Financial product quota allocation method and device, and computer program product

Abstract

The invention discloses a quota allocation method and device of a financial product and a computer program product. The method comprises the following steps: determining M financial institutions participating in quota allocation of a target financial product; for each financial institution, acquiring historical sales data of the target financial product in a preset historical time period to obtain first historical sales data, and generating a first historical condition statistical table model based on the first historical sales data; calculating data in the first historical condition statistical table model to obtain predicted sales data; calculating a quota allocation value of each financial institution according to the predicted sales data of each financial institution and the total quota, and allocating the total quota to M financial institutions based on the quota allocation values; for each financial institution, the quota is allocated to N outlets. According to the invention, the problems of time and labor wasting and error proneness of financial product quota allocation for financial institutions and branches in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a method, device and computer program product for allocating quotas of financial products. Background Art

[0002] In the relevant technology, the quota allocation of financial products mainly relies on manual processing by business personnel. The quota of financial products is allocated to various sales agencies step by step, and then the branches or outlets make secondary allocations. However, the manual allocation method has obvious defects, including the difficulty in scientifically and reasonably evaluating the sales capabilities of each institution, resulting in uneven allocation. At the same time, due to the complexity and time sensitivity of the quota allocation process, manual processing is time-consuming and labor-intensive, and there is a high probability of error. In particular, with the growth of investor demand, manual allocation cannot meet market demand in terms of efficiency and accuracy.

[0003] Currently, no effective solution has been proposed to the problem that allocating financial product quotas to financial institutions and outlets in related technologies is time-consuming, labor-intensive and error-prone. Summary of the invention

[0004] The main purpose of this application is to provide a method, device and computer program product for allocating quotas of financial products to solve the problem in the related art that allocating quotas of financial products to financial institutions and outlets is time-consuming, labor-intensive and error-prone.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for allocating the quota of a financial product is provided. The method includes: determining M financial institutions participating in the quota allocation of a target financial product, where M is a positive integer; for each financial institution, obtaining the historical sales data of the target financial product in a preset historical time period, obtaining the first historical sales data, and generating a first historical situation statistical table model based on the first historical sales data, the historical situation statistical table model storing sales data under different dimensions; for each financial institution, based on an autoregressive time series model, calculating the data in the first historical situation statistical table model to obtain predicted sales data; calculating the quota allocation value of each financial institution based on the predicted sales data and the total quota of each financial institution, and allocating the total quota to M financial institutions based on the quota allocation value; for each financial institution, determining N outlets participating in the quota allocation, and allocating the quota of the financial institution to the N outlets, where N is a positive integer.

[0006] Optionally, the first historical situation statistics table model includes dimension fields and sales fields, the dimension fields include at least a time dimension field, the time dimension field is used to store at least one of the following time information: year, month, and the sales field is used to store at least historical actual sales.

[0007] Optionally, based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain predicted sales data, including: determining the autoregressive order according to the year length of the preset historical time period and the target time dimension, wherein the target time dimension is at least one of the following: year dimension, month dimension; determining the sales observations at P time points under the autoregressive order, and determining the autoregressive coefficient corresponding to each sales observation, wherein the sales observation value is determined by the historical actual sales at the associated time point, and P is a positive integer; determining the predicted sales data based on the P sales observations and the autoregressive coefficients corresponding to the P sales observations.

[0008] Optionally, determining predicted sales data based on P sales observations and autoregressive coefficients corresponding to the P sales observations includes: normalizing the autoregressive coefficients corresponding to the P sales observations to obtain updated P autoregressive coefficients; performing weighted summation of the P sales observations and the updated P autoregressive coefficients to obtain initial predicted sales data; and calculating the sum of the initial predicted sales data and the error value to obtain the predicted sales data.

[0009] Optionally, determining the autoregressive order based on the year length of the preset historical time period and the target time dimension includes: determining the recalculation frequency based on the target time dimension, wherein the recalculation frequency is at least one of the following: annual frequency, monthly frequency; determining the maximum autoregressive period based on the year length of the preset historical time period; determining the autoregressive order based on the maximum autoregressive period and the recalculation frequency.

[0010] Optionally, determining the autoregressive coefficient corresponding to each sales observation includes: calculating the time difference between the current time point and the associated time point of the sales observation in the target time dimension, wherein the time difference is one of the following: year difference, month difference; calculating the product of the maximum autoregressive period and the total time of the target time dimension, wherein the maximum autoregressive period is determined by the year length of a preset historical time period, and the total time is one of the following: the total sum of the months in a year, the total sum of the days in a month; calculating the difference between the product and the time difference, and calculating the ratio of the difference to the product to obtain the autoregressive coefficient corresponding to the sales observation.

[0011] Optionally, allocating the financial institution's credit limit to N outlets includes: for each outlet, obtaining historical sales data of the target financial product within a preset historical time period to obtain second historical sales data, and generating a second historical situation statistical table model based on the second historical sales data; for each outlet, based on an autoregressive time series model, calculating the data in the second historical situation statistical table model to obtain outlet predicted sales data; calculating the outlet credit limit allocation value for each outlet based on the outlet predicted sales data of each outlet and the credit limit of the financial institution, and allocating the financial institution's credit limit to N outlets based on the outlet credit limit allocation value.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a quota automatic allocation device is provided. The device includes: a financial institution determination module, which is used to determine M financial institutions participating in the quota allocation of the target financial product, wherein M is a positive integer; a data acquisition and storage module, which is used to obtain the historical sales data of the target financial product in a preset historical time period for each financial institution, obtain the first historical sales data, and generate a first historical situation statistical table model based on the first historical sales data, and the historical situation statistical table model stores sales data under different dimensions; a data prediction module, which is used to calculate the data in the first historical situation statistical table model based on the autoregressive time series model for each financial institution to obtain the predicted sales data; a financial institution quota allocation module, which is used to calculate the quota allocation value of each financial institution according to the predicted sales data and the total quota of each financial institution, and allocate the total quota to M financial institutions based on the quota allocation value; an outlet quota allocation module, which is used to determine N outlets participating in the quota allocation for each financial institution, and allocate the quota of the financial institution to N outlets, wherein N is a positive integer.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, which includes: a non-volatile computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, a method for allocating a quota of a financial product is implemented.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided. The device includes: a computer program is stored in a memory, and a processor is configured to execute a quota allocation method for a financial product through the computer program.

[0015] In an embodiment of the present application, M financial institutions participating in the quota allocation of the target financial product are determined, where M is a positive integer; for each financial institution, the historical sales data of the target financial product in a preset historical time period is obtained to obtain the first historical sales data, and a first historical situation statistical table model is generated based on the first historical sales data, and the historical situation statistical table model stores sales data under different dimensions; for each financial institution, based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain the predicted sales data; the quota allocation value of each financial institution is calculated according to the predicted sales data and the total quota of each financial institution, and the total quota is allocated to M financial institutions based on the quota allocation value; for each financial institution, N outlets participating in the quota allocation are determined, and the quota of the financial institution is allocated to N outlets, where N is a positive integer. By introducing an autoregressive time series model based on historical sales data, sales data is predicted and the quota allocation of financial products is performed, the purpose of automatic and accurate quota allocation is achieved, thereby achieving the technical effect of improving the efficiency of quota allocation, reducing manual participation, and reducing the error rate, thereby solving the problem of time-consuming, labor-intensive and error-prone allocation of financial product quotas for financial institutions and outlets in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a quota allocation method for financial products;

[0018] Figure 2 is a flow chart of a method for allocating a quota of a financial product provided in an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of an optional automatic quota allocation system provided according to an embodiment of the present application;

[0020] Figure 4 is a schematic diagram of a quota automatic allocation device provided according to an embodiment of the present application;

[0021] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising 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.

[0024] It should be noted that the collected information (including but not limited to user personal information) and data (including but not limited to data for display, analysis, etc.) involved in this application are 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 relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0025] Example 1

[0026] According to an embodiment of the present application, an embodiment of a method for allocating a quota of a financial product is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a quota allocation method for financial products is shown in FIG. Figure 1 As shown, the computer terminal 10 may include one or more ( Figure 1 The system includes a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (MCU, Microcontroller Unit) or a programmable logic device (FPGA, Field-Programmable Gate Array)), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface, Input / Output interface), a universal serial bus (USB, Universal Serial Bus) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the quota allocation method of financial products in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the quota allocation method of the above-mentioned financial products is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display may be, for example, a touch screen liquid crystal display (LCD), which may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0032] Under the above operating environment, this application provides Figure 2 The quota allocation method for the financial products shown. Figure 2 It is a flowchart of a method for allocating a quota of a financial product provided in accordance with an embodiment of the present application.

[0033] Step S201, determining M financial institutions that participate in the quota allocation of the target financial product, where M is a positive integer.

[0034] Electronic devices, application systems, servers and other devices may be used as the execution subject of the present application. In the present embodiment, the quota allocation system of financial products is used as the execution subject to obtain the processing request of the user.

[0035] Specifically, the quota allocation system selects qualified financial institutions from a preset financial institution database. These conditions may include: the historical sales data of the financial institution, the market area covered, and the sales share among similar institutions. The target financial product may be a financial product, and the quota allocation refers to distributing the marketable share of the financial product to qualified financial institutions. The financial institutions participating in the quota allocation can sell the financial product within the allocated quota.

[0036] Step S202: For each financial institution, historical sales data of the target financial product within a preset historical time period is obtained to obtain first historical sales data, and a first historical situation statistical table model is generated based on the first historical sales data, where the historical situation statistical table model stores sales data under different dimensions;

[0037] Specifically, the preset historical time period includes year, month, and day time periods, for example, the past year, the past three months, and the past 100 days, the historical sales data includes historical forecast sales data and historical actual sales data, and the historical situation statistical table model includes a time dimension, an extended dimension, and historical sales data. The first historical situation statistical table model can provide reference data for subsequent calculation of forecast sales data.

[0038] Step S203: For each financial institution, based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain predicted sales data.

[0039] Specifically, the historical sales data of each financial institution is first extracted from the first historical situation statistical table model. The autoregressive time series model uses these historical sales data as a reference to calculate the sales data weight for each period of time, multiply each historical sales data by its corresponding weight, and add up these products to obtain the predicted sales data for the current time point.

[0040] Step S204, calculating the quota allocation value of each financial institution according to the predicted sales data and the total quota of each financial institution, and allocating the total quota to M financial institutions based on the quota allocation value;

[0041] Specifically, the forecast sales data of each financial institution are added together to obtain the total forecast sales data, and then the proportion of the forecast sales data of each financial institution in the total forecast sales data is calculated. The total quota is allocated using this proportion to calculate the specific quota allocation value of each financial institution. For example, if the forecast sales of a financial institution accounts for 25% of the total forecast sales, then its corresponding quota allocation value is equal to 25% of the total quota. Then, the quota allocation system allocates a specific financial product quota to each financial institution based on the calculated quota allocation value.

[0042] Step S205: for each financial institution, determine N outlets that participate in the quota allocation, and allocate the quota of the financial institution to the N outlets, where N is a positive integer.

[0043] Specifically, the predicted sales data of the outlets are used to calculate the allocation ratio of each outlet in the financial institution's quota, and the financial institution's quota is allocated by using the ratio to calculate the specific quota allocation value of each outlet. Then, a specific financial product quota is allocated to each outlet based on the calculated quota allocation value.

[0044] In an embodiment of the present application, M financial institutions participating in the quota allocation of the target financial product are determined, where M is a positive integer; for each financial institution, the historical sales data of the target financial product in a preset historical time period is obtained to obtain the first historical sales data, and a first historical situation statistical table model is generated based on the first historical sales data, and the historical situation statistical table model stores sales data under different dimensions; for each financial institution, based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain the predicted sales data; the quota allocation value of each financial institution is calculated according to the predicted sales data and the total quota of each financial institution, and the total quota is allocated to M financial institutions based on the quota allocation value; for each financial institution, N outlets participating in the quota allocation are determined, and the quota of the financial institution is allocated to N outlets, where N is a positive integer. By introducing an autoregressive time series model based on historical sales data, sales data is predicted and the quota allocation of financial products is performed, the purpose of automatic and accurate quota allocation is achieved, thereby achieving the technical effect of improving the efficiency of quota allocation, reducing manual participation, and reducing the error rate, thereby solving the problem of time-consuming, labor-intensive and error-prone allocation of financial product quotas for financial institutions and outlets in the related technology.

[0045] In order to have sufficient basis for predicting sales data, optionally, in the quota allocation method for financial products provided in the embodiment of the present application, the first historical situation statistical table model includes dimension fields and sales fields, and the dimension fields include at least a time dimension field. The time dimension field is used to store at least one of the following time information: year, month, and the sales field is at least used to store historical actual sales.

[0046] Specifically, the dimension field can be a time dimension field and an extended dimension field. The time dimension field is used to store time information, including year, month, day, etc. The time dimension field is designed as the main dimension and can be used to represent the sales situation in each time period; the extended dimension field has other business characteristics. For example, Table 1 is a schematic table of a historical situation statistical table model provided according to an embodiment of the present application. As shown in Table 1, for the financial product issuance scenario, time dimension 1 represents the year, time dimension 2 represents the month, and time dimension 3 can be expanded or left vacant as needed; extended dimension 1 is term information, and other extended dimensions can be expanded or left vacant as needed, wherein the term information includes 3-year and 5-year terms; the predicted value and the actual value respectively store the predicted value and the final actual statistical value of the corresponding time node. The preset historical time period can be time dimension 1, time dimension 2, and time dimension 3, the historical predicted sales data can be the predicted value, and the historical actual sales data can be the actual value. The sales field is used to store the actual sales data under the time dimension, and the sales can be directly associated with the time information. In this way, by querying these historical sales data, the actual sales performance of each financial institution or outlet in a specific time dimension can be obtained. In addition, it should be noted that Table 1 only lists key field information, and the field type and number of dimensions can be adjusted according to the actual database and business scenarios.

[0047] Table 1

[0048]

[0049]

[0050] The embodiment of the present application stores dimension fields and sales fields through a first historical situation statistical table model, wherein the sales field stores actual historical sales, providing data support for subsequent sales data forecasts.

[0051] In order to more accurately predict future sales data, optionally, in the quota allocation method for financial products provided in the embodiment of the present application, based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain predicted sales data including: determining the autoregressive order according to the year length of the preset historical time period and the target time dimension, wherein the target time dimension is at least one of the following: year dimension, month dimension; determining the sales observations at P time points under the autoregressive order, and determining the autoregressive coefficient corresponding to each sales observation, wherein the sales observation is determined by the historical actual sales at the associated time point, and P is a positive integer; determining the predicted sales data based on the P sales observations and the autoregressive coefficients corresponding to the P sales observations.

[0052] Specifically, the process of calculating the predicted sales data based on the autoregressive time series model is as follows: First, based on the data of the historical time dimension, determine the autoregressive order, that is, how many past time points are selected for the current prediction. These past time points can be sales data divided by year or month. The autoregressive time series model uses these historical data as input variables and generates a model for future sales forecasting by analyzing the correlation between these historical observations.

[0053] Then, the autoregressive coefficient is calculated. When calculating the autoregressive coefficient, by combining the year length of each historical time period and the target time dimension characteristics and the corresponding autoregressive coefficient, it can ensure that the model has differentiated treatment on the data at each time point, so as to better reflect the different impacts of near- and long-term data on the forecast, especially for historical sales data closer to the current time point, a larger autoregressive coefficient is assigned to increase its impact on the predicted sales data.

[0054] Furthermore, the predicted sales data is determined based on the P sales observations and the autoregressive coefficients corresponding to the P sales observations. The formula can be expressed as:

[0055]

[0056] In the formula, c is the model constant and can be set to 0. t-1 is the observed value at time t-1 in the past, which can be the sales observed value, etc. are the autoregression coefficients of the sales observations. A total of P values ​​at time points are selected for calculation, and the predicted value Y at time t is finally obtained. t , the units of t and P can both be months. t is the error value that may occur at time t. It should be noted that the autoregressive time series model may have calculation errors. The error value can be calculated by configuring the error calculation method field, or it can be set to not calculate and ignore the error impact.

[0057] According to the above formula, configure the AR model configuration parameter table shown in Table 2. As shown in Table 2, the AR model configuration parameter table includes the model name, model constant c value, autoregressive maximum period, autoregressive weight calculation method, error calculation method, autoregressive order and recalculation frequency; the primary key refers to one or more fields used to uniquely identify each row of records in the table. The functions of the primary key include: ensuring the uniqueness of the record, ensuring the integrity of the data, and preventing the model from inserting duplicate fields.

[0058] Table 2

[0059]

[0060] According to the above formula, configure the AR model time weight coefficient table shown in Table 3. As shown in Table 3, the AR model time weight coefficient table includes: time dimension 1, time dimension 2, time dimension 3 and weight value, where the weight value is determined by the time dimension. The closer the time dimension 1 is to the current time, the larger the weight value. When the time dimension 1 is the same, the closer the time dimension 2 is to the current time, the larger the weight value. Since the time dimension 3 is empty, the time dimension 3 can be ignored. The weight value is obtained by the autoregressive weight calculation method. The primary key refers to one or more fields used to uniquely identify each row of records in the table. The functions of the primary key include: ensuring the uniqueness of the record, ensuring the integrity of the data, and preventing the model from inserting duplicate fields.

[0061] Table 3

[0062]

[0063] The embodiment of the present application utilizes historical data and an autoregressive time series model to generate predicted sales data for future time periods through a weighted calculation method, thereby providing an effective basis for the reasonable allocation of quotas.

[0064] In order to specifically compare each sales observation value to calculate the predicted sales data, optionally, in the quota allocation method for financial products provided in the embodiment of the present application, determining the predicted sales data based on P sales observation values ​​and the autoregressive coefficients corresponding to the P sales observation values ​​includes: normalizing the autoregressive coefficients corresponding to the P sales observation values ​​to obtain the updated P autoregressive coefficients; performing weighted summation of the P sales observation values ​​and the updated P autoregressive coefficients to obtain the initial predicted sales data; calculating the sum of the initial predicted sales data and the error value to obtain the predicted sales data.

[0065] In actual application, it is necessary to adjust the P value in the autoregressive time series model formula, that is, the autoregressive order, to the autoregressive coefficient value in the formula calculation. Make Taking the P value of 5 as an example, when actually incorporating the calculation, the first five time parameters, that is, the first five sales observations, are used. First, adjust the formula

[0066]

[0067] Before treatment p-1 The last coefficient is obtained by the difference In actual operation, a schematic table of generating autoregressive coefficients is obtained as shown in Table 4. The weights are calculated using the subsequent autoregressive order formula.

[0068] Table 4

[0069]

[0070]

[0071] It should be noted that the normalization process of the autoregressive coefficient will adjust all the coefficients to a relatively consistent scale so that their sum is 1, eliminating the impact of the difference in weight values ​​between different sales observations, ensuring that the data at each time point can participate in the calculation with a reasonable proportion in the forecast calculation, thereby providing a basis for the subsequent weighted summation. The weighted summation process multiplies each sales observation by its updated normalized autoregressive coefficient, and then sums these products to obtain the initial forecast sales data. The historical sales at each time point have a corresponding impact on the forecast results, especially the observations with higher weights have a greater impact on the final forecast results.

[0072] The embodiment of the present application normalizes the autoregressive coefficients corresponding to the sales observation values ​​to obtain updated autoregressive coefficients, and further calculates the initial predicted sales data and the predicted sales data, thereby improving the accuracy of the predicted sales data.

[0073] Optionally, in the quota allocation method for financial products provided in the embodiments of the present application, determining the autoregressive order based on the year length of the preset historical time period and the target time dimension includes: determining the recalculation frequency based on the target time dimension, wherein the recalculation frequency is at least one of the following: annual frequency, monthly frequency; determining the maximum autoregressive period based on the year length of the preset historical time period; determining the autoregressive order based on the maximum autoregressive period and the recalculation frequency.

[0074] Specifically, if the target time dimension is year, the recalculation frequency is yearly, and the model is recalculated once a year; if the target time dimension is month, the recalculation frequency is monthly, and the model is recalculated once a month.

[0075] The maximum autoregressive period represents the longest time span of historical observations that the model is allowed to use when calculating. The determination of the maximum autoregressive period ensures that the model can use sufficiently long historical data to obtain more reliable trends, while avoiding the use of too early historical data to interfere with the prediction results. The preset historical time period used in the embodiment of the present application can be up to two years, and the maximum autoregressive period can be set to two years, so that the model will use the data within the past two years as the basis when making predictions. When the recalculation frequency is monthly and the maximum autoregressive period is two years, the autoregressive order can be determined to be 24.

[0076] The autoregressive order determines the number of historical time points selected when the model is calculated, and is affected by the maximum autoregressive period and the recalculation frequency. The autoregressive order not only matches the time span of the data, but also can flexibly reflect changes in the market and sales. The embodiment of the present application obtains the autoregressive order by determining the recalculation frequency and the maximum autoregressive period, making the autoregressive model more adaptable and accurate, thereby ensuring the accuracy of the sales data forecast results.

[0077] Optionally, in the quota allocation method for financial products provided in the embodiment of the present application, determining the autoregressive coefficient corresponding to each sales observation value includes: calculating the time difference between the current time point and the associated time point of the sales observation value in the target time dimension, wherein the time difference is one of the following: year difference, month difference; calculating the product of the maximum autoregressive period and the sum of the time of the target time dimension, wherein the maximum autoregressive period is determined by the year length of the preset historical time period, and the time sum is one of the following: the sum of the months in a year, the sum of the days in a month; calculating the difference between the product and the time difference, and calculating the ratio of the difference to the product to obtain the autoregressive coefficient corresponding to the sales observation value.

[0078] Specifically, the time difference is obtained by subtracting the associated time point of the sales observation from the current time point, and the unit can be years or months; the time sum of the target time dimension is used to determine the time span under this dimension, such as the total number of months in a year is 12, or the total number of days in a month is 28 to 31. By multiplying the maximum autoregressive period by the time sum, a reference value of the overall time span can be obtained. This product provides a benchmark for the subsequent calculation of the autoregressive coefficient. The calculation method of the autoregressive coefficient shows that it is determined by the product of the maximum autoregressive period and the time sum of the target time dimension and the time difference. The following is the specific calculation formula.

[0079] For example, the autoregressive coefficient can be calculated by the following simple decreasing regression function:

[0080]

[0081] The value m in the formula is the maximum autoregressive period in the AR model configuration parameter table, T is the year and month of the calculation, and T (x,y) For the year and month in the past, TT (x,y) is the month difference. When the recalculation frequency is monthly, the weight values ​​of each month are recalculated at the beginning of each month. Taking 2024-02-01 as an example, the model will automatically generate Table 5 is a graph showing the weight values ​​of the generated A schematic table of weight values ​​is shown in Table 5, where time dimension 1 can be a year and time dimension 2 can be a month.

[0082] Table 5

[0083]

[0084] The embodiment of the present application makes it possible to clarify the autoregressive coefficient of each sales observation value. The autoregressive coefficient reflects the importance of a specific historical observation value relative to the overall time span. The smaller the time difference of the observation value, the larger the corresponding autoregressive coefficient, which means that the historical data closer to the current time point has a more significant impact on the current forecast. Using the autoregressive coefficient, the model can reasonably reflect the degree of impact of historical sales data on the current forecast at different time points.

[0085] Optionally, in the method for allocating the quota of financial products provided in the embodiment of the present application, allocating the quota of a financial institution to N outlets includes: for each outlet, obtaining the historical sales data of the target financial product within a preset historical time period, obtaining second historical sales data, and generating a second historical situation statistical table model based on the second historical sales data; for each outlet, based on an autoregressive time series model, calculating the data in the second historical situation statistical table model to obtain the outlet predicted sales data; calculating the outlet quota allocation value of each outlet based on the outlet predicted sales data of each outlet and the quota of the financial institution, and allocating the quota of the financial institution to N outlets based on the outlet quota allocation value.

[0086] Specifically, the preset historical time period includes the year, month, and day time period, and the historical sales data includes the historical predicted sales data and the historical actual sales data. The data in the second historical situation statistical table model (for example, the time dimension and the historical sales data) can provide reference data for calculating the predicted sales data of the outlets. After obtaining the predicted sales data of each outlet, the predicted sales data of each outlet are added together to obtain the total predicted sales data of the outlet, and then the proportion of the predicted sales data of each outlet to the total predicted sales data of the outlet is calculated, and the total quota is allocated by using the proportion to calculate the specific quota allocation value of each outlet.

[0087] Based on the total forecast sales data of the outlets, the financial product quota Q of each outlet is allocated according to the following formula:

[0088]

[0089] The last branch of the financial all -Q1-Q2-...-Q n-1 Processing. In the formula, Q all is the credit limit of the financial institution, P t is the predicted sales data of outlet t, P1+P2+...+P n Total forecast sales data for outlets.

[0090] The embodiment of the present application further allocates the branch's quota to the outlets by calculating the total predicted sales data of the outlets and the specific quota allocation value of each outlet, thereby achieving the last step of allocating the financial product quota.

[0091] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer device such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0092] Example 2

[0093] The embodiment of the present application also provides an automatic quota allocation system. It should be noted that the automatic quota allocation system of the embodiment of the present application can be used to execute the quota allocation method of the financial product provided in the embodiment of the present application. The automatic quota allocation system provided in the embodiment of the present application is introduced below.

[0094] Figure 3 is a schematic diagram of an optional automatic quota allocation system provided according to an embodiment of the present application, such as Figure 3 As shown, the automatic quota allocation system includes three modules: model self-processing module, historical data loading module and quota allocation module, which specifically include:

[0095] The model self-processing module is used to scan the AR time series model and obtain various data in the model; determine whether the horizontal type has been adjusted; if adjustment has occurred, recalculate the model coefficient factor according to the adjusted model; if no adjustment has occurred, determine whether the current time meets the model reset time; if the model reset time is met, recalculate the model coefficient factor according to the adjusted model; if the model reset time is not met, no processing is performed.

[0096] The historical data loading module is used to load historical data according to the issuance results after the issuance of financial products is completed.

[0097] The quota allocation module is used to set the parameters of the planned financial products, where the financial product parameters can be the financial product quota; calculate the actual coefficient factor based on the AR model, where the actual coefficient factor can be the autoregressive order, the autoregressive coefficient and the sales observation value; predict the sales quota of each level based on the AR model, where the sales quota of each level can be the predicted sales data and the predicted sales data of the outlets; allocate the quota of each branch according to the predicted value ratio, where the quota of each branch can be the quota allocation value of each financial institution; allocate the quota of each outlet according to the predicted value ratio, where the quota of each outlet can be the outlet quota allocation value of each outlet.

[0098] The automatic quota allocation system provided in the embodiment of the present application achieves the purpose of automatic and accurate quota allocation by introducing an autoregressive time series model based on historical sales data to predict sales data and allocate quotas for financial products, thereby achieving the technical effect of improving quota allocation efficiency, reducing manual participation, and lowering error rates, thereby solving the problem in related technologies that allocating financial product quotas to financial institutions and outlets is time-consuming, labor-intensive and error-prone.

[0099] According to an embodiment of the present application, a device for implementing the above-mentioned quota allocation method for financial products is also provided. The quota allocation device for financial products provided in the embodiment of the present application is introduced below. Figure 4 is a schematic diagram of an automatic quota allocation device provided according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0100] The financial institution determination module 401 is used to determine M financial institutions that participate in the quota allocation of the target financial product, where M is a positive integer;

[0101] The data acquisition and storage module 402 is used to acquire the historical sales data of the target financial product in a preset historical time period for each financial institution, obtain the first historical sales data, and generate a first historical situation statistical table model based on the first historical sales data, wherein the historical situation statistical table model stores sales data under different dimensions;

[0102] The data prediction module 403 is used to calculate the data in the first historical situation statistical table model for each financial institution based on the autoregressive time series model to obtain predicted sales data;

[0103] The financial institution quota allocation module 404 is used to calculate the quota allocation value of each financial institution according to the predicted sales data and the total quota of each financial institution, and allocate the total quota to M financial institutions based on the quota allocation value;

[0104] The branch credit allocation module 405 is used to determine N branches participating in credit allocation for each financial institution, and allocate the credit of the financial institution to the N branches, where N is a positive integer.

[0105] The automatic quota allocation device provided in the embodiment of the present application includes a financial institution determination module 401, which is used to determine M financial institutions that participate in the quota allocation of the target financial product, wherein M is a positive integer; a data acquisition and storage module 402, which is used to obtain, for each financial institution, the historical sales data of the target financial product within a preset historical time period, obtain the first historical sales data, and generate a first historical situation statistical table model based on the first historical sales data, wherein the historical situation statistical table model stores sales data under different dimensions; a data prediction module 403, which is used to calculate the data in the first historical situation statistical table model based on an autoregressive time series model for each financial institution to obtain predicted sales data; a financial institution quota allocation module 404, which is used to calculate the quota allocation value of each financial institution based on the predicted sales data and the total quota of each financial institution, and allocate the total quota to the M financial institutions based on the quota allocation value; and a branch quota allocation module 405, which is used to determine, for each financial institution, N branches that participate in the quota allocation, and allocate the quota of the financial institution to the N branches, wherein N is a positive integer. By introducing an autoregressive time series model based on historical sales data to predict sales data and allocate financial product quotas, the goal of automated and accurate quota allocation is achieved, thereby achieving the technical effect of improving quota allocation efficiency, reducing manual participation, and lowering error rates, thereby solving the problem in related technologies that allocating financial product quotas to financial institutions and outlets is time-consuming, labor-intensive and error-prone.

[0106] It should be noted that the above modules correspond to steps S201 to S205 in Example 1, and the examples and application scenarios implemented by each module and the corresponding steps are the same, but are not limited to the contents disclosed in the above Example 1. It should be noted that the above modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above modules can also be run in the computer terminal 10 provided in Example 1 as part of the device.

[0107] Optionally, in the automatic quota allocation device provided in the embodiment of the present application, the data acquisition and storage module 402 includes a field statistics module, which is used to count the first historical situation statistical table model including dimension fields and sales fields. The dimension fields include at least a time dimension field. The time dimension field is used to store at least one of the following time information: year, month, and the sales field is at least used to store historical actual sales.

[0108] Optionally, in the automatic quota allocation device provided in the embodiment of the present application, the data prediction module 403 includes an observation value calculation module, which is used to calculate the data in the first historical situation statistical table model based on the autoregressive time series model to obtain predicted sales data including: an autoregressive order determination module, which is used to determine the autoregressive order according to the year length of a preset historical time period and the target time dimension, wherein the target time dimension is at least one of the following: year dimension, month dimension; an autoregressive coefficient determination module, which is used to determine the sales observation values ​​of P time points under the autoregressive order, and determine the autoregressive coefficient corresponding to each sales observation value, wherein the sales observation value is determined by the historical actual sales at the associated time point, and P is a positive integer; a predicted sales data determination module, which is used to determine the predicted sales data based on P sales observation values ​​and the autoregressive coefficients corresponding to the P sales observation values.

[0109] Optionally, in the automatic quota allocation device provided in the embodiment of the present application, the predicted sales data determination module includes: a normalization module, used to normalize the autoregressive coefficients corresponding to P sales observations to obtain the updated P autoregressive coefficients; a weighted summation module, used to perform weighted summation of the P sales observations and the updated P autoregressive coefficients to obtain initial predicted sales data; and an error calculation module, used to calculate the sum of the initial predicted sales data and the error value to obtain the predicted sales data.

[0110] Optionally, in the automatic quota allocation device provided in the embodiment of the present application, the autoregressive order determination module includes: a recalculation frequency determination module, used to determine the recalculation frequency according to the target time dimension, wherein the recalculation frequency is at least one of the following: annual frequency, monthly frequency; an autoregressive maximum term determination module, used to determine the autoregressive maximum term according to the year length of a preset historical time period; an autoregressive order determination sub-module, used to determine the autoregressive order according to the autoregressive maximum term and the recalculation frequency.

[0111] Optionally, in the automatic quota allocation device provided in the embodiment of the present application, the autoregressive coefficient determination module includes: a time difference determination module, which is used to determine the time difference between the current time point and the associated time point of the sales observation value in the target time dimension, wherein the time difference is one of the following: year difference, month difference; a product calculation module, which is used to calculate the product of the autoregressive maximum term and the time sum of the target time dimension, wherein the autoregressive maximum term is determined by the year length of the preset historical time period, and the time sum is one of the following: the sum of the months in a year, the sum of the days in a month; an autoregressive coefficient determination sub-module, which is used to calculate the difference between the product and the time difference, and calculate the ratio of the difference to the product to obtain the autoregressive coefficient corresponding to the sales observation value.

[0112] Optionally, in the automatic credit allocation device provided in the embodiment of the present application, the branch credit allocation module 405 includes: a second historical situation statistical table model generation module, which is used to obtain the historical sales data of the target financial product within a preset historical time period for each branch, obtain the second historical sales data, and generate a second historical situation statistical table model based on the second historical sales data; a branch predicted sales data determination module, which is used to calculate the data in the second historical situation statistical table model for each branch based on the autoregressive time series model to obtain the branch predicted sales data; a branch credit allocation sub-module, which is used to calculate the branch credit allocation value of each branch according to the branch predicted sales data of each branch and the credit of the financial institution, and allocate the credit of the financial institution to N branches based on the branch credit allocation value.

[0113] Example 3

[0114] An embodiment of the present application may provide an electronic device, Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (only one is shown) processor 502, memory 504, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0115] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0116] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: determine M financial institutions participating in the quota allocation of the target financial product, where M is a positive integer; for each financial institution, obtain the historical sales data of the target financial product within a preset historical time period to obtain the first historical sales data, and generate a first historical situation statistical table model based on the first historical sales data, and the historical situation statistical table model stores sales data under different dimensions; for each financial institution, based on the autoregressive time series model, calculate the data in the first historical situation statistical table model to obtain predicted sales data; calculate the quota allocation value of each financial institution based on the predicted sales data and the total quota of each financial institution, and allocate the total quota to the M financial institutions based on the quota allocation value; for each financial institution, determine N outlets participating in the quota allocation, and allocate the quota of the financial institution to the N outlets, where N is a positive integer.

[0117] The processor can also call the information and applications stored in the memory through the transmission device to perform the following steps: the first historical situation statistical table model includes dimension fields and sales fields, the dimension fields include at least a time dimension field, the time dimension field is used to store at least one of the following time information: year, month, the sales field is at least used to store historical actual sales.

[0118] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain the predicted sales data including: determining the autoregressive order according to the year length of the preset historical time period and the target time dimension, wherein the target time dimension is at least one of the following: year dimension, month dimension; determining the sales observation values ​​of P time points under the autoregressive order, and determining the autoregressive coefficient corresponding to each sales observation value, wherein the sales observation value is determined by the historical actual sales at the associated time point, and P is a positive integer; determining the predicted sales data based on the P sales observation values ​​and the autoregressive coefficients corresponding to the P sales observation values.

[0119] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: determining the predicted sales data based on P sales observations and the autoregressive coefficients corresponding to the P sales observations, including: normalizing the autoregressive coefficients corresponding to the P sales observations to obtain the updated P autoregressive coefficients; performing weighted summation of the P sales observations and the updated P autoregressive coefficients to obtain initial predicted sales data; calculating the sum of the initial predicted sales data and the error value to obtain the predicted sales data.

[0120] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determining the autoregressive order based on the year length of the preset historical time period and the target time dimension, including: determining the recalculation frequency based on the target time dimension, wherein the recalculation frequency is at least one of the following: annual frequency, monthly frequency; determining the maximum autoregressive period based on the year length of the preset historical time period; determining the autoregressive order based on the maximum autoregressive period and the recalculation frequency.

[0121] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determining the autoregressive coefficient corresponding to each sales observation value includes: based on the time difference between the current time point and the associated time point of the sales observation value in the target time dimension, wherein the time difference is one of the following: year difference, month difference; calculating the product of the maximum autoregressive period and the total time of the target time dimension, wherein the maximum autoregressive period is determined by the year length of the preset historical time period, and the total time is one of the following: the total month of a year, the total date of a month; calculating the difference between the product and the time difference, and calculating the ratio of the difference to the product to obtain the autoregressive coefficient corresponding to the sales observation value.

[0122] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: allocating the financial institution's quota to N outlets, including: for each outlet, obtaining the historical sales data of the target financial product within a preset historical time period, obtaining the second historical sales data, and generating a second historical situation statistical table model based on the second historical sales data; for each outlet, based on the autoregressive time series model, calculating the data in the second historical situation statistical table model to obtain the outlet predicted sales data; calculating the outlet quota allocation value of each outlet based on the outlet predicted sales data of each outlet and the quota of the financial institution, and allocating the financial institution's quota to N outlets based on the outlet quota allocation value.

[0123] In an embodiment of the present application, M financial institutions participating in the quota allocation of the target financial product are determined, where M is a positive integer; for each financial institution, the historical sales data of the target financial product in a preset historical time period is obtained to obtain the first historical sales data, and a first historical situation statistical table model is generated based on the first historical sales data, and the historical situation statistical table model stores sales data under different dimensions; for each financial institution, based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain the predicted sales data; the quota allocation value of each financial institution is calculated according to the predicted sales data and the total quota of each financial institution, and the total quota is allocated to M financial institutions based on the quota allocation value; for each financial institution, N outlets participating in the quota allocation are determined, and the quota of the financial institution is allocated to N outlets, where N is a positive integer. By introducing an autoregressive time series model based on historical sales data, sales data is predicted and the quota allocation of financial products is performed, the purpose of automatic and accurate quota allocation is achieved, thereby achieving the technical effect of improving the efficiency of quota allocation, reducing manual participation, and reducing the error rate, thereby solving the problem of time-consuming, labor-intensive and error-prone allocation of financial product quotas for financial institutions and outlets in the related technology.

[0124] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 5 The structure of the electronic device is not limited. Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations are shown.

[0125] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0126] Example 4

[0127] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the quota allocation method of the financial product provided in the first embodiment.

[0128] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0129] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the method for allocating the amount of a financial product.

[0130] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0131] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0135] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions to enable 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 method described in each embodiment of the present application. The aforementioned storage medium 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.

[0136] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for allocating quotas of financial products, characterized in that: include: Determine M financial institutions that participate in the quota allocation of the target financial product, where M is a positive integer; For each financial institution, historical sales data of the target financial product within a preset historical time period is obtained to obtain first historical sales data, and a first historical situation statistical table model is generated based on the first historical sales data, wherein the historical situation statistical table model stores sales data under different dimensions; For each financial institution, based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain predicted sales data; Calculating a quota allocation value for each financial institution according to the predicted sales data and the total quota of each financial institution, and allocating the total quota to the M financial institutions based on the quota allocation value; For each financial institution, N outlets participating in quota allocation are determined, and the quota of the financial institution is allocated to the N outlets, where N is a positive integer.

2. The method for allocating quotas of financial products according to claim 1, characterized in that: The first historical situation statistics table model includes dimension fields and sales fields. The dimension fields include at least a time dimension field. The time dimension field is used to store at least one of the following time information: year, month. The sales field is used to store at least historical actual sales.

3. The method for allocating quotas of financial products according to claim 2, characterized in that: Based on the autoregressive time series model, the data in the first historical situation statistical table model is calculated to obtain the predicted sales data including: Determining the autoregressive order according to the year length of the preset historical time period and the target time dimension, wherein the target time dimension is at least one of the following: year dimension, month dimension; Determine the sales observations at P time points under the autoregressive order, and determine the autoregressive coefficient corresponding to each sales observation, wherein the sales observations are determined by the historical actual sales at the associated time points, and P is a positive integer; Determine predicted sales data based on P sales observations and autoregression coefficients corresponding to the P sales observations.

4. The method for allocating quotas of financial products according to claim 3, characterized in that: Determining the predicted sales data based on P sales observations and the autoregressive coefficients corresponding to the P sales observations includes: Normalizing the autoregressive coefficients corresponding to the P sales observations to obtain updated P autoregressive coefficients; Performing weighted summation on the P sales observations and the updated P autoregressive coefficients to obtain initial predicted sales data; The sum of the initial predicted sales data and the error value is calculated to obtain the predicted sales data.

5. The method for allocating quotas of financial products according to claim 3, characterized in that: Determining the autoregressive order according to the year length of the preset historical time period and the target time dimension includes: Determine a recalculation frequency according to the target time dimension, wherein the recalculation frequency is at least one of the following: annual frequency, monthly frequency; Determining the maximum autoregressive period according to the length of the preset historical time period in years; The autoregressive order is determined based on the autoregressive maximum term and the recalculation frequency.

6. The method for allocating quotas of financial products according to claim 3, characterized in that: Determining the autoregression coefficient for each sales observation involves: The time difference between the current time point and the associated time point of the sales observation value in the target time dimension, wherein the time difference is one of the following: year difference, month difference; Calculate the product of the maximum autoregressive period and the time sum of the target time dimension, wherein the maximum autoregressive period is determined by the year length of the preset historical time period, and the time sum is one of the following: the sum of the months of a year, the sum of the days of a month; The difference between the product and the time difference is calculated, and the ratio of the obtained difference to the product is calculated to obtain the autoregressive coefficient corresponding to the sales observation value.

7. The method for allocating quotas of financial products according to claim 1, characterized in that: Allocating the credit limit of the financial institution to the N outlets includes: For each outlet, historical sales data within the preset historical time period is obtained to obtain second historical sales data, and a second historical situation statistical table model is generated based on the second historical sales data; For each outlet, based on the autoregressive time series model, the data in the second historical situation statistical table model is calculated to obtain the outlet predicted sales data; The outlet quota allocation value of each outlet is calculated according to the outlet forecast sales data of each outlet and the quota of the financial institution, and the quota of the financial institution is allocated to the N outlets based on the outlet quota allocation value.

8. A quota allocation device for financial products, characterized in that: The device comprises: A financial institution determination module, used to determine M financial institutions that participate in the quota allocation of the target financial product, where M is a positive integer; A data acquisition and storage module, configured to acquire, for each financial institution, historical sales data of the target financial product within a preset historical time period, obtain first historical sales data, and generate a first historical situation statistical table model based on the first historical sales data, wherein the historical situation statistical table model stores sales data under different dimensions; A data prediction module, for calculating the data in the first historical situation statistical table model for each financial institution based on an autoregressive time series model to obtain predicted sales data; A financial institution quota allocation module, configured to calculate a quota allocation value for each financial institution based on the predicted sales data and the total quota of each financial institution, and allocate the total quota to the M financial institutions based on the quota allocation value; The branch credit allocation module is used to determine N branches participating in credit allocation for each financial institution, and allocate the credit of the financial institution to the N branches, wherein N is a positive integer.

9. A computer program product, characterized in that It comprises a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for allocating the amount of a financial product as claimed in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to execute the method for allocating a quota of a financial product according to any one of claims 1 to 7 through the computer program.

Images