A sales forecasting method and system based on multi-dimensionality

Abstract

The present invention discloses a multi-dimensional sales forecasting method and system. The method includes the following steps: taking a photo of a user shopping in a supermarket with a shopping cart; identifying the items placed in the cart by the user based on the photo, and obtaining a list of the items placed in the cart; obtaining the settlement order of the user's purchase; comparing the item information in the settlement order with the list of items placed in the cart by the user, and obtaining the items removed from the cart by the user; identifying whether there are items of the same category in the settlement order based on the items removed by the user; if so, obtaining the items of the same category in the settlement order as competing products of the items removed by the user, obtaining the selling price of the competing products from the product information in the settlement order, and obtaining the corresponding selling price based on the items removed by the user. Suppliers can more flexibly judge future product sales. Supermarkets or suppliers can also more accurately predict future sales trends.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a sales forecasting method and system based on multiple dimensions. Background Art

[0002] It is crucial for supermarkets and suppliers to understand which products are more popular and how they are selling. Usually, supermarkets and suppliers can accurately track the sales data of specific products, which are generated based on actual sales orders.

[0003] Despite having specific sales figures, supermarkets and suppliers often lack a critical understanding of the actual customer purchasing process. One crucial piece of information is the primary competitors for a particular product. Existing technologies fail to capture this information, as customers often compare different brands or types of similar products before ultimately deciding to purchase one or more. This limits supermarkets and suppliers' sales forecasts. Summary of the Invention

[0004] In view of the above problems, this application provides a multi-dimensional sales forecasting method and system to solve the problem of how to find corresponding competing products for suppliers' products and provide data support for sales forecasting.

[0005] To achieve the above objectives, the inventors provide a multi-dimensional sales forecasting method, comprising the following steps:

[0006] Take a photo of a user shopping in a supermarket with a shopping cart;

[0007] Identify the items placed in the cart by the user based on the captured photo and obtain a list of items placed in the cart by the user;

[0008] Get the settlement order of the user's shopping;

[0009] Compare the product information of the settled order with the list of products the user has placed in the cart, and obtain the products the user has taken out of the cart;

[0010] Based on the product taken out by the user, it is identified whether there are products of the same category in the settlement order. If so, the products of the same category in the settlement order are obtained and used as competitors of the product taken out by the user, and the selling prices of the competitors are obtained from the product information of the settlement order, and the corresponding selling prices are obtained based on the product taken out by the user.

[0011] Furthermore, the user corresponding to the trolley includes a first user and a second user, and the first user is a child;

[0012] When identifying the commodities placed in the cart by the user based on the photographed photos and obtaining a list of commodities placed in the cart by the user, the following steps are also included:

[0013] The captured photos are used to determine whether the first user has taken the product from the shelf display area and placed it in the trolley. If so, it is determined whether the second user has placed the product back to the display area by himself or with the help of the first user within a preset time. If so, the product placed in the trolley by the first user is removed from all the products placed in the trolley to obtain a list of the products placed in the trolley by the users.

[0014] Furthermore, the first user and the second user are identified by the following steps:

[0015] Get the pixel height of the marker in the captured photo;

[0016] Get the pixel height of the user in the captured photo;

[0017] Get the actual height of the marker, and get the actual height of the user based on the pixel height of the marker, the pixel height of the user, and the actual height of the marker;

[0018] It is determined whether the actual height of the user is less than the height threshold. If so, the user is determined to be the first user; if not, the user is determined to be the second user.

[0019] Furthermore, the identification is a product label on the shelf, an end of a shelf layer, or an identification plate fixed on the layer or the ground.

[0020] Furthermore, when identifying the commodities placed in the cart by the user based on the photographed photos, the following steps are also included:

[0021] Identify the products that the user has taken from the shelf area based on several photos taken before and after;

[0022] Identify the product labels corresponding to the display area based on the photos taken, and obtain the weight of the product based on the product labels;

[0023] Obtain the weight difference detected by the pressure sensor on the placement area;

[0024] Determine whether the weight obtained from the product label and the weight difference is less than the weight threshold. If so, it is determined that the product taken out is correctly identified. If not, use OCR technology or vision and deep learning technology to identify the correct name of the product taken out by the user from the shelf area and output it.

[0025] Furthermore, when identifying the commodities placed in the cart by the user based on the photographed photos, the following steps are also included:

[0026] Identify products in photos using OCR technology or visual and deep learning technology.

[0027] Furthermore, the following steps are included:

[0028] Competing products and their prices, as well as the products picked up by the user and their prices, are sent to the suppliers corresponding to the products picked up by the user.

[0029] Furthermore, the following steps are included:

[0030] Count the number of times the same product is selected by users within a preset period and the corresponding competing products;

[0031] Determine whether the frequency of occurrence of the competing product corresponding to the product selected by the user is greater than the frequency threshold. If so, send a price comparison curve of the selected product and its high-frequency competing products to the supplier of the product selected by the user.

[0032] Furthermore, the following steps are included:

[0033] Get the past purchase date and sales amount of the items that the user took out from the cart;

[0034] Obtaining a time series training dataset based on the sales data of the product, multiple preset date ranges, and the preset activity intensity corresponding to each preset date range, wherein the time series training dataset includes features of the product and sales amounts corresponding to the features, wherein the features include identification features, date features, activity features, and time series features;

[0035] Performing model training using a loss function based on the time series training data set to obtain a sales amount prediction model;

[0036] The sales amount prediction model is used to predict the sales range of the items that the user takes out from the cart.

[0037] To achieve the above objectives, the inventors also provide a multi-dimensional sales forecasting system that stores computer program instructions, which, when executed by a processor, implement the multi-dimensional sales forecasting method described in any of the above embodiments.

[0038] Different from the existing technology, the above technical solution has the following beneficial effects:

[0039] Competing products and their prices, as well as items picked up by users and their prices, can be sent to the corresponding suppliers. This allows suppliers to more flexibly predict future product sales and adjust production plans and inventory management. It also allows supermarkets or suppliers to more accurately predict future sales trends.

[0040] The above-mentioned records related to the content of the invention are only an overview of the technical solution of this application. In order to enable ordinary technicians in this field to understand the technical solution of this application more clearly, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purposes and other purposes, features and advantages of this application easier to understand, the following is an explanation in combination with the specific implementation methods and drawings of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings are only used to illustrate the principles, implementation methods, applications, features and effects of the specific embodiments of the present invention and other related contents, and are not to be considered as limiting the present application.

[0042] In the drawings of the specification:

[0043] Figure 1 This is a flow chart of the sales forecasting method in this embodiment;

[0044] Figure 2 This is a flowchart of identifying the items placed in the cart by the user based on the captured photos and obtaining a list of the items placed in the cart by the user in this embodiment;

[0045] Figure 3 This is a flowchart for identifying a first user and a second user in this embodiment;

[0046] Figure 4 This is a flow chart of identifying the merchandise placed in the cart by the user based on the captured photos in this embodiment;

[0047] Figure 5 This is a flowchart for counting the number of times the same product is taken out by users and the corresponding competing products within a preset period in this embodiment. DETAILED DESCRIPTION

[0048] In order to explain in detail the possible application scenarios, technical principles, specific solutions that can be implemented, and the purpose and effects of this application, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of this application and are therefore only examples and are not intended to limit the scope of protection of this application.

[0049] References to "embodiments" herein mean that the specific features, structures, or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the word "embodiment" in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the various technical features mentioned in the embodiments can be combined in any manner to form a corresponding implementable technical solution.

[0050] Unless otherwise defined, the technical terms used herein have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms herein is only for describing specific embodiments and is not intended to limit this application.

[0051] In the description of this application, the term "and / or" is used to describe a logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and both A and B exist. In addition, the character " / " in this document generally indicates that the objects before and after are in a logical "or" relationship.

[0052] In this application, terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantity, priority or sequence relationship between these entities or operations.

[0053] Without further limitations, in this application, the words "include", "comprise", "have" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product that includes the elements, so that the process, method or product that includes a series of elements may include not only those defined elements, but also other elements that are not explicitly listed, or also include elements inherent to such process, method or product.

[0054] Consistent with the understanding in the Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceed" are understood to exclude the number itself; expressions such as "above," "below," and "within" are understood to include the number itself. Furthermore, in the description of the embodiments of this application, "multiple" means two or more (including two), and similar expressions related to "multiple," such as "multiple groups" and "multiple times," are also understood in this manner, unless otherwise specifically defined.

[0055] In the description of the embodiments of the present application, the space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, it should not be understood as a limitation on the embodiments of the present application.

[0056] The processor described in the embodiments of the present application can be implemented by hardware, firmware, software or a combination thereof, and can use a circuit, a single or multiple application-specific integrated circuits (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, at least one of a microprocessor, and also includes other physical, biological or chemical structures that can achieve similar or equivalent functions to the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of the present application, or any combination of the steps mentioned therein.

[0057] The computer program involved in the embodiment can be stored in a computer device readable storage medium, which includes but is not limited to a disk, a tape, a magnetic card, a floppy disk, a flash memory, an optical disc, an optical card, a read-only memory (ROM), a random access memory (RAM), an erasable programmable ROM (EPROM) and an electrically erasable programmable ROM (EEPROM), etc., and also includes other biological, physical or chemical structures that can achieve similar or equivalent functions to the storage media listed above, such as DNA, RNA, protein and other units with information storage capabilities. In a specific embodiment, the storage medium involved can be one of the above-mentioned media types or a combination of the above-mentioned media types. In different embodiments, the computer program involved in the embodiment can be stored in a single medium in a centralized manner or in a distributed manner on multiple media. The memory containing the computer device readable storage medium can be a non-volatile memory or a random access memory. These computer device readable storage media can be built into the device or connected to the device involved in the embodiment as an external device or part of an external device. In some embodiments, a memory having a computer-readable storage medium is deployed locally; in other embodiments, a solution of deploying the memory away from the processor may also be adopted, such as a network-attached memory accessed via an RF circuit or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), etc., or a suitable combination thereof, as long as the computer device can access the memory. In addition, the computer program involved in the embodiment can be stored in plaintext / ciphertext form, or can be designed as training data, which can be integrated and reorganized through model training and implicitly stored in the parameter state of a deep neural network or other machine learning model.

[0058] See also Figure 1 This embodiment provides a multi-dimensional sales forecasting method, comprising the following steps:

[0059] Step S101, taking photos of a user shopping in a supermarket using a shopping cart, including photos of picking up and placing goods and photos of the shopping cart;

[0060] Step S102: Identify the items placed in the cart by the user based on the captured photo and obtain a list of the items placed in the cart by the user;

[0061] Step S103, obtaining the settlement order of the user's current purchase;

[0062] Step S104: Compare the product information of the settled order with the list of products placed in the cart by the user to obtain the products that the user has taken out of the cart;

[0063] In step S105, the user checks whether there are any products of the same category in the settlement order based on the product removed by the user. If so, the process proceeds to step S106, where the products of the same category in the settlement order are identified as competing products of the product removed by the user. The selling price of the competing products is obtained from the product information in the settlement order, and the corresponding selling price of the product removed by the user is obtained. If not, it indicates that the user has not removed any products from the cart.

[0064] It should be noted that the primary function of the camera is to capture the status of the shopping cart used by users and obtain information such as the type and quantity of items. To ensure the accuracy of the captured product information, the camera requires high resolution and clarity. High-definition cameras with high resolution and clarity are generally recommended, and smart cameras with image processing and analysis capabilities can also be selected as needed. Intelligent camera placement is planned based on the actual supermarket layout to ensure adequate coverage of each key area while avoiding excessive overlap and resource waste. For example, multiple cameras can be installed above supermarket shelves to provide a bird's-eye view of the shelves, capturing the movement of carts and the items placed within. This effectively avoids obstructions and improves recognition accuracy. Cameras installed at both ends of the aisle not only detect items on the shelves at mid-height but also monitor carts entering and exiting the aisles. Cameras installed near the checkout counter not only record the checkout process but also verify that the final purchased items match the items previously captured in the cart. Payment orders can be obtained from the supermarket's sales module. Payment orders typically contain product data, including but not limited to product name, price, and weight.

[0065] The product information of the settlement order includes but is not limited to product name, price, weight, and other information. The product list in the settlement order is compared with the product list obtained through image recognition to identify which products have been removed from the user's cart. For those products that have not been purchased, the settlement order is checked to see if there are similar competing products. If so, the selling price of the competing products is obtained. Of course, other data can also be obtained as needed to provide data support for subsequent supermarket or supplier analysis. This helps supermarkets and suppliers better understand market dynamics and consumer purchasing behavior. For example, by analyzing the price differences between different competing products and their impact on sales, pricing strategies can be optimized.

[0066] "Same category" refers to products with similar functions or uses. For example, different brands of toothpaste belong to the same category, as do different flavors of yogurt. Imagine a customer shopping at a supermarket places the following items in their cart: Brand A's anti-sensitivity toothpaste, Brand B's regular yogurt, and Brand C's chocolate chip cookies. However, at checkout, the customer's final order shows they purchased the following items: Brand A's anti-sensitivity toothpaste, Brand E's low-fat yogurt, and Brand F's oatmeal cookies. Brand B's regular yogurt is removed, and the customer chooses Brand E's low-fat yogurt. Although the specific product attributes of these two products differ, they still belong to the same category (yogurt), meaning Brand E's low-fat yogurt competes with Brand B's regular yogurt. Brand C's chocolate chip cookies are removed, and the customer chooses Brand F's oatmeal cookies. Although the two products differ in ingredients and type, they can both be broadly categorized as snacks or cookies. Therefore, Brand F's oatmeal cookies can be analyzed as a competitor of Brand C's chocolate chip cookies.

[0067] The above technical solution has the following beneficial effects:

[0068] Sales forecasting methods help better manage inventory by understanding users' actual behavioral patterns during selection (such as giving up certain products in favor of their competitors), and also allow supermarkets or suppliers to more accurately predict future sales trends.

[0069] In this embodiment, the sales forecasting method further includes the following steps:

[0070] Competing products and their prices, as well as the products picked up by users and their prices, are sent to the corresponding suppliers of the products. Suppliers can more flexibly predict future product sales and adjust production plans and inventory management.

[0071] When a shopping cart is shared by multiple users (e.g., a parent and a child), the child may randomly remove items from the shelf and put them into the cart. However, these items may not be what the parent intended to buy, and may even be put back on the shelf after being discovered by the parent within a short period of time. This situation leads to inaccurate results on the items removed by the user, which in turn affects the accuracy of the sales forecasting method. Figure 2 ,In this embodiment, the users corresponding to the cart include a first user and a second user, where the first user is a child;

[0072] In step S102, when identifying the commodities placed in the cart by the user based on the photographed photo and obtaining a list of commodities placed in the cart by the user, the following steps are also included:

[0073] Step S201, judging by the photographed photo whether the first user has taken the product from the shelf display area and put it into the trolley, if so, proceeding to step S202, judging whether the second user has put the product back to the display area by himself or with the help of the first user within a preset time, if so, proceeding to step S203, removing the products put into the trolley by the first user from all the products put into the trolley to obtain a list of products put into the trolley by the user, if not, then there is no product put into the trolley by the first user, and all the products are those that the second user wanted to buy.

[0074] Specifically, the first user (a child) takes a toy from the shelf and places it in a cart. The camera captures this action and preliminarily adds the toy to the product list. The second user (a parent) notices the toy and, within a preset time (e.g., 30, 40, or 50 seconds), decides not to allow the child to purchase it. They then have the child return the toy to the shelf. By analyzing the camera image, the user detects the toy's return and determines that it was directed by the second user. Ultimately, the toy is removed from the product list for subsequent analysis, preventing inaccuracies in the product list that could affect the accuracy of competing products.

[0075] Although facial recognition technology can be used as a means to try to distinguish different users, due to the complexity and diversity of facial features, including but not limited to factors such as facial occlusion and age differences, the accuracy of user age recognition is not high. Figure 3 In this embodiment, the sales forecasting method identifies the first user and the second user through the following steps:

[0076] Step S301, obtaining the pixel height of the mark in the captured photo;

[0077] Step S302, obtaining the pixel height of the user in the captured photo;

[0078] Step S303: Obtain the actual height of the marker. Obtain the actual height of the user based on the pixel height of the marker, the pixel height of the user, and the actual height of the marker. The actual height of the user is recorded as h1, the pixel height of the user is recorded as m1, the actual height of the marker is recorded as h2, and the pixel height of the marker is recorded as m2. The actual height of the user h1 is calculated using the following formula:

[0079] ;

[0080] Step S304 determines whether the user's actual height is less than a height threshold (e.g., 1.0 meter, 1.1 meter, or 1.2 meter). If so, the system proceeds to step S305, determining the user as the first user. If not, the system proceeds to step S306, determining the user as the second user. The second user is an adult or adolescent with independent decision-making ability who serves as the decision-maker during the shopping process. Compared to facial recognition, height-based recognition methods are less affected by environmental factors and have higher accuracy. This improves data processing accuracy and operates without infringing on the user's facial privacy.

[0081] In a further embodiment, the markers are product labels on the shelves, ends of shelf shelves, or identification plates fixed to shelves or the ground. Since these markers are usually fixed and cannot be easily moved, calculation errors caused by changes in reference objects are reduced.

[0082] See also Figure 4 In this embodiment, in step S102, when identifying the goods placed in the cart by the user based on the photographed photos, the following steps are also included:

[0083] Step 401: Identify the product that the user has taken from the shelf based on the taken before and after photos.

[0084] Step 402: Identify the product labels corresponding to the display area based on the photographed photos, and obtain the weight of the products based on the product labels;

[0085] Step 403: Obtain the weight difference detected by the pressure sensor on the placement area;

[0086] In step 404, it is determined whether the weight obtained from the product label and the weight difference are less than the weight threshold. If so, the process proceeds to step 405, where it is determined that the product removed is correctly identified and the product is output to the controller for use in step S104. If not, the process proceeds to step 406, where the OCR technology or vision and deep learning technology is used to identify the correct name of the product removed by the user from the shelf placement area and output it for use in step S104.

[0087] Specifically, OCR (Optical Character Recognition) technology is used to extract text from images and convert it into a form readable by a processor. In a supermarket environment, OCR can be used to recognize text on product packaging, barcodes, or labels, and perform post-processing steps such as grammar checking and spelling correction on the recognized text.

[0088] Specifically, vision and deep learning technologies can use deep learning frameworks (such as TensorFlow and PyTorch) to train convolutional neural networks (CNNs) or other models suitable for image classification tasks, automatically extracting complex features from images and performing classification or recognition. Supermarkets can pre-train models using product templates from a database.

[0089] The camera captures multiple video frames before and after a user removes an item. Using an object detection algorithm, the system determines whether the user has removed an item from the shelf. Based on the shelf area where the removed item is located, the camera automatically focuses on the product label (such as price and description) corresponding to that area. Images of product labels not obscured by the user can be used. The system obtains the standard weight of the item (for example, 3 kg). Simultaneously, a pressure sensor installed on the shelf area records the weight difference before and after the item is removed (assuming it is 2.98 kg, which is less than the weight threshold) to determine if the item has been correctly identified. If the weight discrepancy is significant (for example, the label indicates 3 kg, but the weighing discrepancy is 1.5 kg), the system uses optical character recognition (OCR) or a combination of vision and deep learning technologies to re-identify the item, ensuring the correct name and specifications. This multi-dimensional product recognition mechanism reduces the high computing power requirements associated with relying solely on OCR or deep learning.

[0090] In some embodiments, when identifying the items placed in the cart by the user based on the captured photos, the following steps are also included:

[0091] The products in the photographs can be directly identified through OCR technology or vision and deep learning technology without the need to combine with the above-mentioned weight judgment mechanism.

[0092] See also Figure 5 In this embodiment, the sales forecasting method further includes the following steps:

[0093] Step 501: Count the number of times the same product is selected by users within a preset period and the corresponding competing products;

[0094] Step 502: Determine whether the frequency of occurrence of the competing product corresponding to the product retrieved by the user is greater than the frequency threshold. If so, proceed to step 503: Send a price comparison curve of the retrieved product and its high-frequency competing products to the supplier of the retrieved product. If not, store the product retrieved by the user and the competing product information in the database.

[0095] Suppose Brand A milk is frequently added to supermarket carts but is often replaced with Brand B or Brand C milk at checkout. The processor counts the number of times this product has been removed from the cart over the past month and records whether another brand of milk was purchased as a replacement each time. Frequency statistics for these replacement products reveal that Brand B milk appears most frequently, exceeding a set threshold (e.g., more than 1,000 times per month). The processor automatically generates a price comparison curve for this product and Brand B milk, showing the price difference between the two over time. The processor can also generate a frequency ranking chart of all competing products. This analysis can be automatically sent to Brand A's suppliers, alerting them to market competition and helping to predict future sales.

[0096] In this embodiment, the sales forecasting method further includes the following steps:

[0097] Get the past purchase date and sales amount of the items that the user took out from the cart;

[0098] Obtaining a time series training dataset based on the sales data of the product, multiple preset date ranges, and the preset activity intensity corresponding to each preset date range, wherein the time series training dataset includes features of the product and sales amounts corresponding to the features, wherein the features include identification features, date features, activity features, and time series features;

[0099] The model is trained using the loss function according to the time series training data set to obtain a sales amount prediction model. Specifically, the loss function L is constructed based on the mean and standard deviation of the predicted sales amount, which is: ;

[0100] in, is the sales amount at time t The distribution of is the mean of the predicted sales amount, is the standard deviation of the predicted sales amount, i is an integer greater than or equal to 1 and less than or equal to N, and t is an integer greater than or equal to t0 and less than or equal to T.

[0101] The sales amount prediction model predicts the sales range of the items that users remove from their shopping carts. This prediction can be made based on the activity characteristics of the items, with low lag and improved prediction accuracy.

[0102] This embodiment also provides a multi-dimensional sales forecasting system, which stores computer program instructions. When the computer program instructions are executed by a processor, they implement the multi-dimensional sales forecasting method as described in any of the above embodiments.

[0103] In this embodiment, the sales forecasting system includes a processor, a camera, a pressure sensor, and a supermarket database. The processor, as the control core of the entire system, is responsible for executing pre-set computer program instructions and coordinating data flow and task scheduling between modules. For example, it receives raw image data captured by the camera; accesses the supermarket database to obtain basic product information (such as product label, price, category, and weight); controls the sales module to output sales forecast results and competitive product analysis reports, and sends feedback information to suppliers through external communication interfaces. The cameras include high-definition wide-angle cameras and smart cameras with edge computing capabilities, which transmit video streams to the processor via wired / wireless networks. Cameras can be deployed in strategic locations within the supermarket to provide a good field of view, such as above shelves, near aisles, and in the checkout area. Video streams are transmitted to the processor via wired / wireless networks. Pressure sensors monitor the weight changes of items on the shelves, thereby assisting in identifying items removed or returned by users. Typically, high-precision pressure sensors or load cells (such as strain gauge sensors) are used. These sensors can accurately measure the weight of objects placed on them and convert the detected weight changes into electrical signals, which are typically output as digital signals to the processor. Pressure sensors can be installed on different shelves or beneath specific product compartments to independently monitor weight changes of the products above them. The supermarket's database stores basic product information, such as name, specifications, price, category, weight, and brand. It also provides product label images, barcodes, and an OCR feature library for product identification. The database is connected to the sales module and stores historical transaction orders.

[0104] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concepts of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A sales forecasting method based on multiple dimensions, characterized in that: The steps include: Take a photo of a user shopping in a supermarket with a shopping cart; Identify the items placed in the cart by the user based on the captured photo and obtain a list of items placed in the cart by the user; Get the settlement order of the user's shopping; Compare the product information of the settled order with the list of products the user has placed in the cart, and obtain the products the user has taken out of the cart; Identify whether there are products of the same category in the settlement order based on the product taken out by the user. If so, obtain the products of the same category in the settlement order and use them as competing products of the product taken out by the user. Obtain the selling price of the competing products from the product information of the settlement order, and obtain the corresponding selling price of the product taken out by the user. The users corresponding to the trolley include a first user and a second user, wherein the first user is a child; When identifying the commodities placed in the cart by the user based on the photographed photos and obtaining a list of commodities placed in the cart by the user, the following steps are also included: Determine, based on the captured photo, whether the first user has taken a product from the shelf placement area and placed it in a trolley. If so, determine whether the second user has placed the product back to the placement area within a preset time, either alone or with the help of the first user. If so, remove the product placed in the trolley by the first user from all products placed in the trolley to obtain a list of products placed in the trolley by the user. The following steps are also included: Get the past purchase date and sales amount of the items that the user took out from the cart; Obtaining a time series training dataset based on the sales data of the product, multiple preset date ranges, and the preset activity intensity corresponding to each preset date range, wherein the time series training dataset includes features of the product and sales amounts corresponding to the features, wherein the features include identification features, date features, activity features, and time series features; Training the time series training data set using a loss function to obtain a sales amount prediction model; The sales amount prediction model is used to predict the sales range of the items that the user takes out from the cart.

2. The sales forecasting method according to claim 1, characterized in that: Identify the first user and the second user by following the steps below: Get the pixel height of the marker in the captured photo; Get the pixel height of the user in the captured photo; Get the actual height of the marker, and get the actual height of the user based on the pixel height of the marker, the pixel height of the user, and the actual height of the marker; It is determined whether the actual height of the user is less than the height threshold. If so, the user is determined to be the first user; if not, the user is determined to be the second user.

3. The sales forecasting method according to claim 2, characterized in that: The identification is a product label on the shelf, an end of a shelf layer, or an identification plate fixed on the layer or the ground.

4. The sales forecasting method according to claim 1, wherein: When identifying the commodities placed in the cart by the user based on the photographed photos, the method further includes the following steps: Identify the products that the user has taken from the shelf based on several photos taken before and after; Identify the product labels corresponding to the display area based on the photos taken, and obtain the weight of the products based on the product labels; Obtain the weight difference detected by the pressure sensor on the placement area; Determine whether the weight obtained from the product label and the weight difference is less than the weight threshold. If so, it is determined that the product taken out is correctly identified. If not, use OCR technology or vision and deep learning technology to identify the correct name of the product taken out by the user from the shelf area and output it.

5. The sales forecasting method according to claim 1, characterized in that: When identifying the commodities placed in the cart by the user based on the photographed photos, the method further includes the following steps: Identify products in photos using OCR technology or visual and deep learning technology.

6. The sales forecasting method according to claim 1, characterized in that: The following steps are also included: Competing products and their prices, as well as the products picked up by the user and their prices, are sent to the suppliers corresponding to the products picked up by the user.

7. The sales forecasting method according to claim 1, characterized in that: The following steps are also included: Count the number of times the same product is selected by users within a preset period and the corresponding competing products; Determine whether the frequency of occurrence of the competing product corresponding to the product selected by the user is greater than the frequency threshold. If so, send a price comparison curve of the selected product and its high-frequency competing products to the supplier of the product selected by the user.

8. A multi-dimensional sales forecasting system storing computer program instructions, characterized in that: When the computer program instructions are executed by a processor, the multi-dimensional sales forecasting method according to any one of claims 1 to 7 is implemented.

Images