Data management method and system, electronic device, and storage medium

Abstract

The present disclosure provides a data management method and system, electronic equipment, and storage medium, which belongs to the field of data management technology. The method includes: preprocessing first data to obtain the spatiotemporal law of the first data; the first data is the original data sent by the vending machine to the background management platform; determining the target data analysis model based on the spatiotemporal law of the first data; inputting the second data into the target data analysis model to obtain the commodity adjustment strategy corresponding to the vending machine. The spatiotemporal law includes time dimension characteristics and space dimension characteristics, and the target data analysis model includes a time series analysis model and a space analysis model. The data management method and system, electronic equipment, and storage medium provided by the present disclosure can effectively improve the management efficiency of data.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of data management, and more specifically, relates to a data management method and system, an electronic device, and a storage medium. Background Art

[0002] In the modern retail industry, vending machines, as a convenient retail method, have been widely used in various places, such as schools, office areas, public places, etc. These vending machines can record sales data in real time and send these data to the backend management platform. These raw data often contain a lot of information. Traditional data management methods often find it difficult to effectively mine and utilize the potential value of these data, resulting in a waste of data resources. Summary of the invention

[0003] The purpose of the present disclosure is to provide a data management method and system, an electronic device, and a storage medium to improve the utilization rate of data.

[0004] A first aspect of an embodiment of the present disclosure provides a data management method, including:

[0005] Preprocessing the first data to obtain the time and space regularity of the first data; the first data is the original data sent by the vending machine to the background management platform;

[0006] Determine a target data analysis model based on the spatiotemporal regularity of the first data;

[0007] Inputting the spatiotemporal regularity of the first data into the target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine;

[0008] Among them, the spatiotemporal laws include time dimension characteristics and space dimension characteristics, and the target data analysis model includes a time series analysis model and a space analysis model.

[0009] A second aspect of the embodiments of the present disclosure provides a data management system, including:

[0010] A data processing module, used for preprocessing the first data to obtain the time-space regularity of the first data; the first data is the original data sent by the vending machine to the background management platform;

[0011] A model selection module, used to determine a target data analysis model based on the spatiotemporal regularity of the first data;

[0012] A data analysis module, used for inputting the spatiotemporal regularity of the first data into the target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine;

[0013] Among them, the spatiotemporal laws include time dimension characteristics and space dimension characteristics, and the target data analysis model includes a time series analysis model and a space analysis model.

[0014] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned data management method when executing the computer program.

[0015] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned data management method are implemented.

[0016] The data management method and system, electronic device, and storage medium provided by the embodiments of the present disclosure have the following beneficial effects:

[0017] First, the present invention obtains the spatiotemporal law by preprocessing the first data, and the sales situation of the vending machine can be obtained according to the spatiotemporal law, and then the target data analysis model is determined, so that the analysis is more targeted and professional, and the utilization rate of the data is improved.

[0018] Secondly, after determining the spatiotemporal regularity of the first data, the present disclosure can better predict sales demand at different times and locations. The commodity adjustment strategy obtained by inputting the spatiotemporal regularity of the first data into the target model helps to arrange inventory reasonably and avoid inventory backlogs or out-of-stock situations. For example, increase inventory in advance before the peak sales season and appropriately reduce inventory during the off-season to reduce inventory costs and improve capital turnover. At the same time, adjust inventory according to consumer demand in different locations to ensure the supply of popular commodities and meet consumer demand.

[0019] Finally, based on the time-space law analysis and product adjustment strategy of First Data, vending machines can better meet the needs of consumers at different times and places. Consumers can more conveniently buy the products they need at nearby vending machines, which improves the convenience of shopping. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flowchart of a data management method provided by an embodiment of the present disclosure;

[0022] Figure 2 A structural block diagram of a data management system provided by an embodiment of the present disclosure;

[0023] Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0025] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0026] Please refer to Figure 1 , Figure 1 A flowchart of a data management method provided by an embodiment of the present disclosure is provided, and the method includes:

[0027] S101: Preprocess the first data to obtain the spatiotemporal regularity of the first data; the first data is the original data sent by the vending machine to the background management platform.

[0028] In this embodiment, the first data is the original data sent by the vending machine to the backend management platform, including sales records, transaction time, product information, customer usage (such as cash, credit card, etc.), machine status (such as inventory, whether it is out of paper, whether it is faulty, etc.), etc.

[0029] Spatiotemporal regularities are patterns and trends in data over time and space. For vending machine data, spatiotemporal regularities can include sales differences in different time periods (such as weekdays and weekends, morning and evening peaks), sales differences in different geographical locations (such as near schools and near office areas), etc.

[0030] The backend management platform is a computer system used to monitor and manage the operation of vending machines. The backend management system has functions such as data collection, data analysis, and report generation, which can help operators better understand the operating status and sales of the machines.

[0031] A vending machine is an unattended retail device that is usually used to sell goods such as beverages and snacks. Customers can pay and obtain goods by inserting coins, swiping cards or scanning codes. Vending machines can automatically complete the transaction process, reduce labor costs, and improve sales efficiency.

[0032] Preprocessing the first data to obtain the spatiotemporal regularity of the first data includes:

[0033] The first data is cleaned, formatted, and normalized to obtain time dimension features and space dimension features of the first data. Data cleaning includes removing duplicate data, processing missing values, and identifying and correcting outliers. Format conversion includes time format standardization and non-time format standardization. Normalization includes determining a normalization formula, and normalizing the format-converted data according to the normalization formula.

[0034] After performing data cleaning, format conversion, and normalization on the first data to obtain the time dimension features and space dimension features of the first data, the method further includes:

[0035] A dynamic chart is created according to the time dimension characteristics of the first data, and a plane map is created according to the space dimension characteristics of the first data.

[0036] In this embodiment, first data reflecting time dimension characteristics after preprocessing are extracted, and the first data are sorted according to the time dimension characteristics to obtain first sorted data; a chart type is selected according to the characteristics of the first data; and a dynamic chart is established based on the first sorted data and the chart type.

[0037] For example, the first data is sorted according to the time dimension feature, the time node corresponding to the first data is clarified, and the first sorted data is obtained. Assuming that the number of features of the first data is greater than the first value, the chart type is determined to be a bar chart. According to the chart type and the first sorted data, the coordinate axis of the chart is determined, the scale and label are set, and the interactive function is added to obtain a dynamic chart.

[0038] This embodiment can clearly show the trend of data changes over time by extracting and sorting the first data that reflects the time dimension characteristics. Specifically, the chart type is intelligently selected according to the data characteristics, such as using a bar chart when the number of characteristics is large, which improves the readability of the chart and the efficiency of information display; the establishment of dynamic charts not only enhances the interactivity of data visualization, but also enables data managers to understand and analyze data more intuitively, improving the efficiency and accuracy of data analysis and decision-making.

[0039] In this embodiment, the locations of vending machines are marked on a preset map according to the spatial dimension characteristics of the first data to obtain a plane map, and different types of vending machines are marked with different colors.

[0040] This embodiment uses spatial dimension features to mark the locations of vending machines on a preset map, thereby achieving an intuitive display of the distribution of vending machines; different colors are used to identify different types of vending machines, further enhancing the information richness and readability of the map, which not only facilitates data managers to quickly grasp the layout of vending machines, but also provides strong data support for optimizing equipment configuration and improving operational efficiency.

[0041] S102: Determine a target data analysis model based on the spatiotemporal regularity of the first data.

[0042] In this embodiment, the backend management platform has multiple data analysis models, and the target analysis model is a model determined based on the spatiotemporal regularity of the first data and used to perform in-depth analysis, prediction or optimization of spatiotemporal data. The model can reveal the potential regularities and relationships in spatiotemporal data and provide useful information and suggestions for decision makers.

[0043] Determining a target data analysis model based on the spatiotemporal regularity of the first data includes:

[0044] Determining the priority order of the time dimension feature and the space dimension feature of the first data;

[0045] The target data analysis model is determined based on the priority order, and the spatiotemporal rules include time dimension characteristics and space dimension characteristics.

[0046] In this embodiment, the sales trends of different time periods are obtained based on the sales data in the first data, and the consumer demands of different locations are obtained based on the sales data of vending machines at different locations in the first data. If the sales trends of different time periods are similar, it is determined that the priority order of the time dimension feature is greater than the priority order of the space dimension feature, and the target data analysis model is a time series analysis model; if the consumer demands of different locations are similar, it is determined that the priority order of the time dimension feature is less than the priority order of the space dimension feature, and the target data analysis model is a space analysis model. The target data analysis model is determined based on the priority order.

[0047] For example, suppose there is a vending machine operating company that has set up multiple vending machines in different areas of a city.

[0048] Analyze sales trends over different time periods:

[0049] The sales data is divided by time, such as weekdays, weekends, holidays and other time periods. By calculating the average sales amount and sales volume for each time period, it can be seen that the sales trends on weekdays and weekends are relatively similar, the main sales products are beverages and snacks, and the fluctuation range of sales amount and volume is small. The sales trend on holidays is quite different from that on weekdays and weekends, and the sales of some special products such as souvenirs and gift boxes have increased significantly.

[0050] Analyze consumer demand in different locations:

[0051] The sales data is grouped according to the location of the vending machines, into different areas such as commercial areas, residential areas, and around schools.

[0052] Analyze the sales data of each area. For example, vending machines in commercial areas and around schools mainly sell beverages, snacks, and convenience foods, while vending machines in residential areas sell some daily necessities in addition to these products. But in general, the difference in consumer demand in different locations is not particularly obvious. Since there are large differences in sales trends in different time periods, and consumer demand in different locations is relatively similar, it is determined that the priority order of time dimension features is greater than the priority of space dimension features.

[0053] Therefore, when sales data shows certain trends and seasonality over time, consider using time series analysis models, such as the autoregressive integrated moving average model or the seasonal autoregressive integrated moving average model. These models can model and predict time series data, helping companies predict sales in different time periods in the future, so as to reasonably arrange inventory and formulate promotion strategies.

[0054] S103: Input the spatiotemporal law of the first data into the target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine; wherein the spatiotemporal law includes time dimension characteristics and space dimension characteristics, and the target data analysis model includes a time series analysis model and a space analysis model.

[0055] In this embodiment, the target data analysis model is a pre-built mathematical model used to process and analyze input data. In the scenario of vending machines, the target data analysis model is used to analyze sales trends, evaluate inventory status, etc.

[0056] The target data analysis model may be a time series analysis model (used to analyze sales trends), a spatial analysis model, a regression analysis model (used to evaluate the relationship between inventory status and sales), a cluster analysis model (used to classify sales patterns of different vending machines), etc.

[0057] After the spatiotemporal patterns of the first data are input into the target data analysis model, the model will process and analyze the data according to its built-in algorithms and parameters.

[0058] For example, for sales trend analysis, the model will calculate the moving average, growth rate and other indicators of sales data to determine the changing trend of sales. For inventory status assessment, the model will consider factors such as sales speed and replenishment cycle to give reasonable inventory recommendations.

[0059] From the above, it can be concluded that, firstly, the present disclosure obtains the spatiotemporal law by preprocessing the first data, and the sales situation of the vending machine can be obtained according to the spatiotemporal law, and then the target data analysis model is determined, so that the analysis is more targeted and professional, and the utilization rate of the data is improved.

[0060] Secondly, after determining the spatiotemporal regularity of the first data, the present disclosure can better predict sales demand at different times and locations. The commodity adjustment strategy obtained by inputting the spatiotemporal regularity of the first data into the target model helps to arrange inventory reasonably and avoid inventory backlogs or out-of-stock situations. For example, increase inventory in advance before the peak sales season and appropriately reduce inventory during the off-season to reduce inventory costs and improve capital turnover. At the same time, adjust inventory according to consumer demand in different locations to ensure the supply of popular commodities and meet consumer demand.

[0061] Finally, based on the time-space law analysis and product adjustment strategy of First Data, vending machines can better meet the needs of consumers at different times and places. Consumers can more conveniently buy the products they need at nearby vending machines, which improves the convenience of shopping.

[0062] In one embodiment of the present disclosure, preprocessing the first data to obtain the spatiotemporal regularity of the first data includes:

[0063] Preprocessing the first data according to the first identification information to obtain time dimension features and space dimension features;

[0064] The first identification information is identification information for determining the source of the first data.

[0065] In this embodiment, the first identification information is identification information used to determine the source of the first data. In the scenario of a vending machine, the first identification information may include the number, location information, time information, etc. of the vending machine, which can help us distinguish data from different sources and extract corresponding spatiotemporal features accordingly.

[0066] Time dimension features refer to the regularity of data changes over time. For example, in the scenario of vending machines, time dimension features can include the periodic changes in sales data (such as daily sales peaks and troughs), the impact of holidays on sales, etc.

[0067] Spatial dimension features refer to the differences in data at different spatial locations. In the vending machine scenario, spatial dimension features can include differences in sales data of vending machines in different locations, spatial distribution of user behavior, etc.

[0068] In one embodiment of the present disclosure, preprocessing the first data according to the first identification information to obtain the time dimension feature and the space dimension feature of the first data includes:

[0069] The first data is classified according to the first identification information, and the classified data is preprocessed to obtain the time dimension feature and the space dimension feature of the first data. The first identification information includes the number, location information, and time information of the vending machine.

[0070] In this embodiment, the first data is classified according to the first identification information, and the classified data is preprocessed to obtain the time dimension feature and the space dimension feature of the first data, including:

[0071] Classifying the first data according to the serial number and time information of the vending machine, and preprocessing the classified data to obtain the time dimension feature of the first data;

[0072] The first data is classified according to the number and location information of the vending machine, and the classified data is preprocessed to obtain the spatial dimension features of the first data.

[0073] In this embodiment, first, the system will classify the first data according to the vending machine number (as a unique identifier) ​​and time information (such as date, timestamp, etc.). In this way, data from different vending machines and different time points can be distinguished for subsequent targeted analysis. The system will preprocess the classified data to extract time dimension features. These features include time series analysis of sales data (such as daily, weekly, and monthly sales changes), identification of sales peaks and troughs, and the impact of holidays on sales. These features help reveal the trends and periodic laws of sales data over time.

[0074] Secondly, the system will classify the first data according to the number and location information of the vending machine (such as longitude and latitude, city, region, etc.). This can distinguish data from different geographical locations so as to analyze the distribution and differences of sales data in different spatial locations. The system will preprocess the classified data to extract spatial dimension features. These features include sales data comparison in different locations, identification of hot and cold sales areas, and sales data trends with geographical location. These features help to understand the distribution patterns and differences of sales data in different spatial locations.

[0075] It can be concluded from the above that this embodiment can accurately extract the time dimension features and space dimension features, that is, the time-space law, in the data by preprocessing the first data using the first identification information. This processing method not only improves the accuracy and efficiency of data analysis, but also provides a strong basis for subsequent data mining and decision support, which helps enterprises optimize resource allocation and improve overall operational results.

[0076] In one embodiment of the present disclosure, determining a target data analysis model based on the spatiotemporal regularity of first data includes:

[0077] Determining the priority order of the time dimension feature and the space dimension feature of the first data;

[0078] Determine the target data analysis model based on the priority order.

[0079] In this embodiment, the priority order refers to sorting the importance of time dimension features and space dimension features when determining the target data analysis model.

[0080] When the priority of the time dimension feature of the first data is greater than the priority of the space dimension feature, the target data analysis model is determined to be a time series analysis model; when the priority of the time dimension feature of the first data is less than the priority of the space dimension feature, the target data analysis model is determined to be a space analysis model.

[0081] The time series analysis model may be an autoregressive integrated moving average model (ARIMA) or a time series prediction model in machine learning.

[0082] The spatial analysis model can be a spatial autocorrelation analysis model, a spatial clustering analysis model, a spatial regression model, etc.

[0083] For example, suppose there is a vending machine operating company that has placed a large number of vending machines in different locations in multiple cities. The system obtains the first data sent by the vending machine, including information such as sales time, sales location, sales product types and sales amount. First, the first data is preprocessed to analyze its spatiotemporal laws. Through observation, it is found that the sales trends in different time periods are quite different, while the consumer demand in different locations is relatively similar. Therefore, it is determined that the priority of time dimension features is greater than that of spatial dimension features. Based on this, the ARIMA model in the time series analysis model is selected as the target data analysis model. The model is used to analyze historical sales data and predict sales in different time periods in the future. According to the prediction results, the staff can arrange inventory reasonably and prepare goods in advance during the peak sales period to avoid out-of-stock situations. At the same time, corresponding marketing strategies can be formulated according to the sales characteristics of different time periods to improve sales performance.

[0084] If the consumer demand in different locations is significantly different, but the sales trends in different time periods are relatively similar, the system will determine that the priority of spatial dimension features is greater than the priority of temporal dimension features, and then select a spatial analysis model, such as a spatial clustering analysis model, to classify vending machines in different locations in order to better understand the consumer demand in different regions and adjust the product types and inventory levels in a targeted manner.

[0085] In one embodiment of the present disclosure, determining the priority order of the time dimension feature and the space dimension feature of the first data includes:

[0086] The priority order of the time dimension feature and the space dimension feature of the first data is determined according to the environmental feature corresponding to the first data.

[0087] In this embodiment, the environmental features include holidays, weather characteristics, promotional activities, etc. The priority order of the time dimension features and the space dimension features of the first data is determined according to the holiday characteristics corresponding to the first data. For example, during long holidays such as the Spring Festival and National Day, sales data will increase significantly in a specific time period, and the consumption hotspots of different holidays are also different. For example, during the Spring Festival, the demand for snacks, beverages and special gifts may increase; while during holidays such as Labor Day, vending machines near tourist attractions may usher in a sales peak, mainly selling beverages and convenience foods. In this case, the importance of the time dimension feature is highlighted, because the time points of different holidays are clear, and the sales trend changes significantly over time. At this time, the priority of the time dimension feature can be increased. Although holidays will also affect the sales of vending machines in different locations, the changes are relatively gentle relative to the time dimension. For example, in tourist cities, the sales of vending machines in scenic spots and commercial areas will increase during holidays, but the differences between different areas may not be as obvious as the changes in time. Therefore, under the holiday environmental characteristics, the priority of the space dimension feature is relatively low.

[0088] The priority order of the time dimension feature and the space dimension feature of the first data is determined according to the weather characteristics corresponding to the first data. Weather will also change over time to a certain extent. The weather characteristics in different seasons and different time periods are different, which will affect the sales of vending machines. For example, in hot summers, the sales of beverages will increase as the temperature rises; in cold winters, the sales of hot drinks will rise. Different geographical locations have different responses to weather. For example, in coastal cities, cool sea breezes will reduce people's demand for cold drinks, while in inland cities, the sales of cold drinks may be very hot in hot weather. Similarly, in mountainous areas and urban centers, the types and quantities of goods sold under different weather conditions may also vary greatly. Therefore, under the weather characteristics and environmental characteristics, the importance of spatial dimension features is equivalent to that of time dimensions, or even higher in some cases, depending on the distribution location of vending machines and the characteristics of the goods sold.

[0089] The priority order of the time dimension feature and the space dimension feature of the first data is determined according to the promotion activity corresponding to the first data. Promotion activities usually have clear time nodes, and during the promotion activities, the sales of vending machines may show obvious time changes. For example, during the "Double 11" period, merchants launch specific promotion activities, and sales data may increase significantly during this time period. This time concentration makes the time dimension feature have a higher priority in the promotion environment, because the sales trend can be predicted according to the time schedule of the promotion activities, and the inventory and commodity strategies can be adjusted. Promotion activities will also have an impact on the sales of vending machines in different locations, but the changes may be more complex relative to the time dimension. For example, although promotion activities in commercial areas and residential areas at the same time will lead to sales growth, the growth rate may be different due to different consumer groups and consumer demands.

[0090] In general, under the environmental characteristics of promotion activities, the priority of time dimension characteristics is usually higher than that of space dimension characteristics, but it also needs to be considered comprehensively in combination with specific geographical locations and consumer groups.

[0091] From the above, it can be concluded that this embodiment can comprehensively judge the priority order of the time dimension characteristics and space dimension characteristics of the first data by analyzing environmental characteristics such as holidays, weather characteristics, and promotional activities, so as to more accurately determine the target data analysis model and provide a more effective basis for the product adjustment strategy of the vending machine.

[0092] In one embodiment of the present disclosure, determining a target data analysis model based on a priority order includes:

[0093] Obtaining the model category of the target data analysis model from the preset data analysis model set based on the priority order;

[0094] Determine the target data analysis model based on the evaluation metrics and model categories.

[0095] In this embodiment, the evaluation indicators include prediction accuracy, response time, model complexity, etc. If the model category (such as time series analysis model) in which the target data analysis model belongs includes three data analysis models, the prediction accuracy of the first data analysis model is greater than that of the second data analysis model, and the prediction accuracy of the second data analysis model is greater than that of the third data analysis model; the response time of the first data analysis model is greater than that of the second data analysis model, and the response time of the second data analysis model is less than that of the third data analysis model; the model complexity of the first data analysis model is greater than that of the second data analysis model, and the model complexity of the second data analysis model is greater than that of the third data analysis model.

[0096] When the evaluation indicator is prediction accuracy, the target data analysis model is determined based on prediction accuracy and model category. For example, before important holidays or major promotions, it is crucial to accurately predict sales trends in order to accurately prepare goods. At this time, although the first data analysis model has a longer response time and higher model complexity, it can be preferred because of its highest prediction accuracy. In the event preparation stage, the model can be run in advance for prediction to make up for the lack of longer response time.

[0097] When the evaluation indicator is response time, the target data analysis model is determined based on the response time and model category. For the formulation of daily commodity adjustment strategies, it is necessary to shorten the response time as much as possible on the basis of a certain prediction accuracy so as to make timely adjustments according to market changes. In this case, the second data analysis model is a more appropriate choice. Although its prediction accuracy is slightly lower than that of the first model, its response time is shorter and can meet the timeliness requirements of daily decision-making. At the same time, the model complexity is relatively moderate and easy to maintain and manage.

[0098] When the evaluation indicator is model complexity, the target data analysis model is determined based on the model complexity and model category. For example, if the model category belongs to the time series analysis model, and the business scenario has strict restrictions on computing resources and deployment environment, then a low-complexity model is more suitable. For example, in some old vending machine systems, the hardware performance is limited and cannot support complex calculations. At this time, a simple time series analysis model, such as a moving average model, is selected. Although the prediction accuracy may be relatively low, it can run quickly with limited resources and meet basic commodity adjustment needs.

[0099] From the above, it can be concluded that this embodiment, through the method of determining the target data analysis model based on the priority order, can efficiently screen out the target data analysis model that meets the requirements from the preset data analysis model set, which not only improves the accuracy and efficiency of data analysis, but also ensures the scientificity and rationality of model selection, and provides strong support for data analysis and decision-making.

[0100] In one embodiment of the present disclosure, the second data is input into the target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine, including:

[0101] When the second data satisfies the first condition, the target data analysis model outputs a commodity adjustment strategy corresponding to the vending machine according to the first number of influencing factors;

[0102] When the second data satisfies the second condition, the target data analysis model outputs a commodity adjustment strategy corresponding to the vending machine according to the influencing factors of the second quantity;

[0103] The first number is greater than the second number.

[0104] In this embodiment, if the data integrity of the second data is greater than or equal to the third value, the second data meets the first condition. For example, the data of the vending machine includes sales history data, real-time inventory data, and surrounding environment data, and the third value can be the number 3. If the second data includes any two or three of the sales history data, real-time inventory data, and surrounding environment data, the second data meets the first condition; if the second data includes one of the sales history data, real-time inventory data, and surrounding environment data, the second data meets the second condition.

[0105] Alternatively, if the update frequency of the second data is greater than the preset update frequency, the second data satisfies the first condition; if the update frequency of the second data is less than or equal to the preset update frequency, the second data satisfies the second condition. For example, if the preset update frequency is once a day, if the second data is updated once every 12 hours, the second data satisfies the first condition; if the second data is updated once a week, the second data satisfies the second condition.

[0106] The influencing factors include the area, flow of people, cost, etc. of the vending machine. When the second data meets the first condition, the commodity adjustment strategy corresponding to the vending machine can be output according to multiple influencing factors (such as the area, flow of people, and cost of the vending machine); when the second data meets the second condition, the commodity adjustment strategy corresponding to the vending machine can be output according to a single influencing factor (such as the area, flow of people, or cost of the vending machine).

[0107] It can be concluded from the above that this embodiment determines the first condition and the second condition by the data integrity and update frequency of the second data, and then obtains the commodity adjustment strategy. When the first condition is met, a strategy is formulated by integrating multiple influencing factors to fully adapt to complex situations; when the second condition is met, a strategy is quickly generated based on a single influencing factor to improve efficiency. This embodiment can adapt to different scenarios and provide flexible and effective decision support for commodity adjustment of vending machines.

[0108] In one embodiment of the present disclosure, the data management method further includes:

[0109] analyzing a change in the third data relative to the first data;

[0110] If the change is within the first range, a product adjustment strategy is generated at a first update frequency;

[0111] If the change amount is not within the first range, a product adjustment strategy is generated at a second update frequency;

[0112] The third data is data within a first period of time after the vending machine is adjusted according to the product adjustment strategy, and the first update frequency is less than the second update frequency.

[0113] In this embodiment, the third data is data generated within the first period of time after the vending machine is adjusted according to the previously generated commodity adjustment strategy. Analyzing the change amount is to compare the difference between the third data and the first data in various aspects, such as changes in sales quantity, adjustment effects of commodity types, changes in inventory levels, etc.

[0114] When the change obtained by analysis is within a specific first range, it means that the adjustment effect of the vending machine is relatively stable, without large fluctuations or abnormalities. At this time, the commodity adjustment strategy can be generated with a relatively low first update frequency. This is because in this case, the system believes that the current adjustment strategy is basically effective and does not need to be adjusted too frequently. The strategy can be updated after a certain time interval to save computing resources and improve efficiency.

[0115] If the change is not within the first range, it means that the adjusted data of the vending machine has changed significantly compared with the original data, which may be due to poor adjustment strategy effect or new market conditions. In this case, the product adjustment strategy can be generated at the second update frequency, with the purpose of responding to the current situation in a timely manner, quickly adjusting the product strategy to adapt to new changes, avoiding losses or improving sales performance.

[0116] From the above, it can be concluded that this embodiment adjusts the generation frequency of the commodity adjustment strategy by analyzing the change amount of the third data relative to the first data. When the change amount is within the first range, the strategy is updated at a lower frequency to save resources and stabilize operations; if the change amount is not within the first range, the update frequency is increased to respond to emergencies in a timely manner, ensuring that the vending machine always adapts to market changes and improves operational efficiency and benefits.

[0117] In one embodiment of the present disclosure, the data management method further includes:

[0118] If the number of updates of the product adjustment strategy within the second period is greater than the fourth value, the target data analysis model is re-determined.

[0119] In this embodiment, by counting the number of updates of the commodity adjustment strategy within the second time period, the stability of the market environment or internal state of the vending machine can be understood. If the number of updates is small, it means that the situation is relatively stable and the current target data analysis model is more applicable. If the number of updates is greater than the fourth value, it means that the strategy changes frequently during this period, and the current analysis model may not be able to adapt well to the actual situation and needs to be adjusted. When the number of updates exceeds the threshold (the fourth value), redefining the target data analysis model can prompt the system to continuously optimize and adapt to changes. The process of redefining the model may include re-evaluating the spatiotemporal laws of the data, selecting different algorithms, or adjusting model parameters, etc., to improve the accuracy and adaptability of the model.

[0120] From the above, it can be concluded that this embodiment monitors the number of updates of the commodity adjustment strategy within the second time period, and re-determines the target data analysis model when it exceeds the fourth value, so as to ensure that the model is always adapted to the actual situation. It can respond to the complex and changing market environment in a timely manner, improve the accuracy and effectiveness of the strategy, avoid decision-making errors caused by model aging or inadaptability, and improve the operational efficiency and economic benefits of the vending machine.

[0121] Corresponding to the data management method of the above embodiment, Figure 2 This is a structural block diagram of a data management system provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The data management system 20 includes: a data processing module 21, a model selection module 22, and a data analysis module 23.

[0122] The data processing module 21 is used to pre-process the first data to obtain the time-space regularity of the first data; the first data is the original data sent by the vending machine to the background management platform;

[0123] A model selection module 22, for determining a target data analysis model based on the spatiotemporal regularity of the first data;

[0124] A data analysis module 23, used for inputting the spatiotemporal regularity of the first data into a target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine;

[0125] Among them, spatiotemporal laws include time dimension characteristics and space dimension characteristics, and the target data analysis model includes time series analysis model and space analysis model.

[0126] In one embodiment of the present disclosure, the data processing module 21 is specifically used for:

[0127] Preprocessing the first data according to the first identification information to obtain time dimension features and space dimension features;

[0128] The first identification information is identification information for determining the source of the first data.

[0129] In one embodiment of the present disclosure, the data processing module 21 is specifically used for:

[0130] The first data is classified according to the first identification information, and the classified data is preprocessed to obtain time dimension features and space dimension features.

[0131] In one embodiment of the present disclosure, the model selection module 22 is specifically used to:

[0132] Determining the priority order of the time dimension feature and the space dimension feature of the first data;

[0133] Determine the target data analysis model based on the priority order.

[0134] In one embodiment of the present disclosure, the model selection module 22 is specifically used to:

[0135] The priority order of the time dimension feature and the space dimension feature of the first data is determined according to the environmental feature corresponding to the first data.

[0136] In one embodiment of the present disclosure, the model selection module 22 is specifically used to:

[0137] Obtaining the model category of the target data analysis model from the preset data analysis model set based on the priority order;

[0138] Determine the target data analysis model based on the evaluation metrics and model categories.

[0139] In one embodiment of the present disclosure, the data analysis module 23 is specifically used to:

[0140] When the second data satisfies the first condition, the target data analysis model outputs a commodity adjustment strategy corresponding to the vending machine according to the first number of influencing factors;

[0141] When the second data satisfies the second condition, the target data analysis model outputs a commodity adjustment strategy corresponding to the vending machine according to the influencing factors of the second quantity;

[0142] The first number is greater than the second number.

[0143] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0144] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0145] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0146] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0147] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the data management method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0148] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0149] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0150] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. 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 this disclosure.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0152] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0153] 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 embodiments of the present disclosure.

[0154] In addition, each functional unit in each embodiment of the present disclosure 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.

[0155] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A data management method, characterized in that: include: Preprocessing the first data to obtain the spatiotemporal regularity of the first data; The first data is the original data sent by the vending machine to the backend management platform; Determine a target data analysis model based on the spatiotemporal regularity of the first data; Inputting the spatiotemporal regularity of the first data into the target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine; Wherein, the spatiotemporal law includes time dimension characteristics and space dimension characteristics, and the target data analysis model includes a time series analysis model and a space analysis model; The determining of the target data analysis model based on the spatiotemporal regularity of the first data includes: Determining the priority order of the time dimension features and the space dimension features of the first data; Determine the target data analysis model based on the priority order; the priority order refers to sorting the importance of the time dimension features and the space dimension features when determining the target data analysis model; when the priority of the time dimension features of the first data is greater than the priority of the space dimension features, determine that the target data analysis model is a time series analysis model; when the priority of the time dimension features of the first data is less than the priority of the space dimension features, determine that the target data analysis model is a space analysis model; The determining the priority order of the time dimension feature and the space dimension feature of the first data includes: Determining the priority order of the time dimension feature and the space dimension feature of the first data according to the environmental features corresponding to the first data; the environmental features include holidays, weather characteristics, and promotional activities; The data management method further comprises: analyzing a change in the third data relative to the first data; If the change is within the first range, a product adjustment strategy is generated at a first update frequency; If the change amount is not within the first range, a product adjustment strategy is generated at a second update frequency; The third data is data within a first period of time after the vending machine is adjusted according to the product adjustment strategy, and the first update frequency is less than the second update frequency; If the number of updates of the product adjustment strategy within the second period is greater than the fourth value, the target data analysis model is re-determined.

2. The data management method according to claim 1, characterized in that: The preprocessing of the first data to obtain the spatiotemporal regularity of the first data includes: Preprocessing the first data according to the first identification information to obtain time dimension features and space dimension features; The first identification information is identification information for determining the source of the first data.

3. The data management method according to claim 2, characterized in that: The preprocessing of the first data according to the first identification information to obtain a time dimension feature and a space dimension feature includes: The first data is classified according to the first identification information, and the classified data is preprocessed to obtain time dimension features and space dimension features.

4. The data management method according to claim 1, characterized in that: The determining of the target data analysis model based on the priority order includes: Obtaining the model category of the target data analysis model from a preset data analysis model set based on the priority order; The target data analysis model is determined based on the evaluation index and the model category.

5. The data management method according to claim 1, characterized in that: The step of inputting the spatiotemporal regularity of the first data into the target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine includes: When the spatiotemporal regularity of the first data satisfies a first condition, obtaining a commodity adjustment strategy corresponding to the vending machine based on the target data analysis model and the influencing factors of the first quantity; When the spatiotemporal regularity of the first data satisfies a second condition, obtaining a commodity adjustment strategy corresponding to the vending machine based on the target data analysis model and the influencing factors of the second quantity; Wherein, the first number is greater than the second number.

6. A data management system, characterized in that: include: A data processing module, used for preprocessing the first data to obtain the spatiotemporal regularity of the first data; The first data is the original data sent by the vending machine to the backend management platform; A model selection module, used to determine a target data analysis model based on the spatiotemporal regularity of the first data; The determining of the target data analysis model based on the spatiotemporal regularity of the first data includes: Determining the priority order of the time dimension features and the space dimension features of the first data; The target data analysis model is determined based on the priority order; the priority order refers to sorting the importance of the time dimension features and the space dimension features when determining the target data analysis model; when the priority of the time dimension features of the first data is greater than the priority of the space dimension features, the target data analysis model is determined to be a time series analysis model; when the priority of the time dimension features of the first data is less than the priority of the space dimension features, the target data analysis model is determined to be a space analysis model; The determining the priority order of the time dimension feature and the space dimension feature of the first data includes: Determining the priority order of the time dimension feature and the space dimension feature of the first data according to the environmental features corresponding to the first data; the environmental features include holidays, weather characteristics, and promotional activities; A data analysis module, configured to input the spatiotemporal law of the first data into the target data analysis model to obtain a commodity adjustment strategy corresponding to the vending machine, wherein the spatiotemporal law includes time dimension features and space dimension features, and the target data analysis model includes a time series analysis model and a space analysis model; analyzing a change in the third data relative to the first data; If the change is within the first range, a product adjustment strategy is generated at a first update frequency; If the change amount is not within the first range, a product adjustment strategy is generated at a second update frequency; The third data is data within a first period of time after the vending machine is adjusted according to the product adjustment strategy, and the first update frequency is less than the second update frequency; If the number of updates of the product adjustment strategy within the second period is greater than the fourth value, the target data analysis model is re-determined.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images