Banknote adding processing method, device, equipment, medium and product

Abstract

The invention provides a cash replenishing processing method, device and equipment, a medium and a product, and relates to the field of financial science and technology or other related fields. The method comprises the following steps: establishing a first function and a second function based on a log-likelihood function according to weather data and commanded service data before a day to be predicted; the first function represents the number of users of the financial equipment under the weather influence, and the second function represents the number of users of the financial equipment under the substitutive business influence; the weather data of the to-be-predicted day and the commission business data of the to-be-predicted day are respectively substituted into a first function and a second function, and a first number of people output by the first function and a second number of people output by the second function are summed to obtain the number of users of the to-be-predicted day; according to the number of users of the to-be-predicted day, predicting money adding data of the to-be-predicted day; and according to the cash replenishing data, executing cash replenishing operation. According to the scheme of the invention, the accuracy of money adding amount prediction is improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and in particular to a method, device, equipment, medium and product for processing banknotes. Background Art

[0002] By predicting the amount of cash added to the machine, banks can more accurately grasp the cash demand of self-service financial equipment. This helps banks to achieve reasonable allocation of cash on hand and avoid too much or too little cash. When there is too much cash, funds will be idle and the time value of funds will be lost; when there is too little cash, the self-service equipment may be short of cash, affecting the customer's withdrawal experience. Therefore, predicting the amount of cash added to the machine is an important means to achieve cash management optimization.

[0003] The current methods for predicting the amount of additional cash are all based on historical cash withdrawal data to predict the amount of additional cash; however, using this method, the prediction results obtained are inaccurate. Summary of the invention

[0004] The present application provides a method, device, equipment, medium and product for processing banknotes to improve the accuracy of banknote addition amount prediction.

[0005] In a first aspect, the present application provides a method for processing cash addition, comprising: establishing a first function and a second function based on a log-likelihood function according to weather data and agency payment business data before a day to be predicted; the first function represents the number of people using the financial device under the influence of the weather, and the second function represents the number of people using the financial device under the influence of the agency payment business; the weather data of the day to be predicted and the agency payment business data of the day to be predicted are respectively introduced into the first function and the second function, and the first number of people output by the first function and the second number of people output by the second function are summed to obtain the number of users on the day to be predicted; based on the number of users on the day to be predicted, the cash addition data of the day to be predicted is predicted; and the cash addition operation is performed based on the cash addition data.

[0006] In a second aspect, the present application provides a device for processing banknotes, comprising: an establishment module, used to establish a first function and a second function based on a log-likelihood function according to weather data and agency business data before a day to be predicted; the first function represents the number of people using the financial device under the influence of the weather, and the second function represents the number of people using the financial device under the influence of the agency business; a processing module, used to bring the weather data of the day to be predicted and the agency business data of the day to be predicted into the first function and the second function, respectively, and sum the first number of people output by the first function and the second number of people output by the second function to obtain the number of users on the day to be predicted; a prediction module, used to predict the banknote adding data of the day to be predicted according to the number of users on the day to be predicted; and perform a banknote adding operation according to the banknote adding data.

[0007] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the above method.

[0008] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above method.

[0009] In a fifth aspect, the present application provides a computer program product, including a computer program, which is used to implement the above method when executed by a processor.

[0010] In the method, device, equipment, medium and product for processing additional cash provided by the present application, a first function representing the number of people using financial equipment affected by the weather and a second function representing the number of people using financial equipment affected by the additional payment business are established based on the logarithmic natural function according to the weather data and the additional payment business data before the day to be predicted; the weather data and the additional payment business data of the day to be predicted are respectively input into the first function and the second function to obtain the first number of users and the second number of users, and the first number of users and the second number of users are summed to obtain the number of users on the day to be predicted; and based on the number of users on the day to be predicted, the amount of additional cash on the day to be predicted is predicted; the scheme of the present application, combined with multiple dimensions of weather and additional payment business conditions, accurately predicts the number of users of financial equipment based on the logarithmic likelihood function, and accurately predicts the amount of additional cash data based on the number of financial equipment users, thereby improving the accuracy of the prediction of the amount of additional cash. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0012] Figure 1 A schematic diagram of a method for processing banknotes is shown as an example;

[0013] Figure 2 A schematic diagram of a method for processing banknotes is shown as an example;

[0014] Figure 3 A schematic diagram of a method for processing banknotes is shown as an example;

[0015] Figure 4 A schematic diagram of a method for processing banknotes is shown as an example;

[0016] Figure 5 A schematic diagram of a method for processing banknotes is shown as an example;

[0017] Figure 6The schematic diagram of the structure of a banknote adding processing device is shown as an example;

[0018] Figure 7 A structural schematic diagram of an electronic device is exemplarily shown in FIG.

[0019] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0020] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0021] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0022] It should be noted that the brief description of the terms in this application is only for the convenience of understanding the implementation methods described below, and is not intended to limit the implementation methods of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings. The terms "first", "second", etc. in the specification and claims and the above-mentioned drawings in this application are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise indicated. It should be understood that the terms used in this way can be interchangeable where appropriate, for example, they can be implemented in an order other than those given in the diagram or description of the embodiment of this application. The terms "including" and "having" in the specification and claims and the above-mentioned drawings in this application and any of their variations are intended to cover but not exclusively include, for example, a product or device containing a series of components is not necessarily limited to those components clearly listed, but may include other components that are not clearly listed or inherent to these products or devices. The term "module" used in this application refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic or a combination of hardware or / and software code that can perform functions related to the element.

[0023] It should be noted that the banknote adding processing method, device, equipment, medium and product provided in this application can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the banknote adding processing method, device, equipment, medium and product in this application is not limited.

[0024] By predicting the amount of cash added to the machine, banks can more accurately grasp the cash demand of self-service equipment. This helps banks to achieve reasonable allocation of cash on hand and avoid too much or too little cash. When there is too much cash, funds will be idle and the time value of funds will be lost; when there is too little cash, the self-service equipment may be out of money, affecting the customer's withdrawal experience. Therefore, predicting the amount of cash added is an important means to optimize cash management.

[0025] The current methods for predicting the amount of cash added are all based on historical cash withdrawal data to predict the amount of cash added; however, this method cannot accurately predict the amount of cash added, resulting in poor resource benefit effects and reduced customer experience.

[0026] The technical solution provided by the present application is intended to solve the above technical problems of the prior art. In the method, device, equipment, medium and product for processing banknotes provided by the present application, a corresponding first function representing the number of people using financial equipment affected by the weather and a second function representing the number of people using financial equipment affected by the banknotes are established based on the logarithmic natural function according to the weather data and the banknotes data before the day to be predicted; the weather data and the banknotes data of the day to be predicted are input into the first function and the second function respectively to obtain the first number of users and the second number of users, and the first number of users and the second number of users are summed to obtain the number of users on the day to be predicted; and the amount of banknotes added on the day to be predicted is predicted based on the number of users on the day to be predicted; the solution of the present application, combined with multiple dimensions of weather and banknotes, accurately predicts the number of users of financial equipment based on the logarithmic likelihood function, and accurately predicts the amount of banknotes added based on the number of financial equipment users, thereby improving the accuracy of the prediction of the amount of banknotes added.

[0027] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0028] Embodiment 1

[0029] Figure 1 A schematic diagram of a method for adding banknotes is shown as an example; Figure 1 As shown, the method includes:

[0030] Step 101: According to the weather data and agency payment service data before the forecast date, a first function and a second function are established based on the log-likelihood function; the first function represents the number of users of the financial device under the influence of the weather, and the second function represents the number of users of the financial device under the influence of the agency payment service;

[0031] Step 102: Substitute the weather data of the day to be predicted and the agency business data of the day to be predicted into the first function and the second function respectively, and sum the first number of people output by the first function and the second number of people output by the second function to obtain the number of users on the day to be predicted;

[0032] Step 103: predict the banknote adding data for the day to be predicted according to the number of users on the day to be predicted; and perform a banknote adding operation according to the banknote adding data.

[0033] Specifically, when predicting the specific amount of cash added to the cash adding equipment, first, according to the weather data before the predicted date and the agency business data, based on the logarithmic likelihood function, the first function and the second function are established; exemplary, the weather data includes specific weather types, such as rain, snow, sunny, etc.; and the actual temperature values ​​corresponding to different dates. In practical applications, relevant weather data can be collected by setting sensors in the bank; for example, temperature sensors, air sensors, weather sensors, etc. are deployed near bank outlets to collect data such as temperature and weather type; subsequently, a corresponding relationship is established according to the number of people who come to the store corresponding to different weather data, and the number of people who come to the store affected by different weather conditions can be obtained based on the corresponding relationship. Agency business refers to a business in which a bank accepts the entrustment of a commissioned unit and transfers the wages, bonuses and other incomes paid by the commissioned unit to the employees of the unit to the current savings account opened by the designated employee in the bank through transfer. In addition, agency business also includes agency welfare income, agency social security funds, agency insurance premiums and surrender fees, one-time transfer subsidies, demolition and relocation fees and other personal legal income. According to the specific agency payment business data, the number of people who use financial equipment to withdraw cash affected by the agency payment business data can be predicted. Further, the first function established represents the number of people who actually go to the bank outlets to use financial equipment under the influence of weather; the second function established represents the number of people who actually go to the bank to withdraw money using financial equipment affected by the agency payment business; exemplary, the financial equipment is an automatic teller machine; the number of people who use the cash machine at the point affected by the agency payment business refers to the number of people who go to the bank to withdraw wages because their wages have arrived, or the number of people who withdraw pensions, or the number of people who withdraw cash related to other related agency payment businesses. After the first function and the second function are established, the weather data corresponding to the day to be predicted and the agency payment business data are substituted into the first function and the second function respectively, and the predicted first number of people output by the first function and the predicted second number of people output by the second function can be obtained; the first number of people and the second number of people are summed to obtain the number of people who go to the bank to use financial equipment on the day to be predicted. Afterwards, according to the predicted number of people who use financial equipment to withdraw cash on the day to be predicted, the specific amount of money that needs to be added to the financial equipment is predicted. When the actual amount value of the predicted specific money adding data is obtained, the money adding operation is performed according to the predicted result. In this example, the first function and the second function are established based on the constructed logarithmic function according to the historical weather data and the agency business data; and the weather data and the agency business data of the predicted day are brought into the established first function and the second function to obtain the number of machine users on the predicted day; then, based on the predicted number of people, the amount of cash added to the financial device is predicted, and then the specific cash adding operation is performed based on the predicted amount of cash added; this example improves the accuracy of the prediction results of the cash adding amount.

[0034] Specifically, it is necessary to accurately establish the first function and the second function; accordingly, as an example, Figure 2The flowchart of a method for processing banknotes is exemplified. Based on any example, according to the weather data and the agency payment service data before the predicted date, based on the logarithmic likelihood function, a first function and a second function are established, including:

[0035] Step 201: establishing a first operator based on weather data and the number of users on different dates before the day to be predicted; and establishing a second operator based on the agency service data and the number of users on different dates before the day to be predicted;

[0036] Step 202: input the first operator and the second operator into a log-likelihood function, and use an optimization algorithm to determine parameter values ​​of the first operator and the second operator;

[0037] Step 203: Substitute the parameter values ​​of the first operator and the second operator into the first operator and the second operator respectively to obtain the first function and the second function.

[0038] Exemplarily, according to the weather data and the number of people using the financial equipment on different dates before the forecast date, a first operator is established, and the first operator is used to establish a first function of the number of people using the financial equipment affected by the weather; according to the agency payment business data and the number of users on different dates before the forecast date, a second operator is established, and the second operator is used to establish a second function of the number of people using the financial equipment affected by the agency payment business; the established first operator and second operator are brought into the log-likelihood, and the parameter values ​​in the first operator and the second operator are calculated using the optimization algorithm; in practical applications, the log-likelihood function is an important concept in statistics, which is defined based on the likelihood function; the likelihood function describes the probability of a certain parameter value causing the occurrence of these data when a set of known data (usually known results or phenomena) is given; in other words, the likelihood function is a function of the parameter, which represents the probability relationship between the parameter and the known data. Exemplarily, the optimization algorithm is a gradient ascent algorithm or a genetic algorithm; this example does not limit the specific type of the optimization algorithm. The gradient ascent algorithm is an optimization algorithm used to find the local maximum of a function. In contrast to the gradient descent algorithm, the gradient ascent algorithm iteratively updates the parameter value along the positive direction of the function gradient (or slope) in order to reach the local maximum of the function. The genetic algorithm is an optimization search algorithm based on the principles of natural selection and genetics. It simulates the biological evolution process in nature, and gradually optimizes the optimal solution to the problem through operations such as competition, selection, crossover (hybridization) and mutation among individuals in the population. In this example, the gradient ascent algorithm and the genetic algorithm can be used to solve the parameter values ​​of the first operator and the second operator. After obtaining the parameter values ​​of the first operator and the parameter values ​​of the second operator, the parameter values ​​are substituted into the first operator and the second operator respectively, and the first function corresponding to the first operator and the second function corresponding to the second operator can be obtained. In this example, by establishing the first operator and the second operator, and based on the log-likelihood function, the optimization algorithm is used to determine the parameter values ​​of the first operator and the second operator; and the parameter values ​​of the first operator and the second operator are respectively substituted into the first operator and the second operator to obtain the corresponding first function and the second function; the accuracy of establishing the first function and the second function is improved.

[0039] Specifically, weather data includes weather type and temperature; accordingly, as an example, Figure 3 The flowchart of a method for processing banknotes is shown as an example; based on any example, a first operator is established according to weather data and the number of users on different dates before the predicted date, including:

[0040] Step 301: Establish a first mapping relationship; the first mapping relationship includes weather impact indexes corresponding to combinations of different weather types and temperatures;

[0041] Step 302: Obtain weather impact indexes for different dates before the day to be predicted based on weather data for different dates before the day to be predicted and the first mapping relationship;

[0042] Step 303: Establish an exponential function based on the weather impact index and the number of users on different dates before the day to be predicted, and obtain a first operator.

[0043] Specifically, weather data includes weather type and temperature, such as sunny, cloudy, rainy, snowy, etc., and specific temperature values. First, a first mapping relationship is established based on the weather type and temperature; the first mapping relationship includes weather impact indexes corresponding to combinations of different weather type temperatures. For example, Table 1 is an example of an impact index relationship corresponding to different weather types and temperatures; as shown in Table 1, different combinations of weather types and temperatures correspond to different weather impact indexes.

[0044] Table 1

[0045]

[0046] It should be noted that 1 in Table 1 indicates that the willingness of the number of people using financial devices to withdraw cash is positive, 2 indicates that the willingness of the number of people using financial devices to withdraw cash is fair, 3 indicates that the willingness of the number of people using financial devices to withdraw cash is average, and 4 indicates that the willingness of the number of people using financial devices to withdraw cash is negative. In actual application, the missing items in Table 1 are supplemented, and the missing items are set to 3 (indicating that the willingness of the number of people using financial devices to withdraw cash is average) to ensure that each item has a value. According to the specific different weather data before the day to be predicted and the first mapping relationship established as shown in Table 1, the weather impact index of different dates before the day to be predicted can be obtained; then, according to the weather data of different dates before the day to be predicted and the number of users of financial devices, an exponential function is established to obtain the first operator; the first operator can be expressed as:

[0047] μ(t)=(h t ) -1 abe -bt

[0048] Among them, μ represents the first operator, t represents the date, h t represents the weather impact index on any date, and a and b represent the parameter values ​​corresponding to the first operator. In this example, the first operator is established according to the weather data of the day to be predicted and the mapping relationship between the weather data and the weather impact index, thereby improving the accuracy of the establishment of the first operator.

[0049] Specifically, the second operator is established according to the agency service data; accordingly, as an example, Figure 4The flowchart of a method for processing banknotes is exemplified; based on any example, a second operator is established according to the agency payment business data and the number of users on different dates before the predicted date, including:

[0050] Step 401, according to the agency payment business data of different dates before the date to be predicted, obtain the number of agency payments on different dates before the date to be predicted;

[0051] Step 402: Divide the number of users on different dates before the prediction date into a plurality of preset number of sets according to age levels;

[0052] Step 403: distribute the number of agency payments on different dates before the predicted date to different sets according to a predetermined rule, and obtain the number of agency payments corresponding to each set;

[0053] Step 404: Establish a multivariate linear function based on the number of payments corresponding to each set to obtain a second operator.

[0054] Specifically, based on the agency payment business data before the date to be predicted, the number of agency payments on different dates before the date to be predicted under the agency payment business data is obtained; in actual applications, the agency payment business data includes the number of agency payments and the specific amount under each agency payment data; the number of people using the financial equipment on different dates before the date to be predicted is divided into a preset number of sets according to age; illustratively, based on the current age and offline business trends, that is, people under 50 years old tend to use online channels, while the elderly aged 50-80 tend to go to stores to withdraw cash, but after the age of 80, the frequency of going to stores will decrease due to physical reasons; therefore, the number of users under 50 years old is divided into the first set, the number of users between 50 and 80 years old is divided into the second set, and the number of users over 80 years old is divided into the third set. Afterwards, the number of agency payment amounts is allocated to the corresponding set; the number of payments allocated to the first set is k. 1t , the number of items allocated in the second set is k 2t , the number of items allocated in the third set is k 3t ;k 1t , k 2t and k 3t The sum of the number of transactions is the total number of transactions in the transaction business before the predicted date. It should be noted that this application does not limit the specific number of sets. Specifically, according to the number of transactions corresponding to different sets, combined with the influence of the aforementioned weather impact index, the second operator is obtained by establishing a multivariate linear function. Specifically expressed as:

[0055] C(t)=m(h t ) -1 k 1t +p(h t ) -1 k 2t +q(ht ) -1 k 3t

[0056] Among them, C represents the second operator, t represents the date, and h t represents the weather impact index on any date, k 1t Indicates the number of outbound outbound business transactions corresponding to the first set, k 2t represents the number of outbound outbound business transactions corresponding to the second set, k 3t It represents the number of agency services corresponding to the third set, and m, p, q represent the parameter values ​​corresponding to the second operator.

[0057] In this example, by establishing the second operator based on the agency payment business data before the predicted date, the number of users of financial equipment affected by the agency payment business is taken into account, the accuracy of the establishment of the second operator is improved, and the accuracy of the cash addition data prediction results is further improved.

[0058] Specifically, after the first operator and the second operator are established, it is necessary to solve the parameter values ​​in the operators. Accordingly, as an example, the first operator and the second operator are input into the log-likelihood function, and the parameter values ​​of the first operator and the second operator are determined by using an optimization algorithm, including:

[0059] Inputting the first operator and the second operator into the log-likelihood function respectively;

[0060] An optimization algorithm is used to take the parameter value corresponding to the maximum estimation of the log-likelihood function as the parameter value of the first operator and the second operator.

[0061] Specifically, after the first operator establishes the first operator and the second operator, the first operator and the second operator are added together to obtain:

[0062] λ(t)=μ(t)+C(t)

[0063] λ represents the sum of the first operator and the second operator, μ represents the first operator, C represents the second operator, and t represents the date. The first operator and the second operator are added to the established log-likelihood function, and the maximum value can be obtained using mature algorithms such as gradient ascent and genetic algorithm. When the value is the maximum, the optimal parameters can be obtained, that is, the specific values ​​of a and b in the first operator, and m, p, q in the second operator can be obtained.

[0064] The formula for the logarithmic function is:

[0065]

[0066] in, represents the log-likelihood function, L represents the likelihood function, and λ represents the sum of the first operator and the second operator; xi Represents the data value in the log-likelihood function, i represents any data, and n represents the total number of data.

[0067] In this example, an optimization algorithm is used to calculate the parameter values ​​in the first operator and the second operator to obtain the parameter values ​​corresponding to when the log-likelihood function reaches the maximum value, which are the parameter values ​​corresponding to the first operator and the second operator, thereby improving the accuracy of establishing the first operator and the second operator.

[0068] Specifically, after the number of users of the financial device on the forecast day is predicted according to the above-mentioned forecasting method and the forecast result is obtained, the amount of cash to be added needs to be predicted according to the obtained predicted number of users; accordingly, as an example, Figure 5 The flowchart of a method for processing banknotes is exemplarily shown. Based on any example, according to the number of users on the predicted day, banknote adding data on the predicted day is predicted, including:

[0069] Step 501: obtaining first cash adding data according to the first number of people and the single cash withdrawal amount; the single cash withdrawal amount is obtained based on the analysis of historical single cash withdrawal amounts;

[0070] Step 502: Obtain second banknote adding data according to the second number of people and the agency payment business data of the to-be-predicted day;

[0071] Step 503: sum the first banknote adding data and the second banknote adding data to obtain the banknote adding data of the day to be predicted.

[0072] Specifically, the first data for adding banknotes is obtained based on the first number of people obtained by the first function affected by the weather and the amount of a single cash withdrawal; wherein the amount of a single cash withdrawal is obtained based on an analysis of historical single cash withdrawal amounts. Next, the second data for adding banknotes is obtained based on the second number of people obtained by the second function affected by the agency payment business and the agency payment business data of the day to be predicted; the first data for adding banknotes and the second data for adding banknotes are added together to obtain the total amount of banknotes required in the financial device on the day to be predicted. In this example, the predicted total data for adding banknotes is obtained by respectively predicting the first data for adding banknotes and the second data for adding banknotes, and calculating the sum of the first data for adding banknotes and the second data for adding banknotes, thereby improving the accuracy of the prediction results of the data for adding banknotes.

[0073] Further, for the second banknote adding data, the agency payment business data on the to-be-predicted day includes multiple agency payment amounts; according to the second number of people and the agency payment business data on the to-be-predicted day, the second banknote adding data is obtained, including:

[0074] Sort multiple amounts of agency payment to obtain an agency payment amount sequence;

[0075] According to the second number of persons, the same number of agency payment amounts are selected from the agency payment amount sequence;

[0076] The selected amounts for payment are summed up to obtain the second banknote adding data.

[0077] In actual applications, the agency payment business data for the predicted day includes the number of agency payments and the actual amount corresponding to each payment; for agency payment business, the agency payment amount is the specific number of payments actually required and the specific amount of each payment; for users, it can be issued online to personal accounts, and some users will go to offline financial devices to withdraw cash. Sort each amount in the total agency payment business data to obtain an agency payment amount sequence; this example does not limit the sorting method, and it can be sorted from large to small or from small to large. After obtaining the agency payment amount sequence, according to the second number of people predicted above, the agency payment amount equal to the number of the second number of people is selected from the obtained agency payment business sequence; further, the selected amounts are added to obtain the predicted second banknote addition data. In this example, the amount equal to the number of the predicted second number of people is selected and added to obtain the predicted banknote addition data, so that the predicted banknote addition data is more accurate, avoiding the waste of resources caused by inaccurate prediction results or the result of poor user experience.

[0078] Further, according to the second number of persons, the same number of agency payment amounts are selected from the agency payment amount sequence, including:

[0079] Determine the median of the payment amount series;

[0080] Starting from the median, traverse to both sides of the median to obtain the same amount of payment as the second number of people.

[0081] Exemplarily, after the specific second number of people is predicted, the amount of payment equal to the number of the second number of people is selected from the established amount of payment sequence; specifically, the median of the amount of payment sequence is determined; starting from the determined median, the amount of payment is selected on both sides of the median to obtain the amount of payment equal to the number of the second number of people. In an example, the amount of payment sequence is expressed as:

[0082] S={S1,S2,S3...S i-1 , S i , S i+1 …S n}

[0083] Among them, S represents the sequence of the amount of payment, S1, S2, S3…S i-1 , S i , S i+1 …S n Indicates the actual value of the specific payment amount data in the sequence; S i Represents the median of the payment amount sequence;

[0084] Specifically, first select S i , then select S i-1 , S i+1 ...until the amount of money issued by the second number of people is selected and summed up to obtain the predicted second banknote addition data. For example, when the predicted second number of people is an odd number, the median S is selected. i After that, S is preferred i+1 ; When the predicted second number is an even number, the median S is selected i After that, S is preferred i-1 The formula for summing up all the payment amounts is:

[0085]

[0086] Among them, S i represents the median, k represents any second number of people, m represents the total number of second numbers, i represents any amount of payment, and S represents the sum of the amounts in the payment amount sequence. In this example, by determining the median of the payment amount sequence, selecting the payment amount from the median, and predicting the second cash addition data, the prediction accuracy of the second cash addition data is further improved.

[0087] Further, when the first cash addition data is predicted based on the first number of people and the single cash withdrawal data, it is necessary to obtain the single cash withdrawal amount. Accordingly, as an example, the method further includes:

[0088] Calculate the ratio of the total amount of historical cash withdrawals before the predicted date to the number of historical cash withdrawals to obtain the amount of a single cash withdrawal.

[0089] Specifically, it is necessary to obtain the total amount of cash withdrawals before the prediction date and the number of cash withdrawals before the prediction date; then, based on the total amount of cash withdrawals and the number of cash withdrawals before the prediction date, calculate the ratio of the total amount of cash withdrawals before the prediction date to the number of cash withdrawals before the prediction date, and you can get the average amount of cash withdrawals per transaction before the prediction date, and the average amount of cash withdrawals per transaction is the single cash withdrawal amount. In this example, the single cash withdrawal amount is obtained by calculating the total amount of cash withdrawals and the total number of cash withdrawals before the prediction date; subsequently, the first cash addition data can be obtained based on the single cash withdrawal amount and the predicted first number of people, which improves the accuracy of the cash addition data prediction results.

[0090] In the method for processing additional cash provided in the present embodiment, a first function representing the number of people using the financial device affected by the weather and a second function representing the number of people using the financial device affected by the additional payment service are established based on the logarithmic natural function according to the weather data and the additional payment service data before the day to be predicted; the weather data and the additional payment service data of the day to be predicted are respectively input into the first function and the second function to obtain the first number of users and the second number of users, and the first number of users and the second number of users are summed to obtain the number of users on the day to be predicted; and based on the number of users on the day to be predicted, the amount of additional cash on the day to be predicted is predicted; the scheme of the present application, combined with multiple dimensions of weather and additional payment service conditions, accurately predicts the number of users of the financial device based on the logarithmic likelihood function, and accurately predicts the amount of additional cash data based on the number of financial device users, thereby improving the accuracy of the prediction of the amount of additional cash.

[0091] Embodiment 2

[0092] Figure 6 The structural diagram of a banknote adding processing device is shown as an example; Figure 6 As shown, the device comprises:

[0093] Establishing module 21, for establishing a first function and a second function based on the log-likelihood function according to the weather data and the agency payment service data before the forecast date; the first function represents the number of users of the financial device under the influence of the weather, and the second function represents the number of users of the financial device under the influence of the agency payment service;

[0094] The processing module 22 is used to bring the weather data of the day to be predicted and the agency service data of the day to be predicted into the first function and the second function respectively, and sum the first number of people output by the first function and the second number of people output by the second function to obtain the number of users on the day to be predicted;

[0095] The prediction module 23 is used to predict the banknote adding data of the day to be predicted according to the number of users on the day to be predicted; and to perform the banknote adding operation according to the banknote adding data.

[0096] Specifically, when predicting the specific amount of cash added to the cash adding equipment, first, according to the weather data before the predicted date and the agency business data, based on the logarithmic likelihood function, the first function and the second function are established; exemplary, the weather data includes specific weather types, such as rain, snow, sunny, etc.; and the actual temperature values ​​corresponding to different dates. In practical applications, relevant weather data can be collected by setting sensors in the bank; for example, temperature sensors, air sensors, weather sensors, etc. are deployed near bank outlets to collect data such as temperature and weather type; subsequently, a corresponding relationship is established according to the number of people who come to the store corresponding to different weather data, and the number of people who come to the store affected by different weather conditions can be obtained based on the corresponding relationship. Agency business refers to a business in which a bank accepts the entrustment of a commissioned unit and transfers the wages, bonuses and other incomes paid by the commissioned unit to the employees of the unit to the current savings account opened by the designated employee in the bank through transfer. In addition, agency business also includes agency welfare income, agency social security funds, agency insurance premiums and surrender fees, one-time transfer subsidies, demolition and relocation fees and other personal legal income. According to the specific agency payment business data, the number of people who use financial equipment to withdraw cash affected by the agency payment business data can be predicted. Further, the first function established represents the number of people who actually go to the bank outlets to use financial equipment under the influence of weather; the second function established represents the number of people who actually go to the bank to withdraw money using financial equipment affected by the agency payment business; exemplary, the financial equipment is an automatic teller machine; the number of people who use the cash machine at the point affected by the agency payment business refers to the number of people who go to the bank to withdraw wages because their wages have arrived, or the number of people who withdraw pensions, or the number of people who withdraw cash related to other related agency payment businesses. After the first function and the second function are established, the weather data corresponding to the day to be predicted and the agency payment business data are substituted into the first function and the second function respectively, and the predicted first number of people output by the first function and the predicted second number of people output by the second function can be obtained; the first number of people and the second number of people are summed to obtain the number of people who go to the bank to use financial equipment on the day to be predicted. Afterwards, according to the predicted number of people who use financial equipment to withdraw cash on the day to be predicted, the specific amount of money that needs to be added to the financial equipment is predicted. When the actual amount value of the predicted specific money adding data is obtained, the money adding operation is performed according to the predicted result. In this example, the first function and the second function are established based on the constructed logarithmic function according to the historical weather data and the agency business data; and the weather data and the agency business data of the predicted day are brought into the established first function and the second function to obtain the number of machine users on the predicted day; then, based on the predicted number of people, the amount of cash added to the financial device is predicted, and then the specific cash adding operation is performed based on the predicted amount of cash added; this example improves the accuracy of the prediction results of the cash adding amount.

[0097] Specifically, it is necessary to accurately establish the first function and the second function; accordingly, as an example, a module 21 is established for:

[0098] A first operator is established based on weather data and the number of users on different dates before the forecast date; and a second operator is established based on the agency service data and the number of users on different dates before the forecast date;

[0099] Inputting the first operator and the second operator into the log-likelihood function, and using an optimization algorithm to determine parameter values ​​of the first operator and the second operator;

[0100] Substitute the parameter values ​​of the first operator and the second operator into the first operator and the second operator respectively to obtain the first function and the second function.

[0101] Exemplarily, according to the weather data and the number of people using the financial equipment on different dates before the forecast date, a first operator is established, and the first operator is used to establish a first function of the number of people using the financial equipment affected by the weather; according to the agency payment business data and the number of users on different dates before the forecast date, a second operator is established, and the second operator is used to establish a second function of the number of people using the financial equipment affected by the agency payment business; the established first operator and second operator are brought into the log-likelihood, and the parameter values ​​in the first operator and the second operator are calculated using the optimization algorithm; in practical applications, the log-likelihood function is an important concept in statistics, which is defined based on the likelihood function; the likelihood function describes the probability of a certain parameter value causing the occurrence of these data when a set of known data (usually known results or phenomena) is given; in other words, the likelihood function is a function of the parameter, which represents the probability relationship between the parameter and the known data. Exemplarily, the optimization algorithm is a gradient ascent algorithm or a genetic algorithm; this example does not limit the specific type of the optimization algorithm. The gradient ascent algorithm is an optimization algorithm used to find the local maximum of a function. In contrast to the gradient descent algorithm, the gradient ascent algorithm iteratively updates the parameter value along the positive direction of the function gradient (or slope) in order to reach the local maximum of the function. The genetic algorithm is an optimization search algorithm based on the principles of natural selection and genetics. It simulates the biological evolution process in nature, and gradually optimizes the optimal solution to the problem through operations such as competition, selection, crossover (hybridization) and mutation among individuals in the population. In this example, the gradient ascent algorithm and the genetic algorithm can be used to solve the parameter values ​​of the first operator and the second operator. After obtaining the parameter values ​​of the first operator and the parameter values ​​of the second operator, the parameter values ​​are substituted into the first operator and the second operator respectively, and the first function corresponding to the first operator and the second function corresponding to the second operator can be obtained. In this example, by establishing the first operator and the second operator, and based on the log-likelihood function, the optimization algorithm is used to determine the parameter values ​​of the first operator and the second operator; and the parameter values ​​of the first operator and the second operator are respectively substituted into the first operator and the second operator to obtain the corresponding first function and the second function; the accuracy of establishing the first function and the second function is improved.

[0102] Specifically, the weather data includes weather type and temperature; accordingly, as an example, a module 21 is established for:

[0103] Establishing a first mapping relationship; the first mapping relationship includes weather impact indexes corresponding to combinations of different weather types and temperatures;

[0104] Obtaining weather impact indexes of different dates before the day to be predicted based on weather data of different dates before the day to be predicted and the first mapping relationship;

[0105] According to the weather impact index and the number of users on different dates before the day to be predicted, an exponential function is established to obtain the first operator.

[0106] Specifically, weather data includes weather type and temperature, such as sunny, cloudy, rainy, snowy, etc.; and specific temperature values. First, a first mapping relationship is established based on the weather type and temperature; the first mapping relationship includes the weather impact index corresponding to the combination of different weather type temperatures. Exemplarily, 1 indicates that the willingness of the number of people using financial equipment to withdraw cash is positive, 2 indicates that the willingness of the number of people using financial equipment to withdraw cash is fair, 3 indicates that the willingness of the number of people using financial equipment to withdraw cash is average, and 4 indicates that the willingness of the number of people using financial equipment to withdraw cash is negative. In actual application, the missing items in Table 1 are supplemented, and the missing items are set to 3 (indicating that the willingness of the number of people using financial equipment to withdraw cash is average) to ensure that each item has a value. According to the specific different weather data before the day to be predicted and the established first mapping relationship, the weather impact index of different dates before the day to be predicted can be obtained; then, according to the weather data of different dates before the day to be predicted and the number of users of the financial equipment, an exponential function is established to obtain the first operator; the first operator can be expressed as:

[0107] μ(t)=(h t ) -1 abe -bt

[0108] Among them, μ represents the first operator, t represents the date, h t represents the weather impact index on any date, and a and b represent the parameter values ​​corresponding to the first operator. In this example, the first operator is established according to the weather data of the day to be predicted and the mapping relationship between the weather data and the weather impact index, thereby improving the accuracy of the establishment of the first operator.

[0109] Specifically, the second operator is established according to the agency service data; accordingly, as an example, a module 21 is established for:

[0110] According to the agency payment business data of different dates before the forecast date, the number of agency payments on different dates before the forecast date is obtained;

[0111] Divide the number of users on different dates before the prediction date into a plurality of preset sets according to age levels;

[0112] Allocate the number of agency payments on different dates before the predicted date to different sets according to a predetermined rule, and obtain the number of agency payments corresponding to each set;

[0113] According to the number of payments corresponding to each set, a multivariate linear function is established to obtain the second operator.

[0114] Specifically, based on the agency payment business data before the date to be predicted, the number of agency payments on different dates before the date to be predicted under the agency payment business data is obtained; in actual applications, the agency payment business data includes the number of agency payments and the specific amount under each agency payment data; the number of people using the financial equipment on different dates before the date to be predicted is divided into a preset number of sets according to age; illustratively, based on the current age and offline business trends, that is, people under 50 years old tend to use online channels, while the elderly aged 50-80 tend to go to stores to withdraw cash, but after the age of 80, the frequency of going to stores will decrease due to physical reasons; therefore, the number of users under 50 years old is divided into the first set, the number of users between 50 and 80 years old is divided into the second set, and the number of users over 80 years old is divided into the third set. Afterwards, the number of agency payment amounts is allocated to the corresponding set; the number of payments allocated to the first set is k. 1t , the number of items allocated in the second set is k 2t , the number of items allocated in the third set is k 3t ;k 1t , k 2t and k 3t The sum of the number of transactions is the total number of transactions in the transaction business before the predicted date. It should be noted that this application does not limit the specific number of sets. Specifically, according to the number of transactions corresponding to different sets, combined with the influence of the aforementioned weather impact index, the second operator is obtained by establishing a multivariate linear function. Specifically expressed as:

[0115] C(t)=m(h t ) -1 k 1t +p(h t ) -1 k 2t +q(h t ) -1 k 3t

[0116] Among them, C represents the second operator, t represents the date, h t represents the weather impact index on any date, k 1t Indicates the number of outbound outbound business transactions corresponding to the first set, k 2t represents the number of outbound outbound business transactions corresponding to the second set, k3t It represents the number of agency services corresponding to the third set, and m, p, q represent the parameter values ​​corresponding to the second operator.

[0117] In this example, by establishing the second operator based on the agency payment business data before the predicted date, the number of users of financial equipment affected by the agency payment business is taken into account, the accuracy of the establishment of the second operator is improved, and the accuracy of the cash addition data prediction results is further improved.

[0118] Specifically, after the first operator and the second operator are established, it is necessary to solve the parameter values ​​in the operators. Accordingly, as an example, the processing module 22 is used to:

[0119] Inputting the first operator and the second operator into the log-likelihood function respectively;

[0120] An optimization algorithm is used to take the parameter value corresponding to the maximum estimation of the log-likelihood function as the parameter value of the first operator and the second operator.

[0121] Specifically, after the first operator establishes the first operator and the second operator, the first operator and the second operator are added together to obtain:

[0122] λ(t)=μ(t)+C(t)

[0123] λ represents the sum of the first operator and the second operator, μ represents the first operator, C represents the second operator, and t represents the date. The first operator and the second operator are added to the established log-likelihood function, and the maximum value can be obtained using mature algorithms such as gradient ascent and genetic algorithm. When the value is the maximum, the optimal parameters can be obtained, that is, the specific values ​​of a and b in the first operator, and m, p, q in the second operator can be obtained.

[0124] The formula for the logarithmic function is:

[0125]

[0126] in, represents the log-likelihood function, L represents the likelihood function, and λ represents the sum of the first operator and the second operator; x i Represents the data value in the log-likelihood function, i represents any data, and n represents the total number of data.

[0127] In this example, an optimization algorithm is used to calculate the parameter values ​​in the first operator and the second operator to obtain the parameter values ​​corresponding to when the log-likelihood function reaches the maximum value, which are the parameter values ​​corresponding to the first operator and the second operator, thereby improving the accuracy of establishing the first operator and the second operator.

[0128] Specifically, after the number of users of the financial device on the forecast day is predicted according to the above-mentioned prediction method and the prediction result is obtained, the amount of cash to be added needs to be predicted according to the obtained predicted number of users; accordingly, as an example, the prediction module 23 is used to:

[0129] The first cash addition data is obtained according to the first number of people and the single cash withdrawal amount; the single cash withdrawal amount is obtained based on the analysis of the historical single cash withdrawal amounts;

[0130] According to the second number of people and the agency payment business data of the to-be-predicted day, the second banknote adding data is obtained;

[0131] The first banknote adding data and the second banknote adding data are summed to obtain the banknote adding data of the day to be predicted.

[0132] Specifically, the first data for adding banknotes is obtained based on the first number of people obtained by the first function affected by the weather and the amount of a single cash withdrawal; wherein the amount of a single cash withdrawal is obtained based on an analysis of historical single cash withdrawal amounts. Next, the second data for adding banknotes is obtained based on the second number of people obtained by the second function affected by the agency payment business and the agency payment business data of the day to be predicted; the first data for adding banknotes and the second data for adding banknotes are added together to obtain the total amount of banknotes required in the financial device on the day to be predicted. In this example, the predicted total data for adding banknotes is obtained by respectively predicting the first data for adding banknotes and the second data for adding banknotes, and calculating the sum of the first data for adding banknotes and the second data for adding banknotes, thereby improving the accuracy of the prediction results of the data for adding banknotes.

[0133] Further, for the second banknote adding data, the agency payment business data on the to-be-predicted day includes multiple agency payment amounts; according to the second number of people and the agency payment business data on the to-be-predicted day, the second banknote adding data is obtained, including:

[0134] Sort multiple amounts of agency payment to obtain an agency payment amount sequence;

[0135] According to the second number of persons, the same number of agency payment amounts are selected from the agency payment amount sequence;

[0136] The selected amounts for payment are summed up to obtain the second banknote adding data.

[0137] In actual applications, the agency payment business data for the predicted day includes the number of agency payments and the actual amount corresponding to each payment; for agency payment business, the agency payment amount is the specific number of payments actually required and the specific amount of each payment; for users, it can be issued online to personal accounts, and some users will go to offline financial devices to withdraw cash. Sort each amount in the total agency payment business data to obtain an agency payment amount sequence; this example does not limit the sorting method, and it can be sorted from large to small or from small to large. After obtaining the agency payment amount sequence, according to the second number of people predicted above, the agency payment amount equal to the number of the second number of people is selected from the obtained agency payment business sequence; further, the selected amounts are added to obtain the predicted second banknote addition data. In this example, the amount equal to the number of the predicted second number of people is selected and added to obtain the predicted banknote addition data, so that the predicted banknote addition data is more accurate, avoiding the waste of resources caused by inaccurate prediction results or the result of poor user experience.

[0138] Further, according to the second number of persons, the same number of agency payment amounts are selected from the agency payment amount sequence, including:

[0139] Determine the median of the payment amount series;

[0140] Starting from the median, traverse to both sides of the median to obtain the same amount of payment as the second number of people.

[0141] Exemplarily, after the specific second number of people is predicted, the amount of payment equal to the number of the second number of people is selected from the established amount of payment sequence; specifically, the median of the amount of payment sequence is determined; starting from the determined median, the amount of payment is selected on both sides of the median to obtain the amount of payment equal to the number of the second number of people. In an example, the amount of payment sequence is expressed as:

[0142] S={S1,S2,S3...S i-1 , S i , S i+1 …S n}

[0143] Among them, S represents the sequence of the amount of payment, S1, S2, S3…S i-1 , S i , S i+1 …S n Represents the actual value of the specific amount of payment data in the sequence; the median of the sequence is: S i represents the median of the sequence of the amount of payment; specifically, first select S i , then select S i-1 , S i+1...until the amount of money issued by the second number of people is selected and summed up to obtain the predicted second banknote addition data. For example, when the predicted second number of people is an odd number, the median S is selected. i After that, S is preferred i+1 ; When the predicted second number is an even number, the median S is selected i After that, S is preferred i-1 The formula for summing up all the payment amounts is:

[0144]

[0145] Among them, S i represents the median, k represents any second number of people, m represents the total number of second numbers of people, i represents any amount of payment, and S represents the sum of the amounts in the payment amount sequence. In this example, by determining the median of the payment amount sequence, selecting the payment amount from the median, and predicting the second cash addition data, the prediction accuracy of the second cash addition data is further improved.

[0146] Further, when the first cash addition data is predicted based on the first number of people and the single cash withdrawal data, it is necessary to obtain the single cash withdrawal amount. Accordingly, as an example, the prediction module 21 is also used for:

[0147] Calculate the ratio of the total amount of historical cash withdrawals before the predicted date to the number of historical cash withdrawals to obtain the amount of a single cash withdrawal.

[0148] Specifically, it is necessary to obtain the total amount of cash withdrawals before the prediction date and the number of cash withdrawals before the prediction date; then, based on the total amount of cash withdrawals and the number of cash withdrawals before the prediction date, calculate the ratio of the total amount of cash withdrawals before the prediction date to the number of cash withdrawals before the prediction date, and you can get the average amount of cash withdrawals per transaction before the prediction date, and the average amount of cash withdrawals per transaction is the single cash withdrawal amount. In this example, the single cash withdrawal amount is obtained by calculating the total amount of cash withdrawals and the total number of cash withdrawals before the prediction date; subsequently, the first cash addition data can be obtained based on the single cash withdrawal amount and the predicted first number of people, which improves the accuracy of the cash addition data prediction results.

[0149] The device for processing banknotes provided in the present embodiment establishes a first function representing the number of people using the financial device affected by the weather and a second function representing the number of people using the financial device affected by the agency payment service based on the logarithmic natural function according to the weather data and agency payment service data before the day to be predicted; the weather data and agency payment service data of the day to be predicted are respectively input into the first function and the second function to obtain the first number of users and the second number of users, and the first number of users and the second number of users are summed to obtain the number of users on the day to be predicted; and the amount of banknotes added on the day to be predicted is predicted based on the number of users on the day to be predicted; the scheme of the present application, combined with multiple dimensions such as weather and agency payment service conditions, accurately predicts the number of people using the financial device based on the logarithmic likelihood function, and accurately predicts the banknote addition amount data based on the number of financial device users, thereby improving the accuracy of the prediction of the amount of banknotes added.

[0150] Embodiment 3

[0151] Figure 7 exemplarily shows a structural schematic diagram of an electronic device, the device comprising:

[0152] The device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, the memory 292, and the communication interface 293 may communicate with each other through the bus 294. The communication interface 293 may be used for information transmission. The processor 291 may call the logic instructions in the memory 292 to execute the above-mentioned example method.

[0153] In addition, the logic instructions in the above-mentioned memory 292 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0154] The memory 292 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, that is, implementing the methods in the above method examples.

[0155] The memory 292 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 292 may include a high-speed random access memory and may also include a non-volatile memory.

[0156] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method in any embodiment.

[0157] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the method in any embodiment when executed by a processor.

[0158] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0159] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0160] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0161] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0162] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not specifically stated, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not specifically stated, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0163] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0164] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0165] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0166] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for processing banknotes, characterized in that: The method comprises: According to the weather data and agency payment service data before the forecast date, a first function and a second function are established based on the log-likelihood function; the first function represents the number of users of the financial device under the influence of the weather, and the second function represents the number of users of the financial device under the influence of the agency payment service; Substitute the weather data of the day to be predicted and the agency business data of the day to be predicted into the first function and the second function respectively, and sum the first number of people output by the first function and the second number of people output by the second function to obtain the number of users on the day to be predicted; According to the number of users on the to-be-predicted day, predict the banknote adding data for the to-be-predicted day; and perform the banknote adding operation according to the banknote adding data.

2. The method according to claim 1, characterized in that The method of establishing the first function and the second function based on the log-likelihood function according to the weather data and the dispatching service data before the day to be predicted includes: A first operator is established based on weather data and the number of users on different dates before the forecast date; and a second operator is established based on the agency service data and the number of users on different dates before the forecast date; Inputting the first operator and the second operator into a log-likelihood function, and using an optimization algorithm to determine parameter values ​​of the first operator and the second operator; Substitute the parameter values ​​of the first operator and the second operator into the first operator and the second operator respectively to obtain the first function and the second function.

3. The method according to claim 2, characterized in that The weather data includes weather type and temperature; the first operator is established according to the weather data of different dates before the predicted date and the number of users, including: Establishing a first mapping relationship; the first mapping relationship includes weather impact indexes corresponding to combinations of different weather types and temperatures; Obtaining weather impact indexes of different dates before the to-be-predicted date according to the weather data of different dates before the to-be-predicted date and the first mapping relationship; An exponential function is established according to the weather impact index and the number of users on different dates before the day to be predicted, to obtain the first operator.

4. The method according to claim 2, characterized in that: The second operator is established according to the agency payment service data and the number of users on different dates before the predicted date, including: According to the agency payment business data of different dates before the to-be-predicted date, the number of agency payments on different dates before the to-be-predicted date is obtained; Dividing the number of users on different dates before the predicted date into a plurality of preset sets according to age levels; Allocate the number of agency payments on different dates before the predicted date to different sets according to a predetermined rule to obtain the number of agency payments corresponding to each set; According to the number of payments corresponding to each set, a multivariate linear function is established to obtain the second operator.

5. The method according to claim 2, wherein the inputting the first operator and the second operator into a log-likelihood function and using an optimization algorithm to determine parameter values ​​of the first operator and the second operator comprises: Inputting the first operator and the second operator into a log-likelihood function respectively; An optimization algorithm is used to take the parameter value corresponding to the maximum value of the log-likelihood function as the parameter value of the first operator and the second operator.

6. The method according to any one of claims 1 to 5, characterized in that: The method of predicting the banknote adding data on the predicted day according to the number of users on the predicted day includes: According to the first number of people and the single cash withdrawal amount, first cash adding data is obtained; the single cash withdrawal amount is obtained based on the analysis of historical single cash withdrawal amounts; According to the second number of people and the agency payment business data of the to-be-predicted day, second banknote adding data is obtained; The first banknote adding data and the second banknote adding data are summed to obtain the banknote adding data of the day to be predicted.

7. The method according to claim 6, characterized in that The agency payment business data of the to-be-predicted day includes multiple agency payment amounts; the second banknote adding data is obtained according to the second number of people and the agency payment business data of the to-be-predicted day, including: Sort multiple amounts of agency payment to obtain an agency payment amount sequence; According to the second number of persons, selecting the same number of agency payment amounts from the agency payment amount sequence; The selected amounts for payment are summed to obtain the second banknote adding data.

8. The method according to claim 7, characterized in that The selecting the same number of agency payment amounts from the agency payment amount sequence according to the second number of persons includes: Determine the median of the sequence of payment amounts; Taking the median as a starting point, traverse to both sides of the median to obtain the same amount of payment as the second number of people.

9. The method according to claim 6, characterized in that The method further comprises: The ratio of the total amount of historical cash withdrawals before the predicted date to the number of historical cash withdrawals is calculated to obtain the single cash withdrawal amount.

10. A banknote adding processing device, characterized in that: The device comprises: Establishing a module, for establishing a first function and a second function based on the log-likelihood function according to the weather data and the agency payment service data before the forecast date; the first function represents the number of users of the financial device under the influence of the weather, and the second function represents the number of users of the financial device under the influence of the agency payment service; A processing module, used for bringing the weather data of the day to be predicted and the agency business data of the day to be predicted into the first function and the second function respectively, and summing the first number of people output by the first function and the second number of people output by the second function to obtain the number of users on the day to be predicted; The prediction module is used to predict the banknote adding data of the day to be predicted according to the number of users on the day to be predicted; and to perform the banknote adding operation according to the banknote adding data.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 9 when being executed by a processor.

Images