Commodity stockout rate acquisition method and apparatus, and storage medium and computer device

Abstract

Provided in the present disclosure are a commodity stockout rate acquisition method and apparatus, and a storage medium and a computer device. The method comprises: acquiring images of commodity areas at different times, so as to obtain a plurality of area images; performing commodity identification on the plurality of area images, and generating a plurality of corresponding arrangement drawings on the basis of commodity identification results, wherein each arrangement drawing is used for indicating the commodity positions of various commodities in the area images; superposing the plurality of arrangement drawings, so as to obtain a historical arrangement drawing for representing the full stock of various commodities; on the basis of the capturing time sequence of the area images, determining, as a target arrangement drawing, the arrangement drawing corresponding to the last captured area image; and acquiring the stockout rates of various commodities in the commodity areas on the basis of the target arrangement drawing and the historical arrangement drawing.

Description

Method, device, storage medium and computer equipment for obtaining out-of-stock rate of goods

[0001] Related applications

[0002] This disclosure claims priority to the Chinese invention patent application with application number 202311199212.2 filed on September 18, 2023, and cites the entire contents of the above patent application disclosure as part of this disclosure. Technical Field

[0003] The present disclosure relates to the technical field of commodity statistics, and in particular to a method, apparatus, storage medium, and computer equipment for obtaining a commodity out-of-stock rate. Background Art

[0004] Out-of-stock items on shelves can negatively impact the customer experience and limit sales. Therefore, stores closely monitor the out-of-stock rate of items on their shelves. However, existing technologies rely on manual inspections to determine out-of-stock rates, which is inefficient and wastes significant human resources.

[0005] Summary of the Invention

[0006] The purpose of the present disclosure is to overcome the shortcomings and deficiencies in the related art and to provide a method, device, storage medium and computer equipment for obtaining the out-of-stock rate of a product, which can improve the efficiency of obtaining the out-of-stock rate of a product and save human resources.

[0007] A first aspect of an embodiment of the present disclosure provides a method for obtaining a product out-of-stock rate, comprising:

[0008] Acquire images of the product area at different times to obtain multiple area images;

[0009] Identify products in the multiple area images and generate corresponding multiple layout drawings based on the product identification results; each layout drawing is used to indicate the product location of various products in the area images;

[0010] Superimpose multiple layout drawings to obtain historical layout drawings;

[0011] According to the shooting time sequence of the regional images, the row surface drawing corresponding to the last shot regional image is determined as the target row surface drawing;

[0012] According to the target layout drawings and historical layout drawings, the out-of-stock rate of various commodities in the commodity area is obtained.

[0013] Furthermore, the step of obtaining the out-of-stock rate of various commodities in the commodity area according to the target layout drawing and the historical layout drawing includes:

[0014] Obtain the first commodity quantity of each commodity in the target layout drawing and the second commodity quantity of each commodity in the historical layout drawing;

[0015] Obtaining the inventory rate of various commodities in the commodity area according to the quantity of the first commodity and the quantity of the second commodity;

[0016] According to the inventory rate of various commodities in the commodity area, the out-of-stock rate of the corresponding various commodities is obtained.

[0017] Furthermore, the step of obtaining the first commodity quantity of each commodity in the target layout drawing and the second commodity quantity of each commodity in the historical layout drawing includes:

[0018] Obtaining the first product quantity based on the first mask range of each product on the target layout drawing and the individual mask range of each product; wherein the first mask range represents the total occupied range of the corresponding type of products on the target layout drawing, and the individual mask range represents the occupied range of the corresponding type of products on the layout drawing;

[0019] The second commodity quantity is obtained based on the second mask range of various commodities in the historical layout drawing and the individual mask range of various commodities; the second mask range represents the total occupied range of the corresponding type of commodities in the historical layout drawing.

[0020] Furthermore, the step of obtaining the out-of-stock rate of various commodities in the commodity area according to the target layout drawing and the historical layout drawing includes:

[0021] Obtain the first mask range of various commodities in the target layout drawing, and the second mask range of various commodities in the historical layout drawing; the first mask range represents the total occupied range of the corresponding type of commodities in the target layout drawing, and the second mask range represents the total occupied range of the corresponding type of commodities in the historical layout drawings;

[0022] Obtaining the inventory rate of various commodities in the commodity area according to the first mask range and the second mask range;

[0023] According to the inventory rate of various commodities in the commodity area, the out-of-stock rate of the corresponding various commodities is obtained.

[0024] Furthermore, the steps of performing commodity recognition on the multiple region images and generating corresponding multiple layout drawings according to the commodity recognition results include:

[0025] Identify products in multiple area images to obtain product information and product locations of various products in each area image;

[0026] Generate product masks based on product information and product locations, and obtain product masks for various products in each area image;

[0027] According to the commodity masks of various commodities in the same area image, the layout drawing of the corresponding area image is obtained.

[0028] Furthermore, the steps of superimposing multiple layout drawings to obtain a historical layout drawing include:

[0029] The product masks of various products in multiple layout drawings are superimposed to obtain superimposed masks of various products; the superimposed masks represent the mask ranges of various products when they are fully stocked;

[0030] Based on the superimposed masks of various commodities, historical layout drawings are obtained.

[0031] Furthermore, after the step of acquiring images of the product area at different times to obtain multiple area images, the method further includes:

[0032] Perform pedestrian screening, product information screening, and / or product quantity screening on multiple area images to screen out abnormal area images;

[0033] Delete abnormal region images from multiple region images.

[0034] Furthermore, the step of pedestrian screening includes: inputting multiple area images into a trained pedestrian detection model, and determining the images in which pedestrians are found output by the pedestrian detection model as abnormal area images.

[0035] Furthermore, the steps for product information screening include:

[0036] Perform commodity recognition on multiple area images to obtain commodity information of each area image;

[0037] The commodity information with an appearance frequency lower than a preset threshold is determined as abnormal commodity information, and the region image corresponding to the abnormal commodity information is determined as an abnormal region image.

[0038] Furthermore, the steps for product quantity screening include:

[0039] Identify products in multiple area images and obtain the quantity of each product in each area image;

[0040] According to the shooting time sequence of each area image and the quantity of each commodity in each area image, an area image where the quantity of commodities suddenly decreases is obtained;

[0041] The image of the region where the quantity of goods decreases suddenly is determined as an abnormal region image.

[0042] A second aspect of an embodiment of the present disclosure provides a device for obtaining a product out-of-stock rate, including:

[0043] a region image acquisition module configured to acquire images of a commodity region at different times to obtain a plurality of region images;

[0044] A layout drawing acquisition module is configured to perform commodity recognition on the plurality of area images and generate a plurality of corresponding layout drawings based on the commodity recognition results; each layout drawing is used to indicate the commodity position of various commodities in the area image;

[0045] A historical display drawing acquisition module is configured to superimpose multiple display drawings to obtain historical display drawings for indicating full stock of various commodities;

[0046] The target row surface drawing acquisition module is configured to determine the row surface drawing corresponding to the last captured regional image as the target row surface drawing according to the shooting time sequence of the regional images;

[0047] The out-of-stock rate acquisition module is configured to obtain the out-of-stock rate of various commodities in the commodity area based on the target layout drawing and the historical layout drawing.

[0048] A third aspect of an embodiment of the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps of the above method for obtaining the out-of-stock rate of a commodity are implemented.

[0049] A fourth aspect of an embodiment of the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the computer program, the steps of the above-mentioned method for obtaining the out-of-stock rate of goods are implemented.

[0050] In some embodiments of the present disclosure, based on multiple area images of a commodity area at different times, historical display drawings indicating that various commodities are fully stocked, and target display drawings corresponding to the last captured area image are obtained, and the out-of-stock rates of various commodities in the commodity area are obtained. This can efficiently and accurately obtain the out-of-stock rates of commodities and save human resources.

[0051] In order to more clearly understand the present disclosure, the specific embodiments of the present disclosure will be described below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] FIG1 is a flow chart of a method for obtaining a commodity out-of-stock rate according to an embodiment of the present disclosure.

[0053] FIG2 is a schematic diagram of a display drawing of a method for obtaining the out-of-stock rate of a commodity according to an embodiment of the present disclosure.

[0054] FIG3 is a schematic diagram of a historical display drawing of a method for obtaining a product out-of-stock rate according to an embodiment of the present disclosure.

[0055] FIG4 is a schematic diagram of a screening process of a method for obtaining a commodity out-of-stock rate according to an embodiment of the present disclosure.

[0056] FIG5 is a module connection diagram of a device for obtaining a commodity out-of-stock rate according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0058] It should be clear that the embodiments described are only a part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the embodiments of the present disclosure.

[0059] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of the present disclosure, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present disclosure can be understood according to the specific circumstances. The singular forms of "a", "said" and "the" used in the present disclosure and the appended claims are also intended to include the plural forms, unless the context clearly indicates other meanings. The words "if" / "if" used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0060] In addition, throughout this disclosure, unless otherwise specified, "plurality" refers to two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0061] Please refer to FIG1 , which is a flow chart of a method for obtaining a commodity out-of-stock rate according to an embodiment of the present disclosure, including:

[0062] S1: Acquire images of a product area at different times to obtain multiple area images.

[0063] The region image refers to the image of each product area on the shelf. The product area can be divided according to the location of the products on the shelf. For example, each row on the shelf represents a product area. The region image can be obtained by the following steps:

[0064] Use an image acquisition device to obtain RGB images of the shelves. For fixed image acquisition devices such as cameras and AI cameras, ensure that the position and shooting angle of the acquisition device remain unchanged. For non-fixed image acquisition devices, such as wheeled robots and drones, it is necessary to adjust the shooting angle to a fixed point for the same shelf: for wheeled robots, according to the operation route map stored in the robot system, have the robot shoot the shelf at a specific position and angle in the route map; for drones, according to the flight route map stored in the drone system and positioning devices such as electronic compasses, shoot the shelf at a specific plane position and height above the ground at a specific angle.

[0065] For the acquired RGB image, the target detection model of the algorithm processing module in the computing system is used to detect all products and obtain the detection frame; according to the coordinates and width and height of the detection frame, the image of the product area is cropped out using the image processing method to obtain the regional image; wherein, the target detection model is trained using the deep learning method, that is, the collected scene image data is used to label the products, and then the deep network model is trained and verified based on the maximum likelihood idea. The deep network model includes but is not limited to the deep convolutional network model and the visual VIT model.

[0066] S2: Identify products in the multiple area images, and generate corresponding multiple layout drawings based on the product identification results; each layout drawing is used to indicate the product location of various products in the area image.

[0067] Among them, product identification can be performed by inputting the regional image into a trained feature extraction model for feature extraction, searching the extracted features in a pre-set product feature library in the algorithm processing module, and calculating the similarity between the extracted features and the features in the product feature library. For example, similarity is calculated by calculating the Euclidean distance between the features, and the result corresponding to the minimum Euclidean distance is taken as the product identification result with the highest confidence, thereby obtaining the position and size of all product frames and their product identification results. The layout drawing generated in step S2 is shown in Figure 2.

[0068] S3: Superimpose multiple layout drawings to obtain historical layout drawings.

[0069] The historical layout drawing obtained in step S3 is shown in Figure 3. In one example, the historical layout drawing is generated by algorithmically superimposing, fusing, and adjusting the layout drawings of the first 10 batches. It should be understood that the historical layout drawing can also be generated by algorithmically superimposing, fusing, and adjusting the layout drawings of other batches to adaptably meet the needs of identifying product out-of-stock rates.

[0070] S4: According to the shooting time sequence of the regional images, the row surface drawing corresponding to the last shot regional image is determined as the target row surface drawing.

[0071] S5: Obtain the out-of-stock rate of various commodities in the commodity area according to the target layout drawing and the historical layout drawing.

[0072] In a feasible embodiment, S2: performing commodity recognition on the multiple region images and generating corresponding multiple layout drawings based on the commodity recognition results, includes:

[0073] S21: Perform commodity recognition on the multiple region images to obtain commodity information and commodity locations of various commodities in each region image.

[0074] S22: Generate a product mask based on the product information and product location, and obtain a product mask for each product in each area image.

[0075] In step S22, based on the product information and product location, it can be determined whether adjacent products are of the same type. If so, the adjacent products are associated with each other to obtain a group of products of that type. A product mask corresponding to the product type is then constructed based on the product location of the outermost product of the group. In some embodiments, whether adjacent products are of the same type can be determined by determining whether the product information of the adjacent products is the same and whether the distance between the product locations is within a preset threshold.

[0076] Step S22 may also generate individual product masks for each product based on the product information and product location, and then construct a product mask for the corresponding product category based on the individual product masks with the same product information.

[0077] S23: Obtaining a layout drawing of the corresponding regional image based on the product masks of various products in the same regional image.

[0078] In a feasible embodiment, S3: the step of superimposing multiple layout drawings to obtain a historical layout drawing includes:

[0079] S31: superimposing the commodity masks of various commodities in the plurality of layout drawings to obtain superimposed masks of the various commodities; the superimposed masks represent the mask ranges of the various commodities when they are fully stocked.

[0080] It can be understood that the superimposed mask is the union of the product masks of various products in multiple layout drawings.

[0081] S32: Obtain a historical layout drawing based on the superimposed masks of various commodities.

[0082] In a feasible embodiment, after the step of S1: acquiring images of a product area at different times to obtain multiple area images, the following steps are further included:

[0083] S11: Perform pedestrian screening, product information screening, and / or product quantity screening on the multiple area images to screen out abnormal area images.

[0084] The screening performed in step S11 may be one or more of the screening methods. For example, as shown in FIG4 , pedestrian screening, commodity information screening, and / or commodity quantity screening may be performed in sequence.

[0085] S12: Deleting abnormal region images from the plurality of region images.

[0086] In a feasible embodiment, the step of pedestrian screening includes: inputting multiple regional images into a trained pedestrian detection model, and determining the images output by the pedestrian detection model in which pedestrians are found as abnormal regional images.

[0087] In a feasible embodiment, the steps of product information screening include:

[0088] Perform commodity recognition on multiple area images to obtain commodity information of each area image;

[0089] The commodity information with an appearance frequency lower than a preset threshold is determined as abnormal commodity information, and the region image corresponding to the abnormal commodity information is determined as an abnormal region image.

[0090] In a feasible embodiment, the steps of commodity quantity screening include:

[0091] Identify products in multiple area images and obtain the quantity of each product in each area image;

[0092] According to the shooting time sequence of each area image and the quantity of each commodity in each area image, an area image where the quantity of commodities suddenly decreases is obtained;

[0093] The image of the region where the quantity of goods decreases suddenly is determined as an abnormal region image.

[0094] The sudden decrease in the number of goods refers to a situation where the difference between the reduction ratio of the number of goods and the average reduction ratio exceeds a preset difference threshold.

[0095] It should be understood that the screening order illustrated in FIG4 is merely illustrative. Pedestrians, product information, and product quantity may also be screened in other screening orders. This disclosure does not limit the screening order for pedestrians, product information, and product quantity.

[0096] In other embodiments, abnormal area images can be screened based on other information. For example, by obtaining shelf display status data, images of product areas within the period of temporary shelf adjustment can be screened, and images with significant changes in product display information due to temporary shelf adjustment can be identified as abnormal area images.

[0097] In a feasible embodiment, S5: the step of obtaining the out-of-stock rate of various commodities in the commodity area according to the target display drawing and the historical display drawing includes:

[0098] S501: Obtain the first commodity quantity of each commodity in the target layout drawing and the second commodity quantity of each commodity in the historical layout drawing.

[0099] S502: Obtaining the inventory rate of various commodities in the commodity area according to the first commodity quantity and the second commodity quantity.

[0100] The inventory rate of each commodity in the commodity area is the result of dividing the quantity of the corresponding first commodity by the quantity of the second commodity. The inventory rate is a percentage that does not exceed 100%.

[0101] S503: Obtain the corresponding out-of-stock rates of various commodities according to the inventory rates of various commodities in the commodity area.

[0102] The out-of-stock rate is 100% minus the in-stock rate.

[0103] In a feasible embodiment, S502: the step of obtaining the first commodity quantity of each commodity in the target layout drawing and the second commodity quantity of each commodity in the historical layout drawing includes:

[0104] S5021: Obtain the first commodity quantity based on the first mask range of various commodities in the target layout drawing and the individual mask range of various commodities; the first mask range represents the total occupied range of the corresponding type of commodities in the target layout drawing, and the individual mask range represents the individual occupied range of the corresponding type of commodities in the layout drawing.

[0105] The first product quantity is the result of dividing the first mask range of the corresponding product by the individual mask range.

[0106] S5022: Obtain the second commodity quantity according to the second mask range of each commodity in the historical layout drawing and the individual mask range of each commodity; the second mask range represents the total occupied range of the corresponding type of commodity in the historical layout drawing.

[0107] The second product quantity is the result of dividing the second mask range of the corresponding product by the individual mask range.

[0108] In a feasible embodiment, S5: the step of obtaining the out-of-stock rate of various commodities in the commodity area according to the target layout drawing and the historical layout drawing includes:

[0109] S511: Obtain the first mask range of various commodities in the target layout drawing, and the second mask range of various commodities in the historical layout drawing; the first mask range represents the total occupied range of the corresponding type of commodities in the target layout drawing, and the second mask range represents the total occupied range of the corresponding type of commodities in the historical layout drawing.

[0110] S512: Obtain the inventory rate of various commodities in the commodity area according to the first mask range and the second mask range.

[0111] The stock rate is the result of dividing the corresponding first mask range by the second mask range. The stock rate is a percentage that does not exceed 100%.

[0112] S513: Obtain the corresponding out-of-stock rates of various commodities according to the inventory rates of various commodities in the commodity area.

[0113] The out-of-stock rate is the result of subtracting the inventory rate from 100%. Referring to FIG5 , an embodiment of the present disclosure further provides a device for obtaining the out-of-stock rate of a commodity, comprising:

[0114] The regional image acquisition module 1 is configured to acquire images of the commodity region at different times to obtain a plurality of regional images;

[0115] The layout drawing acquisition module 2 is configured to perform commodity recognition on the multiple region images and generate corresponding multiple layout drawings based on the commodity recognition results; each layout drawing is used to indicate the commodity position of various commodities in the region image;

[0116] A historical display drawing acquisition module 3 is configured to superimpose multiple display drawings to obtain a historical display drawing for indicating the full stock of various commodities;

[0117] The target row surface drawing acquisition module 4 is configured to determine the row surface drawing corresponding to the last captured regional image as the target row surface drawing according to the shooting time sequence of the regional images;

[0118] The out-of-stock rate acquisition module 5 is configured to acquire the out-of-stock rate of various commodities in the commodity area according to the target display drawing and the historical display drawing.

[0119] It should be noted that the device for obtaining the out-of-stock rate of goods provided in the embodiments of the present disclosure only uses the division of the above-mentioned functional modules as an example when executing the method for obtaining the out-of-stock rate of goods. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device for obtaining the out-of-stock rate of goods provided in other embodiments of the present disclosure and the method for obtaining the out-of-stock rate of goods in the embodiments of the present disclosure are of the same concept. The implementation process thereof is detailed in the method embodiment and will not be repeated here.

[0120] An embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program, which implements the steps of the above method for obtaining the out-of-stock rate of a commodity when executed by a processor.

[0121] An embodiment of the present disclosure further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the computer program, the steps of the above-mentioned method for obtaining the out-of-stock rate of a commodity are implemented.

[0122] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The present disclosure is described with reference to the flowchart and / or block diagram of the method, device (system), and computer program product according to the embodiment of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram and the combination of the process and / or box in the flowchart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function selected in one process or multiple processes of the flowchart and / or one box or multiple boxes of the block diagram. These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which realizes the function selected in one process or multiple processes of the flowchart and / or one box or multiple boxes of the block diagram.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions selected in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0125] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0126] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0127] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0128] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0129] The above are merely examples of the present disclosure and are not intended to limit the present disclosure. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure are intended to be included within the scope of the claims of the present disclosure.

Claims

1. A method for obtaining the out-of-stock rate of a commodity, characterized in that: include: Acquire images of the commodity area at different times to obtain multiple area images; Perform commodity identification on the plurality of regional images, and generate a plurality of corresponding layout drawings according to the commodity identification results; each of the layout drawings is used to indicate the commodity position of various commodities in the regional images; Overlaying the multiple layout drawings to obtain a historical layout drawing for indicating that various commodities are fully stocked; According to the shooting time sequence of the regional images, determining the row surface drawing corresponding to the regional image shot last as the target row surface drawing; According to the target layout drawing and the historical layout drawing, the out-of-stock rates of various commodities in the commodity area are obtained.

2. The method for obtaining the out-of-stock rate of a commodity according to claim 1, characterized in that: The step of obtaining the out-of-stock rate of various commodities in the commodity area according to the target layout drawing and the historical layout drawing comprises: Acquire the first commodity quantity of each commodity in the target layout drawing and the second commodity quantity of each commodity in the historical layout drawing; Obtaining, according to the first commodity quantity and the second commodity quantity, inventory rates of various commodities in the commodity area; According to the inventory rates of various commodities in the commodity area, the corresponding out-of-stock rates of various commodities are obtained.

3. The method for obtaining the out-of-stock rate of a commodity according to claim 2, characterized in that: The step of obtaining the first commodity quantity of various commodities in the target layout drawing and the second commodity quantity of various commodities in the historical layout drawing comprises: The first commodity quantity is obtained according to the first mask range of various commodities in the target layout drawing and the individual mask range of various commodities; the first mask range represents the total occupied range of the corresponding type of commodities in the target layout drawing, and the individual mask range represents the occupied range of the corresponding type of commodities in the layout drawing; The second commodity quantity is obtained according to the second mask range of various commodities in the historical layout drawing and the individual mask range of various commodities; the second mask range represents the total occupied range of the corresponding type of commodities in the historical layout drawing.

4. The method for obtaining the out-of-stock rate of a commodity according to claim 1, characterized in that: The step of obtaining the out-of-stock rate of various commodities in the commodity area according to the target layout drawing and the historical layout drawing comprises: Obtaining a first mask range of various commodities in the target layout drawing and a second mask range of various commodities in the historical layout drawing; the first mask range represents the total occupied range of the corresponding type of commodities in the target layout drawing, and the second mask range represents the total occupied range of the corresponding type of commodities in the historical layout drawing; Obtaining the inventory rate of various commodities in the commodity area according to the first mask range and the second mask range; According to the inventory rates of various commodities in the commodity area, the corresponding out-of-stock rates of various commodities are obtained.

5. The method for obtaining the out-of-stock rate of a commodity according to claim 1, characterized in that: The step of performing commodity recognition on the plurality of area images and generating a plurality of corresponding layout drawings according to the commodity recognition results comprises: Perform commodity recognition on the plurality of regional images to obtain commodity information and commodity locations of various commodities in each of the regional images; Generate a product mask according to the product information and the product position, and obtain a product mask of each product in each of the area images; According to the commodity masks of various commodities in the same regional image, the layout drawing corresponding to the regional image is obtained.

6. The method for obtaining the out-of-stock rate of a commodity according to claim 5, characterized in that: The step of superimposing the plurality of layout drawings to obtain a historical layout drawing comprises: The commodity masks of various commodities in the plurality of layout drawings are superimposed to obtain superimposed masks of various commodities; the superimposed masks represent the mask ranges of various commodities when they are fully stocked; The historical layout drawing is obtained based on the superimposed masks of various commodities.

7. The method for obtaining the out-of-stock rate of a commodity according to claim 1, characterized in that: After the step of acquiring images of commodity areas at different times to obtain multiple area images, the method further includes: Performing pedestrian screening, commodity information screening, and / or commodity quantity screening on the multiple regional images to screen out abnormal regional images; From the plurality of area images, an abnormal area image is deleted.

8. The method for obtaining the out-of-stock rate of a commodity according to claim 7, characterized in that: The step of pedestrian screening includes: inputting the multiple area images into a trained pedestrian detection model, and determining the image output by the pedestrian detection model in which pedestrians are found as an abnormal area image.

9. The method for obtaining the out-of-stock rate of a commodity according to claim 7, characterized in that: The steps of product information screening include: Perform commodity recognition on the multiple region images to obtain commodity information of each region image; The commodity information whose appearance frequency is lower than a preset threshold is determined as abnormal commodity information, and the region image corresponding to the abnormal commodity information is determined as an abnormal region image.

10. The method for obtaining the out-of-stock rate of a commodity according to claim 7, characterized in that: The steps of commodity quantity screening include: Perform commodity recognition on the multiple regional images to obtain the commodity quantity of each commodity in each regional image; According to the shooting time sequence of each of the regional images and the commodity quantity of each commodity in each regional image, obtaining a regional image where the quantity of commodities suddenly decreases; The regional image where the quantity of goods decreases suddenly is determined as an abnormal regional image.

11. A device for obtaining a commodity out-of-stock rate, characterized in that: include: A region image acquisition module is configured to acquire images of a commodity region at different times to obtain a plurality of region images; A layout drawing acquisition module is configured to perform commodity identification on the plurality of regional images and generate a plurality of corresponding layout drawings according to the commodity identification results; each of the layout drawings is used to indicate the commodity position of various commodities in the regional images; A historical layout drawing acquisition module is configured to superimpose the multiple layout drawings to obtain a historical layout drawing for indicating that various commodities are fully stocked; A target row surface drawing acquisition module is configured to determine the row surface drawing corresponding to the last captured regional image as the target row surface drawing according to the shooting time sequence of the regional images; The out-of-stock rate acquisition module is configured to acquire the out-of-stock rate of various commodities in the commodity area according to the target layout drawing and the historical layout drawing.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for obtaining the out-of-stock rate of a commodity according to any one of claims 1 to 10 are implemented.

13. A computer device, characterized in that: The method comprises a storage device, a processor, and a computer program stored in the storage device and executable by the processor. When the processor executes the computer program, the steps of the method for obtaining the out-of-stock rate of a commodity as described in any one of claims 1 to 10 are implemented.

Images