Commodity shelf life intelligent tracking method, AR glasses, medium and product

Abstract

The invention discloses a commodity shelf life intelligent tracking method, AR glasses, a medium and a product, and relates to the field of AR glasses display.By means of the technical scheme, the AR glasses automatically obtain the commodity number, the storage position, the production date and the shelf life of each commodity on a shelf, and therefore the remaining shelf life of each commodity is calculated; and the expired commodities and the immediate commodities are intelligently identified according to a preset duration threshold. When a user sends out an out-of-date commodity and an in-date commodity query instruction, the AR glasses quickly position a target commodity, determines an out-of-date and in-date commodity processing route with the shortest time according to a target storage position, and displays the out-of-date and in-date commodity processing route in the view in an overlapping manner, so that the route is visually guided and the commodities are visually marked for workers; the efficiency and accuracy of commodity shelf life management are greatly improved, the problem of easy omission of manual inspection is avoided, the processing time is saved through optimal path planning, and the labor intensity of workers is reduced.

Description

Technical Field

[0001] The present application relates to the field of AR glasses display, and in particular to a method for intelligently tracking the shelf life of goods, AR glasses, media and products. Background Art

[0002] With the rapid development of the retail industry and the dramatic increase in the variety and quantity of goods, shelf life management has become a major challenge facing retailers. This not only affects the health and safety of consumers but also directly impacts inventory management and operational efficiency.

[0003] In related technologies, staff typically place products of the same type and batch (with the same production date and expiration date) in the same area of the shelf and record the product's placement, production date, and expiration date. Staff can check the product's expiration date at any time, making it easier to provide early warnings and handle products that are about to expire.

[0004] While relevant technologies can improve the efficiency of handling near-expiry or expired goods to a certain extent, some flaws remain. For example, when handling near-expiry or expired goods, staff rely on backend database query and warning functions, which lack intuitive visual prompts and are prone to omissions or errors. Summary of the Invention

[0005] This application provides a method for intelligently tracking the shelf life of goods, AR glasses, media and products, which are used to improve the efficiency of handling near-expiry goods.

[0006] In the first aspect, the present application provides an intelligent tracking method for the shelf life of goods, which is applied to AR glasses, and the method includes: obtaining basic information of each product on the shelf, the basic information including product number, storage location, production date and shelf life; calculating the remaining shelf life of each product based on the current time, the production date and the shelf life; determining the product whose remaining shelf life is less than or equal to a preset first time threshold as an expired product, and determining the product whose remaining shelf life is less than or equal to a preset second time threshold as a near-expiring product, the preset first time threshold being less than the preset second time threshold; determining the target product number and target storage location in response to the user's query instructions for the expired product and the near-expiring product; determining the expired and near-expiring product processing route with the shortest time based on the target storage location; displaying the expired and near-expiring product processing route, and superimposing the target product corresponding to the target product number in the field of view.

[0007] By adopting the above technical solution, AR glasses automatically obtain the product number, storage location, production date and shelf life of each product on the shelf, thereby calculating the remaining shelf life of each product and intelligently identifying expired and near-expiry products based on a preset time threshold. When a user issues a query instruction for expired and near-expiry products, AR glasses quickly locate the target product and determine the shortest processing route for expired and near-expiry products based on the target storage location. The AR glasses overlay the display in the field of view, intuitively guiding the staff on the path and marking the products. This not only greatly improves the efficiency and accuracy of product shelf life management and avoids problems that are easily missed during manual inspections, but also saves processing time through optimal path planning and reduces the labor intensity of staff.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the expired and near-expiry goods processing route with the shortest time is determined based on the target storage location, specifically including: determining multiple alternative paths based on the layout information of the warehouse and the target storage location; obtaining image data of the warehouse; determining obstacle information on each alternative path based on the image data; determining the time for each alternative path based on the obstacle information; and determining the alternative path with the shortest time as the expired and near-expiry goods processing route.

[0009] By adopting the above technical solution, AR glasses determine multiple alternative paths based on the warehouse layout information and target storage location. At the same time, AR glasses use the warehouse image data to identify obstacle information on each alternative path, and then calculate the actual travel time of each alternative path. Ultimately, AR glasses select the alternative path with the shortest travel time as the processing route for expired and near-expiry goods. Not only does it take into account the static warehouse layout, but it can also optimize path selection based on dynamic environmental conditions (such as temporarily placed items, people walking around, and other obstacles) to ensure that the planned route is both safe and feasible, while maximizing processing efficiency and avoiding the congestion or detour problems that may be encountered with traditional fixed routes.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the processing route of the expired and near-expiry goods is displayed, and the target goods corresponding to the target goods number are superimposed and displayed in the field of view, specifically including: determining the target expired goods and target near-expiry goods among the target goods; dynamically guiding the processing route of the expired and near-expiry goods, and marking the target expired goods and the target near-expiry goods in different display styles in the field of view.

[0011] By employing this technical solution, AR glasses implement intelligent visual guidance and labeling capabilities. Specifically, they differentiate between expired and near-expiry items within a target product and label them using different display styles, enabling workers to clearly identify these two types of merchandise. Furthermore, dynamic routing guides are provided to workers in real time, providing clear and intuitive navigation instructions for handling expired and near-expiry products. This significantly improves operational efficiency and reduces the risk of operational errors.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the remaining shelf life of each commodity based on the current time, the production date and the shelf life, the method also includes: obtaining the selling price of each type of commodity on the shelf; predicting the expected sales volume of each type of commodity within a preset period of time based on historical commodity sales data; when the first expected sales volume of the first type of commodity is less than or equal to the first current inventory of the first type of commodity, inputting the first type, the first remaining shelf life of the first type of commodity, the first current inventory of the first type of commodity and holiday information into a preset discount prediction model to obtain the first optimal discount strength of the first type of commodity; when the second expected sales volume of the second type of commodity is greater than the second current inventory of the second type of commodity, determining the second optimal discount strength of the second type of commodity based on the second remaining shelf life of the second type of commodity and the preset discount rule table; and displaying the first optimal discount strength or the second discount strength within the preset range of each commodity.

[0013] By adopting the above technical solution, AR glasses analyze historical commodity sales data to predict expected sales, and adopt different discount strategies based on the comparative relationship between expected sales and current inventory levels. For commodities with expected sales lower than current inventory, AR glasses use a preset discount prediction model to comprehensively consider multiple dimensions such as commodity category, remaining shelf life, current inventory level, and holiday information to calculate the optimal discount level. For commodities with expected sales higher than current inventory levels, AR glasses determine the optimal discount level based on a preset discount rule table. This differentiated discount management strategy can not only speed up the sales turnover of expiring commodities, but also maximize the economic value of commodities. At the same time, the visual display function of AR glasses makes it easier for staff to adjust commodity price tags in a timely manner.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of displaying the first optimal discount strength or the second discount strength within a preset range for each product, the method also includes: obtaining temperature data and humidity data of each preset position on the shelf; based on the temperature data and the humidity data, calculating the suitability of the product in the first storage position; if the suitability is lower than the suitability threshold, determining the second storage location of the product; displaying the product and the second storage location to guide the user to move the product from the first storage position to the second storage position.

[0015] By adopting the above technical solution, AR glasses obtain temperature and humidity data from each preset location on the shelf and calculate the suitability of the product in the current primary storage location. When the suitability falls below the suitability threshold, AR glasses automatically recommend a more suitable secondary storage location and provide intuitive transfer instructions to staff. This intelligent storage management solution for products based on environmental parameters can not only prevent product deterioration caused by improper storage environment and extend the shelf life of products, but also make product transfer operations more accurate and convenient through the visual guidance of AR technology.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the remaining shelf life of each commodity based on the current time, the production date and the shelf life, the method also includes: inputting the historical sales speed, current inventory and remaining shelf life of each type of commodity into a preset squeeze risk calculation formula to obtain the backlog risk of each type of commodity; when the squeeze risk of the target type of commodity exceeds the preset risk threshold, triggering the allocation process of the target type of commodity to obtain the allocation plan of the target type of commodity, the allocation plan includes allocation commodities, allocation stores and allocation routes; displaying the allocation commodities and the allocation routes to guide users to allocate the allocation commodities to the allocation stores.

[0017] By adopting the above technical solutions, AR glasses comprehensively analyze key indicators such as the historical sales speed, current inventory level, and remaining shelf life of each type of goods to calculate the backlog risk of each type of goods. When the backlog risk of a certain type of goods exceeds the preset risk threshold, AR glasses automatically trigger the allocation process and generate a complete allocation plan that includes the allocated goods, allocation stores, and allocation routes. This proactive risk warning and allocation mechanism can effectively prevent product backlogs and expiration waste, optimize the inventory structure between stores, and through the visual display function of AR glasses, make allocation operations more intuitive and efficient, greatly improving the efficiency of inventory allocation between chain stores.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the preset squeeze risk calculation formula is: Where R represents the backlog risk, α represents the first weight coefficient, β represents the second weight coefficient, the sum of α and β is 1, I represents the current inventory, V represents the historical sales speed, t represents the remaining shelf life, T represents the characteristic time constant, and P represents the shelf life.

[0019] By employing this technical solution, the ratio of current inventory to historical sales velocity reflects the turnover of goods, while the exponential function reflects the nonlinear impact of remaining shelf life on overstocking risk. Furthermore, the pre-set squeeze risk calculation formula also factors in the total shelf life of goods. By adjusting the two weighting coefficients, α and β, the importance of different factors can be flexibly balanced. This mathematical model not only accurately assesses overstocking risk but also exhibits strong versatility and adjustability, allowing parameters to be appropriately adjusted based on the characteristics of different product categories, providing a scientific basis for inventory management decisions.

[0020] In a second aspect, an embodiment of the present application provides an AR glasses, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the AR glasses to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on AR glasses, the AR glasses are enabled to perform the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on AR glasses, the AR glasses execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] It is understandable that the AR glasses provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By adopting the above technical solution, AR glasses automatically obtain the product number, storage location, production date and shelf life of each product on the shelf, thereby calculating the remaining shelf life of each product and intelligently identifying expired and near-expiry products based on a preset time threshold. When a user issues a query instruction for expired and near-expiry products, AR glasses quickly locate the target product and determine the shortest processing route for expired and near-expiry products based on the target storage location. The AR glasses overlay the display in the field of view, intuitively guiding the staff and marking the products. This not only greatly improves the efficiency and accuracy of product shelf life management and avoids problems that are easy to miss during manual inspection, but also saves processing time through optimal path planning and reduces the labor intensity of staff.

[0025] 2. By employing the above-mentioned technical solution, AR glasses implement intelligent visual guidance and labeling capabilities. Specifically, they differentiate between expired and near-expiry items within a target product and label them using different display styles, enabling staff to clearly identify expired and near-expiry items. Furthermore, dynamic routing guides are provided to staff in real time, providing clear and intuitive navigation instructions. This significantly improves operational efficiency and reduces the risk of misoperation.

[0026] 3. By adopting the above technical solutions, AR glasses analyze historical commodity sales data to predict expected sales, and adopt different discount strategies based on the comparative relationship between expected sales and current inventory levels. For commodities with expected sales lower than current inventory, AR glasses use a preset discount prediction model to comprehensively consider multiple dimensions such as commodity category, remaining shelf life, current inventory level, and holiday information to calculate the optimal discount level. For commodities with expected sales higher than current inventory levels, AR glasses determine the optimal discount level based on a preset discount rule table. This differentiated discount management strategy can not only speed up the sales turnover of expiring commodities, but also maximize the economic value of commodities. At the same time, the visual display function of AR glasses facilitates staff to adjust commodity price tags in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of a method for intelligently tracking the shelf life of goods in an embodiment of the present application; Figure 2 This is another flow chart of the method for intelligently tracking the shelf life of goods in an embodiment of the present application; Figure 3 This is a schematic diagram of the physical device structure of the AR glasses in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular expressions "a", "an", "above", "the", and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations of one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0030] A large supermarket chain needs to manage the shelf life status of tens of thousands of products every day. Taking the fresh produce section as an example, at 8 a.m. every day, staff member Li Ming needs to check the shelf life of hundreds of vegetables, fruits, meats, and other products. Due to the wide variety of products and the large differences in the shelf life of different products (ranging from a few days to several months), manual inspection alone is prone to omissions. Especially during holiday promotions, product turnover speeds up and inventory levels increase dramatically, making it more likely that near-expiry products will be piled up and expired products will not be removed from the shelves in a timely manner. At the same time, different products have different storage conditions. If the storage environment is not appropriate (the temperature is too high or the humidity is not suitable), it may accelerate the deterioration of the product, resulting in a shortened actual shelf life. These problems not only affect the economic benefits of the supermarket, but may also endanger food safety, cause customer complaints, and damage the brand reputation.

[0031] A supermarket chain uses barcode scanning and a database management system to track product expiration dates. Staff member Zhang Hua scans product barcodes daily using a handheld PDA, and the database management system automatically records product information and alerts customers about expiring products. However, this presents numerous inconveniences in practice: First, product barcodes must be scanned one by one, which is time-consuming and labor-intensive. Second, when near-expiring products are discovered, staff members must plan routes through the numerous shelves, often resulting in repeated movements and reduced work efficiency. More importantly, during promotional periods, when certain products require price adjustments or allocation to other stores, staff members must repeatedly check the database management system against the actual products, making it easy for price tags to be updated untimely or for the product to be allocated incorrectly.

[0032] After the supermarket adopted AR glasses, employee Li Ming's workflow changed significantly. Every morning during his rounds, he wears AR glasses, which automatically scan the product labels on the shelves and display the shelf life of each item in real time. Expired items are marked in red, and those nearing their expiration date are marked in yellow, making them clear and eye-catching. When he needs to handle these products, the AR glasses automatically plan the shortest processing route and use the superimposed navigation arrows to guide him to quickly find the target products. For example, when handling near-expiry fruits in the fresh produce area, the AR glasses will centrally handle products from adjacent shelves to avoid repeated walking. At the same time, for near-expiry products that need to be discounted for promotion, the AR glasses will directly display recommended discount information in his field of view, allowing him to quickly update the price tags. This approach not only improves work efficiency but also significantly reduces omissions and errors.

[0033] The following describes the process of the method provided by this implementation in combination with the above scenarios. Figure 1 , which is a flow chart of the method for intelligently tracking the shelf life of goods in an embodiment of the present application.

[0034] S101. Obtain basic information of each product on the shelf, including product number, storage location, production date, and shelf life; Among them, AR glasses refer to smart wearable devices with augmented reality display functions; shelves refer to multi-layer display structures used to display and store goods; basic information refers to a set of key attribute data related to the goods; the product number refers to an alphanumeric combination code used to uniquely identify the goods; the storage location refers to the specific spatial coordinates of the goods on the shelf, including shelf number, number of layers, grid position and other information; the production date is used to indicate the production date of the goods; the shelf life is used to indicate the maximum period for which the goods maintain their quality.

[0035] Staff members wearing AR glasses perform this step while inspecting shelves. Specifically, AR glasses use a built-in camera to scan the barcode or QR code of each item on the shelf to obtain the product number, production date, and expiration date. AR glasses can also determine the storage location of each item through a positioning system.

[0036] For products without barcodes or QR codes, AR glasses can use image recognition technology to identify the relevant information printed on the product packaging to obtain the product number, production date, and expiration date. All the information obtained will be temporarily stored in the memory of the AR glasses for subsequent processing.

[0037] S102: Calculate the remaining shelf life of each product based on the current time, the production date, and the shelf life; Among them, the current moment is used to represent the system time when the AR glasses perform calculations; the remaining shelf life refers to the remaining time from the current moment to the expiration time of the product, usually in days.

[0038] AR glasses execute this step immediately after obtaining basic product information. Specifically, they first obtain the current time. Then, for each product, they add the production date and the expiration date to determine the expiration date. They then subtract the current time from the expiration date to determine the remaining shelf life. This calculation takes into account the difference in the number of days in different months to ensure accuracy. For shelf life periods in different units of measurement, AR glasses automatically convert the units.

[0039] S103: Determine the product whose remaining shelf life is less than or equal to a preset first time threshold as an expired product, and determine the product whose remaining shelf life is less than or equal to a preset second time threshold as an expiring product, where the preset first time threshold is less than the preset second time threshold; Among them, the preset first time threshold is the time standard for determining whether the product is expired, which is usually set to 0 days; the preset second time threshold is the time standard for determining whether the product is about to expire, which may be set to different values such as 7 days and 15 days according to different product categories; expired products refer to products that have exceeded their shelf life; near-expiry products refer to products that are about to reach their shelf life.

[0040] The AR glasses perform this step after completing the calculation of the remaining shelf life. Specifically, the AR glasses first read the preset first time threshold and the preset second time threshold from the configuration file, and then compare the remaining shelf life of each product with the two thresholds. If the remaining shelf life of the product is less than or equal to the preset first time threshold (such as 0 days), the product is marked as an expired product; if the remaining shelf life of the product is greater than the preset first time threshold but less than or equal to the preset second time threshold (such as 7 days), the product is marked as an expiring product. For different categories of goods, AR glasses will automatically adjust the preset second time threshold according to their characteristics. For example, fresh products may use a shorter expiring judgment threshold, while dry goods use a longer expiring judgment threshold.

[0041] S104: In response to the user's query instruction for the expired product and the near-expiry product, determine the target product number and target storage location; Among them, the query instruction refers to the information retrieval request issued by the user through voice, gesture or AR glasses touch panel; the target product number refers to the unique identifier set of expired or near-expiring products that need to be processed; the target storage location refers to the specific spatial coordinate set of these products to be processed on the shelf; the user refers to the staff wearing AR glasses.

[0042] AR glasses execute this step when they recognize a user query. Specifically, the AR glasses first determine the user's query intent, including whether they are looking for all expired items, all near-expiry items, or both. They then filter eligible items from memory and create an ordered list of item numbers and storage locations. If the query results are numerous, the AR glasses prioritize the items based on the urgency of their remaining shelf life.

[0043] S105. Determine a shortest processing route for expired or near-expired goods based on the target storage location; Among them, the processing route for expired and near-expiry goods refers to the optimal path to access the target storage locations of all target goods; the shortest time refers to the route plan that takes the least time to complete the processing of all goods after considering various practical factors.

[0044] AR glasses execute this step after obtaining the target storage location of the target product. Specifically, first, AR glasses establish a path network diagram based on all the acquired target storage locations, and use each target storage location as a passing node; then, AR glasses consider the actual layout of the warehouse and mark the inaccessible areas and the locations of obstacles that must be bypassed in the path network diagram; then, AR glasses combine the average walking speed of the staff and the standard time for processing goods at each target storage location to calculate the actual travel time between any two points; after that, AR glasses use the improved nearest neighbor algorithm to try from multiple possible starting points, and select the next target storage location with the least time consumption as the access point in turn, while avoiding all obstacle areas until all target storage locations are visited; finally, AR glasses compare multiple route plans obtained from different starting points, and select the one with the least total time consumption as the final expired and near-expiry product processing route. This expired and near-expiry product processing route not only ensures the rationality of the access sequence, but also fully considers the various limiting factors of on-site operations, and can help staff complete the processing of expired and near-expiry products in the most efficient way.

[0045] Optionally, under normal circumstances, determining the shortest processing route for expired and near-expiry goods based on the target storage location can be achieved in the following ways, which are not limited here: determining multiple alternative paths based on the layout information of the warehouse and the target storage location; obtaining image data of the warehouse; determining obstacle information on each alternative path based on the image data; determining the time for each alternative path based on the obstacle information; and determining the alternative path with the shortest time as the processing route for expired and near-expiry goods.

[0046] First, AR glasses build a digital road network model based on the floor plan of the warehouse (or shopping mall), marking each target storage location as a must-pass point. Then, AR glasses use an improved traveling salesman problem algorithm, taking into account practical factors such as the width of the aisles between shelves, the difficulty of turning corners, and the activities of other customers and staff, to assign a reasonable travel time weight to each path. Through a dynamic programming algorithm, AR glasses calculate the complete processing route with the shortest total time as the processing route for expired and near-expiry goods. This expired and near-expiry goods processing route not only takes into account spatial distance, but also optimizes operational efficiency. For example, the processing of goods on adjacent shelves is arranged at similar times to avoid frequent round trips.

[0047] S106: Display the processing route of the expired or near-expiry product, and overlay the target product corresponding to the target product number in the field of view.

[0048] Among them, overlay display refers to the display method of using AR technology to overlay virtual information on the real scene; field of view refers to the actual scene range observed by the user through AR glasses; target goods refer to the entities of expired or near-expiry goods that need to be processed; display style refers to the visual effect scheme used to mark and highlight the target goods.

[0049] AR glasses perform this step after determining the processing route for expired and near-expiry goods. Specifically, AR glasses first draw translucent navigation lines in the user's field of view, using different colors to distinguish completed sections and sections to be traveled. The navigation lines will adjust the display position and direction in real time as the user's head turns. When the target product appears in the user's field of view, AR glasses will automatically draw a striking marking frame around the product. Expired products will be marked with a red frame, and near-expiry products will be marked with a yellow frame. The key information of the product will be displayed in the marking frame, such as the remaining shelf life, product number, etc. AR glasses will also indicate the direction of the next processing target through dynamic arrows. When the user completes the processing of a certain product, he can confirm it through voice or gestures, and the AR glasses will automatically update the route display and product marking status.

[0050] Optionally, under normal circumstances, displaying the processing route of expired and near-expiry goods and superimposing the target goods corresponding to the target product number in the field of view can be achieved in the following ways, which are not limited here: determining the target expired goods and target near-expiry goods among the target goods; dynamically guiding the processing route of expired and near-expiry goods, and marking the target expired goods and the target near-expiry goods in different display styles in the field of view.

[0051] By adopting the above technical solution, AR glasses automatically obtain the product number, storage location, production date and shelf life of each product on the shelf, thereby calculating the remaining shelf life of each product and intelligently identifying expired and near-expiry products based on a preset time threshold. When a user issues a query instruction for expired and near-expiry products, AR glasses quickly locate the target product and determine the shortest processing route for expired and near-expiry products based on the target storage location. The AR glasses overlay the display in the field of view, intuitively guiding the staff on the path and marking the products. This not only greatly improves the efficiency and accuracy of product shelf life management and avoids problems that are easily missed during manual inspections, but also saves processing time through optimal path planning and reduces the labor intensity of staff.

[0052] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the method for intelligently tracking the shelf life of goods in an embodiment of the present application.

[0053] After step S102, the following steps may be performed or not performed, which is not limited here: S201, obtaining the selling price of each type of commodity on the shelf; Among them, shelves refer to multi-layer display structures used to display and store goods; product categories refer to classified collections of goods with the same attributes and characteristics, such as beverages, snacks, etc.; selling prices refer to the current retail prices of each type of goods, including original prices and promotional prices.

[0054] AR glasses perform this step after calculating the product's shelf life. Specifically, AR glasses obtain the current selling price of each product category by scanning electronic price tags on the shelves or synchronizing data with the store's price management system. For different specifications and packaging of products in the same category, AR glasses record their respective prices. Furthermore, AR glasses mark products on sale and record their promotional price and promotional period. All price information is stored in the AR glasses' memory as structured data, providing data support for subsequent discount analysis.

[0055] S202. Based on historical commodity sales data, predict the expected sales volume of each type of commodity within a preset time period; wherein, historical commodity sales data refers to the sales records of commodities within a certain period in the past, including information such as sales quantity and sales time; the preset time period is used to represent the time span of the prediction, which is usually a fixed period such as 7 days or 30 days; expected sales volume refers to the sales volume within the preset time period predicted through data analysis.

[0056] AR glasses perform this step after obtaining the selling price of each type of commodity. Specifically, first, AR glasses obtain the recent (such as the last 3 months) historical commodity sales data of each commodity from the mall sales system, including information such as average daily sales and holiday sales fluctuations. Then, AR glasses use a time series analysis model, combined with multi-dimensional features such as commodity category, seasonal factors, and promotional activities, to predict the sales volume of each commodity within a preset period of time (such as the next 7 days). The prediction process will take into account factors such as the seasonal characteristics of the commodity, promotional effects, and market trends, and continuously optimize the prediction accuracy through machine learning algorithms. The prediction results will serve as an important basis for the formulation of subsequent discount strategies.

[0057] S203. When the first expected sales volume of the first category of goods is less than or equal to the first current inventory volume of the first category of goods, the first category, the first remaining shelf life of the first category of goods, the first current inventory volume of the first category of goods and holiday information are input into a preset discount prediction model to obtain a first optimal discount intensity for the first category of goods; wherein, the first category refers to a category of goods whose expected sales volume is insufficient to absorb the current inventory volume; the first expected sales volume refers to the expected sales volume of the first category of goods within a preset period of time; the first current inventory volume is used to represent the actual on-shelf quantity of the first category of goods; holiday information refers to vacation arrangements and holiday activity information within a preset period of time; the preset discount prediction model refers to a machine learning model used to calculate the optimal discount intensity; the first optimal discount intensity refers to the price reduction ratio that can maximize the sales revenue of the first category of goods.

[0058] AR glasses execute this step when they find that the expected sales volume of a certain type of goods is lower than the current inventory. Specifically, first, AR glasses standardize data such as product category, remaining shelf life, current inventory, and collect holiday information within a preset period of time. Then, AR glasses input this data into a trained preset discount prediction model (such as a random forest or deep neural network model). The preset discount prediction model will comprehensively consider factors such as product characteristics, inventory pressure, time constraints, and holiday effects, and output a discount ratio that can maximize sales within the shelf life while maintaining reasonable profits. The prediction results of the preset discount prediction model will be continuously optimized and adjusted based on actual sales results.

[0059] S204: When the second expected sales volume of the second category of goods is greater than the second current inventory of the second category of goods, determine a second optimal discount for the second category of goods based on the second remaining shelf life of the second category of goods and the preset discount rule table; Among them, the second category refers to the category of goods whose expected sales exceed the current inventory; the preset discount rule table refers to a standardized discount list set according to the remaining shelf life; the second optimal discount intensity refers to the price adjustment ratio determined based on the preset discount rule table; the preset discount rule table is a comparison table that maps the remaining shelf life range to the corresponding discount intensity.

[0060] AR glasses execute this step when they find that the expected sales volume of a certain type of goods is higher than the current inventory. Specifically, since there is a risk of out-of-stock for such goods, there is no need to adopt a complex preset discount prediction model. AR glasses directly query the preset discount rule table to determine the discount strength. The preset discount rule table usually sets different discount ranges according to the length of the remaining shelf life. For example, a 30% discount may be given for a remaining shelf life of less than 3 days, and a 20% discount may be given for 3-7 days. AR glasses will match the corresponding discount strength from the preset discount rule table based on the remaining shelf life of the second category of goods. This simple rule-based method can respond quickly and ensure that expiring goods are promoted and cleared in a timely manner.

[0061] S205: Displaying the first optimal discount level or the second optimal discount level within a preset range for each product; Among them, the preset range refers to the virtual display area divided by AR glasses for each product in the field of view; display refers to the visualization process of superimposing information on the physical object through AR technology; discount intensity refers to the percentage of price adjustment, such as "30% off", "15% off", etc.; the virtual display area is usually located in a fixed position directly above or on the side of the product.

[0062] AR glasses perform this step immediately after determining the discount level for a product. Specifically, AR glasses first determine the precise location of each product in the user's field of view and then generate a translucent virtual label within a preset range of the product. The virtual label clearly displays the discount information, including key information such as the discount level, promotional price, and remaining shelf life. AR glasses use different colors to identify different discount levels, such as red for a large discount and yellow for a medium discount. These virtual labels adjust their position and orientation in real time as the user's perspective changes, ensuring that the information is always clearly visible.

[0063] S206, obtaining temperature data and humidity data of each preset position on the shelf; Among them, the preset position refers to the pre-determined environmental monitoring point on the shelf; the temperature data represents the real-time measurement value of the ambient temperature in degrees Celsius; the humidity data represents the real-time measurement value of the ambient relative humidity, expressed as a percentage; the environmental monitoring points are usually distributed at different levels and areas of the shelf to ensure the comprehensiveness of the monitoring data.

[0064] Specifically, AR glasses interact with a network of IoT sensors installed on the shelves in real time, acquiring temperature and humidity data at pre-set locations. These IoT sensors, placed at key locations on the shelves, monitor changes in local environmental parameters in real time. AR glasses also record the time of data collection and automatically screen and correct any abnormal data, ensuring the accuracy and reliability of environmental data.

[0065] S207: Calculate the suitability of the product in the first storage location based on the temperature data and the humidity data; Among them, the first storage location is used to indicate the current display location of the product; suitability refers to the degree of matching between environmental conditions and product storage requirements, usually expressed as a value between 0 and 1; product storage requirements refer to the suitable range of temperature and humidity for different products.

[0066] AR glasses perform this step immediately after obtaining environmental data. Specifically, first, AR glasses retrieve the optimal storage condition parameters for each type of product from the database, including the ideal temperature range and suitable humidity range. Then, AR glasses compare the real-time monitored environmental data with these optimal storage condition parameters and calculate a comprehensive suitability score through weighted calculation. The calculation process takes into account the impact of temperature deviation and humidity deviation, as well as the sensitivity of different products to environmental conditions. For example, for fresh products, the temperature factor may have a higher weight; for packaged foods, the humidity factor may be more important.

[0067] S208: If the suitability is lower than the suitability threshold, determine a second storage location for the product; Among them, the suitability threshold represents the minimum standard value acceptable for the commodity storage environment; the second storage location refers to a new location recommended by the system that is more suitable for storing commodities; the determination process includes steps such as location search, environmental assessment, and location optimization; the storage environment includes environmental factors such as temperature and humidity that affect commodity quality.

[0068] AR glasses execute this step when they discover that the environment is not suitable for the product in the first storage location. Specifically, first, AR glasses scan all candidate storage locations in the entire shelf area and obtain the real-time environmental parameters of these candidate storage locations. Then, based on the product storage requirements, AR glasses will score the suitability of each candidate storage location. During the screening process, not only environmental suitability is considered, but also factors such as space utilization efficiency, product classification management requirements, and replenishment operation convenience. Finally, AR glasses will select the candidate storage location with the best overall conditions from the highest-scoring candidate storage location as the second storage location.

[0069] S209: Display the product and the second storage location to guide the user to move the product from the first storage location to the second storage location.

[0070] Among them, display refers to the process of visual guidance through AR technology; guidance refers to providing users with clear instructions on warehouse transfer operations; movement refers to the process of transferring goods from one location (first storage location) to another location (second storage location); user refers to the staff who performs the warehouse transfer operation.

[0071] AR glasses execute this step immediately after determining the new storage location. Specifically, AR glasses highlight the product to be moved in the user's field of view with a prominent visual marker and indicate the second storage location with an arrow or path line. The moving path takes into account shelf layout and aisle width to provide the most convenient transportation route. AR glasses also display relevant instructions for the moving operation, such as the weight and fragility of the product. When the user completes the move, AR glasses automatically update the product's location information and record an environmental improvement log.

[0072] S210: Input the historical sales rate, current inventory, and remaining shelf life of each category of goods into a preset squeeze risk calculation formula to obtain the backlog risk of each category of goods; Among them, the historical sales speed refers to the average daily sales volume of the goods; the current inventory refers to the number of goods actually on the shelves; the backlog risk refers to the probability assessment value that the goods may not be sold within the shelf life; the preset squeeze risk calculation formula is a mathematical model that comprehensively considers multiple factors; the historical sales speed is usually the average value of the last 30 days.

[0073] Specifically, AR glasses first collect historical sales data for each category of goods and calculate a standardized historical sales velocity. Then, AR glasses substitute these historical sales velocity, along with key indicators such as current inventory levels and remaining shelf life, into a preset squeeze risk calculation formula. This preset squeeze risk formula quantitatively assesses the backlog risk of each category of goods through an exponential function and linear combination. The calculation process assigns different weights to different indicators. For example, for near-expiry goods, the weight of remaining shelf life will be increased accordingly. AR glasses will standardize the calculated squeeze risk value to the range of 0-1 to facilitate subsequent risk management decisions.

[0074] The default squeeze risk calculation formula is: Where R represents the backlog risk, α represents the first weight coefficient, β represents the second weight coefficient, the sum of α and β is 1, I represents the current inventory, V represents the historical sales speed, t represents the remaining shelf life, T represents the characteristic time constant, and P represents the shelf life.

[0075] S211. When the squeeze risk of a target product category exceeds a preset risk threshold, triggering an allocation process for the target product category, obtaining an allocation plan for the target product category, the allocation plan including allocated products, allocated stores, and allocated routes; Among them, the preset risk threshold refers to the risk critical value that triggers the allocation operation; the allocation process refers to the standardized operation process for transferring goods between different stores; the allocation plan is used to represent the complete goods transfer execution plan; the allocation store refers to the target sales outlet that receives the transferred goods; the allocation route refers to the optimal path planning for the transportation of goods.

[0076] AR glasses execute this step when they find that the risk of product backlog is too high. Specifically, first, AR glasses query the sales data and inventory status of other stores in the chain store network, and select stores with good sales and low inventory as potential allocation targets. Then, AR glasses will consider multiple factors to formulate an allocation plan: (1) determine the most suitable quantity of goods for allocation, which should not only alleviate the backlog pressure of the current store, but also ensure that the transferred store can sell out the goods within a reasonable time; (2) select the most suitable allocation store, taking into account the sales capacity, inventory capacity and transportation distance of the target store; (3) plan the optimal allocation route, taking into account factors such as traffic conditions, transportation time and cost. The entire plan will be optimized and calculated by AR glasses to ensure the economy and feasibility of the allocation operation.

[0077] S212: Display the allocated product and the allocation route to guide the user to allocate the allocated product to the allocation store.

[0078] AR glasses execute this step immediately after determining the allocation plan. Specifically, AR glasses mark the goods that need to be allocated in the staff's field of view, and use eye-catching visual effects (such as flashing borders or marks of specific colors) to highlight the location of these goods. At the same time, the allocation quantity and packaging requirements of each item are displayed. AR glasses use the AR navigation function to provide staff with step-by-step operation instructions: first, guide the completion of the sorting and packing of the goods, and then display the optimal transportation route to guide the loading of the goods. Throughout the process, AR glasses will update the operation progress in real time to ensure that the allocation work is carried out in an orderly manner.

[0079] The following describes the AR glasses in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of the physical device structure of the AR glasses in an embodiment of the present application.

[0080] It should be noted that Figure 3 The structure of the AR glasses shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0081] like Figure 3As shown, the AR glasses include a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 303. The CPU 301, ROM 302 and RAM 303 are connected to each other via a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0082] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a push button switch, and the like; an output section 307 including a liquid crystal display (LCD), an audio output device, an indicator light, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read therefrom can be installed into the storage section 308 as needed.

[0083] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the various functions defined in the present invention are performed.

[0084] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0086] Specifically, the AR glasses of this embodiment include a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the intelligent tracking method for the shelf life of goods provided in the above embodiment is implemented.

[0087] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the AR glasses described in the above embodiments, or may exist independently and not incorporated into the AR glasses. The storage medium carries one or more computer programs, which, when executed by a processor of the AR glasses, enable the AR glasses to implement the method for intelligently tracking product shelf life as provided in the above embodiments.

[0088] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0089] As used in the above embodiments, the term “when…” may be interpreted to mean “if…” or “after…” or “in response to determining…” or “in response to detecting…”, depending on the context. Similarly, the phrases “upon determining…” or “if (stated condition or event) is detected” may be interpreted to mean “if determining…” or “in response to determining…” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0090] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for intelligently tracking the shelf life of a commodity, characterized in that: Applied to AR glasses, the method includes: Obtain basic information about each product on the shelf, including product number, storage location, production date, and expiration date; Calculate the remaining shelf life of each product based on the current time, the production date, and the shelf life; Determine the product whose remaining shelf life is less than or equal to the first preset time threshold as an expired product, and determine the product whose remaining shelf life is less than or equal to the second preset time threshold as an expiring product, where the first preset time threshold is less than the second preset time threshold; In response to a user's query instruction for the expired product and the near-expiry product, determine the target product number and target storage location; and determine the shortest processing route for the expired or near-expiry product based on the target storage location; The processing route of the expired or near-expiry goods is displayed, and the target goods corresponding to the target goods numbers are superimposed and displayed in the field of view.

2. The method according to claim 1, characterized in that Determining the shortest processing route for expired or near-expired goods based on the target storage location specifically includes: Determining multiple alternative routes based on warehouse layout information and the target storage location; acquiring image data of the warehouse; Determining obstacle information on each alternative path based on the image data; Determining the time required for each of the alternative paths based on the obstacle information; The alternative path with the shortest time is determined as the route for processing expired or near-expiry goods.

3. The method according to claim 1, characterized in that The display of the processing route of the expired or near-expired goods and the superimposed display of the target goods corresponding to the target goods number in the field of view specifically include: Determining target expired products and target near-expiry products among the target products; The dynamic path guides the processing route of the expired and near-expiry commodities, and respectively marks the target expired commodities and the target near-expiry commodities in the field of view in different display styles.

4. The method according to claim 1, wherein After the step of calculating the remaining shelf life of each product based on the current time, the production date, and the shelf life, the method further includes: Obtain the selling price of each type of commodity on the shelf; Based on historical product sales data, predict the expected sales volume of each product category within a preset time period; When a first expected sales volume of a first category of goods is less than or equal to a first current inventory of the first category of goods, the first category, a first remaining shelf life of the first category of goods, a first current inventory of the first category of goods, and holiday information are input into a preset discount prediction model to obtain a first optimal discount amount for the first category of goods; When a second expected sales volume of the second category of goods is greater than a second current inventory of the second category of goods, determining a second optimal discount amount for the second category of goods based on a second remaining shelf life of the second category of goods and a preset discount rule table; The first optimal discount level or the second discount level is displayed within a preset range for each of the commodities.

5. The method according to claim 4, characterized in that After the step of displaying the first optimal discount level or the second optimal discount level within a preset range for each commodity, the method further includes: Acquiring temperature data and humidity data of each preset location on the shelf; calculating the suitability of the product in the first storage location based on the temperature data and the humidity data; If the suitability is lower than the suitability threshold, determining a second storage location for the product; The product and the second storage location are displayed to guide the user to move the product from the first storage location to the second storage location.

6. The method according to claim 1, characterized in that After the step of calculating the remaining shelf life of each product based on the current time, the production date, and the shelf life, the method further includes: Inputting the historical sales velocity, current inventory level, and remaining shelf life of each type of commodity into a preset squeeze risk calculation formula to obtain the overstock risk of each type of commodity; When the squeeze risk of a target category of goods exceeds a preset risk threshold, the allocation process of the target category of goods is triggered, and an allocation plan for the target category of goods is obtained, the allocation plan including allocation goods, allocation stores, and allocation routes; the allocation goods and the allocation routes are displayed to guide users to allocate the allocation goods to the allocation stores.

7. The method according to claim 6, characterized in that The preset squeeze risk calculation formula is: Among them, R represents the backlog risk, α represents the first weight coefficient, β represents the second weight coefficient, the sum of α and β is 1, I represents the current inventory level, V represents the historical sales speed, t represents the remaining shelf life, T represents the characteristic time constant, and P represents the shelf life.

8. AR glasses, characterized in that: The AR glasses include: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the AR glasses to perform the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the AR glasses, the AR glasses are caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on the AR glasses, the AR glasses are caused to perform the method according to any one of claims 1 to 7.

Images