A retail data processing method, device, computer equipment and computer storage medium

Through the preprocessing of real-time transaction data flow and multi-factor calculation, dynamic adjustment of inventory management strategies has been solved, and the problem that traditional inventory management systems cannot respond to market changes and supply chain risks has been achieved, more accurate inventory forecasting and management has been achieved, and inventory management has been improved. Efficiency and economic benefits.

CN118840046BActive Publication Date: 2024-12-06BEIJING ALL VIEW CLOUD DATA TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411288381.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-06
Estimated Expiration
2044-09-14

AI Technical Summary

Technical Problem

Traditional inventory management systems are unable to respond to market changes and supply chain risks in a timely manner, resulting in the problem of overstock or shortage of inventory. The existing methods ignore factors such as seasonal fluctuations and supply chain risks, resulting in inaccurate prediction results.

Method used

Calculate inventory by obtaining real-time transaction data streams, including sales records, user behavior information and market trend data, preprocessing to determine predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response forecast factors, and market trend impact factors. Demand index and dynamically adjust inventory management strategies based on the index.

Benefits of technology

It significantly improves the level of inventory management, ensures that inventory is neither surplus nor shortage, reduces inventory costs, and improves customer satisfaction and the accuracy of procurement decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118840046B_ABST
    Figure CN118840046B_ABST
Patent Text Reader

Abstract

The present application provides a retail data processing method, apparatus, computer equipment and computer storage medium. Obtain a real-time transaction data stream, wherein the real-time transaction data stream includes sales records, user behavior information and market trend data; pre-process the real-time transaction data stream, and determine the predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors and market trend influencing factors based on the pre-processed real-time transaction data; calculate the inventory demand index based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factors, the consumer response prediction factors and the market trend influencing factors; dynamically adjust the inventory management strategy based on the inventory demand index. The technical solution provided by the present application can significantly improve the level of inventory management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing technology, and in particular, to a retail data processing method, apparatus, computer equipment, and computer storage medium. Background Art

[0002] In the retail industry, there is a need to respond quickly to market changes, including consumer purchasing behavior, supply chain uncertainties, and fluctuations in market trends. Traditional inventory management systems often fail to respond to these changes in a timely manner, resulting in problems such as excess or shortage of inventory.

[0003] At present, traditional inventory management systems usually perform simple statistical analysis based on historical sales data to predict future sales. This method is relatively simple and easy to implement, but it has limitations in dealing with market fluctuations and supply chain risks. In other words, current methods often only consider historical sales data, ignoring factors such as seasonal fluctuations and supply chain risks, resulting in inaccurate prediction results. Summary of the invention

[0004] The embodiments of the present application provide a retail data processing method, apparatus, computer equipment and computer storage medium to solve the problem of poor inventory management level in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a retail data processing method, comprising:

[0006] Acquire a real-time transaction data stream, wherein the real-time transaction data stream includes sales records, user behavior information, and market trend data;

[0007] Preprocessing the real-time transaction data stream, and determining predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors, and market trend influencing factors based on the preprocessed real-time transaction data;

[0008] Calculating an inventory demand index based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor;

[0009] The inventory management strategy is dynamically adjusted according to the inventory demand index.

[0010] Optionally, the method further includes: performing anomaly detection on the pre-processed real-time transaction data to generate anomaly detection results.

[0011] Optionally include:

[0012] An anomaly detection is performed on the pre-processed real-time transaction data using an adaptive threshold algorithm; or, an anomaly detection mechanism is used to perform an anomaly detection on the pre-processed real-time transaction data.

[0013] Optionally include:

[0014] By formula:

[0015]

[0016] Calculate the inventory demand index;

[0017] in, It represents the inventory demand index, which is a quantitative indicator of current inventory demand; is the current inventory; represents the predicted sales volume; is a constant used to adjust the weight of the ratio of current inventory to forecast sales; Indicates seasonal fluctuations, is a constant used to adjust the impact of seasonal fluctuations on inventory demand; Indicates a point in time; Indicates seasonal cycles; represents the supply chain risk factor, is a constant used to quantify the impact of supply chain risk factors on inventory demand; represents the consumer response predictor; is a constant used to quantify the degree of influence of consumer response predictors on inventory demand; Indicates the market trend influencing factor; is a constant used to quantify the impact of market trend factors on inventory demand;

[0018] in, Indicates the degree of volatility in forecasted sales and the impact of supply chain delays on inventory demand; Indicates the degree of volatility of the forecasted sales volume; It represents the average level of predicted sales volume; represents delayed sales, which is the amount of sales reduced due to supply chain delays; is a constant used to adjust the impact of delayed sales on inventory demand; is a constant used to adjust the rate of change of delayed sales over time; Indicates the starting time point.

[0019] Optionally, the calculation formula of the supply chain risk factor is:

[0020]

[0021] in, represents the supply chain risk factor; represents the impact of supply chain delays on supply chain risk factors, Indicates delayed sales volume; stands for delay cost, which refers to the additional cost caused by supply chain delays; is a constant used to adjust the impact of supply chain delay on supply chain risk factors; is the time variable; The delayed time point refers to the time point of supply chain delay;

[0022] in, It represents the impact of delay time in the supply chain on the supply chain risk factors, is a constant used to adjust the impact of supply chain delay on supply chain risk factors; It represents the delay time, which is the time interval from one event to another in the supply chain;

[0023] in, It means that the risk distribution of a specific area in the supply chain is considered through the sine series. is a specific length, indicating the length of a specific area; is a position variable, which refers to the position along a specific length The location coordinates of is the number of series items used to calculate the number of terms in the sine series of ; is a coefficient used to adjust the weights of each term in the sine series.

[0024] Optionally, the calculation formula of the consumer response prediction factor is:

[0025]

[0026] in, represents the consumer response predictor, which is used to assess the degree of consumer response to the product; Represents the combined effect of different consumer groups’ responses to the product, is the number of consumer groups; For the The response rate of a consumer group, that is, the intensity of the consumer group's response to the product; For the The response speed of the consumer group, that is, The speed of each consumer group; is the time variable; For the The response time of each consumer group; For the The weight of the consumer group, i.e. the extent to which individual consumer groups contribute to the predictors of overall consumer response; is a constant used to adjust the degree of influence of consumer group response on the consumer response predictor;

[0027] in, represents the effect of product position or attribute variables on the predictors of consumer response, is a position variable, which refers to the product position or attribute variable; for The mean of , which indicates the average level of product position or variable attribute; for The standard deviation of , which indicates the degree of variation in product position or variable attributes; is a constant used to adjust the effect of changes in product location or variable attributes in the consumer response predictors.

[0028] Optionally, the calculation formula of the market trend impact factor is:

[0029]

[0030] in, Indicates the market trend impact factor, which is used to evaluate the impact of market trends on product demand; It indicates the comprehensive effect of different market trend indicators on market trend influencing factors; is the number of market trend indicators; For the The weight of the market trend indicator, indicating the The degree of influence of each market trend indicator on the market trend influencing factors; For the Market trend indicators at a point in time The value of No. The value of a market trend indicator; Indicates Market trend indicators in The value at time No. The value of the market trend indicator, where Indicates time difference; is an empirical constant used to adjust the degree of influence of market trend indicators on market trend influencing factors;

[0031] in, Indicates the distribution of market trends in a specific area. is a specific length, indicating the length of a specific area; is the position variable; is the number of sine series terms used to calculate the number of terms in the sine series of ; is a coefficient used to adjust the weights of each term in the sine series.

[0032] In a second aspect, this embodiment provides a retail data processing device, including:

[0033] An acquisition module, used to acquire real-time transaction data streams, wherein the real-time transaction data streams include sales records, user behavior information, and market trend data;

[0034] A determination module, configured to preprocess the real-time transaction data stream and determine predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors, and market trend influencing factors based on the preprocessed real-time transaction data;

[0035] A calculation module, configured to calculate an inventory demand index based at least on the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor;

[0036] The adjustment module is used to dynamically adjust the inventory management strategy according to the inventory demand index.

[0037] In a third aspect, this embodiment provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a retail data processing method as described in any one of the first aspects.

[0038] In a fourth aspect, this embodiment provides a computer storage medium storing a computer program, wherein when the computer program is executed by a computer, a retail data processing method as described in any one of the first aspects is implemented.

[0039] In the embodiment of the present application, a real-time transaction data stream is obtained, and the real-time transaction data stream includes sales records, user behavior information and market trend data; the real-time transaction data stream is preprocessed, and the predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors and market trend influencing factors are determined based on the preprocessed real-time transaction data; the inventory demand index is calculated based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factors, the consumer response prediction factors and the market trend influencing factors; and the inventory management strategy is dynamically adjusted based on the inventory demand index. The technical solution provided by the present application can significantly improve the level of inventory management.

[0040] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 A flowchart of a retail data processing method provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of the structure of a retail data processing method and device provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0046] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to different types.

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0048] Figure 1 A flowchart of a retail data processing method is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0049] 101. Acquire a real-time transaction data stream, wherein the real-time transaction data stream includes sales records, user behavior information, and market trend data;

[0050] In this step, a real-time transaction data stream is obtained, wherein the real-time transaction data stream includes sales records, user behavior information and market trend data.

[0051] Real-time transaction data stream: refers to transaction data collected continuously from various data sources, which usually contains information about sales records, user behavior, and market trends. Real-time data streams are characterized by large data volume and high speed, and need to be processed immediately to obtain valuable information.

[0052] Sales records: refers to the specific details of each transaction, including but not limited to product name, price, quantity, transaction time, etc.

[0053] User behavior information: including user browsing history, search history, click-through rate, purchase frequency and other data. This information can help analyze user shopping habits and preferences.

[0054] Market trend data: refers to information that reflects the overall market trend, such as industry reports, macroeconomic indicators, competitor sales data, etc., which can be used to predict the direction of market development.

[0055] In the embodiment of the present application, we can collect real-time transaction data streams from different data sources through a real-time data collection system and integrate them into a unified data stream for subsequent processing. Specifically, this step can be divided into the following sub-steps:

[0056] Data source integration: Integrate data from different channels, such as POS (Point of Sale), online shopping platforms, social media platforms, market research reports, etc.

[0057] Data preprocessing: clean the data, remove invalid or duplicate records, process missing values, and ensure data quality.

[0058] Data stream integration: Merge data from different sources into a single data stream for subsequent processing.

[0059] Data storage and transmission: Store real-time data streams in cache or stream processing systems for subsequent analysis.

[0060] Assume that a retail company is running this real-time transaction data stream processing system. The company collects data through its online and offline stores. The specific steps are as follows:

[0061] Data source integration:

[0062] POS System: Collect sales records from offline store’s POS system.

[0063] Online platform: Collect user behavior data from the company's e-commerce platform, such as browsing history, search keywords, etc.

[0064] Social Media: Monitor user comments and feedback on social media platforms.

[0065] Market Research Reports: Get regular access to industry reports and macroeconomic data.

[0066] Data preprocessing:

[0067] Clean data: remove duplicate transaction records and fill in missing price information.

[0068] Data standardization: standardize the date format to YYYY-MM-DD and the amount unit to RMB.

[0069] Data flow integration:

[0070] Use a data stream processing framework (such as Apache Kafka) to integrate data streams from all data sources to ensure data consistency and timeliness.

[0071] Data storage and transmission:

[0072] Store real-time data streams in an in-memory database, such as Redis, for fast access.

[0073] Use a message queue (such as RabbitMQ) to transmit data to the data analysis server.

[0074] Assume that within one hour, the system collects the following data records:

[0075] Sales Record:

[0076] Product ID: 1001, Product name: iPhone14 ProMax, Price: 9999 yuan, Sales quantity: 3, Transaction time: 2024-08-17 14:30:00

[0077] Product ID: 1002, Product name: AirPods Pro 2nd Generation, Price: 1299 yuan, Sales quantity: 5, Transaction time: 2024-08-17 14:35:00

[0078] User behavior information:

[0079] User ID: U001, Views: 10, Search keywords: "wireless headphones", View time: 2024-08-17 14:20:00

[0080] User ID: U002, Views: 5, Search keywords: "new mobile phone", View time: 2024-08-17 14:25:00

[0081] Market trend data:

[0082] Industry report: The smartphone market is expected to grow at an annual rate of 5% in the coming year.

[0083] Macroeconomic data: Gross Domestic Product (GDP) increased by 6.5% year-on-year, and the consumer confidence index was 120.

[0084] Suppose we use a simple moving average to calculate the average daily sales over the past week as part of a market trend. The formula is as follows:

[0085]

[0086] in, Indicates Day's sales.

[0087] If the sales in the past week were: 98,000 yuan, 102,000 yuan, 105,000 yuan, 100,000 yuan, 99,000 yuan, 103,000 yuan, 101,000 yuan, the calculated daily average sales would be:

[0088] Yuan

[0089] Through the above embodiments, we can see how to collect real-time transaction data streams from different data sources, pre-process and integrate them, and lay the foundation for subsequent analysis and inventory management strategy adjustment.

[0090] 102. Preprocessing the real-time transaction data stream, and determining predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors, and market trend influencing factors based on the preprocessed real-time transaction data;

[0091] Optionally, the step 102 of calculating the inventory demand index based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor includes:

[0092] By formula:

[0093]

[0094] Calculate the inventory demand index;

[0095] in, It represents the inventory demand index, which is a quantitative indicator of current inventory demand; is the current inventory; represents the predicted sales volume; is a constant used to adjust the weight of the ratio of current inventory to forecast sales; Indicates seasonal fluctuations, is a constant used to adjust the impact of seasonal fluctuations on inventory demand; Indicates a point in time; Indicates seasonal cycles; represents the supply chain risk factor, is a constant used to quantify the impact of supply chain risk factors on inventory demand; represents the consumer response predictor; is a constant used to quantify the degree of influence of consumer response predictors on inventory demand; Indicates the market trend influencing factor; is a constant used to quantify the impact of market trend factors on inventory demand;

[0096] in, Indicates the degree of volatility in forecasted sales and the impact of supply chain delays on inventory demand; Indicates the degree of volatility of the forecasted sales volume; It represents the average level of predicted sales volume; represents delayed sales, which is the amount of sales reduced due to supply chain delays; is a constant used to adjust the impact of delayed sales on inventory demand; is a constant used to adjust the rate of change of delayed sales over time; Indicates the starting time point.

[0097] Optionally, the calculation formula of the supply chain risk factor in step 102 is:

[0098]

[0099] in, represents the supply chain risk factor; represents the impact of supply chain delays on supply chain risk factors, Indicates delayed sales volume; stands for delay cost, which refers to the additional cost caused by supply chain delays; is a constant used to adjust the impact of supply chain delay on supply chain risk factors; is the time variable; The delayed time point refers to the time point of supply chain delay;

[0100] in, It represents the impact of delay time in the supply chain on the supply chain risk factors, is a constant used to adjust the impact of supply chain delay on supply chain risk factors; It represents the delay time, which is the time interval from one event to another in the supply chain;

[0101] in, It means that the risk distribution of a specific area in the supply chain is considered through the sine series. is a specific length, indicating the length of a specific area; is a position variable, which refers to the position along a specific length The location coordinates of is the number of series items used to calculate the number of terms in the sine series of ; is a coefficient used to adjust the weights of each term in the sine series.

[0102] Optionally, the calculation formula of the consumer response prediction factor in step 102 is:

[0103]

[0104] in, represents the consumer response predictor, which is used to assess the degree of consumer response to the product; Represents the combined effect of different consumer groups’ responses to the product, is the number of consumer groups; For the The response rate of a consumer group, that is, the intensity of the consumer group's response to the product; For the The response speed of the consumer group, that is, The speed of each consumer group; is the time variable; For the The response time of each consumer group; For the The weight of the consumer group, i.e. the extent to which individual consumer groups contribute to the predictors of overall consumer response; is a constant used to adjust the degree of influence of consumer group response on the consumer response predictor;

[0105] in, represents the effect of product position or attribute variables on the predictors of consumer response, is a position variable, which refers to the product position or attribute variable; for The mean of , which indicates the average level of product position or variable attribute; for The standard deviation of , which indicates the degree of variation in product position or variable attributes; is a constant used to adjust the effect of changes in product location or variable attributes in the consumer response predictors.

[0106] Optionally, the calculation formula of the market trend impact factor in step 102 is:

[0107]

[0108] in, Indicates the market trend impact factor, which is used to evaluate the impact of market trends on product demand; It indicates the comprehensive effect of different market trend indicators on market trend influencing factors; is the number of market trend indicators; For the The weight of the market trend indicator, indicating the The degree of influence of each market trend indicator on the market trend influencing factors; For the Market trend indicators at a point in time The value of No. The value of a market trend indicator; Indicates Market trend indicators in The value at time No. The value of the market trend indicator, where Indicates time difference; is an empirical constant used to adjust the degree of influence of market trend indicators on market trend influencing factors;

[0109] in, Indicates the distribution of market trends in a specific area. is a specific length, indicating the length of a specific area; is the position variable; is the number of sine series terms used to calculate the number of terms in the sine series of ; is the coefficient used to adjust the weight of each term in the sine series;

[0110] Inventory Demand Index ( ): The Inventory Demand Index is an indicator calculated based on multiple factors to guide inventory management strategies. It takes into account factors such as current inventory levels, forecasted sales, seasonal fluctuations, supply chain risks, consumer response, and market trends.

[0111] Forecast sales volume ( ): Forecast sales volume is an estimate of sales volume over a period of time in the future based on historical data and current market conditions.

[0112] Seasonal fluctuations: Seasonal fluctuations reflect the periodic changes in sales during certain periods of the year. For example, winter clothing will have higher sales in winter.

[0113] Supply Chain Risk Factors ( ): Supply chain risk factors measure the impact of possible problems in the supply chain (such as delays, cost increases, etc.) on inventory demand.

[0114] Consumer response predictors ( ): Consumer response predictors assess the extent to which consumers react to new products or promotions.

[0115] Market trend influence factors ( ): Market trend influencing factors reflect the impact of macroeconomic conditions, industry trends and other external factors on product demand.

[0116] In this embodiment of the application, assume that we are an electronic product manufacturer and we need to adjust our inventory strategy according to market conditions. The following is a specific calculation example:

[0117] Initial conditions:

[0118] Current inventory Item;

[0119] Forecast sales Item;

[0120] Seasonal cycles Month (assuming the current time is the 8th month of the year, );

[0121] Supply chain delays sales Item;

[0122] Delay Cost element;

[0123] Delay time point (Assuming supply chain problems started 6 months ago);

[0124] Delay time months;

[0125] Specific area length unit;

[0126] Position variables unit;

[0127] Number of market trend indicators ;

[0128] Number of consumer groups ;

[0129] Calculation process:

[0130] Supply Chain Risk Factor SRF:

[0131] Assumptions

[0132]

[0133] Substituting the values:

[0134]

[0135] Predictors of Consumer Response :

[0136] Assumptions:

[0137]

[0138] Substituting the values:

[0139] Market trend factors :

[0140] Assumptions

[0141]

[0142] Substituting the values:

[0143]

[0144] Inventory Demand Index :

[0145] Assumptions

[0146]

[0147]

[0148] Substituting the values:

[0149]

[0150] result:

[0151] Calculated and The calculation results can help companies more accurately predict inventory demand, thereby reducing inventory costs and improving customer satisfaction.

[0152] 103. Calculate an inventory demand index based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor;

[0153] Based on the values ​​provided in step 102, we can calculate the specific and value.

[0154] Assumptions:

[0155] ,

[0156] but The calculated result is approximately

[0157]

[0158] 104. Dynamically adjust the inventory management strategy according to the inventory demand index.

[0159] Inventory Demand Index ( ): is a quantitative indicator used to measure the intensity and urgency of current inventory demand. It combines multiple factors such as forecast sales volume, seasonal fluctuations, supply chain risk factors, consumer response forecast factors, and market trend influence factors.

[0160] Dynamically adjust inventory management strategies: According to changes in the inventory demand index, adjust inventory management strategies in real time to ensure that inventory levels are neither excessive nor insufficient. This includes adjusting procurement plans, inventory replenishment frequency, inventory holdings, etc.

[0161] In the embodiments of this application, we will introduce in detail how to dynamically adjust the inventory management strategy based on the calculated inventory demand index (RIDI), and provide specific implementation steps and examples.

[0162] Dynamically adjust inventory management strategy implementation example:

[0163] Suppose a retail company calculates the inventory demand index for the day ( ), now we need to dynamically adjust the inventory management strategy based on this index. The following are the specific implementation steps:

[0164] Determine the inventory demand index ( ):

[0165] Assume that through the previous calculation, the inventory demand index for the day is obtained ;

[0166] Setting the threshold:

[0167] Set the threshold of the inventory demand index to determine the level of inventory demand. For example, you can set Indicates low demand, Indicates medium demand, Indicates high demand.

[0168] Develop an inventory management strategy:

[0169] According to the relationship between the inventory demand index and the threshold, formulate corresponding inventory management strategies.

[0170] if :Reduce purchase volume and reduce inventory holding costs.

[0171] if : Maintain the current purchasing plan and increase safety stock appropriately.

[0172] if : Increase purchase volume, speed up inventory replenishment frequency, and prepare for high demand.

[0173] Execute inventory management strategies:

[0174] according to ,lie in During the period, the strategy adopted is to maintain the current purchasing plan and appropriately increase safety stock.

[0175] Monitoring and Adjustment:

[0176] Continuously monitor changes in inventory demand index and adjust inventory management strategies in a timely manner based on actual conditions.

[0177] Specific implementation steps:

[0178] Determine the current inventory demand index:

[0179] Assume that the inventory demand index for the day

[0180] Adjust strategy based on inventory demand index:

[0181] because , adopt the strategy of maintaining the current procurement plan and appropriately increasing safety stock.

[0182] Maintain the current procurement plan unchanged.

[0183] Increase the safety stock, for example, increase the safety stock from the original 5% to 10%.

[0184] Monitor inventory levels to ensure that stock-outs do not occur.

[0185] Specific strategy implementation:

[0186] Assume that the current inventory is 300 units, the forecast sales are 500 units, and the safety stock ratio increases from 5% to 10%.

[0187] Calculate the new safety stock level:

[0188]

[0189] Calculate the new total inventory target:

[0190]

[0191] If the current inventory level is lower than the new total inventory target, additional purchases will be required to reach the target inventory level.

[0192] Execution and Monitoring:

[0193] Implement new inventory management strategies and monitor stock levels and sales.

[0194] Continuously adjust inventory management strategies based on market changes and sales data.

[0195] Through the above embodiments, we can see how to dynamically adjust the inventory management strategy according to the inventory demand index calculated in real time to ensure that the inventory level is neither excessive nor insufficient, thereby improving the efficiency and economic benefits of inventory management.

[0196] Optionally, the method further comprises: performing anomaly detection on the preprocessed real-time transaction data to generate anomaly detection results. This includes: performing anomaly detection on the preprocessed real-time transaction data using an adaptive threshold algorithm; or performing anomaly detection on the preprocessed real-time transaction data using an anomaly detection mechanism.

[0197] This step involves the process of performing anomaly detection on pre-processed real-time transaction data. Anomaly detection is an important part of data analysis and is used to identify abnormal patterns or behaviors in data, which may be caused by fraud, system failures, or other abnormal activities. Anomaly detection can be achieved in a variety of ways, including but not limited to using adaptive threshold algorithms or through anomaly detection mechanisms.

[0198] Among them, the adaptive threshold algorithm is a method that can automatically adjust the threshold according to the changes in data. This method is suitable for situations where the data has dynamic characteristics. By monitoring the changes in data over time, appropriate thresholds can be set to distinguish normal data from abnormal data. For example, the threshold can be dynamically adjusted based on statistical data (such as mean and standard deviation) over a recent period of time.

[0199] Anomaly detection mechanisms usually involve more complex statistical models or machine learning methods, such as Isolation Forest, Autoencoder, etc. These methods can learn the normal behavior patterns of the data and identify abnormal behaviors based on these patterns.

[0200] In the embodiment of this application, it is assumed that we are developing a system for detecting anomalies in credit card transactions. To simplify the example, we will use an adaptive threshold algorithm for anomaly detection. First, we need to preprocess the original transaction data, including removing missing values, standardizing the numerical range, etc. In order to set a dynamic threshold, we need to calculate some statistical indicators, such as the mean and standard deviation over a period of time. Based on these statistical indicators, we can set a threshold, such as adding or subtracting a few standard deviations from the mean as the threshold. For new transaction data, if it exceeds the set threshold, the data point is considered to be abnormal.

[0201] Here is a specific example:

[0202] Suppose our credit card transaction dataset looks like this:

[0203] The amount of each transaction;

[0204] Transaction timestamp;

[0205] Other related attributes;

[0206] We select the transaction data in the past 24 hours as the statistical window. Calculate the average value: μ = average transaction amount μ = average transaction amount; calculate the standard deviation: σ = standard deviation of the transaction amount.

[0207] Furthermore, the threshold is set to μ±3σ, that is, the mean plus or minus 3 times the standard deviation. For each new transaction data, check whether its amount exceeds the threshold.

[0208] By using an adaptive threshold algorithm, we successfully detected abnormal transaction data. This simple anomaly detection method can be effectively applied to real-time transaction data streams to help detect potential fraud in a timely manner.

[0209] Figure 2 A schematic diagram of a retail data processing device is provided for an embodiment of the present application. Figure 2 As shown, the device comprises:

[0210] An acquisition module 21, used to acquire a real-time transaction data stream, wherein the real-time transaction data stream includes sales records, user behavior information and market trend data;

[0211] A determination module 22, for preprocessing the real-time transaction data stream, and determining predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors, and market trend influencing factors based on the preprocessed real-time transaction data;

[0212] A calculation module 23, configured to calculate an inventory demand index based at least on the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor;

[0213] The adjustment module 24 is used to dynamically adjust the inventory management strategy according to the inventory demand index.

[0214] Figure 2 The retail data processing device can execute Figure 1 The implementation principle and technical effect of the retail data processing method described in the embodiment are not described in detail. The specific way in which each module and unit performs operations in the retail data processing device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0215] In one possible design, Figure 2 The retail data processing apparatus of the illustrated embodiment may be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0216] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0217] The processing component 32 is used to: obtain a real-time transaction data stream, wherein the real-time transaction data stream includes sales records, user behavior information and market trend data; pre-process the real-time transaction data stream, and determine predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors and market trend influencing factors based on the pre-processed real-time transaction data; calculate an inventory demand index based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factors, the consumer response prediction factors and the market trend influencing factors; and dynamically adjust the inventory management strategy based on the inventory demand index.

[0218] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0219] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0220] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0221] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0222] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0223] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0224] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The retail data processing method of the illustrated embodiment.

[0225] 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.

[0226] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0227] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0228] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A retail data processing method, characterized in that: include: Acquire a real-time transaction data stream, wherein the real-time transaction data stream includes sales records, user behavior information, and market trend data; Preprocessing the real-time transaction data stream, and determining predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors, and market trend influencing factors based on the preprocessed real-time transaction data; Calculating an inventory demand index based at least on the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor; Dynamically adjust inventory management strategies according to the inventory demand index; The calculating of the inventory demand index based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor comprises: By formula: ; Calculate the inventory demand index; in, It represents the inventory demand index, which is a quantitative indicator of current inventory demand; is the current inventory; represents the predicted sales volume; is a constant used to adjust the weight of the ratio of current inventory to forecast sales; Indicates seasonal fluctuations, is a constant used to adjust the impact of seasonal fluctuations on inventory demand; Indicates a point in time; Indicates seasonal cycles; represents the supply chain risk factor, is a constant used to quantify the impact of supply chain risk factors on inventory demand; represents the consumer response predictor; is a constant used to quantify the degree of influence of consumer response predictors on inventory demand; Indicates the market trend influencing factor; is a constant used to quantify the impact of market trend factors on inventory demand; in, Indicates the degree of volatility in forecasted sales and the impact of supply chain delays on inventory demand; Indicates the degree of volatility of the forecasted sales volume; It represents the average level of predicted sales volume; represents delayed sales, which is the amount of sales reduced due to supply chain delays; is a constant used to adjust the impact of delayed sales on inventory demand; is a constant used to adjust the rate of change of delayed sales over time; Indicates the starting time point; The calculation formula of the supply chain risk factor is: ; in, represents the supply chain risk factor; represents the impact of supply chain delays on supply chain risk factors, Indicates delayed sales volume; stands for delay cost, which refers to the additional cost caused by supply chain delays; is a constant used to adjust the impact of supply chain delay on supply chain risk factors; is the time variable; The delayed time point refers to the time point of supply chain delay; in, It represents the impact of delay time in the supply chain on the supply chain risk factors, is a constant used to adjust the impact of supply chain delay on supply chain risk factors; It represents the delay time, which is the time interval from one event to another in the supply chain; in, It means that the risk distribution of a specific area in the supply chain is considered through the sine series. is a specific length, indicating the length of a specific area; is a position variable, which refers to the position along a specific length The location coordinates of is the number of series items used to calculate the number of terms in the sine series of ; is the coefficient used to adjust the weight of each term in the sine series; The calculation formula of the consumer response prediction factor is: ; in, represents the consumer response predictor, which is used to assess the degree of consumer response to the product; Represents the combined effect of different consumer groups’ responses to the product, is the number of consumer groups; For the The response rate of a consumer group, that is, the intensity of the consumer group's response to the product; For the The response speed of the consumer group, that is, The speed of each consumer group; is the time variable; For the The response time of each consumer group; For the The weight of the consumer group, i.e. the extent to which individual consumer groups contribute to the predictors of overall consumer response; is a constant used to adjust the degree of influence of consumer group response on the consumer response predictor; in, represents the effect of product position or attribute variables on the predictors of consumer response, is a position variable, which refers to the product position or attribute variable; for The mean of , which indicates the average level of product position or variable attribute; for The standard deviation of , which indicates the degree of variation in product position or variable attributes; is a constant used to adjust the effect of changes in product location or variable attributes in the consumer response predictor; The calculation formula of the market trend impact factor is: ; in, Indicates the market trend impact factor, which is used to evaluate the impact of market trends on product demand; It indicates the comprehensive effect of different market trend indicators on market trend influencing factors; is the number of market trend indicators; For the The weight of the market trend indicator, indicating the The degree of influence of each market trend indicator on the market trend influencing factors; For the Market trend indicators at a point in time The value of No. The value of a market trend indicator; Indicates Market trend indicators in The value at time No. The value of the market trend indicator, where Indicates time difference; is an empirical constant used to adjust the degree of influence of market trend indicators on market trend influencing factors; in, Indicates the distribution of market trends in a specific area. is a specific length, indicating the length of a specific area; is the position variable; is the number of sine series terms used to calculate the number of terms in the sine series of ; is a coefficient used to adjust the weights of each term in the sine series.

2. The method according to claim 1, characterized in that Also includes: Anomaly detection is performed on the preprocessed real-time transaction data to generate anomaly detection results.

3. The method according to claim 2, characterized in that The method of performing anomaly detection on the pre-processed real-time transaction data comprises: An anomaly detection is performed on the pre-processed real-time transaction data using an adaptive threshold algorithm; or, an anomaly detection mechanism is used to perform an anomaly detection on the pre-processed real-time transaction data.

4. A retail data processing device, characterized in that: include: An acquisition module, used to acquire real-time transaction data streams, wherein the real-time transaction data streams include sales records, user behavior information, and market trend data; A determination module, configured to preprocess the real-time transaction data stream and determine predicted sales volume, seasonal fluctuations, supply chain risk factors, consumer response prediction factors, and market trend influencing factors based on the preprocessed real-time transaction data; A calculation module, configured to calculate an inventory demand index based at least on the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor; An adjustment module, used to dynamically adjust the inventory management strategy according to the inventory demand index; The calculating of the inventory demand index based on at least the predicted sales volume, seasonal fluctuations, the supply chain risk factor, the consumer response prediction factor, and the market trend influencing factor comprises: By formula: ; Calculate the inventory demand index; in, It represents the inventory demand index, which is a quantitative indicator of current inventory demand; is the current inventory; represents the predicted sales volume; is a constant used to adjust the weight of the ratio of current inventory to forecast sales; Indicates seasonal fluctuations, is a constant used to adjust the impact of seasonal fluctuations on inventory demand; Indicates a point in time; Indicates seasonal cycles; represents the supply chain risk factor, is a constant used to quantify the impact of supply chain risk factors on inventory demand; represents the consumer response predictor; is a constant used to quantify the degree of influence of consumer response predictors on inventory demand; Indicates the market trend influencing factor; is a constant used to quantify the impact of market trend factors on inventory demand; in, Indicates the degree of volatility in forecasted sales and the impact of supply chain delays on inventory demand; Indicates the degree of volatility of the forecasted sales volume; It represents the average level of predicted sales volume; represents delayed sales, which is the amount of sales reduced due to supply chain delays; is a constant used to adjust the impact of delayed sales on inventory demand; is a constant used to adjust the rate of change of delayed sales over time; Indicates the starting time point; The calculation formula of the supply chain risk factor is: ; in, represents the supply chain risk factor; represents the impact of supply chain delays on supply chain risk factors, Indicates delayed sales volume; stands for delay cost, which refers to the additional cost caused by supply chain delays; is a constant used to adjust the impact of supply chain delay on supply chain risk factors; is the time variable; The delayed time point refers to the time point of supply chain delay; in, It represents the impact of delay time in the supply chain on the supply chain risk factors, is a constant used to adjust the impact of supply chain delay on supply chain risk factors; It represents the delay time, which is the time interval from one event to another in the supply chain; in, It means that the risk distribution of a specific area in the supply chain is considered through the sine series. is a specific length, indicating the length of a specific area; is a position variable, which refers to the position along a specific length The location coordinates of is the number of series items used to calculate the number of terms in the sine series of ; is the coefficient used to adjust the weight of each term in the sine series; The calculation formula of the consumer response prediction factor is: ; in, represents the consumer response predictor, which is used to assess the degree of consumer response to the product; Represents the combined effect of different consumer groups’ responses to the product, is the number of consumer groups; For the The response rate of a consumer group, that is, the intensity of the consumer group's response to the product; For the The response speed of the consumer group, that is, The speed of each consumer group; is the time variable; For the The response time of each consumer group; For the The weight of the consumer group, i.e. the extent to which individual consumer groups contribute to the predictors of overall consumer response; is a constant used to adjust the degree of influence of consumer group response on the consumer response predictor; in, represents the effect of product position or attribute variables on the predictors of consumer response, is a position variable, which refers to the product position or attribute variable; for The mean of , which indicates the average level of product position or variable attribute; for The standard deviation of , which indicates the degree of variation in product position or variable attributes; is a constant used to adjust the effect of changes in product location or variable attributes in the consumer response predictor; The calculation formula of the market trend impact factor is: ; in, Indicates the market trend impact factor, which is used to evaluate the impact of market trends on product demand; It indicates the comprehensive effect of different market trend indicators on market trend influencing factors; is the number of market trend indicators; For the The weight of the market trend indicator, indicating the The degree of influence of each market trend indicator on the market trend influencing factors; For the Market trend indicators at a point in time The value of No. The value of a market trend indicator; Indicates Market trend indicators in The value at time No. The value of the market trend indicator, where Indicates time difference; is an empirical constant used to adjust the degree of influence of market trend indicators on market trend influencing factors; in, Indicates the distribution of market trends in a specific area. is a specific length, indicating the length of a specific area; is the position variable; is the number of sine series terms used to calculate the number of terms in the sine series of ; is a coefficient used to adjust the weights of each term in the sine series.

5. A computing device, characterized in that: It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a retail data processing method as described in any one of claims 1 to 3.

6. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a retail data processing method as claimed in any one of claims 1 to 3 is implemented.