POS transaction data analysis system based on geographic positioning data analysis

Abstract

The invention relates to the technical field of financial management, and discloses a POS transaction data analysis system based on geographic positioning data analysis, and the system comprises the steps: dividing a plurality of financial transaction regions according to geographic positioning, and calculating the transaction activity of each financial transaction region; screening out a transaction active area according to the transaction activeness, predicting the transaction demand of the transaction active area in a future time period, and obtaining the current maximum processing transaction volume of the transaction active area; whether supply and demand imbalance of the POS terminal exists in the transaction active area is judged according to the transaction demand quantity and the current maximum processing transaction volume, and a judgment result is obtained; when the judgment result shows that the supply is insufficient, obtaining an optimal POS terminal supply quantity by using a pre-configured genetic algorithm, and performing inventory management according to the optimal POS terminal supply quantity; when the market demand fluctuates, the market demand is responded in time, and the supply inventory of the POS terminal is adjusted in time.

Description

Technical Field

[0001] The present invention relates to the technical field of financial management, and more specifically, to a POS transaction data analysis system based on geographic positioning data analysis. Background Art

[0002] With the widespread application of electronic payment and mobile payment, the application of POS (Point of Sale) terminals in financial transactions is becoming increasingly popular, especially in commercial scenarios such as retail and catering. POS terminals have become an important tool for merchants' daily transactions; however, with the diversification of market demand and the fluctuation of transaction frequency, POS service providers are facing huge challenges in equipment supply and demand management; especially in areas with frequent transactions, whether the supply of POS terminals can meet the demand directly affects the smooth progress of transactions and customers' payment experience.

[0003] Existing POS terminal management systems are usually based on static deployment methods, which fail to fully consider the changes in transaction demand in different regions and at different time periods. Due to the lack of intelligent supply and demand analysis methods, POS service providers find it difficult to respond to market demand in a timely manner when facing market demand fluctuations, and are unable to adjust the supply inventory of POS terminals in a timely manner. Furthermore, the sales and service promotion of POS terminals cannot be effectively adjusted according to the actual needs of different regions, making it difficult to effectively reduce the inventory management costs of POS terminals, while affecting the equipment sales and service promotion efficiency of POS service providers. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a POS transaction data analysis system based on geographic positioning data analysis.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A POS transaction data analysis system based on geographic positioning data analysis, the system comprising:

[0007] A region division module is used to obtain the geographic location of the POS terminal in the target geographic area, divide multiple financial transaction areas according to the geographic location, and calculate the transaction activity of each financial transaction area;

[0008] The data acquisition module is used to screen out active trading areas according to the trading activity, predict the trading demand of the active trading areas in the future period, and obtain the current maximum processing transaction volume of the active trading areas;

[0009] A supply and demand judgment module, used to judge whether there is a supply and demand imbalance of POS terminals in the transaction active area according to the transaction demand volume and the current maximum processing transaction volume, and obtain a judgment result; the judgment result includes one of supply and demand imbalance and supply and demand balance; the supply and demand imbalance includes one of insufficient supply and excessive supply;

[0010] The supply and demand adjustment module is used to obtain the optimal POS terminal supply quantity using a pre-configured genetic algorithm when the judgment result shows that the supply is insufficient, and to perform inventory management based on the optimal POS terminal supply quantity.

[0011] Furthermore, the division of multiple financial transaction areas based on geographical positioning includes:

[0012] Construct an empty plane coordinate system, where the horizontal coordinate of the plane coordinate system is longitude and the vertical coordinate of the plane coordinate system is latitude;

[0013] Mapping the geographical locations of all POS terminals into an empty plane coordinate system to obtain a location scatter diagram of the POS terminals; the location scatter diagram includes geographical location scatter points of a plurality of POS terminals;

[0014] Using the convex hull algorithm to find M extension points in the location scatter diagram, and sequentially connect the M extension points in the location scatter diagram to form a closed area where POS terminals are distributed, where M is an integer greater than zero;

[0015] The K-means clustering algorithm is used to cluster the geographical location scattered points in the closed area to obtain multiple clusters, each of which contains multiple geographical location scattered points;

[0016] The convex hull algorithm is used again to find N extension points in each cluster, and the N extension points in each cluster are sequentially connected to form multiple local closed areas, each local closed area is marked as a financial transaction area, and multiple financial transaction areas are obtained, where N is an integer greater than zero.

[0017] Furthermore, the calculation of the transaction activity of each financial transaction area includes:

[0018] Obtaining the number G of POS terminals existing in each financial transaction area, and obtaining POS transaction data of each POS terminal;

[0019] The POS transaction data includes the number of transactions, transaction amount and average transaction time interval of the POS terminal;

[0020] Calculate the transaction activity based on the number of POS terminals and the POS transaction data of each POS terminal to obtain the transaction activity of each financial transaction area;

[0021] The calculation formula of the transaction activity is as follows: ;

[0022] Where: Indicates the trading activity in the financial trading area; It represents the sum of the total number of transactions of all POS terminals in the financial transaction area; Indicates the number of transactions at the g-th POS terminal; Represents the transaction amount of g POS terminals; is the average transaction time interval of the g-th POS terminal.

[0023] Furthermore, the step of selecting the active trading area according to the trading activity includes:

[0024] Set transaction activity thresholds;

[0025] comparing the trading activity of each financial trading area with a trading activity threshold;

[0026] If the transaction activity is greater than or equal to the transaction activity threshold, the corresponding financial transaction area is marked as a transaction active area;

[0027] If the transaction activity is less than the transaction activity threshold, the corresponding financial transaction area is marked as a non-transaction active area.

[0028] Furthermore, the predicted transaction demand in the active transaction area in the future period includes:

[0029] In the current period [QU,Q], extract the number S of POS terminals in the transaction active area, where Q, U, and S are integers greater than zero;

[0030] Extract the actual number of transactions of each POS terminal at each moment, input the number of POS terminals S and the actual number of transactions of each POS terminal at each moment into the pre-built transaction prediction model, and obtain the predicted total number of transactions in the future period [Q+U,Q+2U];

[0031] The training logic of the transaction prediction model is as follows:

[0032] Acquire historical transaction data, and divide the historical transaction data into a transaction demand training set and a transaction demand test set, wherein the historical transaction data includes transaction demand feature data and its corresponding predicted total number of transactions;

[0033] The transaction demand characteristic data includes the number S of POS terminals in the current period [QU, Q] and the actual number of transactions of each POS terminal at each moment;

[0034] Construct a regression network, use the transaction demand feature data in the transaction demand training set as the input of the regression network, and use the predicted total number of transactions in the transaction demand training set as the output of the regression network, train the regression network, and obtain an initial regression network;

[0035] The initial regression network is validated using the transaction demand test set, and an initial regression network with a test error threshold less than or equal to a preset value is output as a pre-built transaction prediction model;

[0036] The predicted total number of transactions [Q+U, Q+2U] in the future period is used as the transaction demand in the active trading area in the future period.

[0037] Furthermore, the obtaining of the current maximum processing transaction volume of the transaction active area includes:

[0038] Determine a fixed transaction duration L according to the future period, extract the number S of POS terminals in the transaction active area, and extract the single transaction processing time of each POS terminal, where L is an integer greater than zero;

[0039] According to the fixed transaction duration, the number of POS terminals S and the single transaction processing time of each POS terminal, the current maximum processing transaction volume of the transaction active area is calculated;

[0040] The expression for calculating the current maximum transaction volume in the active transaction area is as follows: ;

[0041] Where: Indicates the current maximum processing transaction volume in the trading active area; Indicates the single transaction processing time of each POS terminal; where, is the maximum transaction volume that each POS terminal can process within a fixed time L.

[0042] Furthermore, the determining whether there is an imbalance in supply and demand of POS terminals in the transaction active area includes:

[0043] Calculate the difference between the transaction demand and the current maximum processing transaction volume, and mark the difference between the transaction demand and the current maximum processing transaction volume as the supply-demand difference;

[0044] Compare the supply and demand gap with the preset supply and demand range;

[0045] If the difference between supply and demand is greater than or equal to the maximum value of the supply and demand range, it is judged that there is an imbalance between supply and demand in the active trading area, and there is a shortage of supply;

[0046] If the difference between supply and demand is less than or equal to the minimum value of the supply and demand range, it is judged that there is an imbalance between supply and demand in the active trading area, and there is an oversupply;

[0047] If the supply-demand gap is less than the maximum value of the supply-demand interval and greater than the minimum value of the supply-demand interval, it is judged that there is no supply-demand imbalance in the active trading area.

[0048] Further, the method of obtaining the optimal POS terminal supply using a preconfigured genetic algorithm includes:

[0049] a1: Initialize the population: randomly generate an original population, which contains X chromosomes, each chromosome represents a POS terminal supply, and X is an integer greater than zero;

[0050] a2: Fitness evaluation: Under each chromosome, obtain the modified maximum processing transaction volume and extract the transaction demand, and calculate the fitness of each chromosome in the fitness function pre-constructed according to the modified maximum processing transaction volume and transaction demand;

[0051] The calculation formula of the pre-constructed fitness function is: ; Where: For fitness, is the transaction demand, To correct the maximum processing transaction volume;

[0052] a3: Selection: Use the roulette wheel method to select two chromosomes with high fitness in the original population as the father and mother;

[0053] a4: Crossover: Perform crossover operation on the father and mother to generate new chromosomes;

[0054] a5: Mutation: Perform mutation operation on the new chromosomes to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step a2;

[0055] a6: Repeat steps a2 to a5 above until the fitness of the chromosome in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the POS terminal supply represented by the corresponding chromosome as the optimal POS terminal supply.

[0056] A POS transaction data analysis method based on geographic positioning data analysis is implemented based on the above-mentioned POS transaction data analysis system based on geographic positioning data analysis, and the method comprises:

[0057] Obtaining the geographic location of the POS terminal in the target geographic area, dividing multiple financial transaction areas based on the geographic location, and calculating the transaction activity of each financial transaction area;

[0058] Filter out active trading areas according to the trading activity, predict the trading demand of active trading areas in the future period, and obtain the current maximum processing transaction volume of active trading areas;

[0059] Judging whether there is a supply-demand imbalance of POS terminals in the transaction active area according to the transaction demand volume and the current maximum transaction volume, and obtaining a judgment result; the judgment result includes one of a supply-demand imbalance and a supply-demand balance; the supply-demand imbalance includes one of a supply shortage and a supply surplus;

[0060] When the judgment result shows that the supply is insufficient, the pre-configured genetic algorithm is used to obtain the optimal POS terminal supply quantity, and inventory management is performed based on the optimal POS terminal supply quantity.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] The present application discloses a POS transaction data analysis system based on geographic positioning data analysis, comprising: dividing a plurality of financial transaction areas according to geographic positioning, and calculating the transaction activity of each financial transaction area; selecting the transaction active area according to the transaction activity, predicting the transaction demand of the transaction active area in the future period, and obtaining the current maximum transaction volume processed in the transaction active area; judging whether there is a supply and demand imbalance of POS terminals in the transaction active area according to the transaction demand and the current maximum transaction volume processed, and obtaining a judgment result; when the judgment result shows that the supply is insufficient, obtaining the optimal POS terminal supply by using a preconfigured genetic algorithm, and performing inventory management according to the optimal POS terminal supply; based on the above content, the present invention uses a genetic algorithm to find the optimal POS terminal supply in the transaction active area with the purpose of minimizing the difference between supply and demand. The present invention can respond to market demand in a timely manner when facing market demand fluctuations, thereby facilitating timely adjustment of the supply inventory of POS terminals, and further, facilitating effective adjustment of the sales and service promotion of POS terminals according to the actual needs of different regions, thereby effectively reducing the inventory management cost of POS terminals, and improving the equipment sales and service promotion efficiency of POS service providers. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A module structure diagram of a POS transaction data analysis system based on geographic positioning data analysis provided by the present invention;

[0064] Figure 2 A flowchart of a POS transaction data analysis method based on geographic positioning data analysis provided by the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Example 1

[0067] See also Figure 1 As shown, this embodiment discloses a POS transaction data analysis system based on geographic positioning data analysis, the system comprising:

[0068] The area division module 101 is used to obtain the geographical location of the POS terminal in the target geographical area, divide a plurality of financial transaction areas according to the geographical location, and calculate the transaction activity of each financial transaction area;

[0069] It should be noted that the target geographical area is divided by technical personnel according to different business needs and actual application scenarios, including the following methods: division by city or urban area (such as by urban area, county, town, village, etc.), or division by business district (such as commercial clusters with different urban content, etc.); In addition, all POS terminals are equipped with a GPS positioning unit, which is used to locate the geographical location of the corresponding GPS positioning unit, specifically the latitude and longitude coordinates;

[0070] In implementation, the multiple financial transaction areas are divided according to geographic location, including:

[0071] Construct an empty plane coordinate system, where the horizontal coordinate of the plane coordinate system is longitude and the vertical coordinate of the plane coordinate system is latitude;

[0072] Mapping the geographical locations of all POS terminals into an empty plane coordinate system to obtain a location scatter diagram of the POS terminals; the location scatter diagram includes geographical location scatter points of a plurality of POS terminals;

[0073] Using the convex hull algorithm to find M extension points in the location scatter diagram, and sequentially connect the M extension points in the location scatter diagram to form a closed area where POS terminals are distributed, where M is an integer greater than zero;

[0074] It should be understood that the convex hull algorithm is a geometric algorithm used to find the outermost points from a set of two-dimensional or multi-dimensional point sets, and connect these points in sequence to form a closed area. The characteristic of this closed area is that it surrounds all points and does not contain any concave parts inside, that is, the straight line segment between any two points is completely located inside the closed area; among them, the extension points refer to the points located in the outermost layer in a set of points in a two-dimensional or multi-dimensional space; in simple terms, the extension points are the points that constitute the boundary or shell of the point set, these points define the outer contour of the point set, and by connecting them, a closed area can be formed;

[0075] The K-means clustering algorithm is used to cluster the geographical location scattered points in the closed area to obtain multiple clusters, each of which contains multiple geographical location scattered points;

[0076] It should be noted that the K-means clustering algorithm is an unsupervised learning algorithm that is widely used in data clustering problems. In this step, K-means clustering is used to group the geographical location scatter points (i.e., longitude and latitude coordinates) of POS terminals so that the POS terminals in each group (cluster) are geographically closer, thereby forming several financial transaction areas. The selection of the K value is based on the experience of technical personnel, business needs, or the use of the "elbow rule". The "elbow rule" finds the "elbow" position by plotting the relationship between the K value and the intra-cluster square error (SSX). The intra-cluster square error decreases as K increases, but the rate of decrease slows down after a certain point, forming an "elbow". The K value corresponding to this point is the ideal number of clusters, and its specific formula is: , where: Indicates The location of the geographically scattered points, Indicates The centroid of a cluster (cluster center) is a vector representing the average position of all data points in the cluster. is the total number of geographical location scatter points, is the number of clusters, that is, the number of cluster centers;

[0077] The convex hull algorithm is used again to find N extension points in each cluster, and the N extension points in each cluster are sequentially connected to form multiple local closed areas, each local closed area is marked as a financial transaction area, and multiple financial transaction areas are obtained, where N is an integer greater than zero;

[0078] In implementation, the calculation of the transaction activity of each financial transaction area includes:

[0079] Obtaining the number G of POS terminals existing in each financial transaction area, and obtaining POS transaction data of each POS terminal;

[0080] The POS transaction data includes the number of transactions, transaction amount and average transaction time interval of the POS terminal;

[0081] Calculate the transaction activity based on the number of POS terminals and the POS transaction data of each POS terminal to obtain the transaction activity of each financial transaction area;

[0082] The calculation formula of the transaction activity is as follows: ;

[0083] Where: Indicates the trading activity in the financial trading area; It represents the sum of the total number of transactions of all POS terminals in the financial transaction area. The specific formula is: ; Indicates the number of transactions of the g-th POS terminal. The number of transactions reflects the activity of the POS terminal. The more transactions, the greater the contribution of the terminal to the regional activity. represents the transaction amount of g POS terminals. The transaction amount reflects the scale of the transaction. The larger the transaction amount, the greater the impact of the POS terminal on the regional transaction activity. is the average transaction time interval of the g-th POS terminal, indicating the transaction frequency. The shorter the transaction time interval, the more frequent the transactions and the higher the activity. This parameter is measured by weighting the number of transactions and the amount and dividing it by the transaction time interval.

[0084] The data acquisition module 102 is used to select the active trading area according to the trading activity, predict the trading demand of the active trading area in the future period, and obtain the current maximum processing transaction volume of the active trading area;

[0085] In implementation, the process of selecting active trading areas according to the trading activity includes:

[0086] Set transaction activity thresholds;

[0087] It should be noted that the transaction activity threshold is set by technicians based on experimental data or personal experience;

[0088] comparing the trading activity of each financial trading area with a trading activity threshold;

[0089] If the transaction activity is greater than or equal to the transaction activity threshold, the corresponding financial transaction area is marked as a transaction active area;

[0090] If the transaction activity is less than the transaction activity threshold, the corresponding financial transaction area is marked as a non-transaction active area;

[0091] It should be noted that: after obtaining multiple active trading areas, a POS terminal inventory warehouse will be established in each active trading area to respond to the changing market demand for POS terminals in a timely manner;

[0092] In implementation, the predicted transaction demand in the active transaction area in the future period includes:

[0093] In the current period [QU,Q], extract the number S of POS terminals in the transaction active area, where Q, U, and S are integers greater than zero;

[0094] Extract the actual number of transactions of each POS terminal at each moment, input the number of POS terminals S and the actual number of transactions of each POS terminal at each moment into the pre-built transaction prediction model, and obtain the predicted total number of transactions in the future period [Q+U,Q+2U];

[0095] Specifically, the training logic of the transaction prediction model is as follows:

[0096] Acquire historical transaction data, and divide the historical transaction data into a transaction demand training set and a transaction demand test set, wherein the historical transaction data includes transaction demand feature data and its corresponding predicted total number of transactions;

[0097] The transaction demand characteristic data includes the number S of POS terminals in the current period [QU, Q] and the actual number of transactions of each POS terminal at each moment;

[0098] It should be noted that: the number S of POS terminals in the historical transaction data is collected by the technical staff according to the specific geographical location of each POS terminal, the actual number of transactions of each POS terminal in the historical transaction data is collected according to the transaction log in each POS terminal, and the predicted total number of transactions in the historical transaction data is obtained by the technical staff marking and accumulating the actual number of transactions in the corresponding records;

[0099] Construct a regression network, use the transaction demand feature data in the transaction demand training set as the input of the regression network, and use the predicted total number of transactions in the transaction demand training set as the output of the regression network, train the regression network, and obtain an initial regression network;

[0100] The regression network is specifically one of the algorithms such as the ARIMA model or the LSTM model, wherein the ARIMA model or the LSTM model is a statistical model widely used for time series prediction, and is particularly suitable for analyzing and predicting trends and cyclical changes based on historical data; for predicting the total number of transactions in a future period, the ARIMA model or the LSTM model can capture the trend, cyclicality and short-term fluctuations therein based on the historical transaction data, thereby making an accurate prediction;

[0101] The initial regression network is validated using the transaction demand test set, and an initial regression network with a test error threshold less than or equal to a preset value is output as a pre-built transaction prediction model;

[0102] The predicted total number of transactions in the future period [Q+U, Q+2U] is used as the transaction demand of the active trading area in the future period;

[0103] In implementation, the obtaining of the current maximum processing transaction volume of the active transaction area includes:

[0104] Determine a fixed transaction duration L according to the future period, extract the number S of POS terminals in the transaction active area, and extract the single transaction processing time of each POS terminal, where L is an integer greater than zero;

[0105] It should be noted that: the fixed transaction duration L is determined according to the time range of the future period, that is, L=Q+2U-Q+U;

[0106] According to the fixed transaction duration, the number of POS terminals S and the single transaction processing time of each POS terminal, the current maximum processing transaction volume of the transaction active area is calculated;

[0107] The expression for calculating the current maximum transaction volume in the active transaction area is as follows: ;

[0108] Where: Indicates the current maximum transaction volume in the active transaction area, that is, the sum of the maximum transaction volumes processed by all POS terminals within a fixed time L; Indicates the single transaction processing time of each POS terminal, which is collected by the technicians based on the actual situation of each POS terminal; is the maximum transaction volume that each POS terminal can process within a fixed time L.

[0109] The supply and demand judgment module 103 is used to judge whether there is a supply and demand imbalance of POS terminals in the transaction active area according to the transaction demand volume and the current maximum processing transaction volume, and obtain a judgment result; the judgment result includes one of supply and demand imbalance and supply and demand balance; the supply and demand imbalance includes one of insufficient supply and excessive supply;

[0110] In implementation, the determination of whether there is an imbalance in the supply and demand of POS terminals in the transaction active area includes:

[0111] Calculate the difference between the transaction demand and the current maximum processing transaction volume, and mark the difference between the transaction demand and the current maximum processing transaction volume as the supply-demand difference;

[0112] Compare the supply and demand gap with the preset supply and demand range;

[0113] If the difference between supply and demand is greater than or equal to the maximum value of the supply and demand range, it is judged that there is an imbalance between supply and demand in the active trading area, and there is a shortage of supply;

[0114] If the difference between supply and demand is less than or equal to the minimum value of the supply and demand range, it is judged that there is an imbalance between supply and demand in the active trading area, and there is an oversupply;

[0115] If the difference between supply and demand is less than the maximum value of the supply and demand interval and greater than the minimum value of the supply and demand interval, it is judged that there is no supply and demand imbalance in the active trading area;

[0116] It is clear that when the supply-demand gap is less than the maximum value of the supply-demand interval and greater than the minimum value of the supply-demand interval, it means that the supply and demand in the active trading area is balanced. At this time, there is no need to adopt inventory management measures for the management of POS terminals in the active trading area, that is, there is no need to fill the POS terminal inventory warehouse in the active trading area.

[0117] The supply and demand adjustment module 104 is used to obtain the optimal POS terminal supply quantity by using a pre-configured genetic algorithm when the judgment result shows that the supply is insufficient, and perform inventory management according to the optimal POS terminal supply quantity;

[0118] In implementation, the method of obtaining the optimal POS terminal supply using a preconfigured genetic algorithm includes:

[0119] a1: Initialize the population: randomly generate an original population, which contains X chromosomes, each chromosome represents a POS terminal supply, and X is an integer greater than zero;

[0120] a2: Fitness evaluation: Under each chromosome (i.e., the supply of each POS terminal in the original population), obtain the modified maximum transaction volume and extract the transaction demand, and calculate the fitness of each chromosome in the fitness function pre-constructed according to the modified maximum transaction volume and transaction demand;

[0121] It should be noted that the calculation and generation logic of the revised maximum processing transaction volume is the same as the current maximum processing transaction volume mentioned above. For details, please refer to the relevant content about the current maximum processing transaction volume, which will not be repeated here.

[0122] The calculation formula of the pre-constructed fitness function is: ; Where: For fitness, is the transaction demand, To correct the maximum processing transaction volume;

[0123] a3: Selection: Use the roulette wheel method to select two chromosomes with high fitness in the original population as the father and mother;

[0124] a4: Crossover: Perform crossover operation on the father and mother to generate new chromosomes;

[0125] It should be noted that: the crossover operation on the paternal parent and the maternal parent is implemented based on a crossover operation, and the crossover operation includes but is not limited to one of a single-point crossover, a uniform crossover or a sequential crossover, etc.;

[0126] a5: Mutation: Perform mutation operation on the new chromosomes to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step a2;

[0127] In the genetic algorithm, the mutation operation is to introduce gene diversity and prevent the algorithm from falling into the local optimum; the mutation operation on the new chromosome is implemented by uniform mutation or Gaussian mutation;

[0128] a6: Repeat the above steps a2 to a5 until the fitness of the chromosome in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the POS terminal supply represented by the corresponding chromosome as the optimal POS terminal supply;

[0129] For example: Assume that the maximum number of iterations is 100 times, and record the chromosome with the highest fitness in the current population and its fitness value after each iteration; if it is found that the fitness value has not changed significantly in a certain generation, it is considered that the convergence condition is met, the iteration is stopped, and the POS terminal supply represented by the corresponding chromosome is output as the optimal POS terminal supply;

[0130] It can be understood that: with the purpose of minimizing the difference between supply and demand, the genetic algorithm is used to find the optimal supply of POS terminals in the transaction active area. The present invention can respond to market demand in a timely manner when facing market demand fluctuations, which is conducive to timely adjustment of the supply inventory of POS terminals. Further, it is conducive to effectively adjusting the sales and service promotion of POS terminals according to the actual needs of different regions, thereby effectively reducing the inventory management costs of POS terminals and improving the equipment sales and service promotion efficiency of POS service providers.

[0131] Example 2

[0132] See also Figure 2 As shown, this embodiment discloses a POS transaction data analysis method based on geolocation data analysis, the method comprising:

[0133] S201: obtaining the geographic location of the POS terminal in the target geographic area, dividing a plurality of financial transaction areas according to the geographic location, and calculating the transaction activity of each financial transaction area;

[0134] S202: Filter out active trading areas according to the trading activity, predict the trading demand of the active trading areas in the future period, and obtain the current maximum processing transaction volume of the active trading areas;

[0135] S203: judging whether there is a supply-demand imbalance of POS terminals in the transaction active area according to the transaction demand volume and the current maximum transaction volume, and obtaining a judgment result; the judgment result includes one of a supply-demand imbalance and a supply-demand balance; the supply-demand imbalance includes one of insufficient supply and excessive supply;

[0136] S204: When the judgment result shows that the supply is insufficient, the optimal POS terminal supply quantity is obtained by using a pre-configured genetic algorithm, and inventory management is performed according to the optimal POS terminal supply quantity.

[0137] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0138] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0139] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0141] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0142] 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.

[0143] In addition, each functional unit in each embodiment of the present invention 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.

[0144] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0145] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A POS transaction data analysis system based on geographic positioning data analysis, characterized in that: The system comprises: A region division module is used to obtain the geographic location of the POS terminal in the target geographic area, divide multiple financial transaction areas according to the geographic location, and calculate the transaction activity of each financial transaction area; The data acquisition module is used to screen out active trading areas according to the trading activity, predict the trading demand of the active trading areas in the future period, and obtain the current maximum processing transaction volume of the active trading areas; A supply and demand judgment module, used to judge whether there is a supply and demand imbalance of POS terminals in the transaction active area according to the transaction demand volume and the current maximum processing transaction volume, and obtain a judgment result; the judgment result includes one of supply and demand imbalance and supply and demand balance; the supply and demand imbalance includes one of insufficient supply and excessive supply; The supply and demand adjustment module is used to obtain the optimal POS terminal supply quantity using a pre-configured genetic algorithm when the judgment result shows that the supply is insufficient, and to perform inventory management based on the optimal POS terminal supply quantity.

2. The POS transaction data analysis system based on geographic positioning data analysis according to claim 1, characterized in that: The multiple financial transaction areas are divided according to geographic positioning, including: Construct an empty plane coordinate system, where the horizontal coordinate of the plane coordinate system is longitude and the vertical coordinate of the plane coordinate system is latitude; Mapping the geographical locations of all POS terminals into an empty plane coordinate system to obtain a location scatter diagram of the POS terminals; the location scatter diagram includes geographical location scatter points of a plurality of POS terminals; Using the convex hull algorithm to find M extension points in the location scatter diagram, and sequentially connect the M extension points in the location scatter diagram to form a closed area where POS terminals are distributed, where M is an integer greater than zero; The K-means clustering algorithm is used to cluster the geographical location scattered points in the closed area to obtain multiple clusters, each of which contains multiple geographical location scattered points; The convex hull algorithm is used again to find N extension points in each cluster, and the N extension points in each cluster are sequentially connected to form multiple local closed areas, each local closed area is marked as a financial transaction area, and multiple financial transaction areas are obtained, where N is an integer greater than zero.

3. The POS transaction data analysis system based on geographic positioning data analysis according to claim 2, characterized in that: The calculation of the transaction activity of each financial transaction area includes: Obtaining the number G of POS terminals existing in each financial transaction area, and obtaining POS transaction data of each POS terminal; The POS transaction data includes the number of transactions, transaction amount and average transaction time interval of the POS terminal; Calculate the transaction activity based on the number of POS terminals and the POS transaction data of each POS terminal to obtain the transaction activity of each financial transaction area; The calculation formula of the transaction activity is as follows: ; Where: Indicates the trading activity in the financial trading area; It represents the sum of the total number of transactions of all POS terminals in the financial transaction area; Indicates the number of transactions at the g-th POS terminal; Represents the transaction amount of g POS terminals; is the average transaction time interval of the g-th POS terminal.

4. The POS transaction data analysis system based on geographic positioning data analysis according to claim 3, characterized in that: The method of screening out active trading areas according to the trading activity includes: Set transaction activity thresholds; comparing the trading activity of each financial trading area with a trading activity threshold; If the transaction activity is greater than or equal to the transaction activity threshold, the corresponding financial transaction area is marked as a transaction active area; If the transaction activity is less than the transaction activity threshold, the corresponding financial transaction area is marked as a non-transaction active area.

5. The POS transaction data analysis system based on geographic positioning data analysis according to claim 4, characterized in that: The predicted transaction demand in the active transaction area in the future period includes: In the current period [QU,Q], extract the number S of POS terminals in the transaction active area, where Q, U, and S are integers greater than zero; Extract the actual number of transactions of each POS terminal at each moment, input the number of POS terminals S and the actual number of transactions of each POS terminal at each moment into the pre-built transaction prediction model, and obtain the predicted total number of transactions in the future period [Q+U,Q+2U]; The training logic of the transaction prediction model is as follows: Acquire historical transaction data, and divide the historical transaction data into a transaction demand training set and a transaction demand test set, wherein the historical transaction data includes transaction demand feature data and its corresponding predicted total number of transactions; The transaction demand characteristic data includes the number S of POS terminals in the current period [QU, Q] and the actual number of transactions of each POS terminal at each moment; Construct a regression network, use the transaction demand feature data in the transaction demand training set as the input of the regression network, and use the predicted total number of transactions in the transaction demand training set as the output of the regression network, train the regression network, and obtain an initial regression network; The initial regression network is validated using the transaction demand test set, and an initial regression network with a test error threshold less than or equal to a preset value is output as a pre-built transaction prediction model; The predicted total number of transactions [Q+U, Q+2U] in the future period is used as the transaction demand in the active trading area in the future period.

6. The POS transaction data analysis system based on geographic positioning data analysis according to claim 5, characterized in that: The obtaining of the current maximum processing transaction volume of the active transaction area includes: Determine a fixed transaction duration L according to the future period, extract the number S of POS terminals in the transaction active area, and extract the single transaction processing time of each POS terminal, where L is an integer greater than zero; According to the fixed transaction duration, the number of POS terminals S and the single transaction processing time of each POS terminal, the current maximum processing transaction volume of the transaction active area is calculated; The expression for calculating the current maximum transaction volume in the active transaction area is as follows: ； Where: Indicates the current maximum processing transaction volume in the trading active area; Indicates the single transaction processing time of each POS terminal; where, is the maximum transaction volume that each POS terminal can process within a fixed time L.

7. The POS transaction data analysis system based on geographic positioning data analysis according to claim 6, characterized in that: The determining whether there is a supply-demand imbalance of POS terminals in the transaction active area includes: Calculate the difference between the transaction demand and the current maximum processing transaction volume, and mark the difference between the transaction demand and the current maximum processing transaction volume as the supply-demand difference; Compare the supply and demand gap with the preset supply and demand range; If the difference between supply and demand is greater than or equal to the maximum value of the supply and demand range, it is judged that there is an imbalance between supply and demand in the active trading area, and there is a shortage of supply; If the difference between supply and demand is less than or equal to the minimum value of the supply and demand range, it is judged that there is an imbalance between supply and demand in the active trading area, and there is an oversupply; If the supply-demand gap is less than the maximum value of the supply-demand interval and greater than the minimum value of the supply-demand interval, it is judged that there is no supply-demand imbalance in the active trading area.

8. The POS transaction data analysis system based on geographic positioning data analysis according to claim 7, characterized in that: The method of obtaining the optimal POS terminal supply using a preconfigured genetic algorithm comprises: a1: Initialize the population: randomly generate an original population, which contains X chromosomes, each chromosome represents a POS terminal supply, and X is an integer greater than zero; a2: Fitness evaluation: Under each chromosome, obtain the modified maximum processing transaction volume and extract the transaction demand, and calculate the fitness of each chromosome in the fitness function pre-constructed according to the modified maximum processing transaction volume and transaction demand; The calculation formula of the pre-constructed fitness function is: ; Where: For fitness, is the transaction demand, To correct the maximum processing transaction volume; a3: Selection: Use the roulette wheel method to select two chromosomes with high fitness in the original population as the father and mother; a4: Crossover: Perform crossover operation on the father and mother to generate new chromosomes; a5: Mutation: Perform mutation operation on the new chromosomes to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step a2; a6: Repeat steps a2 to a5 above until the fitness of the chromosome in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the POS terminal supply represented by the corresponding chromosome as the optimal POS terminal supply.

9. A POS transaction data analysis method based on geographic positioning data analysis, characterized in that: The method is implemented based on the POS transaction data analysis system based on geographic positioning data analysis according to any one of claims 1 to 8, and the method comprises: Obtaining the geographic location of the POS terminal in the target geographic area, dividing multiple financial transaction areas based on the geographic location, and calculating the transaction activity of each financial transaction area; Filter out active trading areas according to the trading activity, predict the trading demand of active trading areas in the future period, and obtain the current maximum processing transaction volume of active trading areas; Judging whether there is a supply-demand imbalance of POS terminals in the transaction active area according to the transaction demand volume and the current maximum transaction volume, and obtaining a judgment result; the judgment result includes one of a supply-demand imbalance and a supply-demand balance; the supply-demand imbalance includes one of insufficient supply and excessive supply; When the judgment result shows that the supply is insufficient, the pre-configured genetic algorithm is used to obtain the optimal POS terminal supply quantity, and inventory management is performed based on the optimal POS terminal supply quantity.

Images