Abnormal sales commodity analysis method and system based on user order data

Abstract

The invention is suitable for the technical field of offline store user order management, and provides an abnormal sales commodity analysis method and system based on user order data, and the method comprises the steps: analyzing whether an abnormal sales commodity exists or not according to the user order data of a target online store and a target offline store; and if it is determined that the abnormal sales commodity exists, obtaining in-store video data of the target offline store. When the sales performance of some commodities in offline shops is obviously better than that of online shops, the potential reasons causing the sales abnormality are poor commodity display positions and insufficient promotion, or offline pricing is unreasonable compared with online pricing. The analysis results can also be displayed to offline shop managers in a digital form, so that the offline shop managers can effectively, scientifically and accurately adjust and manage the commodities with abnormal sales.

Description

Technical Field

[0001] The present invention belongs to the technical field of offline store user order management, and in particular relates to a method and system for analyzing abnormal sales of goods based on user order data. Background Art

[0002] With the rapid development of the global economy and technology, both the e-commerce and physical retail industries have experienced significant expansion. The convenience and accessibility of e-commerce have made online shopping the first choice for consumers, while physical retail relies on its instant shopping experience and direct customer service to remain competitive. The different characteristics of these two shopping modes have led to significant differences in sales data between online and offline channels.

[0003] With the different approaches and advantages of the two channels in meeting consumer needs, the difference in sales data between online and offline continues to widen. This difference not only reflects the changes in consumer preferences, but also reveals that market trends and business strategies need to adapt to new consumer behaviors. For retailers and market analysts, a deep understanding and effective management of these differences is the key to optimizing marketing strategies, enhancing customer engagement and improving sales efficiency.

[0004] Although existing technologies can provide basic sales data analysis, there are still many problems in dealing with the difference between online and offline sales. First, traditional methods often lack the ability to associate complex user behaviors with sales data, making it difficult to deeply analyze the specific factors that lead to sales differences. Second, existing technologies are often inefficient in data integration and cannot provide real-time feedback on sales anomalies, resulting in a slow or inaccurate response to market changes. Finally, existing solutions often lack quantitative analysis when providing operational advice to offline store managers, making the decision-making process more subjective and lacking scientific basis. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for analyzing abnormal sales of goods based on user order data, aiming to solve the problems raised in the background technology.

[0006] The present invention is implemented as follows: a method for analyzing abnormal sales of goods based on user order data, the method comprising:

[0007] Analyze whether there are abnormal sales products based on the user order data of the target online store and the target offline store;

[0008] If it is determined that there are abnormal sales products, obtain the in-store video data of the target offline store, and calculate the customer engagement and sales conversion value of the abnormal sales products in the target offline store based on the in-store video data;

[0009] When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than a first preset threshold, generating product exposure optimization suggestion information;

[0010] When it is determined that the customer engagement and sales conversion value of the target offline store's sales abnormal products are not higher than the first preset threshold, the pricing-sales impact of the target offline store on the sales abnormal products is analyzed, and pricing and sales association information related to the sales abnormal products is generated based on the pricing-sales impact.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the step of analyzing whether there are abnormal sales of goods based on the user order data of the target online store and the target offline store includes:

[0012] Obtain user order data of target online stores and target offline stores;

[0013] Filter the user order data of the target online store and the target offline store, and extract user orders with the same products;

[0014] Analyze the number of user orders for the same product corresponding to the target online store and the target offline store. When the difference between the number of user orders for a certain product in the target online store and the number of user orders in the target offline store is greater than the preset reasonable difference, determine that the product is an abnormal sales product.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, if it is determined that there are abnormal sales of goods, the steps of obtaining in-store video data of the target offline store, and calculating the customer engagement and sales conversion value of the abnormal sales of the target offline store according to the in-store video data include:

[0016] When it is determined that there are abnormal sales of goods, obtain in-store video data of the target offline store;

[0017] Intelligently analyze in-store video data and obtain the number of interactions between abnormal sales products and customers;

[0018] Obtain the sales volume of abnormally selling products in the target offline store, and divide the sales volume by the number of interactions to obtain the customer engagement and sales conversion value.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the starting time point of the in-store video data is set to the time when the sales-abnormal product starts to be sold in the target offline store.

[0020] As a further limitation of the technical solution of the embodiment of the present invention, when it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than the first preset threshold, the step of generating product exposure optimization suggestion information includes:

[0021] When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than a first preset threshold, generating sales promotion enhancement suggestion information;

[0022] Obtain images of areas where abnormal sales of goods are located based on in-store video data;

[0023] According to the sales promotion efforts, the recommendation information and the images of the areas where the abnormal sales products are located are strengthened to generate the product exposure optimization recommendation information.

[0024] As a further limitation of the technical solution of the embodiment of the present invention, when it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are not higher than the first preset threshold, the steps of analyzing the pricing-sales influence of the target offline store on the abnormal sales product, and generating pricing and sales association information related to the abnormal sales product according to the pricing-sales influence include:

[0025] When it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are not higher than the first preset threshold, obtaining pricing information of the abnormal sales product of the target online store and the target offline store;

[0026] According to the pricing information of the target online store and the target offline store for the abnormal sales product, obtain the pricing values ​​of the target online store and the target offline store for the abnormal sales product, and obtain the sales quantity of the abnormal sales product in the target online store and the target offline store;

[0027] The pricing-sales impact is calculated according to the pricing-sales impact calculation formula, and pricing and sales association information related to the sales abnormality products is generated based on the pricing-sales impact.

[0028] As a further limitation of the technical solution of the embodiment of the present invention, the pricing-sales impact calculation formula is D=R×ΔQ, where R represents the price difference ratio, ΔQ represents the sales volume difference between the two sales channels, and D is the pricing-sales impact;

[0029] In the pricing-sales impact calculation formula, ΔQ=Q online -Q offline , where P online is the pricing value of the target online store for abnormal sales of goods, P offline is the pricing value of the target offline store for abnormal sales of goods, Q online is the sales volume of abnormal products in the target online store, Q offline It is the sales volume of abnormal sales products in the target offline stores.

[0030] A sales abnormal commodity analysis system based on user order data, the system comprises: a sales abnormal commodity judgment module, a customer participation and sales conversion value calculation module, a commodity exposure optimization suggestion information generation module and a pricing-sales influence calculation module, wherein:

[0031] The abnormal sales commodity judgment module is used to analyze whether there are abnormal sales commodities based on the user order data of the target online store and the target offline store;

[0032] A customer engagement and sales conversion value calculation module is used to obtain in-store video data of a target offline store if it is determined that there are abnormal sales products, and calculate the customer engagement and sales conversion value of the abnormal sales products of the target offline store based on the in-store video data;

[0033] A product exposure optimization suggestion information generation module, configured to generate product exposure optimization suggestion information when it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are higher than a first preset threshold;

[0034] The pricing-sales impact calculation module is used to analyze the pricing-sales impact of the target offline store on the sales abnormal products when it is determined that the customer engagement and sales conversion value of the sales abnormal products of the target offline store are not higher than the first preset threshold, and generate pricing and sales association information related to the sales abnormal products based on the pricing-sales impact.

[0035] As a further limitation of the technical solution of the embodiment of the present invention, the abnormal sales commodity judgment module specifically includes:

[0036] A user order data acquisition unit, used to acquire user order data of a target online store and a target offline store;

[0037] A user order screening unit, used to screen user order data of target online stores and target offline stores, and extract user orders with the same product;

[0038] The abnormal sales commodity determination unit is used to analyze the number of user orders for the same commodity corresponding to the target online store and the target offline store. When the difference between the number of user orders for a certain commodity in the target online store and the number of user orders in the target offline store is greater than a preset reasonable difference, the commodity is determined to be an abnormal sales commodity.

[0039] As a further limitation of the technical solution of the embodiment of the present invention, the customer engagement and sales conversion value calculation module specifically includes:

[0040] An in-store video data acquisition unit, used to acquire in-store video data of a target offline store when it is determined that there are abnormal sales of goods;

[0041] In-store video data analysis unit, used to intelligently analyze in-store video data and obtain the number of interactions between abnormal sales products and customers;

[0042] The customer engagement and sales conversion value calculation unit is used to obtain the sales quantity of the abnormal sales products in the target offline store, and divide the sales quantity by the number of interactions to obtain the customer engagement and sales conversion value.

[0043] Compared with the prior art, the present invention analyzes whether there are abnormal sales products according to the user order data of the target online store and the target offline store; if it is determined that there are abnormal sales products, the in-store video data of the target offline store is obtained, and the customer participation and sales conversion value of the abnormal sales products of the target offline store are calculated according to the in-store video data; when it is determined that the customer participation and sales conversion value of the abnormal sales products of the target offline store are higher than the first preset threshold, the product exposure optimization suggestion information is generated; when it is determined that the customer participation and sales conversion value of the abnormal sales products of the target offline store are not higher than the first preset threshold, the pricing-sales influence of the target offline store on the abnormal sales products is analyzed, and the pricing and sales association information related to the abnormal sales products is generated according to the pricing-sales influence. When the sales performance of some products in the offline store is obviously not as good as that of the online store, it can intelligently analyze whether the potential cause of the abnormal sales is the poor display position of the product, insufficient promotion, or the unreasonable offline pricing compared with the online. These analysis results can also be displayed to offline store managers in a digital form, so that they can effectively make scientific and accurate adjustments and management for these abnormal sales products. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0045] Figure 2 A flow chart of determining whether there are abnormal sales of goods in the method provided in an embodiment of the present invention;

[0046] Figure 3 A flow chart of calculating customer engagement and sales conversion value in the method provided in an embodiment of the present invention;

[0047] Figure 4 A flow chart of generating product exposure optimization suggestion information in the method provided in an embodiment of the present invention;

[0048] Figure 5 A flow chart of analyzing the pricing-sales impact of a target offline store on sales of abnormal products in the method provided in an embodiment of the present invention;

[0049] Figure 6 An application architecture diagram of a system provided by an embodiment of the present invention;

[0050] Figure 7 A structural block diagram of a module for determining abnormal sales of goods in a system provided in an embodiment of the present invention;

[0051] Figure 8 This is a structural block diagram of a customer engagement and sales conversion value calculation module in a system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0054] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0055] Specifically, a method for analyzing abnormal sales of goods based on user order data comprises the following steps:

[0056] Step S100, analyzing whether there are any abnormal sales products based on the user order data of the target online store and the target offline store.

[0057] Specifically, Figure 2 A flowchart is shown for determining whether there are any abnormal sales commodities.

[0058] Among them, according to the user order data of the target online store and the target offline store, analyzing whether there are abnormal sales products specifically includes the following steps:

[0059] Step S101, obtaining user order data of a target online store and a target offline store;

[0060] Step S102, filtering user order data of target online stores and target offline stores, and extracting user orders with the same product;

[0061] Step S103, analyzing the number of user orders for the same product corresponding to the target online store and the target offline store. When the difference between the number of user orders for a certain product in the target online store and the number of user orders in the target offline store is greater than a preset reasonable difference, the product is determined to be an abnormally sold product.

[0062] In the embodiment of the present invention, the application aims to assist the target offline store manager in sales management, especially for those products that have a significant gap in sales volume with the target online store;

[0063] When the target online store and the target offline store sell goods, they will keep sales records, and these sales records will be uniformly uploaded to the backend processing cloud and form user order data; the sales records should include the pricing, type and actual selling price of the goods sold;

[0064] After obtaining the user order data of the target online store and the target offline store in the cloud in the background processing, the user order data on both sides should be screened, and user orders with the same products should be obtained. Then, the quantity of several groups of user orders for the same products should be compared. Once it is found that the difference between the user order volume of the target online store and the user order volume of the target offline store for a certain product is greater than the preset reasonable difference, the product is determined to be an abnormal sales product. It can be understood that the number of abnormal sales products can be multiple.

[0065] Furthermore, the method for analyzing abnormal sales of goods based on user order data further includes the following steps:

[0066] Step S200: If it is determined that there are abnormal sales products, the in-store video data of the target offline store is obtained, and the customer engagement and sales conversion value of the abnormal sales products of the target offline store are calculated based on the in-store video data.

[0067] Specifically, Figure 3 A flow chart for calculating customer engagement and sales conversion value is shown.

[0068] If it is determined that there are abnormal sales products, obtaining the in-store video data of the target offline store, and calculating the customer engagement and sales conversion value of the abnormal sales products of the target offline store based on the in-store video data specifically includes the following steps:

[0069] Step S201, when it is determined that there are abnormal sales of goods, obtain in-store video data of the target offline store;

[0070] Step S202, intelligently analyzing the in-store video data and obtaining the number of interactions between the sales of abnormal products and customers;

[0071] Step S203, obtaining the sales quantity of the abnormally selling products in the target offline store, and dividing the sales quantity by the number of interactions to obtain the customer engagement and sales conversion value.

[0072] In the embodiment of the present invention, the target offline store should be equipped with a smart high-definition camera, and the smart high-definition camera should have at least the functions of target tracking, object recognition, data uploading, network connection, etc.;

[0073] After determining that there are abnormal sales products, the backend processing cloud retrieves the in-store video data of the target offline store, and the starting time point of the in-store video data is set to the time when the abnormal sales products start to be sold in the target offline store. After that, the abnormal sales products are locked in the in-store video data as the observation target, and the number of interactions between the abnormal sales products and customers is obtained. It should be understood that the interaction between the abnormal sales products and the in-store sales staff should not be recorded;

[0074] After determining the number of interactions between the sales-abnormal products and customers, the backend processing cloud obtains the sales quantity of the sales-abnormal products in the target offline stores through user order data, and divides the sales quantity by the number of interactions to obtain the customer engagement and sales conversion value. For example, if the number of interactions between the sales-abnormal products and customers is 50 times, and the sales quantity of the sales-abnormal products is 5, then the customer engagement and sales conversion value are 1 / 10.

[0075] Furthermore, the method for analyzing abnormal sales of goods based on user order data further includes the following steps:

[0076] Step S300: When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than the first preset threshold, product exposure optimization suggestion information is generated.

[0077] Specifically, Figure 4 A flow chart for generating product exposure optimization suggestion information is shown.

[0078] When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than the first preset threshold, generating product exposure optimization suggestion information specifically includes the following steps:

[0079] Step S301, when it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than a first preset threshold, generating sales promotion enhancement suggestion information;

[0080] Step S302, obtaining an image of the area where the abnormal sales products are located based on the in-store video data;

[0081] Step S303, generating product exposure optimization suggestion information based on the sales promotion intensity enhancement suggestion information and the image of the area where the abnormal sales product is located.

[0082] In the embodiment of the present invention, a first preset threshold is pre-set in the backend processing cloud, and the size of the first preset threshold is set by the target online and offline store managers according to the normal sales situation of the product;

[0083] It is understandable that the higher the customer engagement and sales conversion value (at least higher than the first preset threshold), the greater the chance that the abnormal sales product will be sold when interacting with customers. However, the abnormal sales product is in a state of poor sales volume (compared to online sales), which may indirectly reflect that the reason for the abnormal sales may be that the display location of the product is relatively hidden or the sales staff's promotion efforts are insufficient;

[0084] Therefore, when the calculated customer engagement and sales conversion value are higher than the first preset threshold, recommendation information for strengthening sales promotion efforts is immediately generated (suggesting sales personnel to increase the sales promotion efforts for the abnormal sales product), and the image of the area where the abnormal sales product is located is obtained through in-store video data (to facilitate managers to know whether the abnormal sales product is in a hidden location). Finally, the recommendation information for strengthening sales promotion efforts and the image of the area where the abnormal sales product is located are combined, and product exposure optimization recommendation information is generated and sent to the target offline store manager's smart terminal.

[0085] Furthermore, the method for analyzing abnormal sales of goods based on user order data further includes the following steps:

[0086] Step S400, when it is determined that the customer engagement and sales conversion value of the target offline store's sales abnormal products are not higher than the first preset threshold, analyze the pricing-sales impact of the target offline store on the sales abnormal products, and generate pricing and sales association information related to the sales abnormal products based on the pricing-sales impact.

[0087] Specifically, Figure 5 A flow chart for analyzing the pricing-sales impact of target offline stores on sales of abnormal products is shown.

[0088] When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are not higher than the first preset threshold, analyzing the pricing-sales influence of the target offline store on the abnormal sales products, and generating pricing and sales association information related to the abnormal sales products according to the pricing-sales influence specifically includes the following steps:

[0089] Step S401, when it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are not higher than the first preset threshold, obtaining pricing information of the abnormal sales product from the target online store and the target offline store;

[0090] Step S402, according to the pricing information of the target online store and the target offline store for the abnormal sales product, obtain the pricing values ​​of the target online store and the target offline store for the abnormal sales product, and obtain the sales quantity of the abnormal sales product in the target online store and the target offline store;

[0091] Step S403, calculating the pricing-sales impact according to the pricing-sales impact calculation formula, and generating pricing and sales association information related to the sales abnormality product according to the pricing-sales impact.

[0092] The formula for calculating the pricing-sales impact is D=R×ΔQ, where R represents the price difference ratio, ΔQ represents the sales volume difference between the two sales channels, and D is the pricing-sales impact;

[0093] In the pricing-sales impact calculation formula, ΔQ=Q online -Q offline , where P online is the pricing value of the target online store for abnormal sales of goods, P offline is the pricing value of the target offline store for abnormal sales of goods, Q online is the sales volume of abnormal products in the target online store, Q offline It is the sales volume of abnormal sales products in the target offline stores.

[0094] In the embodiment of the present invention, when it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are low (at least lower than the first preset threshold), it means that even if the product has interacted with many customers, its sales probability is still small. Based on the sales common sense of those skilled in the art, this situation is usually because the customer interacts with the product and then buys it in the target online store. The reason is often that the target offline store prices the product higher than the target online store.

[0095] Therefore, in order to facilitate the target offline store managers to analyze the specific sales impact of pricing on the abnormal sales of the product, it can be specifically expressed by calculating the pricing-sales impact. The backend processing cloud also sets a second preset threshold, and when making pricing recommendations for the target offline store managers, it should be based on the comparison between the pricing-sales impact and the second preset threshold;

[0096] For example, the second preset threshold is set to 20, and it is assumed that P online , P offline , Q online and Q offlineThe number of is 200, 150, 80 and 10 respectively. Then, the above four data are brought into the pricing-sales impact calculation formula, and the pricing-sales impact value can be calculated to be 17.5, that is, the pricing-sales impact is less than the second preset threshold. It can be concluded that the offline pricing is relatively low or the sales volume is relatively high, and it shows that the price of offline stores is competitive, attracting more customers and increasing sales. At this time, the advice for managers can be: maintain the current pricing strategy, while further improving the exposure and promotion of products to maintain and improve sales performance.

[0097] In another example, suppose P online , P offline , Q online and Q offline The number of is 200, 120, 80 and 10 respectively. Then, the above four data are brought into the pricing-sales impact calculation formula, and the pricing-sales impact value can be calculated to be 28, that is, the pricing-sales impact is greater than the second preset threshold, and then it can be concluded that the offline pricing is relatively high or the sales volume is relatively low, that is, a larger value may indicate that the price of offline stores is high, which suppresses the customer's desire to buy and leads to a decrease in sales. At this time, the suggestion for managers can be: consider adjusting the offline product pricing to make it closer to the online pricing to increase customers' willingness to buy and thus increase sales.

[0098] Understandably, the magnitude of the pricing-sales impact value primarily helps managers understand the extent to which pricing affects sales.

[0099] Through the above technical solution, when the sales performance of some products in offline stores is obviously lower than that of online stores, it can intelligently analyze whether the potential cause of abnormal sales is poor product display location, insufficient promotion, or unreasonable offline pricing compared to online. These analysis results can also be displayed to offline store managers in digital form, allowing them to effectively and scientifically and accurately adjust and manage these abnormal sales products.

[0100] Furthermore, Figure 6 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0101] Among them, in another preferred embodiment provided by the present invention, a sales abnormal commodity analysis system based on user order data includes:

[0102] The abnormal sales commodity judgment module 100 is used to analyze whether there are abnormal sales commodities based on the user order data of the target online store and the target offline store.

[0103] Specifically, Figure 7The structure block diagram of the abnormal sales commodity judgment module 100 in the system provided by the embodiment of the present invention is shown.

[0104] Among them, in the preferred embodiment provided by the present invention, the abnormal sales commodity judgment module 100 specifically includes:

[0105] A user order data acquisition unit 101 is used to acquire user order data of a target online store and a target offline store;

[0106] A user order screening unit 102 is used to screen user order data of a target online store and a target offline store, and extract user orders with the same product;

[0107] The abnormal sales commodity determination unit 103 is used to analyze the number of user orders for the same commodity corresponding to the target online store and the target offline store. When the difference between the number of user orders for a certain commodity in the target online store and the number of user orders in the target offline store is greater than a preset reasonable difference, the commodity is determined to be an abnormal sales commodity.

[0108] In the embodiment of the present invention, the application aims to assist the target offline store manager in sales management, especially for those products that have a significant gap in sales volume with the target online store;

[0109] When the target online store and the target offline store sell goods, they will keep sales records, and these sales records will be uniformly uploaded to the backend processing cloud and form user order data; the sales records should include the pricing, type and actual selling price of the goods sold;

[0110] After obtaining the user order data of the target online store and the target offline store in the cloud in the background processing, the user order data on both sides should be screened, and user orders with the same products should be obtained. Then, the quantity of several groups of user orders for the same products should be compared. Once it is found that the difference between the user order volume of the target online store and the user order volume of the target offline store for a certain product is greater than the preset reasonable difference, the product is determined to be an abnormal sales product. It can be understood that the number of abnormal sales products can be multiple.

[0111] Furthermore, the abnormal sales commodity analysis system based on user order data also includes:

[0112] The customer engagement and sales conversion value calculation module 200 is used to obtain in-store video data of the target offline store if it is determined that there are abnormal sales products, and calculate the customer engagement and sales conversion value of the abnormal sales products of the target offline store based on the in-store video data.

[0113] Specifically, Figure 8It shows a structural block diagram of the customer participation and sales conversion value calculation module 200 in the system provided by the embodiment of the present invention.

[0114] Among them, in the preferred embodiment provided by the present invention, the customer engagement and sales conversion value calculation module 200 specifically includes:

[0115] The in-store video data acquisition unit 201 is used to acquire in-store video data of a target offline store when it is determined that there are abnormal sales of goods;

[0116] The in-store video data analysis unit 202 is used to intelligently analyze the in-store video data and obtain the number of interactions between the sales of abnormal products and customers;

[0117] The customer engagement and sales conversion value calculation unit 203 is used to obtain the sales quantity of the abnormal sales product in the target offline store, and divide the sales quantity by the number of interactions to obtain the customer engagement and sales conversion value.

[0118] In the embodiment of the present invention, the target offline store should be equipped with a smart high-definition camera, and the smart high-definition camera should have at least the functions of target tracking, object recognition, data uploading, network connection, etc.;

[0119] After determining that there are abnormal sales products, the backend processing cloud retrieves the in-store video data of the target offline store, and the starting time point of the in-store video data is set to the time when the abnormal sales products start to be sold in the target offline store. After that, the abnormal sales products are locked in the in-store video data as the observation target, and the number of interactions between the abnormal sales products and customers is obtained. It should be understood that the interaction between the abnormal sales products and the in-store sales staff should not be recorded;

[0120] After determining the number of interactions between the sales-abnormal products and customers, the backend processing cloud obtains the sales quantity of the sales-abnormal products in the target offline stores through user order data, and divides the sales quantity by the number of interactions to obtain the customer engagement and sales conversion value. For example, if the number of interactions between the sales-abnormal products and customers is 50 times, and the sales quantity of the sales-abnormal products is 5, then the customer engagement and sales conversion value are 1 / 10.

[0121] Furthermore, the abnormal sales commodity analysis system based on user order data also includes:

[0122] The product exposure optimization suggestion information generating module 300 is used to generate product exposure optimization suggestion information when it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are higher than the first preset threshold;

[0123] The pricing-sales impact calculation module 400 is used to analyze the pricing-sales impact of the target offline store on the sales abnormal products when it is determined that the customer engagement and sales conversion value of the sales abnormal products of the target offline store are not higher than the first preset threshold, and generate pricing and sales association information related to the sales abnormal products based on the pricing-sales impact.

[0124] In the embodiment of the present invention, a first preset threshold is pre-set in the backend processing cloud, and the size of the first preset threshold is set by the target online and offline store managers according to the normal sales situation of the product;

[0125] It is understandable that the higher the customer engagement and sales conversion value (at least higher than the first preset threshold), the greater the chance that the abnormal sales product will be sold when interacting with customers. However, the abnormal sales product is in a state of poor sales volume (compared to online sales), which may indirectly reflect that the reason for the abnormal sales may be that the display location of the product is relatively hidden or the sales staff's promotion efforts are insufficient;

[0126] Therefore, when the calculated customer engagement and sales conversion value are higher than the first preset threshold, recommendation information for strengthening sales promotion efforts is immediately generated (suggesting sales personnel to increase the sales promotion efforts for the abnormal sales product), and the image of the area where the abnormal sales product is located is obtained through in-store video data (to facilitate managers to know whether the abnormal sales product is in a hidden location). Finally, the recommendation information for strengthening sales promotion efforts and the image of the area where the abnormal sales product is located are combined, and product exposure optimization recommendation information is generated and sent to the target offline store manager's smart terminal.

[0127] The formula for calculating the pricing-sales impact is D=R×ΔQ, where R represents the price difference ratio, ΔQ represents the sales volume difference between the two sales channels, and D is the pricing-sales impact;

[0128] In the pricing-sales impact calculation formula, ΔQ=Q online -Q offline , where P online is the pricing value of the target online store for abnormal sales of goods, P offline is the pricing value of the target offline store for abnormal sales of goods, Q online is the sales volume of abnormal products in the target online store, Q offline It is the sales volume of abnormal sales products in the target offline stores.

[0129] When it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are low (at least lower than the first preset threshold), it means that even if the product has interacted with many customers, its sales probability is still small. Based on the sales common sense of those skilled in the art, this situation is usually because the customer interacts with the product and then buys it in the target online store. The reason is often that the target offline store prices the product higher than the target online store.

[0130] Therefore, in order to facilitate the target offline store managers to analyze the specific sales impact of pricing on the abnormal sales of the product, the pricing-sales impact can be calculated to express it in detail. The backend processing cloud also sets a second preset threshold, and when making pricing recommendations for the target offline store managers, it should be based on the comparison between the pricing-sales impact and the second preset threshold;

[0131] For example, the second preset threshold is set to 20, and it is assumed that P online , P offline , Q online and Q offline The number of is 200, 150, 80 and 10 respectively. Then, the above four data are brought into the pricing-sales impact calculation formula, and the pricing-sales impact value can be calculated to be 17.5, that is, the pricing-sales impact is less than the second preset threshold. It can be concluded that the offline pricing is relatively low or the sales volume is relatively high, and it shows that the price of offline stores is competitive, attracting more customers and increasing sales. At this time, the advice for managers can be: maintain the current pricing strategy, while further improving the exposure and promotion of products to maintain and improve sales performance.

[0132] In another example, suppose P online , P offline , Q online and Q offline The number of is 200, 120, 80 and 10 respectively. Then, the above four data are brought into the pricing-sales impact calculation formula, and the pricing-sales impact value can be calculated to be 28, that is, the pricing-sales impact is greater than the second preset threshold, and then it can be concluded that the offline pricing is relatively high or the sales volume is relatively low, that is, a larger value may indicate that the price of offline stores is high, which suppresses the customer's desire to buy and leads to a decrease in sales. At this time, the suggestion for managers can be: consider adjusting the offline product pricing to make it closer to the online pricing to increase customers' willingness to buy and thus increase sales.

[0133] Understandably, the magnitude of the pricing-sales impact value primarily helps managers understand the extent to which pricing affects sales.

[0134] Through the above technical solution, when the sales performance of some products in offline stores is obviously lower than that of online stores, it can intelligently analyze whether the potential cause of abnormal sales is poor product display location, insufficient promotion, or unreasonable offline pricing compared to online. These analysis results can also be displayed to offline store managers in digital form, allowing them to effectively and scientifically and accurately adjust and manage these abnormal sales products.

[0135] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0136] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0137] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0139] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing abnormal sales of goods based on user order data, characterized in that: The method comprises: Analyze whether there are abnormal sales products based on the user order data of the target online store and the target offline store; If it is determined that there are abnormal sales products, obtain the in-store video data of the target offline store, and calculate the customer engagement and sales conversion value of the abnormal sales products in the target offline store based on the in-store video data; When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than a first preset threshold, generating product exposure optimization suggestion information; When it is determined that the customer engagement and sales conversion value of the target offline store's sales abnormal products are not higher than the first preset threshold, the pricing-sales impact of the target offline store on the sales abnormal products is analyzed, and pricing and sales association information related to the sales abnormal products is generated based on the pricing-sales impact.

2. The method for analyzing abnormal sales of commodities based on user order data according to claim 1, characterized in that: Based on the user order data of the target online store and the target offline store, the steps to analyze whether there are abnormal sales of goods include: Obtain user order data of target online stores and target offline stores; Filter the user order data of the target online store and the target offline store, and extract user orders with the same products; Analyze the number of user orders for the same product corresponding to the target online store and the target offline store. When the difference between the number of user orders for a certain product in the target online store and the number of user orders in the target offline store is greater than the preset reasonable difference, determine that the product is an abnormal sales product.

3. The method for analyzing abnormal sales of commodities based on user order data according to claim 1, characterized in that: If it is determined that there are abnormal sales products, the steps of obtaining in-store video data of the target offline store and calculating the customer engagement and sales conversion value of the abnormal sales products of the target offline store based on the in-store video data include: When it is determined that there are abnormal sales of goods, obtain in-store video data of the target offline store; Intelligently analyze in-store video data and obtain the number of interactions between abnormal sales products and customers; Obtain the sales volume of abnormally selling products in the target offline store, and divide the sales volume by the number of interactions to obtain the customer engagement and sales conversion value.

4. The method for analyzing abnormal sales of commodities based on user order data according to claim 3 is characterized in that: The starting time point of the in-store video data is set to the time when the sales of the abnormal sales product starts to be sold in the target offline store.

5. The method for analyzing abnormal sales of commodities based on user order data according to claim 1, characterized in that: When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than the first preset threshold, the step of generating product exposure optimization suggestion information includes: When it is determined that the customer engagement and sales conversion value of the abnormal sales products of the target offline store are higher than a first preset threshold, generating sales promotion enhancement suggestion information; Obtain images of areas where abnormal sales of goods are located based on in-store video data; According to the sales promotion efforts, the recommendation information and the images of the areas where the abnormal sales products are located are strengthened to generate the product exposure optimization recommendation information.

6. The method for analyzing abnormal sales of commodities based on user order data according to claim 1, characterized in that: When it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are not higher than the first preset threshold, the steps of analyzing the pricing-sales influence of the target offline store on the abnormal sales product, and generating pricing and sales association information related to the abnormal sales product according to the pricing-sales influence include: When it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are not higher than the first preset threshold, obtaining pricing information of the abnormal sales product of the target online store and the target offline store; According to the pricing information of the target online store and the target offline store for the abnormal sales product, obtain the pricing values ​​of the target online store and the target offline store for the abnormal sales product, and obtain the sales quantity of the abnormal sales product in the target online store and the target offline store; The pricing-sales impact is calculated according to the pricing-sales impact calculation formula, and pricing and sales association information related to the sales abnormality products is generated based on the pricing-sales impact.

7. The method for analyzing abnormal sales of commodities based on user order data according to claim 1, characterized in that: The formula for calculating the pricing-sales impact is D=R×ΔQ, where R represents the price difference ratio, ΔQ represents the sales volume difference between the two sales channels, and D is the pricing-sales impact; In the pricing-sales impact calculation formula, ΔQ=Q online -Q offline , where P online is the pricing value of the target online store for abnormal sales of goods, P offline is the pricing value of the target offline store for abnormal sales of goods, Q online is the sales volume of abnormal products in the target online store, Q offline It is the sales volume of abnormal sales products in the target offline stores.

8. A sales abnormal commodity analysis system based on user order data, characterized in that: The system includes: a sales abnormal commodity judgment module, a customer participation and sales conversion value calculation module, a commodity exposure optimization suggestion information generation module, and a pricing-sales influence calculation module, wherein: The abnormal sales commodity judgment module is used to analyze whether there are abnormal sales commodities based on the user order data of the target online store and the target offline store; A customer engagement and sales conversion value calculation module is used to obtain in-store video data of a target offline store if it is determined that there are abnormal sales products, and calculate the customer engagement and sales conversion value of the abnormal sales products of the target offline store based on the in-store video data; A product exposure optimization suggestion information generation module, configured to generate product exposure optimization suggestion information when it is determined that the customer engagement and sales conversion value of the abnormal sales product of the target offline store are higher than a first preset threshold; The pricing-sales impact calculation module is used to analyze the pricing-sales impact of the target offline store on the sales abnormal products when it is determined that the customer engagement and sales conversion value of the sales abnormal products of the target offline store are not higher than the first preset threshold, and generate pricing and sales association information related to the sales abnormal products based on the pricing-sales impact.

9. The abnormal sales commodity analysis system based on user order data according to claim 8 is characterized in that: The abnormal sales commodity judgment module specifically includes: A user order data acquisition unit, used to acquire user order data of a target online store and a target offline store; A user order screening unit, used to screen user order data of target online stores and target offline stores, and extract user orders with the same product; The abnormal sales commodity determination unit is used to analyze the number of user orders for the same commodity corresponding to the target online store and the target offline store. When the difference between the number of user orders for a certain commodity in the target online store and the number of user orders in the target offline store is greater than a preset reasonable difference, the commodity is determined to be an abnormal sales commodity.

10. The abnormal sales commodity analysis system based on user order data according to claim 9 is characterized in that: The customer engagement and sales conversion value calculation module specifically includes: An in-store video data acquisition unit, used to acquire in-store video data of a target offline store when it is determined that there are abnormal sales of goods; In-store video data analysis unit, used to intelligently analyze in-store video data and obtain the number of interactions between abnormal sales products and customers; The customer engagement and sales conversion value calculation unit is used to obtain the sales quantity of the abnormal sales products in the target offline store, and divide the sales quantity by the number of interactions to obtain the customer engagement and sales conversion value.

Images