A commodity inventory method and device based on visual recognition

Abstract

The present invention discloses a commodity inventory method based on visual recognition, comprising the following steps: an inventory personnel moves an inventory device along the commodity display position, and places the commodities to be counted on the equipment scale body one by one; after the weight value is stable, it is determined as the weight value of the commodity, and then the image recognition unit collects the image of the weighed commodity, and transmits the image of the commodity to the identifier for recognition, and obtains the category of the weighed commodity; after the weight or quantity of the commodity is confirmed, the inventory data of the commodity is formed; after the inventory personnel complete the inventory of all commodities, if necessary, the review personnel check the difference between the book inventory and the actual inventory, and if there is an error, the inventory is adjusted, and then the result is formed to complete the inventory. The solution provided by the present invention optimizes the process of inventory operations, reduces the number of people involved in inventory, improves the efficiency and accuracy of inventory, and saves the operating costs of business units.

Description

[0001] This disclosure is a divisional application of the following invention patent application: Application number: 202210838836.3, Application date: July 18, 2022, Invention name: A commodity inventory method and device based on visual recognition. Technical Field

[0002] The present disclosure relates to information processing technology, and in particular to a commodity inventory method and device based on visual recognition. Background Art

[0003] When supermarkets and shopping malls receive and count goods, they usually need to manually check and count the categories and quantities of goods, and manually enter the checked and counted data into the product management system. The entire sorting process of goods is time-consuming and laborious, especially the need to regularly sort and update data according to changes in goods, which increases the workload. At the same time, manual inventory, inspection and counting will also cause certain statistical errors, which will bring great economic risks to the operation of supermarkets and shopping malls. Therefore, the intelligent operation of supermarkets has always been the direction and goal of development.

[0004] For example, CN113781730A provides a smart supermarket with intelligent monitoring function, which is connected to the supermarket backend module through the commodity input module and the monitoring module, and the processing chip recognizes and calculates the commodity information, and issues an early warning for the change of the commodity information. In this way, the intelligent monitoring of the supermarket can be realized, the burden of manual statistics can be reduced, and the efficiency of statistics can be improved.

[0005] However, the intelligent monitoring system is relatively complex and has low efficiency in recognition and calculation, and cannot meet the needs of instant recognition, storage, and output when goods are received and counted.

[0006] Therefore, how to design a fast, efficient, accurate and intelligent method for inventory counting and receiving goods to achieve instant identification of goods, instant storage of commodity information and instant output of commodity data is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0007] In response to the defects existing in the above-mentioned prior art, the present invention provides a commodity inventory method and device based on visual recognition. Based on a device that can perform intelligent receiving and inventory, it automatically distinguishes the type of commodities, performs weight verification of commodities, automatically completes data management during inventory and receipt, and provides inventory documents for commodities, thereby reducing manual operations, reducing errors, greatly improving work efficiency and accuracy, and saving operating costs.

[0008] On the one hand, the present disclosure provides a commodity inventory counting device, comprising: a scale pan with a weighing sensor, wherein the weighing sensor is configured to sense the weight value of the commodity being weighed; a display touch screen configured to interact with a user; an image acquisition component configured to acquire images of the commodity; a mobile device configured to enable the commodity inventory counting device to move; a power supply configured to supply power to the commodity inventory counting device; a controller configured to: identify the category of the weighed commodity based on the image acquired by the image acquisition component and determine the commodity code of the corresponding commodity category; store the weight or quantity value and the commodity code of the commodity into the warehouse management system of the controller respectively to form inventory data of the commodity; compare the inventory data of the commodity with the book inventory, generate an inventory list of the commodity, and complete the inventory of the commodity.

[0009] In one embodiment, the controller receives user feedback on the identified commodity category displayed on the touch screen, adds the captured image to the memory, and optimizes the recognition result.

[0010] In one embodiment, the weighing sensor is configured to determine the weight value of the commodity after the weight value is stabilized.

[0011] In one embodiment, the controller is configured to:

[0012] Collect commodity images, perform commodity category recognition and analysis to obtain the commodity category to be weighed;

[0013] Give the product code of the corresponding product category.

[0014] On the other hand, a method for operating a commodity inventory counting device is provided, comprising: a first user moves the commodity inventory counting device and places commodities one by one on the scale pan of the commodity inventory counting device according to the order of commodity display shelves, wherein the weighing sensor is configured to determine the weight value of the commodity after the weight value is stable, the image acquisition component acquires the image of the commodity, the controller of the commodity inventory counting device identifies the category of the weighed commodity based on the image acquired by the image acquisition component and determines the commodity code of the corresponding commodity category, and the display touch screen displays the weight value of the commodity or the quantity of the commodity; the first user confirms the weight value of the commodity or the quantity of the commodity displayed on the display touch screen, wherein the controller of the commodity inventory counting device stores the weight value and / or the quantity of the commodity and the commodity code into the storage management system of the controller respectively to form the inventory data of the commodity; the second user compares and verifies the inventory data of the commodity with the inventory difference on the system book, and then generates the inventory document of the commodity to complete the inventory of the commodity.

[0015] In one embodiment, if there is a difference between the book inventory of the product and the inventory data of the store products and the inventory data of the inventory products, the second user makes an inventory adjustment.

[0016] In one embodiment, the first user and the second user are the same user or different users.

[0017] In one embodiment, the first user is an inventory person, and the second user is a review person.

[0018] On the other hand, the present disclosure provides a commodity inventory method based on visual recognition, comprising the following steps:

[0019] Search for items in inventory and weigh the items found;

[0020] After the weight value stabilizes, it is determined as the weight value of the product. Then, the image of the weighed product is collected, and the image of the product is analyzed and identified to obtain the category of the weighed product.

[0021] The weight value and category of the goods are stored in the warehouse management system to form the inventory data of the goods;

[0022] Compare the inventory data of the goods with the pre-built receipt data of the goods, generate the inventory documents of the goods, and complete the inventory of the goods.

[0023] Furthermore, the goods in inventory include store goods and warehouse goods, and the inventory data of the goods include the inventory data of the store goods and the inventory data of the warehouse goods.

[0024] Furthermore, after the weight value stabilizes, it is determined as the weight value of the product, including:

[0025] Continuously and uninterruptedly collect the initial weight values ​​of the goods placed for weighing, and analyze and process the adjacent initial weight values;

[0026] According to the adjacent initial weight values, the collection time interval and the scale value of the weighing pan, the initial weight value is derived and the calculation formula is as follows:

[0027]

[0028]

[0029] Among them, X i is the time point of the i-th commodity weight collection, W(X i ) is the initial weight value of the i-th commodity weight collection, t is the interval time of commodity weight collection, N is the division value of the weighing scale, W′(X i ) is the derivation of the initial weight value for collecting the weight of the commodity;

[0030] Iterate the weight value of the product for several rounds until Then the weight value is stable, determine W(X i+1 ) is the weight of the product.

[0031] Furthermore, the image of the product is analyzed and identified to obtain the category of the product being weighed, including:

[0032] By edge detection, the area other than the product target in the product image is cropped and removed to obtain a processed cropped image;

[0033] After the cropped images are normalized and compressed, they are analyzed for commodity category recognition;

[0034] Given the commodity code of the corresponding commodity type, obtain the category of the commodity being weighed.

[0035] Furthermore, by edge detection, the area other than the product target in the product image is cropped and removed, specifically including:

[0036] Perform filtering on the product image to obtain a smooth image;

[0037] Calculate the gradient magnitude and gradient direction of the smoothed image to obtain a gradient image;

[0038] Scan the amplitude of all pixels in the gradient image and calculate the threshold for edge recognition. The calculation formula is as follows:

[0039]

[0040] Where H is the threshold, P is the number of columns of pixels in the gradient image, Q is the number of rows of pixels in the gradient image, i is the horizontal coordinate value of the pixel point in the gradient image, j is the vertical coordinate value of the pixel point in the gradient image, and T(i,j) is the amplitude of the pixel point (i,j) in the gradient image;

[0041] Pixels with amplitudes higher than a threshold are determined as edge points, pixels with amplitudes lower than a preset multiple of the threshold are determined as non-edge points, and other pixels are determined as suspected edge points;

[0042] If there is an edge point among the adjacent pixels of the suspected edge point, it is considered as an edge point; otherwise, it is considered as a non-edge point, and the edge points are connected to obtain the product edge curve;

[0043] The area outside the product target in the product image is removed by cropping along the product edge curve.

[0044] Furthermore, the pre-built goods receipt data, the specific pre-building method includes the following steps:

[0045] Weigh the goods to be stored, collect images of the goods to be stored, identify the categories of the goods, and give the weight and category of the goods to be stored;

[0046] Compare the historical data of the goods, verify the relationship between the visual area and weight of the goods to be stored, and complete the storage inspection;

[0047] The receipt data of the goods to be stored in the warehouse is stored in the warehouse management system to complete the pre-construction of the receipt data of the goods.

[0048] Furthermore, the historical data of the goods is compared to verify the relationship between the visual area and weight of the goods to be stored, and the storage inspection is completed, including:

[0049] Retrieve the verification standard value of the type of product to be stored in the historical data;

[0050] According to the visual area and weight of the goods to be stored, a weight value per unit visual area of ​​the goods to be stored is given as a first data value;

[0051] Compare the first data value with the verification standard value, and if it meets the set threshold conditions, complete the warehouse inspection.

[0052] Furthermore, the verification standard value is preset, and the verification standard value of any type of commodity to be stored is calculated, specifically including:

[0053] Take the product category, product weight and visual area data in the product history data, and aggregate the product history data of the same product category;

[0054] According to the weight and visual area of ​​the goods in the same commodity category in the collection, the weight value per unit visual area of ​​the commodity category is given to obtain the verification standard value of the commodity category.

[0055] Furthermore, the inventory data of the goods is compared with the pre-built goods receipt data, and the inventory document of the goods is generated to complete the inventory of the goods, which specifically includes:

[0056] Update the pre-built product receipt data in real time based on sales data;

[0057] According to the product category, the receipt data of the products of the same product category, the inventory data of the store products and the inventory data of the inventory products are sorted out accordingly;

[0058] The difference between the goods receiving data and the inventory data of the store goods and the inventory data of the inventory goods is given, and the inventory document of the goods is generated to complete the inventory of the goods.

[0059] In a second aspect, the present disclosure further provides a device for implementing the above commodity inventory method, comprising: a device body, a display touch screen, a controller and an image acquisition component fixedly connected above the device body, a scale plate on the surface of the device body and a power component for driving the device to move;

[0060] The display touch screen is used to display the commodity information during the commodity inventory and commodity receipt process. The controller is used to determine the weight data of the commodity, and control the image acquisition component to collect the image of the commodity and analyze and identify the image of the commodity to give the commodity category.

[0061] The commodity inventory method and device based on visual recognition provided by the present disclosure have at least the following beneficial effects:

[0062] (1) Commodity inventory based on visual recognition can automatically identify the type of goods, automatically check the weight of goods, and complete data management during the inventory and receipt process, reducing manual operations and errors, greatly improving work efficiency and accuracy, and saving operating costs.

[0063] (2) Based on the commodity weight information collected multiple times, the collection time interval and the scale division value are iterated to obtain stable commodity weight data, which not only improves the accuracy of the commodity information data, but also connects the image acquisition process, avoids the operating pressure of the image acquisition component, reduces the memory consumption of the controller, and efficiently and conveniently realizes the identification and data storage of different types of commodities.

[0064] (3) Based on edge detection, the visual area and type of the product are given, and the threshold setting is more suitable for the specific application scenario, with strong adaptability and higher edge recognition accuracy.

[0065] (4) Verification standard values ​​are designed for each product type, which improves the accuracy of the product receiving process and eliminates errors that may occur during manual filling. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A flowchart of a commodity inventory method based on visual recognition provided by the present disclosure;

[0067] Figure 2 A schematic diagram of the structure of a device based on visual recognition provided by the present disclosure;

[0068] Figure 3 A flowchart of a method for receiving goods based on visual recognition provided by the present invention. DETAILED DESCRIPTION

[0069] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0070] like Figure 2 The visual recognition device comprises: a device body 1, a display touch screen 2 fixedly connected above the device body 1, a controller and an image acquisition component 3, a weighing pan 4 on the surface of the device body, and a power component 5 for driving the device to move.

[0071] The display touch screen 2 is used to display the commodity information during the commodity inventory and commodity receipt process. The controller is used to determine the weight data of the commodity, control the image acquisition component 3 to acquire the image of the commodity, analyze and identify the image of the commodity, and give the commodity category.

[0072] use Figure 2 The device performs inventory of goods, such as Figure 1 As shown, the following steps are included:

[0073] The power assembly drives the device to travel along a predetermined route and search for goods in the inventory, and weigh the searched goods;

[0074] After the weight value stabilizes, it is determined as the weight value of the product. Then the image acquisition component collects the image of the weighed product and transmits the image of the product to the controller for analysis and identification to obtain the category of the weighed product.

[0075] The weight value and the category of the goods are stored in the storage management system of the controller to form the inventory data of the goods;

[0076] Compare the inventory data of the goods with the pre-built receipt data of the goods, generate the inventory documents of the goods, and complete the inventory of the goods.

[0077] The scheduled route can be determined in advance based on the specific arrangement of the goods in the inventory and the specific scene of inventory and harvesting, and is not limited here. The goods to start searching can also be set in advance, without specifically limiting which type of goods to start with.

[0078] The warehouse management system stores all the inventory data and the receipt data of the goods. The above two types of data are collected and stored by the device during the inventory and receipt process of the goods.

[0079] Based on the device that can perform intelligent receiving and inventory, it can automatically identify the types of goods, check the weight of goods, automatically complete the data management during inventory and receiving, and provide inventory documents for goods, thus reducing manual operations, reducing errors, greatly improving work efficiency and accuracy, and saving operating costs.

[0080] The goods in inventory include store goods and warehouse goods, and the inventory data of the goods include the inventory data of store goods and the inventory data of warehouse goods.

[0081] After the weight value stabilizes, it is determined as the weight value of the product, including:

[0082] The controller continuously and uninterruptedly collects the initial weight values ​​of the goods placed on the scale plate, and analyzes and processes the adjacent initial weight values;

[0083] According to the adjacent initial weight values, the collection time interval and the scale division value of the scale, the initial weight value is derived, and the calculation formula is as follows:

[0084]

[0085]

[0086] Among them, X i is the time point of the i-th commodity weight collection, W(X i ) is the initial weight value of the i-th commodity weight collection, t is the interval time of commodity weight collection, N is the scale division value of the device, W′(X i ) is the derivation of the initial weight value for collecting the weight of the commodity;

[0087] Iterate the weight value of the product for several rounds until Then the weight value is stable, determine W(X i+1 ) is the weight of the product.

[0088] According to the commodity weight information collected multiple times, it is iterated with the collection time interval and the scale division value to obtain stable commodity weight data, which not only improves the accuracy of commodity information data, but also connects the image acquisition process, avoids the operating pressure of the image acquisition component, reduces the memory consumption of the controller, and efficiently and conveniently realizes the recognition and data storage of different types of commodities.

[0089] The image of the product is transmitted to the controller for analysis and recognition to obtain the category of the product being weighed, including:

[0090] The controller cuts out the area other than the product target in the product image through edge detection to obtain a processed cropped image;

[0091] After normalization and compression, the cropped image is transmitted to the recognition unit of the controller for commodity category recognition and analysis;

[0092] Given the commodity code of the corresponding commodity type, obtain the category of the commodity being weighed.

[0093] The controller uses edge detection to crop and remove areas other than the product target in the product image, including:

[0094] Perform filtering on the product image to obtain a smooth image;

[0095] The filtering process can use a Gaussian filter function to filter and reduce noise on the product image, and obtain a processed smooth image by controlling the smoothness.

[0096] Calculate the gradient magnitude and gradient direction of the smoothed image to obtain a gradient image;

[0097] After obtaining the smoothed image, the partial derivatives of the pixels of the smoothed image are solved in the four directions of horizontal, vertical, 45°, and 135°, and the gradient amplitude and gradient direction are calculated using the first-order finite difference.

[0098] T x (i,j)=[t(i+1,j-1)+2t(i+1,j)+t(i+1,j+1)]

[0099] -[t(i-1,j+1)+2t(i-1,j)+t(i-1,j+1)]

[0100] T y (i,j)=[t(i-1,j+1)+2t(i,j+1)+t(i+1,j+1)]

[0101] -[t(i-1,j-1)+2t(i,j-1)+t(i+1,j-1)]

[0102] T 45° (i,j)=[t(i+1,j)+2t(i+1,j+1)+t(i,j+1)]

[0103] -[t(i-1,j)+2t(i-1,j-1)+t(i,j-1)]

[0104] T 145° (i,j)=[t(i,j+1)+2t(i-1,j+1)+t(i-1,j)]

[0105] -[t(i+1,j)+2t(i+1,j-1)+t(i,j-1)]

[0106] Get the current gradient amplitude T(i,j) and gradient angle They are:

[0107]

[0108]

[0109] Expanding the values ​​of gradient amplitude and gradient angle can improve the accuracy of determining the edge of the commodity target and is less likely to lose part of the real edge.

[0110] Scan the amplitude of all pixels in the gradient image and calculate the threshold for edge recognition. The calculation formula is as follows:

[0111]

[0112] Where H is the threshold, P is the number of columns of pixels in the gradient image, Q is the number of rows of pixels in the gradient image, i is the horizontal coordinate value of the pixel point in the gradient image, j is the vertical coordinate value of the pixel point in the gradient image, t(i,j) is the pixel value of point (i,j), and T(i,j) is the amplitude of pixel point (i,j) in the gradient image;

[0113] Pixels with amplitudes higher than a threshold are determined as edge points, pixels with amplitudes lower than a preset multiple of the threshold are determined as non-edge points, and other pixels are determined as suspected edge points;

[0114] If there is an edge point among the adjacent pixels of the suspected edge point, it is considered as an edge point; otherwise, it is considered as a non-edge point, and the edge points are connected to obtain the product edge curve;

[0115] The area outside the product target in the product image is removed by cropping along the product edge curve.

[0116] Based on edge detection, the visual area and type of the product are given, and the threshold setting is more suitable for specific application scenarios, with strong adaptability and higher edge recognition accuracy.

[0117] The pre-built goods receiving data is also obtained based on the collection, analysis and storage of the device in the receiving link. The specific pre-building method includes the following steps:

[0118] The driving component driving device weighs the goods to be stored, and the image acquisition component acquires the image of the goods to be stored and identifies the category of the goods, and gives the weight value and category of the goods to be stored;

[0119] Compare the historical data of the goods, verify the relationship between the visual area and weight of the goods to be stored, and complete the storage inspection;

[0120] The goods receipt data to be put into the warehouse is stored in the warehouse management system of the controller to complete the pre-construction of the goods receipt data.

[0121] The weighing process of the incoming goods is the same as the weighing process based on the device during the inventory counting process. That is:

[0122] The controller continuously and uninterruptedly collects the initial weight values ​​of the goods to be stored on the scale plate, and analyzes and processes the adjacent initial weight values;

[0123] According to the adjacent initial weight values, the collection time interval and the scale division value of the scale, the initial weight value is derived, and the calculation formula is as follows:

[0124]

[0125]

[0126] Among them, Xi is the time point at which the weight of the goods to be stored is collected for the i-th time, W(X i ) is the initial weight value of the i-th weight collection of the goods to be stored, t is the interval time of the weight collection of the goods to be stored, N is the scale division value of the device, W′(X i ) is the derivation of the initial weight value of the goods to be stored;

[0127] Iterate the weight value of the goods to be stored for several rounds until Then the weight value is stable, determine W(X i+1 ) is the weight value of the commodity to be stored.

[0128] The visual area and product category recognition of the goods to be stored during the receiving process is also the same as the product category recognition process based on the device during the inventory process. That is:

[0129] The controller cuts out the area other than the target of the goods to be stored in the image of the goods to be stored by edge detection, gives the visual area of ​​the goods to be stored, and obtains a processed cut image;

[0130] After being normalized and compressed, the cropped image is transmitted to the recognition unit of the controller for identification and analysis of the category of the goods to be stored;

[0131] Given the commodity code corresponding to the type of commodity to be stored, obtain the category of the weighed commodity to be stored.

[0132] The controller cuts out the area other than the target of the commodity to be stored in the image of the commodity to be stored by edge detection, specifically including:

[0133] Filter the image of the goods to be stored to obtain a smooth image;

[0134] The filtering process may adopt a Gaussian filter function to filter and reduce noise on the image of the goods to be stored, and obtain a processed smooth image by controlling the degree of smoothness.

[0135] Calculate the gradient magnitude and gradient direction of the smoothed image to obtain a gradient image;

[0136] After obtaining the smoothed image, the partial derivatives of the pixels of the smoothed image are solved in the four directions of horizontal, vertical, 45°, and 135°, and the gradient amplitude and gradient direction are calculated using the first-order finite difference.

[0137] T x (i,j)=[t(i+1,j-1)+2t(i+1,j)+t(i+1,j+1)]

[0138] -[t(i-1,j+1)+2t(i-1,j)+t(i-1,j+1)]

[0139] T y (i,j)=[t(i-1,j+1)+2t(i,j+1)+t(i+1,j+1)]

[0140] -[t(i-1,j-1)+2t(i,j-1)+t(i+1,j-1)]

[0141] T 45° (i,j)=[t(i+1,j)+2t(i+1,j+1)+t(i,j+1)]

[0142] -[t(i-1,j)+2t(i-1,j-1)+t(i,j-1)]

[0143] T 145° (i,j)=[t(i,j+1)+2t(i-1,j+1)+t(i-1,j)]

[0144] -[t(i+1,j)+2t(i+1,j-1)+t(i,j-1)]

[0145] Get the current gradient amplitude T(i,j) and gradient angle They are:

[0146]

[0147]

[0148] Scan the amplitude of all pixels in the gradient image and calculate the threshold for edge recognition. The calculation formula is as follows:

[0149]

[0150] Where H is the threshold, P is the number of columns of pixels in the gradient image, Q is the number of rows of pixels in the gradient image, i is the horizontal coordinate value of the pixel point in the gradient image, j is the vertical coordinate value of the pixel point in the gradient image, t(i,j) is the pixel value of point (i,j), and T(i,j) is the amplitude of pixel point (i,j) in the gradient image;

[0151] Pixels with amplitudes higher than a threshold are determined as edge points, pixels with amplitudes lower than a preset multiple of the threshold are determined as non-edge points, and other pixels are determined as suspected edge points;

[0152] If there is an edge point among the adjacent pixels of the suspected edge point, it is considered as an edge point; otherwise, it is considered as a non-edge point, and the edge points are connected to obtain the product edge curve;

[0153] The area other than the target of the commodity to be stored in the image of the commodity to be stored is removed by cutting along the edge curve of the commodity to be stored.

[0154] Compare the historical data of the goods, verify the relationship between the visual area and weight of the goods to be stored, and complete the storage inspection, including:

[0155] Retrieve the verification standard value of the type of commodity to be stored in the controller's historical data;

[0156] According to the visual area and weight of the goods to be stored, a weight value per unit visual area of ​​the goods to be stored is given as a first data value;

[0157] Compare the first data value with the verification standard value, and if it meets the set threshold conditions, complete the warehouse inspection.

[0158] For example, assuming that the goods to be stored are apples, the verification standard value of apples in the historical data of the controller retrieved is 0.05m 2 / kg; the weight per unit visual area of ​​the goods to be stored is 0.045m 2 / kg, error: (0.045m 2 / kg-0.05m 2 / kg) / 0.05=10%, and the set threshold is 20%. Therefore, within the allowable error range, the warehouse inspection is completed and the goods can be put into storage.

[0159] The verification standard value is pre-set, and the verification standard value of any type of product to be entered into the warehouse is calculated, including:

[0160] Take the product category, product weight and visual area data in the product history data, and aggregate the product history data of the same product category;

[0161] According to the weight and visual area of ​​the goods in the same commodity category in the collection, the weight value per unit visual area of ​​the commodity category is given to obtain the verification standard value of the commodity category.

[0162] The calculation formula for the verification standard value is as follows:

[0163]

[0164] Among them, C v is the verification standard value, λ is the standard coefficient, which can be set according to the normal distribution of commodity historical data, G i is the weight of the ith product of this type, S i is the value of the visual area of ​​the ith product of this type, G is the average value of the weight of this type of product, s is the average value of the visual area of ​​this type of product, and f i Same as this type of product For historical data of commodities that follow normal distribution, standard coefficients are set to meet the needs of specific scenarios. The calculated and determined approval standard values ​​are more in line with actual requirements and improve the accuracy of goods receipt identification and judgment.

[0165] Compare the inventory data of the goods with the pre-built goods receipt data, generate the inventory documents of the goods, and complete the inventory of the goods, including:

[0166] Update the pre-built product receipt data in real time based on sales data;

[0167] According to the product category, the receipt data of the products of the same product category, the inventory data of the store products and the inventory data of the inventory products are sorted out accordingly;

[0168] The difference between the goods receiving data and the inventory data of the store goods and the inventory data of the inventory goods is given, and the inventory document of the goods is generated to complete the inventory of the goods.

[0169] Although preferred embodiments of the present disclosure have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present disclosure. Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A commodity inventory device, comprising: A weighing pan having a weighing sensor configured to sense a weight value of a commodity being weighed; display touch screen configured to interact with a user; An image acquisition component, configured to acquire an image of the product; A moving device configured to enable the commodity inventory counting device to move; A power supply configured to supply power to the commodity inventory counting device; The controller is configured as: Identifying the category of the commodity to be weighed based on the image captured by the image acquisition component and determining the commodity code corresponding to the commodity category; The weight or quantity value and the commodity code of the commodity are stored in the storage management system of the controller to form the inventory data of the commodity; Compare the inventory data of the goods with the book inventory, generate the inventory list of the goods, and complete the inventory of the goods. The controller is configured to identify the category of the commodity to be weighed and determine the commodity code of the corresponding commodity category based on the image captured by the image acquisition component through the following steps: By edge detection, the area other than the product target in the product image is cropped and removed to obtain a processed cropped image; After the cropped images are normalized and compressed, they are analyzed for commodity category recognition; Get the category of the product being weighed and give the product code of the corresponding product type. Among them, by edge detection, cropping and removing the area other than the product target in the product image includes: Perform filtering on the product image to obtain a smooth image; Calculate the gradient magnitude and gradient direction of the smoothed image to obtain a gradient image; Scan the amplitude of all pixels in the gradient image and calculate the threshold for edge recognition. The calculation formula is as follows: Where H is the threshold, P is the number of columns of pixels in the gradient image, Q is the number of rows of pixels in the gradient image, i is the horizontal coordinate value of the pixel point in the gradient image, j is the vertical coordinate value of the pixel point in the gradient image, and T(i,j) is the amplitude of the pixel point (i,j) in the gradient image; Pixels with amplitudes higher than a threshold are determined as edge points, pixels with amplitudes lower than a preset multiple of the threshold are determined as non-edge points, and other pixels are determined as suspected edge points; If there is an edge point among the adjacent pixels of the suspected edge point, it is considered as an edge point; otherwise, it is considered as a non-edge point, and the edge points are connected to obtain the product edge curve; The area outside the product target in the product image is removed by cropping along the product edge curve.

2. The commodity inventory counting device according to claim 1, wherein the controller receives user feedback on the identified commodity category displayed on the touch screen, adds the collected image to the memory, and optimizes the recognition result.

3. The commodity inventory counting device according to claim 1, characterized in that: The weighing sensor is configured to determine the weight value of the commodity after the weight value is stabilized.

4. The commodity inventory counting device according to claim 1, characterized in that: The controller is configured to: Collect commodity images, perform commodity category recognition and analysis to obtain the commodity category to be weighed; Give the product code of the corresponding product category.

5. A method for operating the commodity inventory counting device according to any one of claims 1 to 4, comprising: The first user moves the commodity inventory counting device and places the commodities on the weighing pan of the commodity inventory counting device one by one according to the order of commodity display shelves, wherein the weighing sensor is configured to determine the weight value of the commodity after the weight value is stable, the image acquisition component acquires the image of the commodity, the controller of the commodity inventory counting device identifies the category of the weighed commodity based on the image acquired by the image acquisition component and determines the commodity code of the corresponding commodity category, and the display touch screen displays the weight value of the commodity or the quantity of the commodity; The first user confirms the weight value of the commodity or the quantity of the commodity displayed on the display touch screen, wherein the controller of the commodity inventory counting device stores the weight value of the commodity and / or the quantity of the commodity and the commodity code into the storage management system of the controller respectively to form the inventory counting data of the commodity, wherein the weight value of the commodity is obtained by iterating the weight information of the commodity collected multiple times, the collection time interval and the scale division value of the scale pan; The second user compares and verifies the inventory data of the goods with the inventory differences on the system books, and then generates an inventory document for the goods to complete the inventory of the goods.

6. The method according to claim 5, characterized in that If there is a difference between the book inventory of the goods and the inventory data of the store goods and the inventory data of the inventory goods, the second user will conduct a re-inventory and inventory adjustment.

7. The method according to claim 5 or 6, characterized in that: The first user and the second user are the same user or different users.

Images