Commodity type verification method and device and storage medium

Abstract

The invention discloses a commodity type verification method and device and a storage medium, and belongs to the technical field of data processing. The method comprises the following steps: after a commodity verification process is triggered, obtaining a commodity type and a commodity arrangement length corresponding to a shelf propeller, obtaining a commodity single-piece length corresponding to the commodity type, calculating a quotient value of the commodity arrangement length and the commodity single-piece length, comparing the quotient value with a preset value range, and obtaining a commodity verification result; and obtaining a commodity verification result of the shelf propeller according to a comparison result. According to the condition that different commodity single-piece lengths are different, when wrong placement of non-class commodities occurs and the quotient value of the actual arrangement length and the standard commodity single-piece length exceeds the preset reasonable range, the commodity type is judged to be abnormal, the situation that sizes of different classes of commodities are wrongly counted into total quantity for calculation is avoided, and the commodity quality is improved. Therefore, the accuracy of commodity quantity statistics is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, and storage medium for verifying commodity types. Background Art

[0002] Shelf pushers are used to store goods to be sold and push the goods on the shelves forward through baffles, ensuring that the goods are always kept at the front of the shelves, making it convenient for customers to access and replenish goods.

[0003] In related technologies, the shelf pusher identifies the position of the baffle by setting up laser, infrared and other sensors, and determines the length of the goods arranged on the shelf based on the baffle position, thereby calculating the remaining number of goods on the shelf based on the length of the goods arranged and the size of the goods.

[0004] However, when products are stacked disorderly due to user shopping behavior, the shelf pusher will add the size information of the incorrectly placed products to the length of the product arrangement, so that the calculated number of remaining products does not match the actual number.

[0005] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of this application is to provide a method, device and storage medium for verifying the type of goods, aiming to solve the technical problem that the number of remaining goods counted by the shelf pusher is easily miscalculated due to interference caused by incorrectly placed goods.

[0007] To achieve the above objectives, the present application provides a method for verifying the type of goods, the method comprising the following steps:

[0008] After triggering the product type verification process, obtain the product type and product arrangement length corresponding to the shelf pusher;

[0009] Obtaining the length of a single item of the item corresponding to the item type, and calculating the quotient of the item arrangement length and the length of the single item of the item;

[0010] The quotient value is compared with a preset value range, and a verification result of the product type is obtained according to the comparison result.

[0011] In one embodiment, after the step of comparing the quotient with a preset value range and obtaining a verification result of the product type according to the comparison result, the following step is further included:

[0012] Obtaining the weight of the goods on the shelf pusher through a weight sensor;

[0013] Determining the remaining quantity of goods based on the quotient, and determining the target weight of goods corresponding to the quantity of goods;

[0014] The product weight is compared with the target product weight, and the verification result is adjusted according to the comparison result.

[0015] In one embodiment, the shelf pusher includes a counting sensor and a baffle, and the counting sensor generates and outputs sensor data based on the movement distance of the baffle. After triggering the product type verification process, before obtaining the product type and product arrangement length corresponding to the shelf pusher, the step further includes:

[0016] Upon receiving the sensing data sent by the counting sensor, determining the baffle movement distance corresponding to the sensing data;

[0017] Update the length of the product arrangement according to the movement distance of the baffle;

[0018] When the length of the commodity arrangement increases, the verification process of the commodity type is triggered.

[0019] In one embodiment, the counting sensor is a roller sensor, which is connected to the baffle via a connecting rope. The roller sensor retracts and extends the connecting rope based on the movement distance of the baffle and generates a pulse signal. The step of updating the product arrangement length according to the movement distance of the baffle includes:

[0020] receiving the pulse signal and accumulating pulse quantity information of the pulse signal;

[0021] Determining the baffle movement distance according to the pulse quantity information, the pulse unit distance of the pulse signal, and the pulse signal type;

[0022] The commodity arrangement length is updated according to the commodity length change corresponding to the baffle movement distance.

[0023] In one embodiment, the step of comparing the quotient with a preset value range and obtaining a verification result of the product type according to the comparison result includes:

[0024] Extracting the decimal part of the quotient to obtain a verification value;

[0025] By comparing the verification value with the boundary value of the preset value range, determining whether the verification value is within the preset value range;

[0026] If the verification value is within the preset value range, the verification result is determined to be an abnormal commodity type;

[0027] Alternatively, if the verification value is not within the preset value range, the verification result is determined to be that the commodity type is normal.

[0028] In one embodiment, the shelf pusher is further equipped with a display screen, and after the step of comparing the quotient with a preset value range and obtaining a verification result of the commodity type based on the comparison result, the following steps are further included:

[0029] When the verification result shows that the commodity type is abnormal, determining the shelf number corresponding to the shelf pusher;

[0030] Obtain a prompt information template, and fill the shelf number into the prompt information template to generate an abnormal prompt information;

[0031] The abnormal prompt information is output to the administrator terminal and / or the display screen.

[0032] In one embodiment, the shelf pusher further includes an environmental sensor, and the step of obtaining the length of a single commodity corresponding to the commodity type and calculating the quotient of the commodity arrangement length and the single commodity length further includes:

[0033] Obtaining a deformation compensation model corresponding to the product type and a thrust analysis model of the baffle based on the baffle position;

[0034] Determining the deformation pressure corresponding to the degree of deformation of the remaining number of commodities in the shelf pusher at different baffle positions according to the deformation compensation model;

[0035] Determining the baffle thrust corresponding to the baffle position based on the thrust analysis model;

[0036] determining a target baffle position when the deformation pressure matches the baffle thrust, and determining a target arrangement length according to the target baffle position;

[0037] The length of each commodity is determined based on the ratio of the target arrangement length to the number of remaining commodities.

[0038] In one embodiment, after the step of comparing the quotient with a preset value range and obtaining a verification result of the product type according to the comparison result, the following step is further included:

[0039] When the verification result shows that the commodity type is abnormal, a shelf image of the shelf pusher is obtained through a camera;

[0040] Identifying feature information of the shelf image using a semantic segmentation model;

[0041] Matching the characteristic information with commodity characteristic information, and determining commodity storage information of the shelf pusher according to the matching result;

[0042] Based on the commodity storage information, the verification result of the commodity type is adjusted.

[0043] In addition, to achieve the above-mentioned purpose, the present application also provides a commodity type verification device, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the commodity type verification method as described above.

[0044] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the commodity type verification method as described above are implemented.

[0045] One or more technical solutions proposed in this application have at least the following technical effects:

[0046] After triggering the product verification process, this application obtains the product type and product arrangement length corresponding to the shelf pusher, and then calculates the quotient of the product arrangement length and the product single piece length based on the product single piece length associated with the product type. By comparing the quotient with the preset value range, it is determined whether the product arrangement on the current shelf meets the standard size characteristics of the product type. Among them, when non-type products are incorrectly placed, due to the differences in the lengths of different products, the quotient of their actual arrangement length and the standard product single piece length will exceed the preset reasonable range, thereby determining that the placement of the product type is abnormal, avoiding the incorrect inclusion of the size of different products in the total amount calculation, ensuring the accuracy of product quantity statistics from the source, and avoiding the limitations of relying solely on sensors to measure the length of product arrangements. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 This is a flowchart of the first embodiment of the method for verifying the product type of this application;

[0050] Figure 2 This is a flow chart of a second embodiment of the method for verifying the product type of this application;

[0051] Figure 3 This is a flowchart of the third embodiment of the method for verifying the product type of this application;

[0052] Figure 4 This is a schematic structural diagram of a shelf pusher according to a third embodiment of the present application;

[0053] Figure 5 This is a flowchart of a fourth embodiment of the method for verifying product types of this application;

[0054] Figure 6 This is a flowchart of a fifth embodiment of the method for verifying the product type of this application;

[0055] Figure 7 This is a flowchart of a sixth embodiment of the method for verifying the product type of this application;

[0056] Figure 8 It is a structural diagram of a commodity type verification device for the hardware operating environment involved in the embodiment of the present application.

[0057] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0059] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0060] The main solution of the embodiment of the present application is: after triggering the product verification process, obtain the product type and product arrangement length corresponding to the shelf pusher; obtain the single product length corresponding to the product type, and calculate the quotient of the product arrangement length and the single product length; compare the quotient with the preset value range, and obtain the product verification result of the shelf pusher based on the comparison result.

[0061] In existing technologies, shelf pushers use laser, infrared, or other sensors to identify the position of baffles and determine the length of the shelves based on the baffle positions. This allows them to calculate the number of remaining items based on the length and size of the items. However, if items are stacked out of order due to user shopping behavior, the shelf pushers will add the size information of incorrectly placed items to the length of the shelves, causing the calculated number of remaining items to be inconsistent with the actual number.

[0062] After triggering the product verification process, this application obtains the product type and product arrangement length corresponding to the shelf pusher, and then calculates the quotient of the product arrangement length and the product single piece length based on the product single piece length associated with the product type. By comparing the quotient with the preset value range, it is determined whether the product arrangement on the current shelf meets the standard size characteristics of the product type. Among them, when non-type products are incorrectly placed, due to the differences in the lengths of different products, the quotient of their actual arrangement length and the standard product single piece length will exceed the preset reasonable range, thereby determining that the placement of the product type is abnormal, avoiding the incorrect inclusion of the size of different products in the total amount calculation, ensuring the accuracy of product quantity statistics from the source, and avoiding the limitations of relying solely on sensors to measure the length of product arrangements.

[0063] To better understand the above technical solutions, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0064] It should be noted that the execution entity of this embodiment can be a product management system, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions, a product type verification device, etc., and this embodiment does not specifically limit this. The following uses the product management system as an example to illustrate this embodiment and the following embodiments.

[0065] Based on this, the embodiment of the present application provides a method for verifying the type of goods, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for verifying the product type of this application.

[0066] In this embodiment, the commodity type verification method includes steps S10 to S40:

[0067] Step S10: After triggering the verification process of the commodity type, obtain the commodity type and commodity arrangement length corresponding to the shelf pusher;

[0068] In this embodiment, a shelf pusher is an automated device installed on a shelf, used to push products and detect their arrangement. Shelf pushers are typically equipped with sensors, such as counting sensors and weight sensors, to obtain physical parameters of the products, such as arrangement length and weight. The arrangement length is the total length of the products on the shelf along a specific direction, such as horizontally or vertically. This is typically determined by sensors based on measurements of the distance a barrier moves or the space occupied by the products.

[0069] Specifically, the product management system maintains a wired or wireless communication connection with each shelf pusher, receives sensor signals, and calculates the product arrangement length based on the sensor signals, storing the product arrangement length in a database. When the product verification process is triggered, the product management system can query the database to obtain the updated and saved product arrangement length based on the shelf pusher sensor signals. The database can be a local database of the product management system or a cloud database connected to the product management system.

[0070] For example, the baffle of a shelf pusher moves when products are put on or taken off the shelf. The product management system receives sensor data from a counting sensor, measures the distance the baffle moves, and thus calculates the length of the product arrangement. For example, a roller sensor is connected to the baffle via a connecting rope. When the baffle moves, the roller rotates and generates a pulse signal, with the number of pulses proportional to the distance moved.

[0071] Optionally, the product type verification process can be triggered in a variety of ways, such as manual initiation by an administrator, sensor detection of product placement or removal, or system timer task triggering. The core of the trigger mechanism is to ensure that the verification process is initiated in a timely manner when the status of the product changes. For example, when a shelf pusher receives a product type verification request from the shelf pusher, it can trigger the product type verification process in the shelf pusher. Alternatively, when the shelf pusher receives sensor data, it can verify the change in the length of the product arrangement corresponding to the sensor data according to preset rules, and trigger the product type verification process when the verification passes.

[0072] Furthermore, the product management system can obtain product types in different ways based on different verification process triggering methods. For example, when a shelf pusher receives a product type verification request, it can obtain the shelf number from the verification request and determine the product type associated with that shelf number in the database. Furthermore, when a shelf pusher triggers a verification process based on sensor data, the product management system can also determine the corresponding shelf pusher number based on the source of the sensor data and obtain the associated product type from the database.

[0073] As an optional implementation for obtaining product types, each shelf pusher is connected to a base station that receives sensor data from the shelf pusher. The base station can determine the source of the sensor data and, based on the source of the pulse signal, determine the shelf pusher number corresponding to the shelf pusher where the sensor is located. The shelf pusher number is then sent to the product management system. The product management system then searches the database for the corresponding product type based on the shelf pusher number.

[0074] As another alternative implementation for obtaining product types, for example, when a restocker restocks a shelf, the shelf pusher can proactively send a verification request to the product management system, triggering a verification process to verify the correct product type. The verification request also includes the shelf ID or shelf pusher ID, allowing the product management system to query the database for the corresponding product type.

[0075] Step S20: obtaining the length of a single commodity corresponding to the commodity type, and calculating the quotient of the commodity arrangement length and the length of the single commodity;

[0076] In this embodiment, the length of a single item is the length of a single item in a specific direction, such as the width of a beverage bottle or the length of a snack package. This length is determined based on the position of the item as it is placed on the shelf pusher. The length of a single item is typically stored in a database and associated with the item type. The quotient is the ratio of the length of the array of items to the length of the single item, and is used to determine whether the actual number of items on the shelf is consistent with the expected number. This quotient can be represented by a floating-point number or other data result.

[0077] Specifically, the product management system queries the database for the unit length corresponding to the current product type. The database stores the dimensions of all products, and using the product type as an index, it quickly retrieves the corresponding unit length. The quotient is calculated by dividing the length of the product array by the unit length. The integer portion of the quotient represents the actual number of products, while the decimal portion indicates any anomalies (such as tilted or misaligned products).

[0078] Step S30: comparing the quotient with a preset value range, and obtaining a verification result of the commodity type according to the comparison result.

[0079] In this embodiment, the preset value range is a reasonable interval of the quotient value, which is usually set in advance based on data such as the physical characteristics and arrangement rules of the goods. The product management system verifies the quotient value by comparison based on the preset value range to obtain a verification result of the product type.

[0080] As an optional implementation, the product management system extracts the decimal portion of the quotient to obtain a verification value. This verification value, based on the characteristic that the decimal portion of the quotient can indicate possible anomalies in product placement, is used to determine the verification result of the product type. The product management system compares the verification value with the boundary value of a preset value range to determine whether it is within the preset value range.

[0081] It is understood that the preset value range can be a range within which the verification result is judged to be an abnormal product type, or a range within which the verification result is judged to be a normal product type. For example, if the verification value is greater than the left boundary value of the preset value range and less than the right boundary value, that is, it is within the preset value range, then the product verification result is judged to be an abnormal product type. Alternatively, if the verification value is not within the preset value range, then the product type verification result is judged to be a normal product type. Optionally, the preset value range can also be a preset threshold value, which only includes a single boundary value. When the verification value is greater than the preset threshold value, the product type is judged to be abnormal.

[0082] It should be noted that in shelf pushers, because the retraction of baffles keeps products clustered, the impact of abnormal placement factors such as tilted or misaligned products on the fractional portion of the quotient is minimal. Therefore, the product management system can infer the impact of incorrect product type based on the size of the fractional portion of the quotient and determine whether products are placed abnormally based on different product types.

[0083] As another optional implementation, the product management system can also calculate a preset value range based on the quotient. For example, the integer portion of the quotient can be combined with the decimal portion of the preset boundary feature to obtain the left and right boundary values ​​of the preset value range. The quotient can then be judged to determine whether it is within the preset value range, thereby determining the verification result.

[0084] The embodiment of the present application obtains the product type and product arrangement length corresponding to the shelf pusher after triggering the product verification process, and then calculates the quotient of the product arrangement length and the product single-piece length based on the product single-piece length associated with the product type, and judges whether the product arrangement on the current shelf meets the standard size characteristics of the product type by comparing the quotient with the preset value range. In particular, when non-type products are incorrectly placed, due to the differences in the lengths of different products, the quotient of their actual arrangement length and the standard product single-piece length will exceed the preset reasonable range, thereby determining that the placement of the product type is abnormal, avoiding the incorrect inclusion of the size of different products in the total amount calculation, ensuring the accuracy of the product quantity statistics from the source, and avoiding the limitations of relying solely on sensors to measure the product arrangement length.

[0085] Based on the same inventive concept, this application also provides a second embodiment, referring to Figure 2 , Figure 2This is a flow chart of the second embodiment of the method for verifying the product type of this application.

[0086] In this embodiment, if Figure 1 After comparing the quotient with the preset value range in step S30 and obtaining the verification result of the commodity type according to the comparison result, steps S41 to S43 are also included:

[0087] Step S41: Obtaining the weight of the goods on the shelf pusher through a weight sensor;

[0088] Step S42: determining the remaining quantity of goods based on the quotient, and determining the target weight of goods corresponding to the quantity of goods;

[0089] Step S43: comparing the commodity weight with the target commodity weight, and adjusting the verification result according to the comparison result.

[0090] It should be noted that in order to avoid the situation where the size information of different types of goods is relatively similar, which causes the product management system to be unable to identify abnormal types of goods on the shelf based on the single dimension of size information, the shelf pusher is further provided with a weight sensor to identify the wrong heterogeneous goods placed on the shelf based on the fact that different types of goods usually have different weights.

[0091] In this embodiment, the weight sensor converts physical weight into an electrical signal and is typically mounted on the bottom of the shelf pusher or supporting structure. Optionally, when a product is placed on the shelf, the weight sensor detects the weight of the product and converts the analog signal into a digital signal using an analog-to-digital converter (ADC) for processing by the product management system.

[0092] Specifically, the quotient is the ratio of the length of the arrayed items to the length of a single item. The integer portion of this quotient represents the actual number of items. After determining the remaining number of items using the quotient, the product management system calculates the target product weight based on the unit weights corresponding to the product type stored in the database. The target product weight is the theoretical total weight of the items, which is used for comparison with the actual weight measured by the weight sensor.

[0093] Optionally, the product management system may compare the decimal portion of the quotient with a preset value range. If the decimal portion is greater than the preset value range, the integer portion of the quotient is incremented by one to obtain the remaining number of products. Alternatively, if the decimal portion is less than the preset value range, the integer portion of the quotient is directly used as the remaining number of products.

[0094] Furthermore, by comparing the actual measured product weight with the target product weight, the accuracy of the product quantity can be further verified. If the difference between the two exceeds a preset threshold (e.g., 5%), the product verification result is considered abnormal, possibly due to incorrect product placement or weight sensor failure. If the comparison result shows a mismatch, the product management system adjusts the verification result to an abnormal product type.

[0095] This embodiment of the application uses a weight sensor to obtain the weight of goods and compares it with the target weight, further verifying the accuracy of the product quantity. Weight verification, as an auxiliary measure, can effectively reduce misjudgments caused by misaligned goods or sensor errors, thereby improving the reliability of product verification. Furthermore, weight verification results can be directly fed back into the system for subsequent inventory management and exception handling.

[0096] Since the system described in Example 2 of this application is the system used to implement the method of Example 1 of this application, those skilled in the art will be able to understand the specific structure and variations of the system based on the method described in Example 1 of this application, and therefore, no further description is given here. All systems used in the method of Example 1 of this application fall within the scope of protection to be provided by this application.

[0097] Based on the same inventive concept, this application also provides a third embodiment, referring to Figure 3 , Figure 3 This is a flow chart of the third embodiment of the product type verification method of this application.

[0098] In this embodiment, the commodity type verification method further includes steps S01 to S03:

[0099] Step S01: upon receiving the sensing data sent by the counting sensor, determining the baffle movement distance corresponding to the sensing data;

[0100] Step S02: updating the product arrangement length according to the baffle movement distance;

[0101] In this embodiment, the shelf pusher includes a counting sensor and a baffle, and the counting sensor generates and outputs sensor data based on the moving distance of the baffle. The counting sensor is a device that can detect physical displacement and generate a pulse signal, and can be optionally installed near the baffle of the shelf pusher, or at the tail end of the commodity slot of the shelf pusher. When the baffle moves, the counting sensor detects the moving distance through a mechanical connection (such as a roller or gear) or a sensor signal (such as infrared or laser), and generates a pulse signal proportional to the moving distance. The moving distance of the baffle can be accurately calculated based on the number of pulses and the unit pulse distance. Among them, the moving distance of the baffle directly reflects the change in the arrangement length of the goods on the shelf. The commodity management system updates the commodity arrangement length based on the received sensor data, ensures that the verification process is based on the real-time commodity status, and improves the real-time and accuracy of the verification.

[0102] As an optional embodiment, the counting sensor in the shelf pusher can be a roller sensor, wherein the roller sensor is connected to the baffle via a connecting rope. The roller sensor retracts or releases the connecting rope based on the distance the baffle moves, thereby generating a pulse signal. The number of pulse signals is proportional to the distance the baffle moves. When the product management system receives the pulse signal, it accumulates the number of pulse signals. The product management system determines the distance the baffle moves based on the number of pulses over a period of time and the pulse unit distance corresponding to the pulse signal.

[0103] Optionally, the roller sensor can emit different types of pulse signals based on different roller rotation directions to indicate different movement directions of the baffle. The product management system can further determine the direction of baffle movement based on the pulse signal type corresponding to the shelf pusher. The product management system can determine the product change length based on the baffle movement distance and the baffle movement direction. For example, when the product arrangement length increases, the product change length is greater than zero, and when the product arrangement length decreases, the product change length is less than zero. The product management system updates the product arrangement length based on the product change length corresponding to the baffle movement distance.

[0104] For example, Figure 4 As shown, Figure 4 The figure is a schematic diagram of the shelf pusher structure involved in this embodiment. The shelf pusher includes a roller sensor, a connecting rope, a baffle, a display screen and a commodity slot. The commodity slot is used to store commodities. The connecting rope is connected to the baffle around the horizontal column below the display screen, and when the commodities are taken out, the baffle is pulled toward the commodity pickup position based on the tension of the connecting rope recovered by the roller sensor, so that the commodities on the commodity slot are gathered. At the same time, a sensor chip is provided in the roller sensor, which can send a pulse signal based on the rotation of the roller when the connecting rope is retracted by the roller. The roller sensor is provided with a serial port, which can send the pulse signal to the terminal where the commodity management system is located through wired communication.

[0105] As another optional embodiment, the shelf pusher can also be equipped with a laser sensor at the end of the commodity slot. The laser sensor can send laser light to the baffle and identify the position of the baffle by receiving the reflected laser light, thereby determining the distance the baffle has moved.

[0106] Step S03: When the length of the commodity arrangement increases, triggering the verification process of the commodity type.

[0107] In this embodiment, an increase in the length of a product array typically indicates that a new product has been placed on the shelf. This increase in the length of a product array may be due to a restock or a user placing a product. In the case of restocking, the product management system verifies the product type to determine whether the restocked product is of the correct type. Furthermore, in the case of a user placing a product, the product type verification can determine whether the user has placed the product on the correct shelf, allowing the administrator to promptly correct the product placement.

[0108] The present embodiment utilizes a counting sensor and baffle to achieve real-time updates of product arrangement lengths and automatically trigger the verification process. This method enables rapid response to product placement and removal, ensuring the timeliness and accuracy of the verification process. Furthermore, the high-precision measurement of the counting sensor reduces misjudgments caused by human intervention or sensor errors, improving system reliability and automation.

[0109] Since the system described in Example 3 of this application is the system used to implement the method of Example 1 of this application, those skilled in the art will be able to understand the specific structure and variations of the system based on the method described in Example 1 of this application, and therefore will not be described in detail here. All systems used in the method of Example 1 of this application fall within the scope of protection to be provided by this application.

[0110] Based on the same inventive concept, this application also provides a fourth embodiment, referring to Figure 5 , Figure 5 This is a flow chart of the fourth embodiment of the method for verifying product types of this application.

[0111] In this embodiment, if Figure 1 After comparing the quotient with the preset value range in step S30 and obtaining the commodity verification result of the shelf pusher according to the comparison result, the steps S51 to S53 are also included:

[0112] Step S51: when the commodity verification result is that the commodity type is abnormal, determining the shelf number corresponding to the shelf pusher;

[0113] Step S52: Obtain a prompt information template, and fill the shelf number into the prompt information template to generate abnormal prompt information;

[0114] Step S53: Output the abnormal prompt information to the administrator terminal and / or the display screen.

[0115] In this embodiment, the shelf number is the identification information of the shelf pusher, which is used to quickly locate abnormal shelves. When the verification result is abnormal, the administrator can quickly determine the shelf location based on the shelf number. The prompt information template is a predefined text format used to generate abnormal prompt information. By filling the shelf number into the template, prompt information containing the specific location can be quickly generated, which facilitates the administrator to respond quickly. Abnormal prompt information needs to be notified to the administrator in a timely manner so that corrective measures can be taken. By outputting to the administrator terminal and / or display screen, timely transmission and visual display of information can be ensured.

[0116] Specifically, a prompt message template is loaded from system resources, such as "An abnormal product type has been detected on shelf {number}. Please check." By filling the shelf number into the placeholder position in the template, the product management system can generate a complete abnormal prompt message. Furthermore, the product management system can also fill in information such as product quantity, value, and product type into the prompt message template.

[0117] In an alternative embodiment, if Figure 4 As shown, the shelf pusher also includes a display. This displays information such as the product name, remaining quantity, and price. The display maintains a data connection with the sensor data in the roller sensor via a data cable below the product slot. When the roller sensor sends a pulse signal, it synchronizes this pulse signal to the display via the data cable, causing the display to update the displayed product quantity.

[0118] Furthermore, when the commodity management system determines that the commodity type is abnormal, it will also send a prompt message to the display screen to update the shelf pusher status information displayed on the display screen to prompt the user or administrator that the current shelf is in a non-sale state.

[0119] In another alternative embodiment, the shelf pusher can also proactively trigger the product verification process by sending a product type verification request to the product management system during replenishment. If the verification result indicates that the product type is abnormal, the product management system will promptly display an abnormality prompt on the shelf pusher's display screen to inform the replenisher at the shelf that the replenished product type is abnormal.

[0120] Optionally, based on the length of the product arrangement and the length of a single product, the product management system can also calculate the remainder of the ratio of the length of the product arrangement to the length of a single product, match the remainder with different product size information, and filter the type of abnormal cause or the type of heterogeneous product based on the matching results. For example, the product management system matches the remainder with the product size information of each product to determine the target product type whose length information or width information of the size information is a multiple of the remainder, and arranges the target product type from near to far based on the positional relationship between the target shelf position and the current shelf position, so as to assist the administrator in determining the product type of the incorrectly placed product.

[0121] The embodiment of the present application achieves rapid location and notification of abnormal situations by generating and outputting abnormal prompt information. The generation and transmission of prompt information ensures that the administrator can understand the abnormal location and cause in a timely manner, reducing the time required to resolve the problem.

[0122] Since the system described in Example 4 of this application is the system used to implement the method of Example 1 of this application, those skilled in the art will be able to understand the specific structure and variations of the system based on the method described in Example 1 of this application, and therefore will not be described in detail here. All systems used in the method of Example 1 of this application fall within the scope of protection to be provided by this application.

[0123] Based on the same inventive concept, this application also provides a fifth embodiment, referring to Figure 6 , Figure 6 This is a flowchart of the fifth embodiment of the product type verification method of this application.

[0124] In this embodiment, the commodity type verification method further includes steps S61 to S63:

[0125] Step S61: obtaining a deformation compensation model corresponding to the product type and a thrust analysis model of the baffle based on the baffle position;

[0126] Step S62: determining the deformation pressure corresponding to the deformation degree of the remaining number of commodities in the shelf pusher at different baffle positions according to the deformation compensation model;

[0127] Step S63: determining the baffle thrust corresponding to the baffle position based on the thrust analysis model;

[0128] Step S64: determining a target baffle position when the deformation pressure matches the baffle thrust, and determining a target arrangement length according to the target baffle position;

[0129] Step S65: Determine the length of each product based on the ratio of the target arrangement length to the number of remaining products.

[0130] In this embodiment, as the shelf pusher retracts the baffle via the connecting rope, the baffle exerts a thrust on the products arranged in the shelf pusher, causing them to gather and deform to a certain extent. For example, sealed bagged products such as potato chips, rubber products, and plastic products are susceptible to deformation within the shelf pusher's product slot after being subjected to the force exerted by the shelf pusher, causing a certain change in the length of each product. Therefore, the product length obtained by the product management system based on product size information cannot be directly used to calculate the quotient of the product arrangement length and the individual product length.

[0131] Specifically, the commodity management system can obtain the degree of deformation of different quantities of goods under different pressures, or the pressure information corresponding to different degrees of deformation, based on the deformation compensation model corresponding to the commodity type. At the same time, the commodity management system can determine the thrust of the baffle at different positions based on the thrust analysis model corresponding to the pre-set shelf pusher. Among them, the deformation compensation model is based on the item characteristics corresponding to different commodity types, pre-built through big data analysis or deep learning, and saved in the commodity management system. The thrust analysis model is pre-built based on the structure of the shelf pusher.

[0132] When the baffle thrust and the corresponding deformation pressure information for the baffle position are identical, the baffle in the shelf pusher is at rest. The product management system iterates through each baffle position and, when the deformation pressure calculated based on the deformation compensation model and the baffle thrust calculated based on the thrust analysis model are identical at that baffle position, the arrangement length corresponding to the current baffle position is used as the target arrangement length—the expected length of the products arranged in the shelf pusher. The product management system can use the ratio of this target arrangement length to the number of remaining products as the unit length.

[0133] Furthermore, the product management system can further construct a mapping relationship between the remaining number of products and the length of a single product based on the product type, and store this mapping relationship in association with the shelf pusher. When the shelf pusher triggers the product type verification process again, the mapping relationship between the remaining number of products and the length of a single product corresponding to the product type is obtained from the mapping relationship associated with the shelf pusher, thereby improving the length of a single product after deformation compensation and the corresponding verification speed.

[0134] Optionally, the commodity management system can determine the corresponding unit length of the commodity at different remaining quantities of commodities in the shelf pusher by obtaining historical arrangement information corresponding to the commodity type. Specifically, the commodity management system forms a deformation compensation model by constructing a mapping relationship between the quantity of commodities of the commodity type and the unit length of commodities. The commodity management system can obtain the corresponding unit length of commodities based on the mapping relationship at different remaining quantities of commodities. Specifically, when the replenisher replenishes the commodity type corresponding to the shelf pusher for the first time, it is necessary to construct the configuration information of the elastic compensation of the commodity type. The replenisher will increase the number of commodities put in based on the operating instructions. The commodity management system obtains the commodity arrangement length under different commodity quantities based on the replenisher's operations. The commodity management system can use the ratio of the commodity arrangement length to the commodity quantity as the commodity unit length, or the commodity management system can also use the difference between the commodity arrangement length under the current commodity quantity and the commodity arrangement length of the adjacent commodity quantity with one less commodity than the current commodity quantity as the commodity unit length.

[0135] Optionally, the commodity management system can also calculate or obtain the elastic compensation coefficient of the commodity type based on the thrust coefficient of the baffle at different positions, and further obtain the unit length of the commodity based on the product size information and the product elastic compensation coefficient. The commodity management system constructs the elastic compensation coefficient by counting the deformation effects of different commodities on the inference coefficient. The commodity management system can multiply the first expected commodity arrangement length corresponding to the current number of commodities based on the elastic compensation coefficient to obtain the first commodity arrangement length. And in the same way, calculate the second commodity arrangement length of the adjacent commodity number with one less commodity than the current number of commodities. The commodity management system can use the difference between the first commodity arrangement length and the second commodity arrangement length as the unit length of the commodity, or use the first commodity arrangement length as the unit length of the commodity.

[0136] Optionally, a pressure sensor is provided on the baffle, and the baffle thrust at different positions of the baffle is identified by the pressure sensor.

[0137] The embodiment of the present application targets a special type of commodity, elastic items, and introduces a deformation compensation model to correct the length of a single item of commodity. This fully considers the dimensional changes of elastic items caused by external forces and other factors during actual placement, making the results of commodity type verification more accurate and reliable.

[0138] Since the system described in Example 5 of this application is the system used to implement the method of Example 1 of this application, those skilled in the art will be able to understand the specific structure and variations of the system based on the method described in Example 1 of this application, and therefore will not be described in detail here. All systems used in the method of Example 1 of this application fall within the scope of protection to be provided by this application.

[0139] Based on the same inventive concept, this application also provides a sixth embodiment, referring to Figure 7 , Figure 7 This is a flow chart of the sixth embodiment of the method for verifying product types of this application.

[0140] In this embodiment, the commodity type verification method further includes steps S71 to S74:

[0141] Step S71: When the verification result shows that the commodity type is abnormal, a shelf image of the shelf pusher is acquired through a camera;

[0142] Step S72: identifying feature information of the shelf image using a semantic segmentation model;

[0143] Step S73: matching the characteristic information with the commodity characteristic information, and determining the commodity storage information of the shelf pusher according to the matching result;

[0144] Step S74: Based on the commodity storage information, adjust the verification result of the commodity type.

[0145] In this embodiment, the camera is used to capture real-time images of the shelf pusher to provide data support for image recognition. When the verification result is abnormal, the system triggers the camera to capture images for further analysis of the cause of the abnormality. The semantic segmentation model is a deep learning model that can classify each pixel in the image into a specific semantic category (such as product, shelf, background, etc.). Through semantic segmentation, the product management system can extract feature information of the product, such as location, type, quantity, etc. Product feature information is the appearance features of the product (such as color, shape, barcode, etc.) pre-stored in the database. The product management system can determine the type and quantity of the products actually stored on the shelf by matching the extracted feature information with the feature information in the database. Based on the image recognition results, the product verification results can be adjusted. If the image recognition results are inconsistent with the initial verification results, the verification results may need to be updated to reflect the actual product status.

[0146] Exemplarily, when it is detected that the verification result of the product is abnormal, the image acquisition process is triggered, and the shelf image is captured by the camera arranged on the shelf. The product management system loads the pre-trained semantic segmentation model from the local and inputs the captured shelf image into the semantic segmentation model. The semantic segmentation model processes the image and outputs the feature information of the product (such as location coordinates, shape outline, etc.). The system queries the feature information of the target product type from the product database. The extracted feature information is matched using a matching algorithm (such as template matching or feature vector comparison). Based on the matching results, the type and quantity of the products actually stored on the shelf are determined. Compare the image recognition result with the initial verification result to determine whether there is a difference. If there is a difference, update the verification result based on the image recognition result.

[0147] The embodiment of the present application provides an additional verification method for commodity verification through image recognition technology, especially when there is uncertainty in the commodity verification result, the commodity status can be further confirmed through visual information.

[0148] Since the system described in Example 6 of this application is the system used to implement the method of Example 1 of this application, those skilled in the art will be able to understand the specific structure and variations of the system based on the method described in Example 1 of this application, and therefore will not be described in detail here. All systems used in the method of Example 1 of this application fall within the scope of protection to be provided by this application.

[0149] The present application provides a commodity type verification device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the commodity type verification method in the above-mentioned embodiment one.

[0150] Reference below Figure 8 , which shows a schematic diagram of the structure of a commodity type verification device suitable for implementing the embodiments of the present application. The commodity type verification device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The verification device for the commodity type shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0151] like Figure 8 As shown, the commodity type verification device may include a processing device 1001 (e.g., a core processor, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the commodity type verification device are also stored in the random access memory 1004. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the commodity type verification device to communicate wirelessly or wired with other devices to exchange data. Although commodity type verification devices with various systems are shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.

[0152] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0153] The product type verification device provided in this application, which adopts the product type verification method of the above-mentioned embodiment, can solve the technical problem that the number of remaining products counted by the shelf pusher is easily miscalculated due to interference caused by incorrectly placed products. Compared with the existing technology, the beneficial effects of the product type verification device provided in this application are the same as the beneficial effects of the product type verification method provided in the above-mentioned embodiment, and the other technical features of the product type verification device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0154] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0155] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0156] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the commodity type verification method in the above-mentioned embodiment.

[0157] The computer-readable storage medium provided in this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media can 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, Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM, CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, radio frequency (RF, Radio Frequency), etc., or any suitable combination thereof.

[0158] The computer-readable storage medium may be included in a commodity-type verification device, or may exist independently without being assembled into a commodity-type verification device.

[0159] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the commodity type verification device, the commodity type verification device: obtains the commodity type and commodity arrangement length corresponding to the shelf pusher after triggering the commodity verification process; obtains the single-piece length of the commodity corresponding to the commodity type, and calculates the quotient of the commodity arrangement length and the single-piece length of the commodity; compares the quotient with a preset value range, and obtains the commodity verification result of the shelf pusher based on the comparison result.

[0160] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0161] 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 application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0162] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0163] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for verifying product types. This computer-readable storage medium can address the technical issue of shelf pushers easily miscalculating the number of remaining products due to interference caused by misplaced products. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the method for verifying product types provided in the aforementioned embodiments, and are not further elaborated here.

[0164] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for verifying commodity types, characterized in that: The method comprises the following steps: After triggering the product type verification process, obtain the product type and product arrangement length corresponding to the shelf pusher; Obtaining the length of a single item of the item corresponding to the item type, and calculating the quotient of the item arrangement length and the length of the single item of the item; The quotient value is compared with a preset value range, and a verification result of the product type is obtained according to the comparison result.

2. The method according to claim 1, wherein After the step of comparing the quotient with the preset value range and obtaining the verification result of the product type according to the comparison result, the method further includes: Obtaining the weight of the goods on the shelf pusher through a weight sensor; Determining the remaining quantity of goods based on the quotient, and determining the target weight of goods corresponding to the quantity of goods; The product weight is compared with the target product weight, and the verification result is adjusted according to the comparison result.

3. The method according to claim 1, wherein The shelf pusher includes a counting sensor and a baffle, and the counting sensor generates and outputs sensor data based on the movement distance of the baffle. After triggering the product type verification process, before obtaining the product type and product arrangement length corresponding to the shelf pusher, the method further includes: Upon receiving the sensing data sent by the counting sensor, determining the baffle movement distance corresponding to the sensing data; Update the product arrangement length according to the baffle movement distance; When the length of the commodity arrangement increases, the verification process of the commodity type is triggered.

4. The method according to claim 3, wherein The counting sensor is a roller sensor, which is connected to the baffle via a connecting rope. The roller sensor retracts and extends the connecting rope based on the moving distance of the baffle and generates a pulse signal. The step of updating the length of the commodity arrangement according to the moving distance of the baffle includes: receiving the pulse signal and accumulating pulse quantity information of the pulse signal; Determining the baffle movement distance according to the pulse quantity information, the pulse unit distance of the pulse signal, and the pulse signal type; The commodity arrangement length is updated according to the commodity length change corresponding to the baffle movement distance.

5. The method according to claim 1, wherein The step of comparing the quotient with a preset value range and obtaining a verification result of the product type according to the comparison result includes: Extracting the decimal part of the quotient to obtain a verification value; By comparing the verification value with the boundary value of the preset value range, determining whether the verification value is within the preset value range; If the verification value is within the preset value range, the verification result is determined to be an abnormal commodity type; Alternatively, if the verification value is not within the preset value range, the verification result is determined to be that the commodity type is normal.

6. The method according to claim 1, wherein The shelf pusher is further equipped with a display screen. After the step of comparing the quotient with a preset value range and obtaining a verification result of the commodity type according to the comparison result, the step further includes: When the verification result shows that the commodity type is abnormal, determining the shelf number corresponding to the shelf pusher; Obtain a prompt information template, and fill the shelf number into the prompt information template to generate an abnormal prompt information; The abnormal prompt information is output to the administrator terminal and / or the display screen.

7. The method according to claim 1, wherein The step of obtaining the length of a single product corresponding to the product type and calculating the quotient of the product arrangement length and the length of the single product further includes: Obtaining a deformation compensation model corresponding to the product type and a thrust analysis model of the baffle based on the baffle position; Determining the deformation pressure corresponding to the degree of deformation of the remaining number of commodities in the shelf pusher at different baffle positions according to the deformation compensation model; Determining the baffle thrust corresponding to the baffle position based on the thrust analysis model; determining a target baffle position when the deformation pressure matches the baffle thrust, and determining a target arrangement length according to the target baffle position; The length of each commodity is determined based on the ratio of the target arrangement length to the number of remaining commodities.

8. The method according to claim 1, wherein After the step of comparing the quotient with the preset value range and obtaining the verification result of the product type according to the comparison result, the method further includes: When the verification result shows that the commodity type is abnormal, a shelf image of the shelf pusher is obtained through a camera; Identifying feature information of the shelf image using a semantic segmentation model; Matching the characteristic information with commodity characteristic information, and determining commodity storage information of the shelf pusher according to the matching result; Based on the commodity storage information, the verification result of the commodity type is adjusted.

9. A commodity type verification device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the commodity verification method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the commodity type verification method according to any one of claims 1 to 8 are implemented.

Images