Online monitoring method and system for hot commodities

Abstract

The invention discloses an online monitoring method and system for hot-sell commodities, and relates to the technical field of e-commerce, and the method comprises the steps: collecting consumer behavior data, and carrying out the preprocessing of the data, and forming a consumer behavior data set; based on the consumer behavior data set, constructing a consumer behavior popularity model, and obtaining a popularity score of the commodity; performing geographic position analysis on the sales data of the potential hot commodities through a geographic information technology, generating a regional commodity sales thermodynamic diagram, and identifying and marking regional hot commodities; linking the identified regional hot-sell commodities with a supply chain management system, obtaining commodity inventory data, and calculating an inventory consumption rate and inventory depletion time; according to a calculation result, triggering inventory early warning and generating replenishment suggestions, and automatically adjusting inventory management; a regional commodity sales thermodynamic diagram is generated in combination with a geographic information technology, and spatial autocorrelation analysis is performed by using a Moran index, so that the capability of linkage of an enterprise internal supply chain management system is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to an online monitoring method and system for hot-selling commodities. Background Art

[0002] In the development of e-commerce and retail industries, the collection and analysis of consumer behavior data has gradually become a key means to optimize supply chain management and improve sales efficiency. With the advancement of big data technology and machine learning algorithms, more and more companies are beginning to use these technologies to predict commodity demand trends in order to achieve more accurate commodity management and inventory control. However, most existing solutions focus on static data analysis and fail to fully consider the impact of dynamic changes in consumer behavior on commodity popularity, as well as the regional differences in commodity sales patterns caused by geographical factors.

[0003] The shortcomings of existing technologies are mainly reflected in two aspects: first, there is a lack of capturing the dynamic characteristics of consumer behavior, that is, there is no adjustment of weights according to time changes, ignoring the importance of user behavior evolving over time; second, traditional methods rarely combine geographic information systems (GIS) for spatial autocorrelation analysis, and cannot accurately identify regional hot-selling products, which limits the company's ability to fine-tune operations in different market areas. Therefore, the current technical solutions are difficult to provide product popularity assessments and replenishment recommendations that are both timely and regionally targeted. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an online monitoring method for hot-selling commodities to solve the problem that the prior art fails to fully reflect the dynamic changes in consumer behavior and the influence of geographical factors.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides an online monitoring method for hot-selling commodities, which comprises: Collect consumer behavior data and pre-process it to form a consumer behavior data set; Based on the consumer behavior dataset, a consumer behavior heat model is constructed to obtain the heat score of the product; Identify potential hot-selling products based on their popularity scores; Use geographic information technology to analyze the geographic location of sales data of potential hot-selling products, generate regional product sales heat maps, and identify and mark regional hot-selling products; Link the identified regional hot-selling products with the supply chain management system to obtain product inventory data and calculate inventory consumption rate and inventory depletion time; Based on the calculation results, inventory warnings are triggered and replenishment suggestions are generated to automatically adjust inventory management.

[0007] As a preferred solution of the online monitoring method of the hot-selling products described in the present invention, the consumer behavior data includes browsing history, number of clicks, add-to-cart behavior, purchase frequency, evaluation and feedback; and the preprocessing includes deep cleaning and standardization processing.

[0008] As a preferred solution of the online monitoring method for hot-selling products of the present invention, the following steps are included: constructing a consumer behavior heat model based on a consumer behavior data set to obtain a heat score of a product: Based on the different degrees of influence of consumer behavior on product popularity, the weight distribution is dynamically adjusted, and the expression is: ; in, Indicates Consumer-specific behaviors over time The dynamic weight of Indicates The importance coefficient of a specific consumer behavior, Indicates The importance coefficient of the consumer behavior type, represents the consumer specific behavior index, represents the consumer behavior type index, Indicates time; Based on the influence of mutual influence between users on the popularity of commodities, a correction factor is introduced to correct the influence of social networks. The expression is: ; in, Display products The social network influence correction factor, represents the social influence strength parameter, represents the user identifier, Display and products Related user collections, Indicates user PageRank scores in social networks; Based on the adjusted weights and social network influence correction factors, a consumer behavior heat model is constructed to obtain the heat score of the product, which is expressed as: ; in, Display products The final heat score of A balance parameter that indicates the importance of the control behavior indicator, represents the total number of consumer-specific behaviors, represents the time decay rate, Indicates that from The first The time difference between the occurrence of a specific consumer behavior and the present. Indicates The first The number of consumer-specific behaviors, represents the equilibrium parameter affecting the social network, Display products The activation function of the nonlinear feature representation.

[0009] As a preferred solution of the online monitoring method for hot-selling products of the present invention, the following steps are included in the process of identifying potential hot-selling products according to the popularity scores of the products: Set the heat threshold according to the heat distribution in the historical data, and sort the heat scores from high to low to form a preliminary candidate list; Conduct multi-stage screening for each candidate product in the preliminary candidate list; Preliminarily screen out a set of candidate products whose popularity scores are higher than the popularity threshold, and perform secondary screening in the product set based on sales growth rate; The potential hot-selling products after the secondary screening are finally screened in combination with seasonality and promotional activities to finally obtain potential hot-selling products.

[0010] As a preferred solution of the online monitoring method of hot-selling products of the present invention, the sales data of potential hot-selling products are analyzed by geographic information technology to generate a regional product sales heat map, and the identification and marking of regional hot-selling products includes the following steps: Extract sales data for each item from potential hot-selling items and associate it with geographic location information; Construct a spatial weight matrix to assess the correlation and impact between different regions; Generate regional sales heat maps based on spatial weight matrix and extracted sales data using geographic information system tools; The Moran index is used to perform spatial autocorrelation analysis on the regional sales heat map to measure the similarity between the observed value and its neighbors. The expression is: ; in, represents the Moran index, represents the total number of geographic regions participating in the analysis, represents the sum of all non-zero elements in the spatial weight matrix, Indicates Regions and The elements of the regional spatial weight matrix, Indicates Sales volume in each region, Indicates Sales volume in each region, represents the average sales volume of all regions, and Indicates the index variable for traversing all regions; Based on the results of spatial autocorrelation analysis, commodities showing strong spatial clustering characteristics are automatically identified and marked as regional hot-selling commodities.

[0011] As a preferred solution of the online monitoring method for hot-selling products of the present invention, the following steps are included: linking the identified regional hot-selling products with the supply chain management system, obtaining product inventory data, and calculating the inventory consumption rate and inventory depletion time. Get the latest inventory data of goods from the supply chain management platform; Based on the generated regional sales heat map and Moran index analysis results, the inventory consumption rate of each product is calculated as follows: ; in, Indicates The average daily inventory consumption rate of products, Indicates Products at time The inventory volume, Indicates Products at time The inventory volume, Indicates the length of the past time window for calculating the consumption rate; Using the inventory consumption rate of each product, determine the time when the inventory is exhausted. The expression is: ; in, Indicates The time required for the inventory of a product to be completely depleted.

[0012] As a preferred solution of the online monitoring method for hot-selling products of the present invention, wherein: according to the calculation results, triggering inventory warning and generating replenishment suggestions, automatically adjusting inventory management includes the following steps: Set safety stock levels for each product and replenishment lead time ,when < When the inventory is triggered, the inventory warning is triggered; Generate replenishment suggestions based on the products that trigger the warning. The expression is: ; in, Indicates The number of stocks that need to be replenished for each product. represents the demand volatility parameter; Based on the generated replenishment suggestions, order requests are automatically sent to suppliers and internal inventory records are updated simultaneously.

[0013] In a second aspect, the present invention provides an online monitoring system for hot-selling commodities, comprising: The data collection module collects consumer behavior data and performs preprocessing to form a consumer behavior data set; The heat modeling module builds a consumer behavior heat model based on the consumer behavior data set to obtain the heat score of the product; Hot-selling identification module, which identifies potential hot-selling products based on their popularity scores; The geographic analysis module uses geographic information technology to analyze the sales data of potential hot-selling products, generate regional product sales heat maps, and identify and mark regional hot-selling products; The inventory management module links the identified regional hot-selling products with the supply chain management system to obtain product inventory data and calculate the inventory consumption rate and inventory depletion time; The early warning replenishment module triggers inventory warnings and generates replenishment suggestions based on calculation results, automatically adjusting inventory management.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the online monitoring method for hot-selling products as described in the first aspect of the present invention is implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the online monitoring method for hot-selling products as described in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are as follows: by introducing a dynamic weight allocation mechanism and a social network influence correction factor, a consumer behavior heat model that can respond to changes in consumer behavior in real time is constructed, thereby achieving a more accurate quantitative evaluation of commodity heat; combining geographic information technology to generate a regional commodity sales heat map, and using the Moran index to perform spatial autocorrelation analysis, effectively improving the ability to link the internal supply chain management system of the enterprise; based on the inventory early warning system triggered by the calculation results and the automated replenishment suggestion generation process, the efficiency and accuracy of inventory management are ensured, the risk of out-of-stock is reduced, and customer satisfaction and the market competitiveness of the enterprise are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 This is a flow chart of the online monitoring method for hot-selling products in Example 1.

[0019] Figure 2 This is a module diagram of the online monitoring system for hot-selling products in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an online monitoring method for hot-selling products, comprising the following steps: S1. Collect consumer behavior data and preprocess it to form a consumer behavior data set.

[0024] S1.1. Consumer behavior data includes browsing history, number of clicks, add-to-cart behavior, purchase frequency, evaluation and feedback; preprocessing includes deep cleaning and standardization.

[0025] Specifically, deep cleaning refers to the use of a hybrid cleaning method based on rules and machine learning to clean consumer behavior data, including: For structured fields, regular expressions are used to match the correct pattern. For unstructured text content, natural language processing technology is applied to clean up noise words and extract key information. To address the problem of duplicate item detection, the MinHash algorithm is used to calculate document similarity, and a similarity threshold is set based on different types of consumer behavior data. When the hash values ​​of two items are lower than the similarity threshold, they are considered to be duplicate records and are deleted.

[0026] Standardization refers to making data from different sources have the same representation. This involves a series of operations such as date / time format unification, geo-coding, currency symbol conversion, etc. In particular, for ratings and comments, they can be quantified into numerical indicators through sentiment analysis models.

[0027] S2. Based on the consumer behavior dataset, a consumer behavior heat model is constructed to obtain the heat score of the product.

[0028] S2.1 Dynamically adjust the weight distribution based on the different degrees of influence of consumer behavior on product popularity. The expression is: ; in, Indicates Consumer-specific behaviors over time The dynamic weight of different behaviors is the proportion of their occurrence time and importance when calculating the popularity score of the product. Indicates The importance coefficient of a specific consumer behavior, Indicates The importance coefficient of the consumer behavior type, represents the consumer specific behavior index, represents the consumer behavior type index, Indicates time.

[0029] S2.2. Based on the influence of mutual influence between users on the popularity of commodities, a correction factor is introduced to correct the influence of social networks. The expression is: ; in, Display products The social network influence correction factor, represents the social influence strength parameter, represents the user identifier, Display and products Related user collections, Indicates user PageRank scores in social networks.

[0030] Specifically, the expression of PageRank score is: ; in, Display products PageRank score, represents the damping coefficient, Display and products The associated user collection, Indicates The number of products associated with a specific consumer behavior. Indicates A basic influence score for a specific consumer behavior.

[0031] It should be noted that the PageRank score not only takes into account the user's direct behavior (such as comments, sharing, etc.), but also takes into account the user's indirect influence in the entire social network, thereby more comprehensively reflecting the user's impact on the popularity of the product.

[0032] S2.3. Based on the adjusted weights and social network influence correction factors, a consumer behavior heat model is constructed to obtain the heat score of the product, which is expressed as: ; in, Display products The final heat score of A balance parameter that indicates the importance of the control behavior indicator, represents the total number of consumer-specific behaviors, represents the time decay rate, Indicates that from The first The time difference between a specific consumer behavior and the present reflects the freshness of the behavior. The newer the behavior, the greater the impact on popularity. Indicates The first The number of consumer-specific behaviors, represents the equilibrium parameter affecting the social network, Display products The activation function of the nonlinear feature representation.

[0033] S3. Identify potential hot-selling products based on the popularity scores of the products.

[0034] S3.1. Set a heat threshold according to the heat distribution in the historical data, and sort the heat scores from high to low to form a preliminary candidate list; perform multi-stage screening on each candidate product in the preliminary candidate list; preliminarily screen out a set of candidate products whose heat scores are higher than the heat threshold, and perform secondary screening in the product set based on the sales growth rate.

[0035] Specifically, the expression of sales growth rate is: ; in, Indicates The sales growth rate of a product, Indicates Products at the time of sales, Indicates Products at the time of sales, Indicates the length of the time window.

[0036] Based on historical sales data, a sales growth rate threshold is set, and the calculated sales growth rate is compared with the growth rate threshold. Products with a sales growth rate higher than the threshold are marked as potential hot-selling products after secondary screening.

[0037] S3.2. Perform a final screening on the potential hot-selling products after the secondary screening in combination with seasonality and promotional activities, and finally obtain the potential hot-selling products.

[0038] Collect sales records from the same time period in the past few years and sort them according to the attributes of the goods (such as clothing, food, electronic products, etc.); use time series analysis tools (such as STL decomposition, ARIMA model) to decompose sales data into trend components, seasonal components and random components to identify obvious seasonal patterns; establish a multivariate regression model, using sales volume as the dependent variable and time and climate variables as independent variables to evaluate the impact of different factors on sales; cluster goods according to the similarity of sales patterns to find categories of goods with similar seasonal characteristics; Obtain detailed promotion plans for historical market activities from the marketing department, including discount strength, promotion type (such as discount for purchases above a certain amount, buy one get one free), promotion duration, promotion scope, etc.; refer to the effectiveness evaluation reports of previous promotion activities to understand the specific impact of different types of promotions on sales; By analyzing historical sales data and historical market activity information, seasonal sales and promotional activities are obtained; the potential hot-selling products after the secondary screening are finally screened in combination with seasonality and promotional activities, and seasonal factors and promotional factors are introduced to adjust the popularity scores of products that are significantly affected by seasonality or promotions. The expression is: ; in, represents the adjusted heat score, represents the seasonal factor, Represents the promotion factor.

[0039] The adjusted popularity score is compared with the popularity threshold, and the potential hot-selling products after secondary screening that are higher than the popularity threshold are the final potential hot-selling products.

[0040] S4. Use geographic information technology to conduct geographic location analysis on the sales data of potential hot-selling products, generate regional product sales heat maps, and identify and mark regional hot-selling products.

[0041] S4.1. Extract the sales data of each product in each region from the potential hot-selling products, including product ID, sales date, sales quantity, sales amount and geographical location information; associate it with the geographical location information, that is, match the geographical location information in the sales data with the pre-prepared geographical area division table (such as province, city, district and county level) to ensure that each sales record can correspond to a specific geographical area; construct a spatial weight matrix based on the spatial adjacency relationship of geographical areas to evaluate the correlation and influence between different regions. If two regions are geographically adjacent, their corresponding element values ​​in the matrix are larger; conversely, if the distance is far, the corresponding element value is smaller; use geographic information system tools to generate a regional sales heat map based on the spatial weight matrix and the extracted sales data; apply the Moran index to perform spatial autocorrelation analysis on the regional sales heat map to measure the similarity between the observed value and its neighbors. The expression is: ; in, represents the Moran index, represents the total number of geographic regions participating in the analysis, Represents the sum of all non-zero elements in the spatial weight matrix, which is used to standardize the calculation of the Moran index. Indicates Regions and The elements of the regional spatial weight matrix, Indicates Sales volume in each region, Indicates Sales volume in each region, represents the average sales volume of all regions, and Indicates the index variable for traversing all regions; Based on the results of spatial autocorrelation analysis, commodities showing strong spatial clustering characteristics are automatically identified and marked as regional hot-selling commodities.

[0042] Specifically, the Moran index It indicates whether there is a certain pattern of correlation between all regions in the entire study area. The value range is usually between -1 and +1. Specifically: when >0, indicating positive spatial autocorrelation, that is, high values ​​(sales in a certain geographic area are higher than the average sales of all regions, which is considered a sales hotspot, i.e., a place where commodity sales are particularly strong) and low values ​​(sales in a certain geographic area are lower than the average sales of all regions, which is a sales cold spot, i.e., a place where commodity sales are relatively weak) tend to cluster together.

[0043] when <0, it indicates negative spatial autocorrelation, that is, high and low values ​​tend to be dispersed.

[0044] when =0, which means there is no obvious spatial autocorrelation and the distribution of data points may be random.

[0045] S5. Link the identified regional hot-selling products with the supply chain management system to obtain product inventory data and calculate the inventory consumption rate and inventory depletion time.

[0046] S5.1. Obtain the latest inventory data of the goods from the supply chain management platform; based on the generated regional sales heat map and Moran index analysis results, understand the sales patterns and spatial dependencies of different regions, and calculate the inventory consumption rate of each product, expressed as: ; in, Indicates The average daily inventory consumption rate of products, Indicates Products at the time The inventory volume, Indicates Products at the time The inventory volume, Indicates the length of the past time window over which the consumption rate is calculated.

[0047] It should be noted that by introducing spatial effect adjustment, the calculation of inventory consumption rate is more in line with actual sales conditions, thereby improving the prediction accuracy.

[0048] S5.2. Using the inventory consumption rate of each commodity, determine the time when the inventory is exhausted. The expression is: ; in, Indicates The time required for the inventory of a product to be completely depleted.

[0049] It should be noted that by calculating the time it takes for inventory to run out, companies can predict in advance when they need to replenish inventory, avoid sales losses due to insufficient inventory, and help rationally arrange warehousing and logistics resources, reduce operating costs, and improve supply chain efficiency.

[0050] S6. Based on the calculation results, trigger inventory warnings and generate replenishment suggestions to automatically adjust inventory management.

[0051] Set safety stock levels for each product and replenishment lead time ,when < When , the inventory warning is triggered; based on the product that triggered the warning, a replenishment suggestion is generated, the expression is: ; in, Indicates The number of stocks that need to be replenished for each product. represents the demand volatility parameter; Based on the generated replenishment suggestions, order requests are automatically sent to suppliers and internal inventory records are updated simultaneously.

[0052] It should be noted that setting personalized safety stock and replenishment lead time according to the characteristics of different commodities and market demand improves the flexibility and responsiveness of inventory management, effectively reduces the risk of out-of-stocks, and ensures the continuous supply of hot-selling commodities.

[0053] This embodiment also provides an online monitoring system for hot-selling products, including: The data collection module collects consumer behavior data and performs preprocessing to form a consumer behavior data set; The heat modeling module builds a consumer behavior heat model based on the consumer behavior data set to obtain the heat score of the product; Hot-selling identification module, which identifies potential hot-selling products based on their popularity scores; The geographic analysis module uses geographic information technology to analyze the sales data of potential hot-selling products, generate regional product sales heat maps, and identify and mark regional hot-selling products; The inventory management module links the identified regional hot-selling products with the supply chain management system to obtain product inventory data and calculate the inventory consumption rate and inventory depletion time; The early warning replenishment module triggers inventory warnings and generates replenishment suggestions based on calculation results, automatically adjusting inventory management.

[0054] This embodiment also provides a computer device, which is suitable for the online monitoring method of hot-selling goods, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the online monitoring method of hot-selling goods proposed in the above embodiment.

[0055] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0056] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the online monitoring method for hot-selling products proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0057] In summary, the present invention constructs a consumer behavior heat model that can respond to changes in consumer behavior in real time by introducing a dynamic weight allocation mechanism and a social network influence correction factor, thereby achieving a more accurate quantitative evaluation of commodity heat. It combines geographic information technology to generate a regional commodity sales heat map, and uses the Moran index to perform spatial autocorrelation analysis, effectively improving the ability to link the internal supply chain management system of the enterprise. The inventory early warning system triggered by the calculation results and the automated replenishment suggestion generation process ensure the efficiency and accuracy of inventory management, reduce the risk of out-of-stock, and improve customer satisfaction and the market competitiveness of the enterprise.

[0058] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An online monitoring method for hot-selling products, characterized in that: include, Collect consumer behavior data and pre-process it to form a consumer behavior data set; Based on the consumer behavior dataset, a consumer behavior heat model is constructed to obtain the heat score of the product; Identify potential hot-selling products based on their popularity scores; Use geographic information technology to analyze the geographic location of sales data of potential hot-selling products, generate regional product sales heat maps, and identify and mark regional hot-selling products; Link the identified regional hot-selling products with the supply chain management system to obtain product inventory data and calculate inventory consumption rate and inventory depletion time; Based on the calculation results, inventory warnings are triggered and replenishment suggestions are generated to automatically adjust inventory management.

2. The online monitoring method for hot-selling products according to claim 1, characterized in that: The consumer behavior data includes browsing history, number of clicks, add-to-cart behavior, purchase frequency, evaluation and feedback; the preprocessing includes deep cleaning and standardization processing.

3. The online monitoring method for hot-selling products according to claim 2, characterized in that: Based on the consumer behavior dataset, building a consumer behavior heat model and obtaining the heat score of the product includes the following steps: Based on the different degrees of influence of consumer behavior on product popularity, the weight distribution is dynamically adjusted, and the expression is: ； in, Indicates Consumer-specific behaviors over time The dynamic weight of Indicates The importance coefficient of a specific consumer behavior, Indicates The importance coefficient of the consumer behavior type, represents the consumer specific behavior index, represents the consumer behavior type index, Indicates time; Based on the influence of mutual influence between users on the popularity of commodities, a correction factor is introduced to correct the influence of social networks. The expression is: ； in, Display products The social network influence correction factor, represents the social influence strength parameter, represents the user identifier, Display and products Related user collections, Indicates user PageRank scores in social networks; Based on the adjusted weights and social network influence correction factors, a consumer behavior heat model is constructed to obtain the heat score of the product, which is expressed as: ； in, Display products The final heat score of A balance parameter that indicates the importance of the control behavior indicator, represents the total number of consumer-specific behaviors, represents the time decay rate, Indicates that from The first The time difference between the occurrence of a specific consumer behavior and the present. Indicates The first The number of consumer-specific behaviors, represents the equilibrium parameter affecting the social network, Display products The activation function of the nonlinear feature representation.

4. The online monitoring method for hot-selling products according to claim 3, characterized in that: According to the popularity score of the product, identifying potential hot-selling products includes the following steps: Set the heat threshold according to the heat distribution in the historical data, and sort the heat scores from high to low to form a preliminary candidate list; Conduct multi-stage screening for each candidate product in the preliminary candidate list; Preliminarily screen out a set of candidate products whose popularity scores are higher than the popularity threshold, and perform secondary screening in the product set based on sales growth rate; The potential hot-selling products after the secondary screening are finally screened in combination with seasonality and promotional activities to finally obtain potential hot-selling products.

5. The online monitoring method for hot-selling products according to claim 4, characterized in that: The sales data of potential hot-selling products are analyzed by geographic information technology to generate a regional product sales heat map. The identification and marking of regional hot-selling products include the following steps: Extract sales data for each item from potential hot-selling items and associate it with geographic location information; Construct a spatial weight matrix to assess the correlation and impact between different regions; Generate regional sales heat maps based on spatial weight matrix and extracted sales data using geographic information system tools; The Moran index is used to perform spatial autocorrelation analysis on the regional sales heat map to measure the similarity between the observed value and its neighbors. The expression is: ； in, represents the Moran index, represents the total number of geographic regions participating in the analysis, represents the sum of all non-zero elements in the spatial weight matrix, Indicates Regions and The elements of the regional spatial weight matrix, Indicates Sales volume in each region, Indicates Sales volume in each region, represents the average sales volume of all regions, and Indicates the index variable for traversing all regions; Based on the results of spatial autocorrelation analysis, commodities showing strong spatial clustering characteristics are automatically identified and marked as regional hot-selling commodities.

6. The online monitoring method for hot-selling products according to claim 5, characterized in that: Linking the identified regional hot-selling products with the supply chain management system to obtain product inventory data and calculate the inventory consumption rate and inventory depletion time includes the following steps: Get the latest inventory data of goods from the supply chain management platform; Based on the generated regional sales heat map and Moran index analysis results, the inventory consumption rate of each product is calculated as follows: ； in, Indicates The average daily inventory consumption rate of products, Indicates Products at time The inventory volume, Indicates Products at time The inventory volume, Indicates the length of the past time window for calculating the consumption rate; Using the inventory consumption rate of each product, determine the time when the inventory is exhausted. The expression is: ； in, Indicates The time required for the inventory of a product to be completely depleted.

7. The online monitoring method for hot-selling products according to claim 6, characterized in that: According to the calculation results, the inventory warning is triggered and replenishment suggestions are generated. The automatic adjustment of inventory management includes the following steps: Set safety stock levels for each product and replenishment lead time ,when < When the inventory is triggered, the inventory warning is triggered; Generate replenishment suggestions based on the products that trigger the warning. The expression is: ； in, Indicates The number of stocks that need to be replenished for each product. represents the demand volatility parameter; Based on the generated replenishment suggestions, order requests are automatically sent to suppliers and internal inventory records are updated at the same time.

8. An online monitoring system for hot-selling products, based on the online monitoring method for hot-selling products according to any one of claims 1 to 7, characterized in that: include, The data collection module collects consumer behavior data and performs preprocessing to form a consumer behavior data set; The heat modeling module builds a consumer behavior heat model based on the consumer behavior data set to obtain the heat score of the product; Hot-selling identification module, which identifies potential hot-selling products based on their popularity scores; The geographic analysis module uses geographic information technology to analyze the sales data of potential hot-selling products, generate regional product sales heat maps, and identify and mark regional hot-selling products; The inventory management module links the identified regional hot-selling products with the supply chain management system to obtain product inventory data and calculate the inventory consumption rate and inventory depletion time; The early warning replenishment module triggers inventory warnings and generates replenishment suggestions based on calculation results, automatically adjusting inventory management.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the online monitoring method for hot-selling products described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the online monitoring method for hot-selling products described in any one of claims 1 to 7 are implemented.

Images