Automatic weighing method and system for intelligent fresh goods shelf, medium and program product

Abstract

The invention discloses an automatic weighing method and system for an intelligent fresh goods shelf, a medium and a program product, and relates to the field of goods identification systems.The method comprises the steps that when it is detected that the weight of fresh goods on a target goods shelf is reduced, the weight reduction value of the fresh goods and a shopping basket identifier of a shopping basket interconnected with the target goods shelf are obtained; generating a cargo record according to the cargo identifier and the weight reduction value of the fresh cargo, and binding the cargo record to the shopping basket identifier; when it is detected that the shopping basket is interconnected with the weighing terminal, determining a plurality of to-be-settled target cargo records based on the shopping basket identifier of the shopping basket; the weighing weight of the to-be-settled goods on the weighing terminal is determined, and a target goods record corresponding to the to-be-settled goods is determined; and when the difference value between the weight reduction value in the target cargo record and the weighing weight is lower than a preset loss threshold value, taking the weighing weight as the settlement weight of the to-be-settled cargo, and generating a settlement list. By implementing the method, the weighing accuracy can be ensured while the weighing efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of cargo identification systems, and in particular to an automatic weighing method, system, medium and program product for a fresh food smart shelf. Background Art

[0002] With the rapid development of the retail industry and the upgrading of consumer shopping needs, the accurate measurement and efficient management of fresh goods have become an important issue for supermarket companies. Especially in the context of the rapid expansion of chain supermarkets, the inventory monitoring and sales management of fresh goods in each store plays a key role in the company's operational efficiency and cost control. At the same time, consumers' requirements for shopping experience are constantly improving, requiring faster and more convenient shopping methods.

[0003] In related technologies, the measurement and management of fresh goods mainly uses electronic weighing equipment to measure and record weight. In the sales process, the staff puts the goods on the electronic scale, enters the product category through the key, obtains the weight data and prints the price tag. Some supermarkets have introduced self-service weighing equipment, and customers can complete the product weighing and labeling process by themselves. In terms of inventory management, the staff enters the product weight data into the management system through regular inventory and recording, which is used to track the inventory changes of various fresh products.

[0004] However, the manual operation of electronic scales takes a long time, which can easily cause customers to wait in line during peak hours. Self-service weighing equipment has poor working stability in complex environments, especially in environments with high temperature and humidity, which will affect the measurement accuracy of the sensor. Summary of the invention

[0005] The present application provides a method, system, medium and program product for automatic weighing of a fresh food smart shelf, which are used to improve weighing efficiency while ensuring weighing accuracy.

[0006] In a first aspect, the present application provides an automatic weighing method for a fresh food smart shelf, which is applied to a weighing system, and the method includes: when it is detected that the weight of fresh food on a target shelf is reduced, obtaining the weight reduction value of the fresh food and a shopping basket identifier of a shopping basket connected to the target shelf; generating a goods record according to the goods identifier and the weight reduction value of the fresh food, and binding the goods record to the shopping basket identifier; when it is detected that the shopping basket is connected to a weighing terminal, determining multiple target goods records to be settled based on the shopping basket identifier of the shopping basket; determining the weighing weight of the goods to be settled on the weighing terminal, and determining the target goods record corresponding to the goods to be settled; when the difference between the weight reduction value in the target goods record and the weighing weight is lower than a preset loss threshold, using the weighing weight as the settlement weight of the goods to be settled, and generating a settlement list.

[0007] In the above embodiment, the weighing system automatically obtains the reduction value and the shopping basket identifier when detecting that the weight of the fresh goods on the target shelf has decreased, and generates a binding record. At the time of settlement, the accuracy of the settlement weight is determined by comparing whether the difference between the actual weight and the recorded weight of the weighing terminal is within the threshold. This achieves full automated tracking and accurate measurement of fresh goods from pickup to settlement, avoids the time-consuming and error-prone traditional manual weighing, and improves settlement efficiency and accuracy.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of obtaining the weight reduction value of the fresh goods and the shopping basket identifier of the shopping basket interconnected with the target shelf when the weight reduction of the fresh goods on the target shelf is detected, the method further includes: when there are multiple shopping basket identifiers, obtaining monitoring image information of the target shelf portion; based on the monitoring image information, determining multiple joint shopping baskets for storing fresh goods, and determining the joint shopping basket identifier of the multiple joint shopping baskets; generating a joint goods record according to the goods identifier and the weight reduction value of the fresh goods, and binding the joint goods record to the joint shopping basket identifier; when it is detected that the joint shopping basket is interconnected with the weighing terminal, determining the weighing weight of the goods to be settled on the weighing terminal, and determining the joint goods record corresponding to the goods to be settled; when the difference between the weight reduction value in the joint goods record and the weighing weight is within the joint difference range, using the weighing weight as the settlement weight of the goods to be settled, and generating a settlement list.

[0009] In the above embodiment, when the weighing system determines multiple joint shopping baskets through monitoring images, the system can intelligently identify the shopping basket combination that actually stores the goods, and generate a joint goods record for binding. At the time of settlement, accurate settlement is ensured by judging the joint difference range, which solves the problem of difficulty in determining the ownership of goods when multiple people are shopping at the same time, and improves the shopping experience.

[0010] In combination with some embodiments of the first aspect, in some embodiments, when the difference between the weight reduction value in the joint cargo record and the weighing weight is within the joint difference range, the weighing weight is used as the settlement weight of the goods to be settled, and a settlement list is generated, specifically including: determining the shopping settlement information of other joint shopping baskets corresponding to the current shopping basket; determining the joint settlement weight of the corresponding joint cargo record based on the shopping settlement information, and correcting the weight reduction value to the remaining weight value; the joint settlement weight is the sum of the settlement weights of other joint shopping baskets; the remaining weight value is the weight reduction value after deducting the joint settlement weight; based on the shopping settlement information, determining the joint difference range; when the difference between the remaining weight value and the weighing weight is within the joint difference range, using the weighing weight as the settlement weight of the goods to be settled, and generating a settlement list.

[0011] In the above embodiment, the weighing system determines the settlement information of other joint shopping baskets, calculates the remaining weight to be settled, and dynamically adjusts the joint difference range based on actual conditions, so that the system can more accurately handle batch settlement problems in scenarios where multiple people shop together, avoiding duplicate billing or omissions.

[0012] In combination with some embodiments of the first aspect, in some embodiments, a joint difference range is determined based on the shopping settlement information, specifically including: after determining the joint settlement weight based on the shopping settlement information, determining multiple remaining unsettled joint shopping baskets as shopping baskets to be settled; determining the weight ratio of the settlement weight of the current shopping basket in the remaining weight value of the shopping basket to be settled based on the monitoring image information; and determining the joint difference range between the remaining weight value and the weighing weight based on the weight ratio.

[0013] In the above embodiment, the weighing system determines the current shopping weight ratio based on the monitoring image information, and dynamically determines the joint difference range accordingly, so that the system can adaptively adjust the judgment criteria according to the actual shopping scenario, thereby improving the settlement accuracy and flexibility when multiple people shop together.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the steps of generating a goods record based on the goods identification and weight reduction value of the fresh goods, and binding the goods record to the shopping basket identification, the method also includes: when an increase in the weight of the fresh goods on the target shelf is detected, obtaining the weight increase value of the fresh goods; when the difference between the weight increase value and the weight reduction value is lower than a preset loss threshold, removing the goods record on the shopping basket identification.

[0015] In the above embodiment, the weighing system detects the increase in the weight of the goods and compares it with the decrease. When the difference is within the threshold, the corresponding record is automatically removed, thereby realizing intelligent identification and processing of customer returns or exchanges, avoiding duplicate billing, and improving the fault tolerance of the system.

[0016] In combination with some embodiments of the first aspect, in some embodiments, when the weight increase of fresh goods on the target shelf is detected, the weight increase value of the fresh goods is obtained, specifically including: when the weight increase of fresh goods on the target shelf is detected, obtaining monitoring image information of the target shelf position; after determining that the newly added goods at the target shelf position are fresh goods according to the monitoring image information, obtaining the weight increase value of the fresh goods.

[0017] In the above embodiment, the weighing system confirms the type of newly added goods in combination with the monitoring image and then records the weight increase, thereby avoiding misjudgment caused by the placement of other items, improving the accuracy of the system's identification of goods changes, and reducing erroneous records.

[0018] In combination with some embodiments of the first aspect, in some embodiments, when the difference between the weight reduction value in the target cargo record and the weighed weight is lower than a preset loss threshold, the weighed weight is used as the settlement weight of the cargo to be settled, and after the step of generating a settlement list, the method also includes: monitoring the remaining quantity of fresh goods on the target shelf; determining the shipment quantity of fresh goods within a preset time period based on multiple weight reduction values; determining the quantity of fresh goods to be replenished based on historical shipment data, combined with the shipment quantity and the remaining quantity, and sending the quantity of fresh goods to be replenished to the shipment management terminal.

[0019] In the above embodiment, the weighing system realizes intelligent management of fresh commodity inventory by real-time monitoring of the remaining goods on the shelves, analyzing the shipping trend in combination with historical data, automatically calculating the amount of goods to be replenished and notifying the management terminal, thereby avoiding out-of-stock or inventory backlogs.

[0020] In a second aspect, an embodiment of the present application provides a weighing system, which includes: 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 weighing system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, and when the above-mentioned computer program product runs on a weighing system, the above-mentioned weighing system executes the method described in the first aspect and any possible implementation method 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 a weighing system, the weighing system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It can be understood that the weighing system 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 method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the adoption of a mechanism in which smart shelves automatically sense weight changes and establish associations with shopping carts, as well as a settlement method based on the comparison of the difference between actual weighing and recorded weight, the system can automatically track the entire process from pickup to settlement without manual intervention. This effectively solves the problem in related technologies that customers or store clerks need to manually operate electronic scales, which easily results in long queues and large measurement errors. This in turn realizes the automation and precision of the fresh product transaction process, improving supermarket operating efficiency and customer shopping experience.

[0025] 2. Since a mechanism is adopted to determine the weight proportion of shopping baskets based on monitoring images and dynamically adjust the joint difference range, the system can adaptively adjust the judgment criteria according to the usage of each shopping basket in the actual shopping scenario, effectively solving the problem in related technologies that when multiple people shop together, it is impossible to accurately distinguish the ownership of goods in each shopping basket, which easily causes settlement confusion, thereby realizing accurate settlement in scenarios where multiple people shop together and improving the adaptability and reliability of the system.

[0026] 3. Since the system adopts a mechanism that combines monitoring images to confirm the type of goods and then records weight changes, it can accurately identify whether the actual changes on the shelf are changes in the target fresh products. This effectively solves the problem that related technologies that only rely on weight sensors are easily affected by interference and misjudge changes in goods, thereby achieving accurate identification and recording of changes in goods and improving the reliability and stability of system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of the automatic weighing method of the fresh food smart shelf in the embodiment of the present application; Figure 2 This is another flow chart of the automatic weighing method of the fresh food smart shelf in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of a weighing system in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0031] In the fresh food area of ​​a large supermarket chain, thousands of customers buy fresh products such as fruits and vegetables every day. In the traditional shopping process, customers need to put the products into the shopping basket first, and then queue up to wait for the special fresh food checkout counter to weigh and settle the bill. During the peak traffic hours of 9 am and 5 pm, it is often the case that one checkout counter needs to serve 5-6 customers at the same time, and each customer needs to wait for an average of 3-5 minutes. At the same time, due to the characteristics of fresh products, they are prone to loss during multiple handling and waiting processes, affecting the quality of the products. In addition, cashiers need to manually identify the types of goods and enter them into the system, which is prone to operational errors and leads to settlement errors.

[0032] In related technologies, the measurement and settlement of fresh products can be achieved by using electronic scales and manual identification. Specifically, supermarkets will set up multiple electronic scales in the fresh food area, and staff or customers will manually operate to complete the weighing, and complete the product identification by manually selecting the product category and printing the price tag.

[0033] The following introduces a scenario of using the automatic weighing method of fresh food smart shelves in related technologies.

[0034] A supermarket has introduced a self-service checkout system and set up multiple self-service weighing machines in the fresh food area. After purchasing goods, customers need to take out the fresh food in the shopping cart one by one and put them on the self-service weighing machine, manually select the type of goods on the touch screen, confirm the order, and finally settle the bill online. However, in actual use, since some customers are not familiar with the operation process, they often need the assistance of staff, which increases the shopping time. At the same time, the sensors of the self-service weighing machines are easily affected by environmental factors such as water stains and temperature, and inaccurate weighing or system failures often occur, resulting in the need for repeated weighing or manual settlement.

[0035] By adopting the automatic weighing method of the fresh food smart shelf in the embodiment of the present application, by integrating a high-precision weight sensor, an image recognition device and a shopping basket recognition module on the shelf, automatic detection of commodity weight changes, intelligent identification of commodity types and real-time tracking of shopping behavior are achieved. The following introduces the scenario of using the automatic weighing method of the fresh food smart shelf in the present application.

[0036] In the smart supermarket that adopts this solution, the shelves in the fresh food area are equipped with high-precision weight sensors and image recognition systems. Customer A brings a shopping basket to pick fruits. When he takes 2.5kg of mangoes from the mango shelf and puts them into the shopping basket, the system automatically records the weight change and the corresponding shopping basket logo. At checkout, the system automatically checks the weight and completes the settlement. The whole process is fast and accurate, and no manual operation is required.

[0037] It can be seen that the automatic weighing method of the fresh food smart shelf in the embodiment of the present application can not only realize the automatic measurement of fresh food, but also effectively solve the problems of traditional manual weighing, such as time-consuming and error-prone, thereby improving shopping efficiency and accuracy.

[0038] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of the automatic weighing method of the fresh food smart shelf in the embodiment of the present application.

[0039] S101. When it is detected that the weight of fresh goods on a target shelf is reduced, a weight reduction value of the fresh goods and a shopping basket identifier of a shopping basket connected to the target shelf are obtained.

[0040] Among them, the target shelf refers to an intelligent shelf with a weight sensor, which is used to store and weigh fresh goods; fresh goods refer to fresh agricultural products, aquatic products and other commodities that need to be weighed and priced; the weight reduction value represents the weight change value after a certain type of fresh goods on the shelf is taken away; the shopping basket refers to the shopping container used by customers to hold goods; the shopping basket identifier refers to the electronic tag code used to uniquely identify the shopping basket.

[0041] The weighing system executes this step when it detects that a customer has taken fresh goods from the smart shelf. Specifically, the weighing system monitors the weight changes of goods in real time through the weight sensors on the shelves. When it detects that the weight of a certain type of fresh goods has decreased, it records the decrease value. At the same time, it detects the shopping basket that is currently wirelessly connected to the shelf through radio frequency identification technology, obtains its electronic tag information, and thus determines the flow of goods.

[0042] In some embodiments, the acquisition of the weight reduction value and the determination of the shopping basket identification can be achieved in a variety of ways: optionally, the weight change is detected by the shelf partition gravity sensor; the category of the removed goods is confirmed by image recognition; the shopping basket identification is obtained through near-field communication. Optionally, the nearest shopping basket is determined by the Bluetooth signal strength; the residence time of the shopping basket near the shelf is analyzed; the actual interactive shopping basket is determined based on the shelf camera. It is understandable that other sensing technologies and identification methods can also be used to achieve weight change detection and shopping basket association, which is not limited here.

[0043] S102: Generate a goods record according to the goods identification and weight reduction value of the fresh goods, and bind the goods record to the shopping cart identification.

[0044] Among them, the cargo identification refers to the code used to uniquely identify the type of fresh cargo; the cargo record refers to the data entry containing information such as cargo identification and weight reduction value.

[0045] The weighing system executes this step after obtaining the weight loss value and the shopping basket identifier. Specifically, the system first determines the type code of the fresh goods based on the shelf partition information, combines the code with the weight loss value to generate a goods record containing complete information such as product information, weight information, timestamp, etc., and then establishes a binding relationship between the record and the corresponding shopping basket identifier through data association, thereby realizing the information association between the goods and the shopping basket.

[0046] In some embodiments, the generation and binding of goods records can be achieved in a variety of ways: optionally, determining the type of goods according to the shelf partition code; generating a record item containing complete product information; and storing the record in the electronic tag of the shopping cart. Optionally, creating an association table item in the system database; recording the binding relationship through the blockchain; and writing the record index in the shopping cart chip. It is understandable that other data structures and storage methods can also be used to achieve record generation and binding, which are not limited here.

[0047] S103: When it is detected that the shopping basket is interconnected with the weighing terminal, a plurality of target goods records to be settled are determined based on the shopping basket identifier of the shopping basket.

[0048] Among them, the weighing terminal refers to the intelligent electronic scale device used for weighing confirmation during settlement; the target goods record refers to all the information of the goods to be settled that are bound to the current shopping cart.

[0049] The weighing system executes this step when the customer places the shopping basket on the weighing terminal for settlement. Specifically, the system identifies the electronic tag of the shopping basket through the near field communication module of the weighing terminal, reads the identification information, and then queries the system database based on the identification to obtain all the unsettled goods records associated with the shopping basket, forming a list of goods to be settled.

[0050] In some embodiments, shopping cart identification and record acquisition can be achieved in a variety of ways: optionally, reading shopping cart tags through NFC; querying related databases to obtain records; filtering valid records that have not been settled. Optionally, scanning shopping cart QR code identification; synchronizing cloud database records; arranging pending settlement records in chronological order. It is understandable that other identification methods and data processing methods can also be used to achieve record acquisition, which is not limited here.

[0051] S104: Determine the weighing weight of the goods to be settled on the weighing terminal, and determine the target goods record corresponding to the goods to be settled.

[0052] The weighing weight indicates the weight of the goods to be settled actually measured by the weighing terminal; the goods to be settled refer to the commodities currently placed on the weighing terminal and the pricing needs to be confirmed.

[0053] The weighing system executes this step after obtaining the records to be settled. Specifically, the system obtains the weight of the actual placed goods through the high-precision sensor of the weighing terminal, and confirms the specific type of goods through image recognition or product feature matching, matches the actual weighing data with the product information in the records to be settled, and finds the corresponding target record for subsequent settlement.

[0054] In some embodiments, weight measurement and record matching can be achieved in a variety of ways: optionally, using a high-precision gravity sensor to measure weight; identifying goods through machine vision; matching corresponding record information. Optionally, using multi-point weighing to eliminate errors; analyzing product features to confirm the type; matching records based on weight similarity. It is understandable that other weighing technologies and matching algorithms can also be used to achieve weight confirmation and record correspondence, which is not limited here.

[0055] S105. When the difference between the weight reduction value in the target cargo record and the weighed weight is lower than a preset loss threshold, the weighed weight is used as the settlement weight of the cargo to be settled, and a settlement list is generated.

[0056] Among them, the preset loss threshold indicates the allowable weight error range; the settlement weight refers to the weight of the goods finally used for pricing; and the settlement list refers to the payment voucher containing product information, weight, amount, etc.

[0057] The weighing system performs this step after completing the weight matching. Specifically, the system compares the actual weighing weight value with the weight reduction value in the record, calculates the difference and compares it with the preset loss threshold. If the difference is within the allowable range, the actual weighing weight is used as the settlement basis, and a settlement list containing complete information such as product information, weight, unit price, amount, etc. is generated.

[0058] In some embodiments, weight confirmation and list generation can be achieved in a variety of ways: optionally, calculating the weight difference percentage; querying the commodity loss standard; confirming the final settlement weight. Optionally, dynamically adjusting the loss threshold; applying the loss standard of different commodity categories; generating an electronic settlement voucher. It is understandable that other calculation methods and list formats can also be used to achieve settlement confirmation, which is not limited here.

[0059] In the above embodiment, the weighing system realizes automatic detection and recording of commodity changes through weight sensors and image recognition technology. In actual applications, the weighing system can also dynamically adjust the weight loss threshold based on historical transaction data to achieve more accurate settlement; by analyzing sales trends, it can automatically predict replenishment needs and optimize inventory management.

[0060] The following is a supplement to the scenario of this embodiment.

[0061] By analyzing historical sales data, the smart supermarket system found that Tuesday morning is the peak of fruit sales, and notified suppliers in advance to replenish the stock appropriately. When it detects that the mango inventory is lower than the warning value, it automatically calculates the replenishment quantity and notifies the backend. At the same time, the system can also identify customers' shopping habits. When it is found that customers put the goods back after selecting them, it automatically analyzes the reasons and optimizes the display of goods. For example, if it is found that multiple customers put back a batch of mangoes after selecting them, the system will prompt to adjust the price of the batch of goods or change the display location to improve sales efficiency.

[0062] After combining the above scenarios, 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 automatic weighing method of the fresh food smart shelf in the embodiment of the present application.

[0063] S201. When it is detected that the weight of the fresh goods on the target shelf is reduced, the weight reduction value of the fresh goods and the shopping basket identifier of the shopping basket connected to the target shelf are obtained.

[0064] Referring to step S101, the weighing system determines the weight reduction value and the shopping basket identifier.

[0065] S202: When there are multiple shopping basket identifiers, obtain monitoring image information of the target shelf location.

[0066] Among them, the target shelf part represents the shelf area where the weight change occurs; the monitoring image information refers to the real-time scene image collected by the shelf camera; and the multiple shopping basket identifiers represent the electronic identifiers of multiple shopping baskets that are simultaneously connected to the shelf.

[0067] The weighing system executes this step when it detects that multiple shopping baskets are connected to the shelf at the same time. Specifically, the system activates the surveillance camera in the shelf area to collect high-definition image information including the shelf area, surrounding environment and shopping basket location, which is used to analyze and determine the actual interactive shopping basket situation to ensure accurate tracking of the flow of goods.

[0068] In some embodiments, image acquisition of multiple shopping basket scenes can be achieved in a variety of ways: optionally, activating multi-angle camera acquisition; adjusting the camera focus and angle; performing image preprocessing enhancement. Optionally, collecting infrared thermal imaging data; combining with a depth camera to obtain spatial information; collecting continuous frames to construct dynamic scenes. It is understandable that other image acquisition and processing methods can also be used to achieve scene monitoring, which is not limited here.

[0069] S203: Based on the monitoring image information, determine a plurality of joint shopping baskets for storing fresh goods, and determine joint shopping basket identifiers of the plurality of joint shopping baskets.

[0070] Among them, the joint shopping basket refers to multiple shopping baskets that store the same batch of fresh goods; the joint shopping basket identifier refers to the coding information used to uniquely identify the combination of multiple associated shopping baskets.

[0071] The weighing system performs this step after acquiring the monitoring image. Specifically, the system analyzes the image content through computer vision algorithms, identifies the location and relative relationship of the shopping baskets in the image, determines which shopping baskets are involved in the storage of goods, and then assigns a unified joint identifier to these shopping basket groups to establish the association relationship between the shopping basket combination and the goods.

[0072] In some embodiments, the determination of the joint shopping basket can be achieved in a variety of ways: optionally, analyzing the spatial distribution of the shopping basket; identifying customer interaction behaviors; generating a shopping basket association group. Optionally, tracking the collaborative shopping trajectory of multiple people; analyzing the shopping basket movement pattern; establishing a shopping basket combination identifier. It is understandable that other scenario analysis methods can also be used to achieve shopping basket combination confirmation, which is not limited here.

[0073] S204: Generate a combined goods record according to the goods identification and weight reduction value of the fresh goods, and bind the combined goods record to the combined shopping basket identification.

[0074] Among them, the combined goods record represents a data entry containing the goods information carried by multiple shopping carts; binding the combined goods record represents combining the goods information with the shopping cart to establish an association relationship.

[0075] The weighing system performs this step after determining the joint shopping basket. Specifically, the system integrates information such as the product category identification and weight reduction value to generate a joint goods record, and at the same time establishes a binding relationship between the record and the previously determined joint shopping basket identification to achieve product information tracking in multiple shopping basket scenarios.

[0076] In some embodiments, the generation and binding of joint records can be achieved in a variety of ways: optionally, integrating commodity and weight information; generating joint record numbers; establishing multi-basket association relationships. Optionally, creating a distributed data structure; setting record sharing attributes; synchronously updating association status. It is understandable that other data organization methods can also be used to achieve joint record management, which is not limited here.

[0077] S205: When it is detected that the combined shopping basket is interconnected with the weighing terminal, the weighing weight of the goods to be settled on the weighing terminal is determined, and a combined goods record corresponding to the goods to be settled is determined.

[0078] Among them, the interconnection between the shopping basket and the weighing terminal means that any shopping basket in the shopping basket combination is connected to the weighing device.

[0079] The weighing system executes this step when it detects any associated shopping basket for settlement. Specifically, the system identifies the ID of the current settlement shopping basket, searches for the combined shopping basket combination to which it belongs, obtains the complete commodity record of the combination, and measures the actual weight of the commodities to be settled in the current shopping basket for record matching.

[0080] In some embodiments, settlement matching in a joint shopping scenario can be achieved in a variety of ways: optionally, identifying the combination to which the shopping cart belongs; obtaining a list of combined goods; measuring the actual settlement weight. Optionally, tracking the settlement order of the shopping cart; synchronously updating the combination status; calculating the share to be settled. It is understandable that other matching methods can also be used to achieve joint shopping settlement, which is not limited here.

[0081] S206. When the difference between the weight reduction value in the combined cargo record and the weighed weight is within the combined difference range, the weighed weight is used as the settlement weight of the cargo to be settled, and a settlement list is generated.

[0082] Among them, the combined difference range represents the allowable weight error range considering the multi-basket shopping scenario; the weight reduction value in the combined cargo record represents the expected weight value assigned to the current shopping basket.

[0083] The weighing system performs this step after completing the weight measurement. Specifically, the system compares the actual weight value obtained by weighing with the weight value assigned to the current shopping cart in the joint record, calculates the difference range according to a specific algorithm, and if the actual difference is within the allowable range, confirms the current weight as the basis for settlement and generates the corresponding settlement voucher.

[0084] In some embodiments, settlement confirmation in a joint scenario can be achieved in a variety of ways: optionally, calculating the difference in weight distribution; dynamically adjusting the allowable range; generating a sub-item settlement form. Optionally, applying a multi-level error model; considering commodity characteristics adjustment; updating the combined settlement status. It is understandable that other calculation methods can also be used to achieve joint scenario settlement, which is not limited here.

[0085] In some embodiments, the weighing system determines the shopping settlement information of other joint shopping baskets corresponding to the current shopping basket; determines the joint settlement weight of the corresponding joint goods record based on the shopping settlement information, and corrects the weight reduction value to the remaining weight value; the joint settlement weight is the sum of the settlement weights of other joint shopping baskets; the remaining weight value is the weight reduction value after deducting the joint settlement weight; determines the joint difference range based on the shopping settlement information; when the difference between the remaining weight value and the weighing weight is within the joint difference range, the weighing weight is used as the settlement weight of the goods to be settled, and a settlement list is generated.

[0086] Among them, the shopping settlement information represents the transaction data of the joint shopping basket that has completed the settlement; the joint settlement weight refers to the total weight of the settled shopping baskets; the remaining weight value represents the remaining value after deducting the settled weight from the total weight; the joint difference range refers to the allowable weight error range considering the multi-basket scenario.

[0087] The weighing system executes this process when it detects that a shopping basket in the combined shopping basket combination has been settled. Specifically, the system first queries the transaction records of other associated shopping baskets that have completed settlement, calculates the total settled weight, and then subtracts the settled total weight from the original reduction value to obtain the remaining weight to be distributed. Based on the data characteristics of the settled shopping basket, the system calculates the error range applicable to the current settlement, and confirms the settlement when the difference between the actual weighed weight and the remaining weight is within the range.

[0088] In some embodiments, step-by-step settlement in a joint shopping scenario can be achieved in a variety of ways: optionally, obtaining settled basket information; accumulating and calculating the total settlement weight; dynamically updating the remaining amount. Optionally, analyzing historical settlement patterns; establishing an error prediction model; and adjusting settlement parameters in real time. It is understandable that other calculation methods can also be used to achieve multi-basket settlement management, which is not limited here.

[0089] In some embodiments, after determining the combined settlement weight based on the shopping settlement information, the weighing system will determine the remaining multiple unsettled combined shopping baskets as shopping baskets to be settled; based on the monitoring image information, determine the weight ratio of the settlement weight of the current shopping basket in the remaining weight value of the shopping basket to be settled; based on the weight ratio, determine the combined difference range between the remaining weight value and the weighing weight.

[0090] Among them, the shopping basket to be settled refers to the shopping basket that has not yet completed settlement in the joint shopping combination; the remaining unsettled shopping basket refers to the number of shopping baskets that are still to be processed; the weight proportion indicates the proportion of the expected weight of the current shopping basket in the total remaining weight; the joint difference range refers to the allowable error range calculated based on the proportion.

[0091] The weighing system executes this process after calculating the settled weight. Specifically, the system first counts the number of shopping baskets that have not yet been settled, and then evaluates the weight proportion that the current shopping basket to be settled should carry by analyzing the distribution of goods in the monitoring image. Based on this weight proportion, the system dynamically calculates the allowable error range applicable to the current settlement, making the error control more targeted and reasonable.

[0092] In some embodiments, the dynamic error range determination based on the percentage can be achieved in a variety of ways: optionally, counting the number of unsettled baskets; analyzing the distribution characteristics of goods; calculating the expected weight percentage. Optionally, establishing a multi-level error model; combining the loss characteristics of goods; generating an adaptive threshold. It is understandable that other algorithms can also be used to achieve dynamic adjustment of the error range, which is not limited here.

[0093] S207: Generate a goods record according to the goods identification and weight reduction value of the fresh goods, and bind the goods record to the shopping cart identification.

[0094] Referring to step S102, the weighing system will bind the goods record to the shopping basket identifier.

[0095] S208: When it is detected that the weight of the fresh goods on the target shelf increases, the weight increase value of the fresh goods is obtained.

[0096] Among them, the weight increase value indicates the actual weight value of the goods when they are put back; the weight increase of fresh goods indicates the return operation of similar goods.

[0097] The weighing system executes this step when it detects an increase in the weight of the shelf. Specifically, the system monitors the weight change in real time through the shelf sensor. When it detects an increase in the weight of a certain type of commodity area, it records the specific value of the increase and confirms whether it is the return of the same type of commodity through image recognition for subsequent record verification processing.

[0098] In some embodiments, the detection and confirmation of weight gain can be achieved in a variety of ways: optionally, monitoring positive weight changes; identifying the category of returned goods; and recording the increased weight value. Optionally, analyzing the weight change trend; confirming the corresponding relationship of goods; and generating a return record. It is understandable that other detection methods can also be used to achieve weight gain monitoring, which is not limited here.

[0099] In some embodiments, the weighing system will obtain monitoring image information of the target shelf portion when detecting an increase in the weight of fresh goods on the target shelf; after determining that the newly added goods at the target shelf portion are fresh goods based on the monitoring image information, the weight increase value of the fresh goods is obtained.

[0100] Among them, the target shelf part indicates the specific area where the weight change is detected; the monitoring image information refers to the real-time scene data collected by the shelf camera; and the newly added goods refer to the goods put back on the shelf.

[0101] The weighing system executes this process when it detects an increase in the weight of the shelf. Specifically, the system immediately starts the camera in the corresponding area to collect images and confirms the type of items put back through image recognition technology. When it is confirmed that it is the return operation of the original fresh goods, the system records the actual increase detected by the weight sensor for subsequent record verification processing. If it is not the original fresh goods, it is returned incorrectly, and a prompt message is generated and sent to the administrator terminal to prompt the goods to be sorted.

[0102] In some embodiments, confirmation and recording of returned goods can be achieved in a variety of ways: optionally, triggering multi-angle shooting; performing image recognition analysis; verifying the consistency of goods. Optionally, collecting weight change curves; matching product feature information; generating return records. It is understandable that other monitoring methods can also be used to achieve confirmation of returned goods, which are not limited here.

[0103] S209: When the difference between the weight increase value and the weight decrease value is lower than a preset loss threshold, remove the goods record on the shopping cart identifier.

[0104] Among them, the preset loss threshold represents the allowable weight error range; the difference represents the numerical difference between the weight increase and the previous weight decrease; and removing the cargo record means canceling the corresponding commodity transaction information.

[0105] The weighing system executes this step after confirming the weight increase. Specifically, the system compares the detected weight increase with the previously recorded weight decrease and calculates the difference between the two. If the difference is within the preset loss threshold, it is considered a valid return and the corresponding goods record previously bound to the shopping cart logo is deleted or marked as invalid, thus revoking the transaction.

[0106] In some embodiments, the record removal operation can be implemented in a variety of ways: optionally, calculating the weight difference deviation; verifying the rationality of the loss; executing the record cancellation. Optionally, marking the record invalid; updating the shopping cart binding; synchronizing the database information. It is understandable that other processing methods can also be used to implement record removal, which is not limited here.

[0107] S210: When it is detected that the shopping basket is interconnected with the weighing terminal, a plurality of target goods records to be settled are determined based on the shopping basket identifier of the shopping basket.

[0108] Referring to step S103 , the weighing system determines a plurality of target goods records to be settled in the shopping cart.

[0109] S211, determining the weighing weight of the goods to be settled on the weighing terminal, and determining the target goods record corresponding to the goods to be settled.

[0110] Referring to step S104, the weighing system determines the target cargo record corresponding to the cargo to be settled.

[0111] S212: When the difference between the weight reduction value in the target cargo record and the weighed weight is lower than a preset loss threshold, the weighed weight is used as the settlement weight of the cargo to be settled, and a settlement list is generated.

[0112] Referring to step S105, the weighing system generates a settlement list.

[0113] In some embodiments, the weighing system monitors the remaining quantity of fresh goods on the target shelf; determines the shipment quantity of fresh goods within a preset time period based on multiple weight reduction values; determines the quantity of fresh goods to be replenished based on historical shipment data, combined with the shipment quantity and the remaining quantity, and sends the quantity of fresh goods to be replenished to the shipment management terminal.

[0114] Among them, the remaining quantity refers to the real-time inventory on the shelves; the shipment volume refers to the total sales volume within a specific time period; the historical shipment data represents past sales records; the quantity to be replenished refers to the number of goods that need to be replenished; and the shipment management terminal refers to the management equipment responsible for replenishing goods.

[0115] The weighing system executes this process after completing the commodity transaction processing. Specifically, the system continuously monitors the remaining quantity of various fresh commodities on the shelves and counts the sales data within a preset time period. By analyzing historical sales trends and combining current inventory and sales conditions, the system calculates the optimal replenishment quantity and pushes the replenishment information to relevant managers.

[0116] In some embodiments, intelligent replenishment management can be implemented in a variety of ways: optionally, real-time monitoring of inventory changes; analysis of sales periodicity; prediction of replenishment demand. Optionally, establishing a dynamic inventory model; optimizing replenishment time points; generating replenishment warnings. It is understandable that other prediction methods can also be used to implement intelligent inventory management, which is not limited here.

[0117] It should be noted that the replenishment method in this application will use image recognition models and sales forecasting models.

[0118] The image recognition model is trained using a large number of labeled fresh product image data sets during the training phase. The input includes product images at different angles and lighting conditions, as well as scene images of multiple shopping baskets at the same time. The output is the product category identification and shopping basket location information. The training standards include that the product recognition accuracy must reach more than 95% and the shopping basket positioning error must be less than 10 pixels. The image recognition model adopts a deep convolutional neural network architecture, which includes a feature extraction layer, a target detection layer, and a classification layer. The feature extraction layer is used to identify the color, shape, texture and other features of the product; the target detection layer is used to locate the shopping basket position in the picture; the classification layer is used to determine the association between the product category and the shopping basket. In real-time monitoring, the image recognition model receives the image stream collected by the shelf camera, and the output includes: product category judgment results, shopping basket location coordinates, and spatial relationship judgment results of multiple shopping baskets, which are used to support the system to track the flow of goods and associate multiple baskets.

[0119] The sales forecasting model uses multi-dimensional data such as long-term sales records, holiday information, and weather data for training during the training phase. The input includes historical sales volume, time characteristics, environmental factors, etc., and the output is the sales forecast for the future period. The training standard requires the prediction accuracy to reach more than 90%. The sales forecasting model uses a time series prediction model, combined with multivariate correlation analysis, including a trend analysis module, a cycle identification module, and a fluctuation prediction module. It can identify sales patterns and predict short-term and medium-term sales trends. The sales forecasting model continuously receives real-time sales data, combines historical patterns, and outputs sales volume forecasts for a certain period in the future to guide the system in inventory management and replenishment decisions.

[0120] In the embodiment of the present application, due to the use of weight sensing and image recognition, combined with shopping basket automatic recognition and joint shopping behavior analysis technology, it is possible to achieve full automatic tracking and recording of fresh goods from pickup to settlement, effectively solving the problems of the traditional technology that requires manual operation of weighing equipment, easy queuing, large weighing errors, and difficulty in handling multiple people shopping together, thereby achieving improved shopping efficiency, improved settlement accuracy, reduced labor costs, and intelligent inventory management. At the same time, through functions such as dynamic threshold adjustment and intelligent replenishment warning, the operational management efficiency of fresh goods is further optimized, bringing a better shopping experience to supermarkets and customers.

[0121] The weighing system in the embodiment of the present invention is described below from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a weighing system in an embodiment of the present application.

[0122] It should be noted that Figure 3 The structure of the weighing system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0123] like Figure 3 As shown, the weighing system includes 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. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through the bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0124] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. 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. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0125] 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, which includes a computer program carried on a computer-readable medium, and the computer program includes 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 through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0126] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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 disk 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 may be used by or in combination with an instruction execution system, apparatus, or device.

[0127] 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 may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a 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 may also occur in an order different from that marked in the accompanying drawings.

[0128] Specifically, the weighing system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the automatic weighing method of the fresh food smart shelf provided in the above embodiment is implemented.

[0129] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the weighing system described in the above embodiment; or may exist independently without being assembled into the weighing system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the weighing system, the weighing system implements the automatic weighing method of the fresh smart shelf provided in the above embodiment.

[0130] 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned 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.

[0132] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for automatic weighing of fresh food intelligent shelves, characterized in that: Applied to a weighing system, the method comprises: When it is detected that the weight of the fresh goods on the target shelf is reduced, the weight reduction value of the fresh goods and the shopping basket identifier of the shopping basket interconnected with the target shelf are obtained; Generate a goods record according to the goods identifier of the fresh goods and the weight reduction value, and bind the goods record to the shopping basket identifier; When it is detected that the shopping basket is interconnected with the weighing terminal, a plurality of target goods records to be settled are determined based on the shopping basket identifier of the shopping basket; Determine the weighing weight of the goods to be settled on the weighing terminal, and determine the target goods record corresponding to the goods to be settled; When the difference between the weight reduction value in the target cargo record and the weighed weight is lower than a preset loss threshold, the weighed weight is used as the settlement weight of the cargo to be settled, and a settlement list is generated.

2. The method according to claim 1, characterized in that After the step of acquiring the weight reduction value of the fresh goods and the shopping basket identifier of the shopping basket interconnected with the target shelf when the weight reduction of the fresh goods on the target shelf is detected, the method further includes: When there are multiple shopping basket identifiers, acquiring monitoring image information of the target shelf location; Based on the monitoring image information, determining a plurality of joint shopping baskets for storing the fresh goods, and determining joint shopping basket identifiers of the plurality of joint shopping baskets; generating a combined goods record according to the goods identification of the fresh goods and the weight reduction value, and binding the combined goods record to the combined shopping basket identification; When it is detected that the joint shopping basket is interconnected with the weighing terminal, the weighing weight of the goods to be settled on the weighing terminal is determined, and the joint goods record corresponding to the goods to be settled is determined; When the difference between the weight reduction value in the combined cargo record and the weighed weight is within the combined difference range, the weighed weight is used as the settlement weight of the cargo to be settled, and a settlement list is generated.

3. The method according to claim 2, characterized in that When the difference between the weight reduction value in the combined cargo record and the weighed weight is within the combined difference range, the weighed weight is used as the settlement weight of the cargo to be settled, and a settlement list is generated, which specifically includes: Determine shopping settlement information of other joint shopping carts corresponding to the current shopping cart; Determine the joint settlement weight corresponding to the joint goods record based on the shopping settlement information, and correct the weight reduction value to the remaining weight value; the joint settlement weight is the sum of the settlement weights of the other joint shopping baskets; the remaining weight value is the weight reduction value after deducting the joint settlement weight; Determining a combined difference range based on the shopping settlement information; When the difference between the remaining weight value and the weighed weight is within the combined difference range, the weighed weight is used as the settlement weight of the goods to be settled, and a settlement list is generated.

4. The method according to claim 3, characterized in that The determining of the combined difference range based on the shopping settlement information specifically includes: After determining the joint settlement weight based on the shopping settlement information, determining a plurality of remaining unsettled joint shopping baskets as shopping baskets to be settled; Determine, according to the monitoring image information, the weight ratio of the settled weight of the current shopping basket to the remaining weight of the shopping basket to be settled; According to the weight ratio, a combined difference range between the remaining weight value and the weighing weight is determined.

5. The method according to claim 1, characterized in that After the step of generating a goods record according to the goods identification of the fresh goods and the weight reduction value, and binding the goods record to the shopping basket identification, the method further includes: When detecting that the weight of the fresh goods on the target shelf increases, obtaining the weight increase value of the fresh goods; When the difference between the weight increase value and the weight decrease value is lower than the preset loss threshold, the goods record on the shopping basket identifier is removed.

6. The method according to claim 5, characterized in that When the weight increase of the fresh goods on the target shelf is detected, obtaining the weight increase value of the fresh goods specifically includes: When the weight of the fresh goods on the target shelf is detected to increase, monitoring image information of the target shelf portion is obtained; After determining that the newly added goods at the target shelf position are the fresh goods according to the monitoring image information, the weight increase value of the fresh goods is obtained.

7. The method according to claim 1, characterized in that When the difference between the weight reduction value in the target cargo record and the weighed weight is lower than a preset loss threshold, the weighed weight is used as the settlement weight of the cargo to be settled, and after the step of generating a settlement list, the method further includes: Monitoring the remaining quantity of the fresh goods on the target shelf; Determining the shipment volume of the fresh goods within a preset time period according to the plurality of weight reduction values; Based on the historical shipment data, in combination with the shipment volume and the remaining volume, the volume of the fresh goods to be replenished is determined, and the volume of the fresh goods to be replenished is sent to the shipment management terminal.

8. A weighing system, characterized in that: The weighing system comprises: 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 comprises computer instructions, and the one or more processors call the computer instructions so that the weighing system executes the method as 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 a weighing system, the weighing system is 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 is run on a weighing system, the weighing system is caused to perform the method according to any one of claims 1 to 7.

Images