding to the target ATM and the target initial spatiotemporal feature, and a second spatiotemporal weighted feature is generated based on the weight values ​​of other ATMs corresponding to each other ATM and each other initial spatiotemporal feature; the feature splicing results of the first spatiotemporal weighted feature and the second spatiotemporal weighted feature are input into the graph attention network, and the spatial correlation coefficient is determined based on the output result of the graph attention network, so that the topological structure between the target ATM and other ATMs is captured by using the graph attention network, ensuring the rationality and accuracy of the determination of the spatial correlation coefficient.

[0102] S208. Determine the target spatiotemporal fusion features corresponding to the target ATM based on the spatial correlation coefficients and other initial spatiotemporal features, and predict the target cash deposit amount corresponding to the target ATM at the current time point based on the target spatiotemporal fusion features.

[0103] Example 3

[0104] Figure 3 This is a flow chart of a method for generating target initial spatiotemporal features provided by the third embodiment of the present invention. This embodiment further optimizes and expands the above embodiment and can be combined with the above optional implementations. Figure 3 As shown, the method includes:

[0105] S301. Generate a query matrix based on the target time enhancement feature and the first weight matrix, generate a key matrix based on the target time enhancement feature and the second weight matrix, and generate a value matrix based on the target time enhancement feature and the third weight matrix.

[0106] In one embodiment, the query matrix, key matrix, and value matrix are generated as follows:

[0107] Q=θ(t)W1; K=θ(t)W2; V=θ(t)W3;

[0108] Where θ(t) represents the target temporal enhancement feature, W1 represents the first weight matrix, W2 represents the second weight matrix, W3 represents the third weight matrix, Q represents the query matrix, K represents the key matrix, and V represents the value matrix.

[0109] S302. Divide the query matrix according to the target time step to obtain at least one first submatrix, divide the key matrix according to the target time step to obtain at least one second submatrix, and divide the value matrix according to the target time step to obtain at least one third submatrix.

[0110] For example, the query matrix, key matrix, and value matrix are divided according to the target time step, which can be expressed as follows:

[0111] Q=[Q'1=Concat(Q1,……,Q s ),Q'2=Concat(Q s+1 ,……,Q 2s ),……,Q' n ];

[0112] K=[K1'=Concat(K1,……,K s ),K2'=Concat(K s+1 ,……,K 2s ),……,K n '];

[0113] V=[V1'=Concat(V1,……,V s ),V2'=Concat(V s+1 ,……,V 2s ),……,V' n ];

[0114] Where s represents the target time step, Q'1, ..., Q' n represents the first submatrix, K1', ..., K n ' represents the second sub-matrix, V1', ..., V' n represents the third submatrix.

[0115] S303: Perform attention mechanism processing on each first sub-matrix and each second sub-matrix respectively to obtain at least one attention score, and generate at least one segmented time feature based on each attention score and each third sub-matrix.

[0116] In one embodiment, the attention score is determined using the following formula:

[0117] Attn ij =Attention(Q i ',K j ')

[0118] Among them, Q i ' represents the first sub-matrix of i, K j ' represents the jth second sub-matrix. ij Represents Q i ' and K j 'Attention score between.

[0119] The following formula is used to generate segment time features:

[0120] Y i =Softmax(Attn i1 ,Attn i2 ,……,Attnin )V j

[0121] Among them, V j Represents the jth third submatrix, Attn i1 ,Attn i2 ,……,Attn in Represents Q i ' and K j 'Each attention score between. Y i Represents segmented time features.

[0122] S304: Generate target time splicing features based on the feature splicing results of each segment time feature, and generate target initial time-space features based on the target time splicing features and the target space features.

[0123] In one embodiment, the target time splicing feature is generated using the following formula:

[0124] Y ′ =w s Concat(Y1,Y2,……,Y s )

[0125] Among them, w s Represents the learnable scaling factors of each segment time feature determined according to the target time step, Y1, Y2, ..., Y s Represents the time characteristics of each segment, Y ′ Represents the target temporal splicing feature.

[0126] Furthermore, the target initial spatiotemporal features are generated according to the target temporal splicing features and the target spatial features.

[0127] By generating a query matrix according to the target time enhancement feature and the first weight matrix, generating a key matrix according to the target time enhancement feature and the second weight matrix, and generating a value matrix according to the target time enhancement feature and the third weight matrix; dividing the query matrix according to the target time step to obtain at least one first sub-matrix, dividing the key matrix according to the target time step to obtain at least one second sub-matrix, and dividing the value matrix according to the target time step to obtain at least one third sub-matrix, it is beneficial to better capture the dynamic trend of the cash deposit amount over time, so as to facilitate the fusion of high time granularity global information and low time granularity local information in the feature extraction process.

[0128] By performing attention mechanism processing on each first sub-matrix and each second sub-matrix respectively, at least one attention score is obtained, and at least one segmented time feature is generated based on each attention score and each third sub-matrix; a target time splicing feature is generated based on the feature splicing results of each segmented time feature, and a target initial spatiotemporal feature is generated based on the target time splicing feature and the target spatial feature, thereby realizing the extraction of time correlation from continuous time segments containing richer time feature information, thereby obtaining the corresponding output effect at different time scales.

[0129] Example 4

[0130] Figure 4 This is a flowchart of a target spatiotemporal fusion feature generation method provided by the fourth embodiment of the present invention. This embodiment further optimizes and expands the above embodiment and can be combined with the above optional implementation methods. Figure 4 As shown, the method includes:

[0131] S401 , performing weighted summation on other initial spatiotemporal features according to the spatial correlation coefficients, and determining a topological spatiotemporal feature according to the weighted summation result.

[0132] In one embodiment, the topological spatiotemporal characteristics are determined using the following formula:

[0133] a t,i,j =Softmax(e t,i,j );

[0134] x t ′ ,i =LeakyReLU(∑ j∈N a t,i,j W j x t,j )

[0135] Among them, e t,i,j W represents the spatial correlation coefficient between the target ATM i and other ATM j. j x t,j Represents other initial spatiotemporal features corresponding to other ATMs j. t ′ ,i Represents topological spatiotemporal features.

[0136] S402: Input the topological spatiotemporal features into the first long short-term memory network so that the first long short-term memory network can capture the temporal dependencies in the topological spatiotemporal features, and determine the temporal optimization features based on the output results of the first long short-term memory network.

[0137] In one embodiment, the time optimization feature is determined using the following formula:

[0138] H intra,t ,C intra,t =LSTM1(X intra,t ,H intra,t-1 ,C intra,t-1 ,W,b);

[0139] X intra,t =x ′ t,i ;

[0140] Among them, X intra,t is the topological spatiotemporal feature, LSTM1 represents the first long short-term memory network, H intra,t represents the time optimization feature, H intra,t-1 ,C intra,t-1 Represents the hidden layer state and memory unit at the previous moment, W, b represent the learnable weights and biases in the input unit, forgetting unit, output unit and memory unit respectively.

[0141] S403: Input the auxiliary spatiotemporal features into the second long short-term memory network so that the second long short-term memory network can capture the spatial dependencies in the auxiliary spatiotemporal features, and determine the spatial optimization features based on the output results of the second long short-term memory network.

[0142] The auxiliary spatiotemporal features are determined according to the topological spatiotemporal features and the target distance value, and the target distance value is determined according to the distance values ​​between the target ATM and other ATMs.

[0143] In one embodiment, the spatial optimization feature is determined using the following formula:

[0144] H inter,t ,C inter,t =LSTM2(X inter,t ,H inter,t-1 ,C inter,t-1 ,W,b);

[0145] X inter,t =x ′ t,i ·S;

[0146] Among them, X inter,t is the auxiliary spatiotemporal feature, S is the inverse of the target distance. LSTM2 represents the second long short-term memory network, H inter,t represents the spatial optimization feature, H inter,t-1 ,C inter,t-1 Represents the hidden layer state and memory unit at the previous moment, W, b represent the learnable weights and biases in the input unit, forgetting unit, output unit and memory unit respectively.

[0147] S404: Determine target spatiotemporal fusion features based on a weighted summation result between the temporal optimization features and the spatial optimization features.

[0148] In one embodiment, the target spatiotemporal fusion feature is determined using the following formula:

[0149] H fusion,t =θ intra °H intra,t +θ inter °H inter,t

[0150] Among them, H fusion,t represents the target spatiotemporal fusion feature, H intra,t represents the time optimization feature, H inter,t represents the spatial optimization feature, θ intra and θ inter They represent learnable weights, and “°” represents the multiplication operation of matrix elements one by one.

[0151] By performing weighted summation on the other initial spatiotemporal features according to the spatial correlation coefficients, and determining the topological spatiotemporal features based on the weighted summation results; inputting the topological spatiotemporal features into the first long short-term memory network for the first long short-term memory network to capture the time dependency in the topological spatiotemporal features, and determining the time optimization features based on the output results of the first long short-term memory network; inputting the auxiliary spatiotemporal features into the second long short-term memory network for the second long short-term memory network to capture the spatial dependency in the auxiliary spatiotemporal features, and determining the space optimization features based on the output results of the second long short-term memory network; determining the target spatiotemporal fusion features based on the weighted summation results between the time optimization features and the space optimization features, thereby achieving the effect of capturing the dependency between time and space, avoiding the problem of weakening the spatiotemporal relationship caused by the separate learning of time features and space features, improving the feature accuracy of the target spatiotemporal fusion features, and further improving the accuracy of the cash deposit prediction.

[0152] Optionally, the method further includes:

[0153] The target spatiotemporal fusion features are input into the target fully connected neural network, and based on the output results of the target fully connected neural network, the predicted spatiotemporal fusion features corresponding to the target ATM at at least one future time point are determined; and the predicted cash deposit amount corresponding to the target ATM at each future time point is predicted based on the predicted spatiotemporal fusion features.

[0154] In one embodiment, the target spatiotemporal fusion feature is determined using the following formula:

[0155]

[0156] Y t+k =ReLU(WFC H fusion,t +b FC );

[0157] Among them, H fusion,t is the output of multi-scale spatiotemporal fusion features, θ output,s For each time scale s, different learnable weights are used. Flatten is the expansion operation, and “°” represents the operation of multiplying matrix elements one by one. W FC and b FC is the learnable weight and bias matrix for the target fully connected neural network, ReLU is the activation function, Y t+k Represents the predicted spatiotemporal fusion features corresponding to the target ATM at at least one future time point.

[0158] By inputting the target spatiotemporal fusion features into the target fully connected neural network, and based on the output results of the target fully connected neural network, the predicted spatiotemporal fusion features corresponding to the target ATM at at least one future time point are determined; the predicted cash deposits corresponding to the target ATM at each future time point are predicted based on the predicted spatiotemporal fusion features, thereby achieving the effect of predicting the cash deposits of the target ATM at future moments, which is conducive to continuously ensuring that banks rationally allocate cash resources and effectively prevent risks.

[0159] Example 5

[0160] Figure 5 This is a schematic diagram of the structure of a device for predicting the amount of cash stored in an ATM provided by the fifth embodiment of the present invention, which can be used to predict the amount of cash stored in an ATM by using three feature dimensions: time feature, spatial feature, and static feature. Figure 5 As shown, the device includes:

[0161] The time-enhanced feature generation module 51 is configured to obtain at least one target time feature and at least one target static feature corresponding to the current time point, and generate a target time-enhanced feature based on the target time feature and the target static feature; wherein the target static feature includes at least one of a user behavior feature, a payment method feature, and a withdrawal fee feature;

[0162] A spatial correlation coefficient determination module 52 is configured to determine the spatial correlation coefficient between each of the other cash dispensers and the target cash dispenser based on the target initial spatiotemporal characteristics corresponding to the target cash dispenser and other initial spatiotemporal characteristics corresponding to at least one other cash dispenser; wherein the target initial spatiotemporal characteristics are determined based on at least one target spatial characteristic corresponding to the target cash dispenser and the target time enhancement characteristic, and the other initial spatiotemporal characteristics are determined based on at least one other spatial characteristic corresponding to the other cash dispenser and the target time enhancement characteristic;

[0163] The cash deposit amount prediction module 53 is used to determine the target spatiotemporal fusion features corresponding to the target ATM based on each of the spatial correlation coefficients and each of the other initial spatiotemporal features, and predict the target cash deposit amount corresponding to the target ATM at the current time point based on the target spatiotemporal fusion features.

[0164] Optionally, the time enhancement feature generation module 51 is specifically configured to:

[0165] Inputting at least one candidate static feature into a first gated residual network, and determining first selection weight values ​​corresponding to each of the candidate static features according to an output result of the first gated residual network;

[0166] Inputting each of the candidate static features into a second gated residual network, and determining a first feature variable value corresponding to each of the candidate static features according to an output result of the second gated residual network;

[0167] According to each of the first feature variable values ​​and each of the first selection weight values, the first weighted feature variable value corresponding to each of the candidate static features is determined, and according to each of the first weighted feature variable values, the target static feature is determined from the candidate static features.

[0168] Optionally, the time enhancement feature generation module 51 is further configured to:

[0169] Inputting at least one candidate temporal feature and a first contextual feature into the first gated residual network, and determining a second selection weight value corresponding to each of the candidate temporal features based on an output result of the first gated residual network; wherein the first contextual feature is determined based on the target static feature;

[0170] Inputting each of the candidate time features into a third gated residual network, and determining a second feature variable value corresponding to each of the candidate time features according to an output result of the third gated residual network;

[0171] According to each second feature variable value and each second selection weight value, the second weighted feature variable value corresponding to each candidate time feature is determined, and the target time feature is determined from each candidate time feature according to each second weighted feature variable value.

[0172] Optionally, the time enhancement feature generation module 51 is further configured to:

[0173] Performing position encoding on each of the target time features to generate a first encoding feature, and performing timestamp encoding on each of the target time features to generate a second encoding feature;

[0174] A target coding feature is generated based on the first coding feature and the second coding feature, and the target coding feature and the second context feature are input into the fourth gated residual network. The target temporal enhancement feature is determined based on the output result of the fourth gated residual network; wherein the second context feature is generated based on the target static feature.

[0175] Optionally, the device further includes a target initial spatiotemporal feature generation module, specifically configured to:

[0176] generating a query matrix according to the target time enhancement feature and a first weight matrix, generating a key matrix according to the target time enhancement feature and a second weight matrix, and generating a value matrix according to the target time enhancement feature and a third weight matrix;

[0177] Partitioning the query matrix according to a target time step to obtain at least one first submatrix, partitioning the key matrix according to the target time step to obtain at least one second submatrix, and partitioning the value matrix according to the target time step to obtain at least one third submatrix;

[0178] Performing attention mechanism processing on each of the first sub-matrices and each of the second sub-matrices to obtain at least one attention score, and generating at least one segmented time feature based on each of the attention scores and each of the third sub-matrices;

[0179] A target time splicing feature is generated according to the feature splicing results of each of the segmented time features, and the target initial spatiotemporal feature is generated according to the target time splicing feature and the target spatial feature.

[0180] Optionally, the spatial correlation coefficient determination module 52 is specifically configured to:

[0181] Generate a first spatiotemporal weighted feature based on the target ATM weight value corresponding to the target ATM and the target initial spatiotemporal feature, and generate a second spatiotemporal weighted feature based on the other ATM weight values ​​corresponding to each of the other ATMs and each of the other initial spatiotemporal features;

[0182] The feature splicing result of the first spatiotemporal weighted feature and the second spatiotemporal weighted feature is input into a graph attention network, and the spatial correlation coefficient is determined according to the output result of the graph attention network.

[0183] Optionally, the cash deposit amount prediction module 53 is specifically configured to:

[0184] Performing weighted summation on each of the other initial spatiotemporal features according to each of the spatial correlation coefficients, and determining a topological spatiotemporal feature according to the weighted summation result;

[0185] Inputting the topological spatiotemporal features into a first long short-term memory network, allowing the first long short-term memory network to capture the temporal dependencies in the topological spatiotemporal features, and determining a time optimization feature based on an output result of the first long short-term memory network;

[0186] Inputting the auxiliary spatiotemporal features into a second long short-term memory network so that the second long short-term memory network can capture spatial dependencies in the auxiliary spatiotemporal features, and determining spatial optimization features based on output results of the second long short-term memory network; wherein the auxiliary spatiotemporal features are determined based on the topological spatiotemporal features and a target distance value, and the target distance value is determined based on the distance values ​​between the target ATM and each of the other ATMs;

[0187] The target spatiotemporal fusion feature is determined according to a weighted summation result between the time optimization feature and the space optimization feature.

[0188] Optionally, the device further includes a spatiotemporal fusion feature prediction module, specifically configured to:

[0189] Inputting the target spatiotemporal fusion features into a target fully connected neural network, and determining the predicted spatiotemporal fusion features corresponding to the target ATM at at least one future time point based on the output results of the target fully connected neural network;

[0190] The predicted cash deposit amount of the target ATM at each of the future time points is predicted based on the predicted spatiotemporal fusion features.

[0191] The device for predicting the cash deposit amount of an ATM provided by an embodiment of the present invention can execute the method for predicting the cash deposit amount of an ATM provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0192] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0193] Example 6

[0194] Figure 6A schematic diagram of the structure of an electronic device 60 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0195] like Figure 6 As shown, the electronic device 60 includes at least one processor 61 and a memory, such as a read-only memory (ROM) 62, a random access memory (RAM) 63, etc., which is communicatively connected to the at least one processor 61. The memory stores a computer program that can be executed by the at least one processor. The processor 61 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 62 or the computer program loaded from the storage unit 68 into the random access memory (RAM) 63. Various programs and data required for the operation of the electronic device 60 can also be stored in the RAM 63. The processor 61, ROM 62, and RAM 63 are connected to each other via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0196] Multiple components in the electronic device 60 are connected to the I / O interface 65, including an input unit 66, such as a keyboard, a mouse, etc.; an output unit 67, such as various types of displays, speakers, etc.; a storage unit 68, such as a magnetic disk, an optical disk, etc.; and a communication unit 69, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 69 allows the electronic device 60 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0197] Processor 61 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any other suitable processor, controller, microcontroller, etc. Processor 61 executes the various methods and processes described above, such as the method for predicting the cash level of an ATM.

[0198] In some embodiments, the method for predicting the amount of cash deposited at an ATM can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 68. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 60 via the ROM 62 and / or the communication unit 69. When the computer program is loaded into the RAM 63 and executed by the processor 61, one or more steps of the method for predicting the amount of cash deposited at an ATM described above can be performed. Alternatively, in other embodiments, the processor 61 can be configured to execute the method for predicting the amount of cash deposited at an ATM by any other appropriate means (for example, by means of firmware).

[0199] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0200] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0201] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0202] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0203] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0204] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0205] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0206] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for predicting the amount of cash deposited in an ATM, characterized in that: The method comprises: Obtaining at least one target time feature and at least one target static feature corresponding to the current time point, and generating a target time enhancement feature based on the target time feature and the target static feature; wherein the target static feature includes at least one of a user behavior feature, a payment method feature, and a withdrawal fee feature; Determine, based on the target initial spatiotemporal features corresponding to the target ATM and other initial spatiotemporal features corresponding to at least one other ATM, the spatial correlation coefficients between each of the other ATMs and the target ATM; wherein the target initial spatiotemporal features are determined based on at least one target spatial feature and the target time enhancement feature corresponding to the target ATM, and the other initial spatiotemporal features are determined based on at least one other spatial feature and the target time enhancement feature corresponding to the other ATM; According to each of the spatial correlation coefficients and each of the other initial spatiotemporal features, the target spatiotemporal fusion features corresponding to the target ATM are determined, and the target cash deposit amount corresponding to the target ATM at the current time point is predicted based on the target spatiotemporal fusion features.

2. The method according to claim 1, characterized in that The obtaining of at least one static feature of the target corresponding to the current time point includes: Inputting at least one candidate static feature into a first gated residual network, and determining first selection weight values ​​corresponding to each of the candidate static features according to an output result of the first gated residual network; Inputting each of the candidate static features into a second gated residual network, and determining a first feature variable value corresponding to each of the candidate static features according to an output result of the second gated residual network; According to each of the first feature variable values ​​and each of the first selection weight values, the first weighted feature variable value corresponding to each of the candidate static features is determined, and according to each of the first weighted feature variable values, the target static feature is determined from the candidate static features.

3. The method according to claim 2, characterized in that The obtaining of at least one target time feature corresponding to the current time point includes: Inputting at least one candidate temporal feature and a first contextual feature into the first gated residual network, and determining a second selection weight value corresponding to each of the candidate temporal features based on an output result of the first gated residual network; wherein the first contextual feature is determined based on the target static feature; Inputting each of the candidate time features into a third gated residual network, and determining a second feature variable value corresponding to each of the candidate time features according to an output result of the third gated residual network; According to each second feature variable value and each second selection weight value, the second weighted feature variable value corresponding to each candidate time feature is determined, and the target time feature is determined from each candidate time feature according to each second weighted feature variable value.

4. The method according to claim 1, wherein Generating a target time enhancement feature according to the target time feature and the target static feature includes: Performing position encoding on each of the target time features to generate a first encoding feature, and performing timestamp encoding on each of the target time features to generate a second encoding feature; A target coding feature is generated based on the first coding feature and the second coding feature, and the target coding feature and the second context feature are input into a fourth gated residual network. The target temporal enhancement feature is determined based on the output result of the fourth gated residual network; wherein the second context feature is generated based on the target static feature.

5. The method according to claim 1, further comprising: generating a query matrix according to the target time enhancement feature and a first weight matrix, generating a key matrix according to the target time enhancement feature and a second weight matrix, and generating a value matrix according to the target time enhancement feature and a third weight matrix; Partitioning the query matrix according to a target time step to obtain at least one first submatrix, partitioning the key matrix according to the target time step to obtain at least one second submatrix, and partitioning the value matrix according to the target time step to obtain at least one third submatrix; Performing attention mechanism processing on each of the first sub-matrices and each of the second sub-matrices to obtain at least one attention score, and generating at least one segmented time feature based on each of the attention scores and each of the third sub-matrices; A target time splicing feature is generated according to the feature splicing results of each of the segmented time features, and the target initial spatiotemporal feature is generated according to the target time splicing feature and the target spatial feature.

6. The method according to claim 1, characterized in that The step of determining the spatial correlation coefficient between each of the other ATMs and the target ATM based on the target initial spatiotemporal characteristics corresponding to the target ATM and other initial spatiotemporal characteristics corresponding to at least one other ATM includes: Generate a first spatiotemporal weighted feature based on the target ATM weight value corresponding to the target ATM and the target initial spatiotemporal feature, and generate a second spatiotemporal weighted feature based on the other ATM weight values ​​corresponding to each of the other ATMs and each of the other initial spatiotemporal features; The feature splicing result of the first spatiotemporal weighted feature and the second spatiotemporal weighted feature is input into a graph attention network, and the spatial correlation coefficient is determined according to the output result of the graph attention network.

7. The method according to claim 1, characterized in that Determining the target spatiotemporal fusion feature corresponding to the target ATM according to each of the spatial correlation coefficients and each of the other initial spatiotemporal features includes: Performing weighted summation on each of the other initial spatiotemporal features according to each of the spatial correlation coefficients, and determining a topological spatiotemporal feature according to the weighted summation result; Inputting the topological spatiotemporal features into a first long short-term memory network, allowing the first long short-term memory network to capture the temporal dependencies in the topological spatiotemporal features, and determining a time optimization feature based on an output result of the first long short-term memory network; Inputting the auxiliary spatiotemporal features into a second long short-term memory network so that the second long short-term memory network can capture spatial dependencies in the auxiliary spatiotemporal features, and determining spatial optimization features based on output results of the second long short-term memory network; wherein the auxiliary spatiotemporal features are determined based on the topological spatiotemporal features and a target distance value, and the target distance value is determined based on the distance values ​​between the target ATM and each of the other ATMs; The target spatiotemporal fusion feature is determined according to a weighted summation result between the time optimization feature and the space optimization feature.

8. The method according to claim 7, further comprising: Inputting the target spatiotemporal fusion features into a target fully connected neural network, and determining the predicted spatiotemporal fusion features corresponding to the target ATM at at least one future time point based on the output results of the target fully connected neural network; The predicted cash deposit amount of the target ATM at each of the future time points is predicted based on the predicted spatiotemporal fusion features.

9. A device for predicting the amount of cash stored in an ATM, characterized in that: The device comprises: a time-enhanced feature generation module, configured to obtain at least one target time feature and at least one target static feature corresponding to a current time point, and generate a target time-enhanced feature based on the target time feature and the target static feature; wherein the target static feature includes at least one of a user behavior feature, a payment method feature, and a withdrawal fee feature; A spatial correlation coefficient determination module is configured to determine the spatial correlation coefficient between each of the other cash dispensers and the target cash dispenser based on the target initial spatiotemporal characteristics corresponding to the target cash dispenser and other initial spatiotemporal characteristics corresponding to at least one other cash dispenser; wherein the target initial spatiotemporal characteristics are determined based on at least one target spatial characteristic corresponding to the target cash dispenser and the target time enhancement characteristic, and the other initial spatiotemporal characteristics are determined based on at least one other spatial characteristic corresponding to the other cash dispenser and the target time enhancement characteristic; The cash deposit amount prediction module is used to determine the target spatiotemporal fusion features corresponding to the target ATM based on each of the spatial correlation coefficients and each of the other initial spatiotemporal features, and predict the target cash deposit amount corresponding to the target ATM at the current time point based on the target spatiotemporal fusion features.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the cash storage amount of an ATM according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute the method for predicting the cash deposit amount of an ATM according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, wherein when executed by a processor, the computer program implements the method for predicting the cash deposit amount of an ATM according to any one of claims 1 to 8.

Images