Automatic vending system based on pressure sensor

Through flexible pressure sensor array and dynamic pressure distribution mapping technology, the identification accuracy and cost-effectiveness of traditional vending machines are solved, accurate identification of goods and inventory management are achieved, and the intelligence and efficiency of the retail environment are improved.

CN119028058AActive Publication Date: 2024-11-26BEIJING MUJIA TECH LTD

Patent Information

Application Number
CN202410977977.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-26
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

Traditional vending machines rely on RFID, visual recognition or weighing sensing technology to have problems with identification accuracy, real-timeness and cost-effectiveness, especially in an environment where there are many types of products, they cannot accurately identify specific types and quantities of products.

Method used

Using flexible pressure sensor array and dynamic pressure distribution mapping technology, the product pick-up and placement action is identified through adaptive pressure baseline and dynamic change threshold, combined with machine learning to identify product name, quantity and pick-up and placement time, and realize automatic price calculation and inventory management, based on Historical data predicts replenishment demand.

Benefits of technology

It realizes accurate identification of product pick-up and placement actions, automatic judgment of type and quantity, real-time total price calculation, real-time update of inventory records and intelligent replenishment prediction, which improves customer experience and operational efficiency, reduces operating costs, and creates high efficiency and low efficiency. Cost retail environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028058A_ABST
    Figure CN119028058A_ABST
Patent Text Reader

Abstract

The invention discloses an automatic vending system based on pressure sensors, and relates to the technical field of Internet of Things, comprising: deploying a flexible pressure sensor array on a shelf, and connecting the flexible pressure sensor array with a control unit; the control unit identifies the taking and placing actions of the commodities based on the change of the flexible pressure sensor array; identifying the names, the number and the pick-and-place time of the commodities through a dynamic pressure distribution mapping technology; automatically calculating the total price of the commodity according to the commodity identification result; after the customer confirms and completes payment, the control unit updates an inventory record; on the basis of historical sales data, a replenishment demand is predicted, and a replenishment list is automatically generated; according to the scheme, the flexible pressure sensor array and the advanced data analysis technology are utilized, accurate recognition and automatic selling management of commodities are achieved, the shopping experience of customers is remarkably improved, inventory control is optimized, the operation cost is effectively reduced, and transformation and upgrading of the retail industry to the intelligent and unmanned direction are promoted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an automatic vending system based on a pressure sensor. Background Art

[0002] In the field of vending systems, with the rapid development of Internet of Things technology, traditional mechanical vending machines are gradually transforming towards intelligence, aiming to improve user experience and operational efficiency. At present, most common vending machines on the market rely on RFID (radio frequency identification), visual recognition or weighing sensor technology to monitor the access of goods. However, each of these methods has certain limitations. The cost of RFID tags and their potential pollution to the environment cannot be ignored; although visual recognition technology can provide rich information, its accuracy and processing speed are greatly affected by lighting conditions, obstructions and the complexity of product packaging; and traditional weighing sensors can only detect weight changes and cannot accurately identify specific product types and quantities, which seems to be inadequate in a sales environment with a wide variety of products. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a pressure sensor-based vending system that solves the limitations of traditional vision and RFID technology-based vending systems in terms of commodity identification accuracy, real-time performance, and cost-effectiveness, as well as improves the accuracy of inventory management and replenishment forecasting.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides an automatic vending system based on a pressure sensor, which includes a sensor deployment module for deploying a flexible pressure sensor array on a shelf and connecting to a control unit;

[0007] A pick-and-place action recognition module, used to recognize the pick-and-place action of the commodity based on the changes of the flexible pressure sensor array in the control unit;

[0008] The commodity identification module is used to identify the commodity name, quantity and pick-up and placement time through dynamic pressure distribution mapping technology;

[0009] The price calculation module is used to automatically calculate the total price of the product based on the product identification results;

[0010] The inventory management module is used to control the control unit to update the inventory record after the customer confirms and completes the payment;

[0011] The intelligent replenishment forecasting module is used to predict replenishment needs based on historical sales data and automatically generate replenishment lists.

[0012] As a preferred solution of the automatic vending system based on the pressure sensor of the present invention, wherein: the adaptive pressure baseline means that when there is no pick-up and place action on the shelf, the control unit continuously reads and records the pressure values ​​at multiple time points, uses an algorithm to remove abnormal values, calculates the adaptive pressure baseline B(t), and stores it in the control unit for comparative analysis of pressure changes;

[0013] The adaptive pressure baseline B(t) is expressed as,

[0014] B(t)=μ+φ(P(t-1)-B(t-1))+θ∈(t-1)+∈(t);

[0015] Among them, μ represents the intercept term, φ represents the autoregressive coefficient, θ represents the moving average coefficient, ∈(t) represents the white noise error term, P(t-1) represents the pressure value at the previous time, B(t-1) represents the baseline value at the previous time, and t represents time.

[0016] As a preferred solution of the automatic vending system based on pressure sensors of the present invention, the control unit identifies the picking and placing action of the commodity based on the change of the flexible pressure sensor array, and the specific steps are as follows:

[0017] Based on the weight of the product, set the dynamic change threshold B d (t), expressed as,

[0018]

[0019] Among them, B d (t) represents the dynamic change threshold at time point t, α represents the adjustment parameter of the average weight of the commodity for the dynamic change threshold, W a represents the average weight of the goods on the shelf, β represents the adjustment parameter of the historical pressure change volatility to the dynamic change threshold, m represents the number of historical data points, and w k represents the weight of the kth historical time point, k represents the historical time point, P(tk) represents the pressure value at the time point tk, and B(tk) represents the baseline value at the time point tk;

[0020] The control unit receives a continuous data stream from the flexible pressure sensor array and processes the sensor data in real time;

[0021] The difference between the processed sensor pressure value P(t) and the adaptive pressure baseline B(t) and the dynamic change threshold B d (t) compare and identify the pick-and-place actions;

[0022] When |P(t)-B(t)|>B d(t), it indicates that a pick-and-place action occurs, and the pick-and-place action is marked;

[0023] When |P(t)-B(t|≤B d (t) indicates that there is no pick-and-place action.

[0024] As a preferred solution of the automatic vending system based on pressure sensor of the present invention, the steps of building a commodity pressure feature library are as follows:

[0025] List all products planned to be put on the shelves and assign a unique coding identification to each product;

[0026] The control unit records the pressure change data of the sensor before and after the product is placed;

[0027] Use the scikit-learn library in Python for feature engineering and machine learning to extract the feature vector f from the pressure change data i ;

[0028] The feature vectors of each commodity are sorted and stored in the database, associated with the commodity code, and a commodity pressure feature database K is formed, where K contains the jth feature vector f of the commodity ij and product code c i .

[0029] As a preferred solution of the automatic vending system based on pressure sensors of the present invention, the product name is identified by dynamic pressure distribution mapping technology, and the specific steps are as follows:

[0030] The control unit receives the real-time data stream P(t) from the sensor and uses P(t) and the adaptive pressure baseline B(t) to calculate the dynamic pressure distribution D(t), which is expressed as,

[0031] D(t) = P(t) - B(t);

[0032] Based on the dynamic pressure distribution D(t) and the commodity pressure feature library K, the commodity identification function is designed, which is expressed as:

[0033]

[0034] Among them, Ω(D(t),K) represents the product recognition function, the output is the product code, d j (t) represents the jth feature extracted from D(t), α j represents the jth feature weight, β j Represents the similarity decay rate;

[0035] Based on the identified product code c i , determine the name of the product to be taken.

[0036] As a preferred solution of the automatic vending system based on pressure sensors of the present invention, the specific steps of identifying the quantity of goods and the time of picking and placing goods are as follows:

[0037] Divide D(t) into multiple local areas. For each divided area, detect the local maximum pressure, analyze the distribution characteristics around each local maximum, and calculate the number of commodities in the area based on the pressure distribution characteristics of each area and the matching results with the commodity feature library.

[0038] Based on the marked pick-and-place action, the time series analysis method is used to determine when the product is taken out by detecting the mutation point in the pressure signal and identifying the pick-and-place time;

[0039] If the product recognition fails, it will be re-recognized in the product pressure feature library.

[0040] As a preferred solution of the automatic vending system based on the pressure sensor of the present invention, the total price of the commodity is automatically calculated according to the commodity recognition result. The specific steps are as follows:

[0041] Use the product name as a keyword to find the corresponding product information in the product database;

[0042] If the product information search fails, search again in the product database;

[0043] Whenever an item is successfully identified and confirmed to be added to the shopping cart, the price of the item is immediately read from the item database and added to the current shopping cart total amount to automatically calculate the total price of the item.

[0044] As a preferred solution of the automatic vending system based on pressure sensors of the present invention, the customer confirms the product and the total price, and the specific steps are as follows:

[0045] The electronic display screen displays the list of goods purchased by customers and the cumulative total price in real time;

[0046] If the customer puts the product back on the shelf, the total price of the product will be updated immediately, and the control unit will update the product information;

[0047] If a customer adds product types and quantities, the displayed total price is updated immediately, allowing the customer to know the status of the shopping cart at any time;

[0048] Use encryption technology to protect customers' shopping records and personal information;

[0049] After the customer confirms that the product and total price are correct, multiple payment methods are provided for the customer to choose from and complete the payment.

[0050] As a preferred solution of the automatic vending system based on the pressure sensor of the present invention, after the customer completes the payment, the control unit updates the inventory record, and the specific steps are as follows:

[0051] After the payment is completed, the system communicates with the payment platform through the API interface to verify whether the payment status is successful;

[0052] When the payment verification is not completed, the control unit reminds the customer to confirm the payment information again and pay again;

[0053] After receiving the confirmation signal of successful payment, the control unit immediately starts the inventory adjustment program and updates the inventory record.

[0054] As a preferred solution of the automatic vending system based on pressure sensors of the present invention, the following specific steps are taken to predict replenishment demand and automatically generate a replenishment list based on historical sales data:

[0055] Analyze historical sales data to identify hot-selling products;

[0056] Use time series models to predict future sales based on past sales data of popular products;

[0057] Monitor inventory levels in real time and identify items that are below safety stock;

[0058] Calculate the replenishment requirements for each product based on the forecasted sales volume and current inventory status;

[0059] Automatically generate a replenishment list, listing each product's ID, predicted demand, recommended replenishment quantity, and priority.

[0060] The beneficial effects of the present invention are as follows: by deploying flexible pressure sensor arrays and innovative dynamic pressure distribution mapping technology on the shelves, the present invention realizes accurate identification of commodity picking and placing actions, automatic judgment of type and quantity, instant total price calculation, real-time updating of inventory records, and intelligent replenishment prediction based on historical data analysis. This series of steps not only significantly improves the customer's shopping experience, reduces waiting time, and ensures sufficient goods, but also greatly optimizes the retailer's inventory management, reduces operating costs, and improves overall operating efficiency and supply chain response speed, ultimately achieving a highly intelligent, efficient, and low-cost retail environment, creating a win-win situation for customers and merchants. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0062] Figure 1 This is a flow chart of the automatic vending system based on pressure sensors in Example 1.

[0063] Figure 2 This is the logic diagram of automatic purchase by customers in Example 1. DETAILED DESCRIPTION

[0064] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0066] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0067] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an automatic vending system based on a pressure sensor, comprising the following steps:

[0068] S1. Deploy the flexible pressure sensor array on the shelf and connect it to the control unit. The specific steps are as follows:

[0069] Use flexible pressure sensors with high sensitivity and wide range to ensure accurate capture of weight changes of goods while having good durability and environmental adaptability;

[0070] Design the layout of the sensor array based on the size of the shelf and the density of the goods placed, ensuring that each product placement area has sufficient sensor coverage to achieve accurate pressure change detection;

[0071] Securely mount the sensor array on the shelf, using dedicated fixing materials or structures to ensure that the sensor is not easily displaced or damaged during daily use;

[0072] Use dedicated signal cables or wireless modules to connect the sensor array to the central control unit to ensure the stability and security of data transmission;

[0073] Configure the communication parameters of the sensor array on the control unit, such as baud rate, address, data format, etc., to ensure that the sensor data can be correctly parsed and processed.

[0074] It should be noted that by deploying flexible pressure sensor arrays on the shelves, the status of goods on the shelves can be monitored in real time, including the picking and placing of goods. This deployment enables the system to sense the slight movement of goods, thereby capturing customers' purchasing behavior in a timely manner and recording the dynamic changes of goods without human intervention, thereby improving the accuracy of product tracking and reducing human errors. At the same time, it also provides basic data support for subsequent product identification and inventory management.

[0075] S2. The control unit identifies the picking and placing action of the commodity based on the changes in the flexible pressure sensor array. The specific steps are as follows:

[0076] S2.1, Adaptive pressure baseline means that when there is no pick-up and place action on the shelf, the control unit continuously reads and records the pressure values ​​at multiple time points, uses an algorithm to remove abnormal values, calculates the adaptive pressure baseline B(t), and stores it in the control unit for comparative analysis of pressure changes;

[0077] The adaptive pressure baseline B(t) is expressed as,

[0078] B(t)=μ+φ(P(t-1)-B(t-1))+θ∈(t-1)+∈(t);

[0079] Among them, μ represents the intercept term, which represents the standard value of the pressure baseline when there is no external influence. This value usually reflects the average output of the sensor when the shelf is empty or in a stable state, which can be understood as the static bias of the sensor. φ represents the autoregressive coefficient, which is used to capture the autocorrelation of time series data. θ represents the moving average coefficient, which is used to reflect the impact of the error of past observations on the current baseline. ∈(t) represents the white noise error term, which represents the unpredictable instantaneous disturbance or measurement error. P(t-1) represents the pressure value at the previous time, B(t-1) represents the baseline value at the previous time, and t represents time.

[0080] It should be noted that the basis for designing the adaptive pressure baseline B(t)B(t) is to dynamically adjust and calibrate the zero reference of the pressure sensor in a constantly changing environment, thereby eliminating the influence of environmental factors (such as temperature changes, sensor drift, etc.) and long-term trends on measurement accuracy, and ensuring that the system can accurately identify subtle pressure changes caused by the action of picking and placing goods.

[0081] S2.2. Set dynamic change threshold B based on product weight d (t), expressed as,

[0082] B d (t) = αWa +βσ(t);

[0083] Among them, B d (t) represents the dynamic change threshold at time point t, which is used to identify whether the pressure change of the product placement action on the shelf is significant enough to trigger the system response. α represents the adjustment parameter of the dynamic change threshold for the average weight of the product. W a It represents the average weight of the goods on the shelf, reflecting the general weight level of the goods on the shelf. β represents the adjustment parameter of the historical pressure change volatility on the dynamic change threshold. By adjusting β, the importance of historical data volatility in threshold calculation can be controlled. σ(t) represents the weighted standard deviation of historical pressure changes.

[0084]

[0085] Integration to obtain the complete dynamic change threshold B d (t), expressed as,

[0086]

[0087] Where m represents the number of historical data points, w k represents the weight of the kth historical time point, k represents the historical time point, P(tk) represents the pressure value at the time point tk, that is, the pressure reading k time units ago, and B(tk) represents the baseline value at the time point tk, that is, the baseline reading k time units ago.

[0088] It should be noted that the dynamic change threshold Bd(t)B d The design basis of (t) is to ensure that the system can sensitively detect significant pressure changes caused by the removal and placement of goods on the shelf while taking into account the average weight of the goods and the historical volatility of pressure changes, while being able to exclude slight environmental interference or false alarms, thereby accurately triggering system response.

[0089] S2.3, the control unit receives a continuous data stream from the flexible pressure sensor array and processes the sensor data in real time;

[0090] The difference between the processed sensor pressure value P(t) and the adaptive pressure baseline B(t) and the dynamic change threshold B d (t) compare and identify the pick-and-place actions;

[0091] When |P(t)-B(t)|>B d (t), it indicates that a pick-and-place action occurs, and the pick-and-place action is marked;

[0092] When |P(t)-B(t|≤B d (t) indicates that there is no pick-and-place action.

[0093] Furthermore, the difference algorithm can be used to identify the mutation points in the sensor data to represent the picking and placing actions of the goods; the positioning algorithm can be used to determine the specific location where the change occurs based on the pressure distribution characteristics of the change point;

[0094] Start the detailed data collection mode to record the continuous pressure data for a period of time before and after the change, including timestamp, pressure value, change rate, etc., for subsequent analysis. If an abnormally large pressure change is detected, it may be a system failure or abnormal operation, which should be recorded and marked immediately.

[0095] It should be noted that the control unit identifies the customer's taking and placing of goods by analyzing the changing patterns of sensor data. This identification process is the core of the automated vending system. It can distinguish different operations of customers and lay the foundation for subsequent product name, quantity identification and price calculation, ensuring the accuracy and fairness of transactions, while reducing customer waiting time and improving the shopping experience.

[0096] S3. Use dynamic pressure distribution mapping technology to identify product name, quantity, and pick-up and placement time. The specific steps are as follows:

[0097] S3.1. List all products planned to be put on the shelves and assign a unique coding identification to each product;

[0098] The control unit records the pressure change data of the sensor before and after the product is placed;

[0099] Use the scikit-learn library in Python for feature engineering and machine learning to extract the feature vector f from the pressure change data i ;

[0100] The feature vectors of each commodity are sorted and stored in the database, associated with the commodity code, and a commodity pressure feature database K is formed, where K contains the jth feature vector f of the commodity ij and product code c i .

[0101] S3.2, the control unit receives the real-time data stream P(t) from the sensor, and uses P(t) and the adaptive pressure baseline B(t) to calculate the dynamic pressure distribution D(t), expressed as,

[0102] D(t) = P(t) - B(t);

[0103] Based on the dynamic pressure distribution D(t) and the commodity pressure feature library K, the commodity identification function is designed, which is expressed as:

[0104]

[0105] Among them, Ω(D(t),K) represents the product recognition function, the output is the product code, d j (t) represents the jth feature extracted from D(t), α j Represents the feature weight, which is a non-negative value, which indicates the importance of the jth feature in the recognition process, β j Represents the similarity decay rate, which controls the influence of feature value differences on the similarity score;

[0106] It should be noted that the basis for designing the product recognition function is to efficiently and accurately identify the product from the dynamic pressure distribution D(t). By comparing the real-time pressure characteristics with the patterns in the product feature library K, the feature weight α is used to identify the product. j and similarity decay rate β j To adjust the relative importance and difference sensitivity of different features, so as to accurately match the name of the current product among many products.

[0107] Based on the identified product code c i , determine the name of the product to be taken.

[0108] S3.3, divide D(t) into multiple local areas. These areas can be defined based on spatial position or the coherence of pressure changes. The purpose of segmentation is to identify the spatial range occupied by a single commodity. For each segmented area, detect the local pressure maximum, which may correspond to the center or main stress point of the commodity. Analyze the distribution characteristics around each local maximum, such as the shape, area, and intensity of the pressure distribution. According to the pressure distribution characteristics of each area and the matching results with the commodity feature library, calculate the number of commodities in the area;

[0109] Introduce error correction mechanisms, such as historical data verification and multi-round measurement averaging, to improve the accuracy of quantity calculations;

[0110] Based on the marked pick-and-place action, the time series analysis method is used to determine when the product is taken out by detecting the mutation point in the pressure signal and identifying the pick-and-place time;

[0111] If the product recognition fails, it will be re-recognized in the product pressure feature library.

[0112] It should be noted that the role of dynamic pressure distribution mapping technology in this step is to analyze the real-time data of the flexible pressure sensor array on the shelf, and then identify the type, quantity and pick-up and placement time of the goods to achieve automated product tracking and management.

[0113] It should be noted that by using dynamic pressure distribution mapping technology, the system can analyze the pressure distribution characteristics of different commodities on the shelves, and then identify the types and quantities of commodities. This technology can automatically distinguish different commodities, even if they have similar appearances, through subtle differences in pressure distribution. It greatly improves the accuracy of commodity identification, reduces disputes caused by incorrect commodity identification, and provides a basis for subsequent inventory management and replenishment decisions.

[0114] S4. Automatically calculate the total price of the goods based on the item recognition results. The specific steps are as follows:

[0115] Use the product name as a keyword to search for the corresponding product information in the product database, including unit price, specifications, and brand;

[0116] If the product information search fails, search again in the product database;

[0117] Whenever an item is successfully identified and confirmed to be added to the shopping cart, the price of the item is immediately read from the item database and added to the current shopping cart total amount to automatically calculate the total price of the item.

[0118] It should be noted that based on the product identification results, the system automatically retrieves the product price from the database and calculates the total price of the products selected by the customer. This process realizes unmanned settlement. Customers can instantly see the total price of the selected products, which is convenient and fast, speeds up the settlement process, reduces waiting time in queues, and improves customer satisfaction and store operating efficiency.

[0119] S5. After the customer confirms and completes the payment, the control unit updates the inventory record. The specific steps are as follows:

[0120] The electronic display screen displays the list of goods purchased by customers and the cumulative total price in real time;

[0121] If the customer puts the product back on the shelf, the total price of the product will be updated immediately, and the control unit will update the product information;

[0122] If a customer adds product types and quantities, the displayed total price is updated immediately, allowing the customer to know the status of the shopping cart at any time;

[0123] If an unrecognizable product appears, provide timely feedback to the customer and guide them to take corrective actions;

[0124] Use encryption technology to protect customers' shopping records and personal information, ensuring the security of all transaction data;

[0125] After the customer confirms that the product and total price are correct, a variety of payment methods are provided for the customer to choose from to ensure that the payment process is safe and fast and complete the payment.

[0126] After the payment is completed, the system communicates with the payment platform through the API interface to verify whether the payment status is successful;

[0127] When the payment verification is not completed, the control unit reminds the customer to confirm the payment information again and pay again;

[0128] After receiving the confirmation signal of successful payment, the control unit immediately starts the inventory adjustment program and updates the inventory record;

[0129] Specifically, detailed information of the sold goods is extracted from the shopping cart record, and the corresponding quantity of goods is deducted from the inventory database according to the goods information;

[0130] If the inventory of a product drops to the minimum threshold A, the system automatically triggers an early warning mechanism to remind you to restock or stop selling;

[0131] Save all transaction details, including product type, quantity, unit price, total price, purchase time, payment method, customer ID, etc., encrypt and store transaction data, and regularly back up to the cloud or local server to ensure data security and recoverability, create transaction logs, and record the complete life cycle of each transaction, including creation, modification, and closing status, for audit and tracking purposes.

[0132] It should be noted that when the customer completes the payment, the system automatically updates the inventory database, records the sales of the goods, ensures the real-time and accuracy of the inventory data, provides a decision-making basis for subsequent inventory management, avoids inventory backlogs or out-of-stock situations, optimizes inventory turnover, and reduces operating costs.

[0133] S6. Based on historical sales data, predict replenishment demand and automatically generate a replenishment list. The specific steps are as follows:

[0134] Analyze historical sales data to identify patterns such as hot-selling items, seasonal sales trends, and holiday effects;

[0135] Use time series models to predict future sales based on past sales data of popular products;

[0136] Use machine learning algorithms to make predictions based on external factors (weather, economic indicators, social media trends, etc.), use cross-validation to evaluate model performance, and select the best model;

[0137] Simulate different market events to test their impact on forecasts;

[0138] Monitor inventory levels in real time, identify items that are below safety stock, consider in-transit inventory and items that have been ordered but not yet arrived, and avoid duplicate ordering;

[0139] Calculate the replenishment requirements for each product based on forecasted sales and current inventory status, and apply the safety stock principle to ensure that there will be no shortage of stock due to unexpected increase in demand;

[0140] Automatically generate a replenishment list, listing each product's ID, predicted demand, recommended replenishment quantity, and priority;

[0141] Furthermore, the overall inventory strategy can be optimized by manually reviewing the replenishment list, adjusting the replenishment quantity and priority according to the actual situation.

[0142] It should be noted that the system analyzes historical sales data, predicts sales trends in the future, and automatically generates replenishment lists. This forecasting mechanism helps merchants prepare in advance and ensure adequate supply of popular products. Through accurate replenishment forecasts, it reduces potential sales losses caused by out-of-stock situations. It also avoids the capital occupation problem caused by excessive inventory and improves the overall efficiency of the supply chain.

[0143] In summary, the present invention deploys flexible pressure sensor arrays and innovative dynamic pressure distribution mapping technology on the shelves, and realizes accurate identification of commodity picking and placing actions, automatic judgment of type and quantity, instant total price calculation, real-time update of inventory records, and intelligent replenishment prediction based on historical data analysis. This series of steps not only significantly improves customers' shopping experience, reduces waiting time, and ensures sufficient goods, but also greatly optimizes retailers' inventory management, reduces operating costs, and improves overall operating efficiency and supply chain response speed, ultimately achieving a highly intelligent, efficient, and low-cost retail environment, creating a win-win situation for customers and merchants.

[0144] Example 2

[0145] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of an automatic vending system based on a pressure sensor is provided.

[0146] To verify the performance of the pressure sensor-based vending system, experiments were conducted in a simulated supermarket environment. The environment is equipped with shelves equipped with flexible pressure sensor arrays to monitor the picking and placing of goods. The experiment is divided into several stages: preparation stage, operation stage, and data analysis stage.

[0147] The preparation phase involved installing sensors, setting up control units, defining adaptive pressure baseline algorithms and dynamic change threshold algorithms. In addition, a product pressure feature library was created, which contained the coding identifiers of all products and their corresponding pressure change feature vectors. To ensure the accuracy and reliability of the data, standardized products were used in the experiment, including products of different weights and volumes.

[0148] During the operation phase, the control unit continuously receives data streams from sensors, processes the data in real time, and identifies pick-up and drop-off actions based on a preset algorithm. At the same time, the system automatically calculates the total price of the goods, updates inventory records, and adjusts inventory after the customer completes payment. During the experiment, a large amount of data on product pick-up and drop-off, sales trends, inventory levels, and replenishment needs was collected.

[0149] During the data analysis phase, the experimental data was compared with the data from the traditional manual sales system to quantify the efficiency and accuracy of the new system. The data collection period was one month, covering the peak sales periods on weekdays and weekends.

[0150] The details are shown in Table 1:

[0151] Table 1 Experimental record table

[0152]

[0153] By analyzing the above table data, it can be observed that the automatic vending system based on pressure sensors shows significant advantages in product identification, inventory management and replenishment forecasting. For example, the average number of pick-and-place times for apples is 1,200, and the automatic identification success rate is as high as 98.5%, which shows that the system can maintain high accuracy even in a high-traffic environment. The inventory update delay is between 0.1 and 0.3 seconds, which is much lower than the manual update time of the traditional system, improving operational efficiency.

[0154] The replenishment forecast accuracy is also excellent, reaching an average of more than 96%, which means that the system can effectively avoid inventory backlogs and out-of-stock situations, reduce waste, and improve customer satisfaction. Compared with the traditional manual vending system, the automatic vending system has significantly improved in recognition speed, accuracy, real-time inventory updates, and forecasting capabilities, reflecting its innovation and practicality.

[0155] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An automatic vending system based on pressure sensor, Features: include, A sensor deployment module, used to deploy a flexible pressure sensor array on the shelf and connect to a control unit; A pick-and-place action recognition module, used to recognize the pick-and-place action of the commodity based on the changes of the flexible pressure sensor array in the control unit; The commodity identification module is used to identify the commodity name, quantity and pick-up and placement time through dynamic pressure distribution mapping technology; The price calculation module is used to automatically calculate the total price of the product based on the product identification results; The inventory management module is used to control the control unit to update the inventory record after the customer confirms and completes the payment; The intelligent replenishment forecasting module is used to predict replenishment needs based on historical sales data and automatically generate replenishment lists.

2. The pressure sensor-based vending system according to claim 1, Features: Adaptive pressure baseline means that when there is no pick-up and place action on the shelf, the control unit continuously reads and records the pressure values ​​at multiple time points, uses an algorithm to remove abnormal values, calculates the adaptive pressure baseline B(t), and stores it in the control unit for comparative analysis of pressure changes; The adaptive pressure baseline B(t) is expressed as, B(t)=μ+φ(P(t-1)-B(t-1))+θ∈(t-1)+∈(t); Among them, μ represents the intercept term, φ represents the autoregressive coefficient, θ represents the moving average coefficient, ∈(t) represents the white noise error term, P(t-1) represents the pressure value at the previous time, B(t-1) represents the baseline value at the previous time, and t represents time.

3. The pressure sensor-based vending system according to claim 2, Features: The control unit identifies the picking and placing actions of the goods based on the changes in the flexible pressure sensor array. The specific steps are as follows: Based on the weight of the product, set the dynamic change threshold B d (t), expressed as, Among them, B d (t) represents the dynamic change threshold at time point t, α represents the adjustment parameter of the average weight of the commodity for the dynamic change threshold, W a represents the average weight of the goods on the shelf, β represents the adjustment parameter of the historical pressure change volatility to the dynamic change threshold, m represents the number of historical data points, and w k represents the weight of the kth historical time point, k represents the historical time point, P(tk) represents the pressure value at the time point tk, and B(tk) represents the baseline value at the time point tk; The control unit receives a continuous data stream from the flexible pressure sensor array and processes the sensor data in real time; The difference between the processed sensor pressure value P(t) and the adaptive pressure baseline B(t) and the dynamic change threshold B d (t) compare and identify the pick-and-place actions; When |P(t)-B(t)|>B d (t), it indicates that a pick-and-place action occurs, and the pick-and-place action is marked; When |P(t)-B(t|≤B d (t) indicates that there is no pick-and-place action.

4. The pressure sensor-based vending system according to claim 3, Features: To build a commodity pressure feature library, the specific steps are as follows: List all products planned to be put on the shelves and assign a unique coding identification to each product; The control unit records the pressure change data of the sensor before and after the product is placed; Use the scikit-learn library in Python for feature engineering and machine learning to extract the feature vector f from the pressure change data i ; The feature vectors of each commodity are sorted and stored in the database, associated with the commodity code, and a commodity pressure feature database K is formed, where K contains the jth feature vector f of the commodity ij and product code c i .

5. The pressure sensor-based vending system according to claim 4, Features: Through dynamic pressure distribution mapping technology, the product name is identified. The specific steps are as follows: The control unit receives the real-time data stream P(t) from the sensor and uses P(t) and the adaptive pressure baseline B(t) to calculate the dynamic pressure distribution D(t), which is expressed as, D(t) = P(t) - B(t); Based on the dynamic pressure distribution D(t) and the commodity pressure feature library K, the commodity identification function is designed, which is expressed as: Among them, Ω(D(t),K) represents the product recognition function, the output is the product code, d j (t) represents the jth feature extracted from D(t), α j represents the feature weight, β j Represents the similarity decay rate; Based on the identified product code c i , determine the name of the product to be taken.

6. The pressure sensor-based vending system of claim 5, Features: Identify the quantity of goods and the time of pick-up and placement. The specific steps are as follows: Divide D(t) into multiple local areas. For each divided area, detect the local maximum pressure, analyze the distribution characteristics around each local maximum, and calculate the number of commodities in the area based on the pressure distribution characteristics of each area and the matching results with the commodity feature library. Based on the marked pick-and-place action, the time series analysis method is used to determine when the product is taken out by detecting the mutation point in the pressure signal and identifying the pick-and-place time; If the product recognition fails, it will be re-recognized in the product pressure feature library.

7. The pressure sensor-based vending system of claim 6, Features: According to the product recognition results, the total price of the product is automatically calculated. The specific steps are as follows: Use the product name as a keyword to find the corresponding product information in the product database; If the product information search fails, search again in the product database; Whenever an item is successfully identified and confirmed to be added to the shopping cart, the price of the item is immediately read from the item database and added to the current shopping cart total amount to automatically calculate the total price of the item.

8. The pressure sensor-based vending system of claim 7, Features: The customer confirms the product and total price. The specific steps are as follows: The electronic display screen displays the list of goods purchased by customers and the cumulative total price in real time; If the customer puts the product back on the shelf, the total price of the product will be updated immediately, and the control unit will update the product information; If a customer adds product types and quantities, the displayed total price is updated immediately, allowing the customer to know the status of the shopping cart at any time; Use encryption technology to protect customers' shopping records and personal information; After the customer confirms that the product and total price are correct, multiple payment methods are provided for the customer to choose from and complete the payment.

9. The pressure sensor-based vending system of claim 8, Features: After the customer completes the payment, the control unit updates the inventory record. The specific steps are as follows: After the payment is completed, the system communicates with the payment platform through the API interface to verify whether the payment status is successful; When the payment verification is not completed, the control unit reminds the customer to confirm the payment information again and pay again; After receiving the confirmation signal of successful payment, the control unit immediately starts the inventory adjustment program and updates the inventory record.

10. The pressure sensor based vending system as claimed in claim 9, Features: Based on historical sales data, forecast replenishment demand and automatically generate a replenishment list. The specific steps are as follows: Analyze historical sales data to identify hot-selling products; Use time series models to predict future sales based on past sales data of popular products; Monitor inventory levels in real time and identify items that are below safety stock; Calculate the replenishment requirements for each product based on the forecasted sales volume and current inventory status; Automatically generate a replenishment list, listing each product's ID, predicted demand, recommended replenishment quantity, and priority.

Citation Information

Patent Citations

  • Intelligent goods management system and method and intelligent storage cabinet

    CN107749114A

  • Article classification and identification method based on pressure sensing array and system thereof

    CN110031074A

  • Encoding and decoding digital signals in conductive ink structures

    US10686963B1

  • Systems and methods for auto-replenishment of products using pressure mapping sensors and machine learning

    US20240054453A1

  • Unmanned vending system and control method, device, and medium

    WO2023051775A1

Cited By

  • Intelligent freezer automatic settlement system based on cashier linkage

    CN120543260A

  • Intelligent retail method and system based on NFC identity authentication and weighing settlement

    CN121170940A

  • Commodity identification method, commodity identification device, selling cabinet and medium

    CN121211372A