Supply chain management method and system based on artificial intelligence

Abstract

The invention relates to the field of image processing, in particular to a supply chain management method and system based on artificial intelligence, and the method comprises the steps: obtaining a gray image of each surface when a cargo is warehoused; selecting the grayscale image of any surface as a target image, marking all initial recognition areas in the target image, obtaining intersection areas of all the initial recognition areas, calculating the outburst indexes of the intersection areas, and forming a recognition area set of the target image by the intersection areas with the outburst indexes greater than a preset outburst threshold value; inputting the identification area set of each target image of the goods into a neural network for training, and obtaining a multi-classification network after the training is completed; inputting cargo gray level images collected in real time into the multi-classification network to obtain an output set containing probability values of each cargo category; and according to the output set, the goods are stored on specified storage locations or goods shelves according to categories. According to the invention, the goods category can be quickly identified and the goods can be accurately stored.

Description

Technical Field

[0001] The present invention relates to the field of image processing. More specifically, the present invention relates to a supply chain management method and system based on artificial intelligence. Background Art

[0002] In supply chain management, warehousing cargo collection is a crucial link. As the core hub of the supply chain, warehousing connects multiple links such as production, procurement, and sales. As a key activity in warehousing operations, the efficiency and accuracy of cargo collection directly affect the operational efficiency and cost control of the entire supply chain. Efficient cargo collection can shorten the order processing cycle, reduce logistics costs, and improve customer satisfaction.

[0003] Prior art, such as the patent application document with publication number CN118840040A, discloses a three-dimensional warehouse system based on machine vision, which includes: first, an image acquisition unit captures an image of the goods to be stored. The preprocessing unit extracts the minimum circumscribed rectangle of the goods in the image and rotates the rectangular area image to be upright. The goods recognition unit uses a scale-invariant feature conversion algorithm to match the rotated image with template images of a variety of known goods, and further determines the most matching goods template by calculating the pixel similarity, thereby identifying the category of the goods. Finally, the warehousing unit controls the warehousing equipment to store the goods in the corresponding allocable storage location in the three-dimensional warehouse according to the identified category of the goods.

[0004] However, the light in an actual warehouse environment is prone to change, and if a collision occurs during warehousing, the appearance of the existing goods will also change, thereby affecting the quality of the images collected by the image acquisition unit, resulting in the inability to perform efficient warehouse management later. Summary of the invention

[0005] In order to solve the above-mentioned technical problem that the quality of cargo image acquisition is reduced and affects efficient warehouse management, the present invention provides solutions in the following aspects.

[0006] In a first aspect, a supply chain management method based on artificial intelligence comprises: Obtain grayscale images of each side of the goods when they enter the warehouse; Selecting a grayscale image of any surface as a target image, marking all the initial recognition areas in the target image, obtaining the intersection area of ​​all the initial recognition areas, calculating the prominence index of the intersection area, and forming the intersection area whose prominence index is greater than a preset prominence threshold into a recognition area set of the target image; the recognition area set includes multiple cargo categories; The identification area set of each target image of the goods is put into the neural network for training, and a multi-classification network is obtained after the training is completed; the grayscale image of the goods collected in real time is put into the multi-classification network to obtain an output set containing probability values ​​of each category of the goods; Based on the output collection, the goods are stored by category in the designated storage locations or shelves.

[0007] The present invention can accurately determine the key feature areas of the goods by obtaining grayscale images of each side of the goods, marking the initial recognition area in the target image, and then calculating the prominence index of the intersection area. These feature areas contain significant information about the appearance of the goods, such as shape, texture, etc. When these recognition area sets are put into the neural network for training, the neural network can learn the characteristic patterns of different categories of goods and then quickly identify the category of goods; and according to the probability values ​​of each category of goods in the output set, the goods can be accurately stored in the designated storage location or shelf, so that the storage of goods in the warehouse is more orderly, and different categories of goods can be neatly placed together.

[0008] Preferably, the step of marking all initially identified areas in the target map comprises: Subtract the target image from all other grayscale images to obtain multiple difference images; A center point is randomly selected on the difference map, and a circular area is constructed with the center point as the center and an initial radius of 0. Based on the preset expansion conditions, the initial radius is gradually increased to obtain a circular area of ​​the corresponding radius. The recognition feature evaluation value of each circular area is calculated until the recognition feature evaluation value decreases for the first time, then the radius increase is stopped. The circular area after the increase in the stop radius is used as the initial recognition area of ​​the difference map, and then all the initial recognition areas in the target map are obtained.

[0009] By calculating the difference map and evaluating the local features, the important areas in the target image can be found adaptively, thereby improving the accuracy and robustness of image analysis.

[0010] Preferably, the protrusion index satisfies the relationship: ; In the formula, is the prominence index of the intersection area, is the number of initial recognition areas contained in the intersection area, is the mean value of all pixel values ​​in the intersection area, is the mean value of all pixel values ​​in the target image, is the hyperbolic tangent function.

[0011] By calculating and screening the prominence index, it can be ensured that the target image's recognition area contains only the areas with high prominence in the target image. These areas are more likely to contain key features of the goods, such as shape, texture, color, etc., thus providing more accurate feature information for subsequent goods identification and classification.

[0012] Preferably, storing the goods by category in designated storage locations or shelves according to the output set includes: A first classification threshold is set. If the maximum probability value of the goods category in the output set is greater than the first classification threshold, the input goods image is determined to belong to the goods category corresponding to the maximum probability value, and the corresponding goods are stored in the designated storage location or shelf according to the goods category.

[0013] By setting the first classification threshold, a clear judgment standard is provided for the classification of goods. Only when the maximum probability value of the goods category exceeds the first classification threshold, the goods are considered to belong to this category, thus reducing the possibility of misclassification.

[0014] Preferably, storing the goods by category in designated storage locations or shelves according to the output set further comprises: Setting a classification threshold interval, and treating goods with the maximum probability value within the classification threshold interval as high-probability goods; For each high-probability cargo, the judgment network is trained, and the real-time cargo image is input into all the trained judgment networks to obtain the output probability values ​​of multiple judgment networks. The judgment network corresponding to the maximum output probability value is found. The high-probability cargo corresponding to the judgment network is the cargo category to which the real-time collected cargo image belongs.

[0015] In actual classification, the probability value may be close to the threshold, but there is still a certain degree of uncertainty. Setting the classification threshold interval can handle these boundary conditions and avoid misclassification due to small probability differences; training the judgment network for each high-probability cargo means that each cargo category has a corresponding judgment network. When the real-time cargo image is input into all the trained judgment networks, the output probability values ​​of multiple judgment networks can be obtained. By finding the judgment network corresponding to the maximum output probability value, the cargo category to which the real-time collected cargo image belongs can be determined. This method comprehensively considers the results of multiple judgment networks, reduces the errors that may be caused by a single judgment network, and further improves the accuracy of classification.

[0016] Preferably, the training process of the judgment network includes: A second classification threshold is set, and the goods whose maximum probability value is less than the second classification threshold are regarded as low-probability goods; for each high-probability goods, the area containing only the low-probability goods category is eliminated from its recognition area set to obtain a new recognition area set; in the new recognition area set, if any recognition area contains high-probability goods, the maximum probability value corresponding to the high-probability goods is added by 1 as the mark value of the recognition area, otherwise 1 is used as the mark value of the recognition area; all the mark values ​​are weighted to obtain the weight of each recognition area in the new recognition area set; each recognition area in the new recognition area set is encoded to obtain the corresponding encoding vector, all the encoding vectors are accumulated to obtain the discriminant vector, and training is performed according to the discriminant vector to obtain a judgment network for high-probability goods.

[0017] For the new set of identification areas, different tag values ​​are assigned to each identification area according to whether the identification area contains high-probability goods, thereby highlighting the characteristics of high-probability goods and making the classification results more accurate; further, the characteristic information of high-probability goods is extracted through the encoding and accumulation process. According to the judgment network of high-probability goods, the goods can be more accurately classified and stored in designated storage locations or shelves, making the layout of goods in the warehouse more reasonable, and different categories of goods can be neatly placed together for easy management and search.

[0018] Preferably, a cross entropy loss function is used in the judgment network training process, and the training of the judgment network is completed when a preset number of training times is reached or the loss function value is less than a preset loss threshold.

[0019] In a second aspect, a supply chain management system based on artificial intelligence includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned supply chain management method based on artificial intelligence is implemented.

[0020] The beneficial effects of the present invention are: The present invention collects cargo images in real time and processes and analyzes them, so as to timely classify and store the cargo. At the same time, when faced with new cargo types or changing cargo characteristics, the present invention can quickly adapt and accurately identify them by continuously training and optimizing neural networks, thereby maintaining the dynamics and flexibility of supply chain management. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1It is a method flow chart of steps S1 to S4 in a supply chain management method based on artificial intelligence in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] The application scenario of the present invention is: performing image analysis on a six-sided rectangular parallelepiped cargo as an example.

[0024] The embodiment of the present invention discloses a supply chain management method based on artificial intelligence, referring to Figure 1 , including steps S1 to S4, which are specifically as follows: S1: Obtain grayscale images of each surface of the goods when they are put into storage.

[0025] The appearance characteristics of goods may vary due to factors such as placement angle and lighting conditions. If only a grayscale image of one surface is collected, the characteristic information of the goods may not be analyzed intuitively. However, collecting grayscale images of all surfaces can more comprehensively reflect the appearance characteristics of the goods, thereby improving the accuracy of goods identification. In addition, the shapes, sizes and materials of goods vary. Some goods may have multiple similar surfaces, while some goods may have unique characteristics on each surface.

[0026] Specifically, place the goods within the shooting range of the image acquisition device to ensure that the goods are stable and avoid movement or tilting during the shooting process. A conveyor belt or a fixing device can be used to assist in positioning the goods.

[0027] In a preset order, photograph each side of the goods in turn. For example, for a common six-sided rectangular cargo, you need to photograph its six sides, including the top, bottom, front, back, left, and right sides. When photographing each side, make sure the lens is perpendicular to the surface of the cargo to obtain a clear, distortion-free image.

[0028] The original images collected above are converted into grayscale images.

[0029] S2: Select a grayscale image of any surface as a target image, mark all initial recognition areas in the target image, obtain the intersection area of ​​all initial recognition areas, calculate the prominence index of the intersection area, and form the intersection areas whose prominence index is greater than a preset prominence threshold into a recognition area set of the target image; the recognition area set includes multiple cargo categories.

[0030] In practical applications, the image acquisition process may be affected by various factors such as lighting, shadows, reflections, etc., resulting in a decrease in image quality. By generating a difference map, we can eliminate these interference factors to a certain extent, because they may be weakened or eliminated in the difference map.

[0031] In addition, since the goods may be placed at any angle when entering the warehouse, it is necessary to consider the recognition of images at different rotation angles. By generating difference maps at multiple rotation angles, the algorithm's robustness to rotation can be improved. Even if the placement angle of the goods changes, the goods can still be identified by comparing the difference maps.

[0032] Specifically, a grayscale image of any side is used as the target image for analysis. For the target image, pixel values ​​are subtracted from the images of all other corresponding sides of the goods at five rotation angles (such as 0 degrees, 90 degrees, 180 degrees, 270 degrees, and 360 degrees; although 360 degrees is equal to the original image, it is included in the rotation angle for completeness) to obtain five difference images.

[0033] After obtaining the difference map of the target image, there may be multiple distinctive feature areas in the difference map. These features may be trademarks, labels, special patterns or textures, etc. These features are crucial to distinguish different goods.

[0034] Specifically, for a difference map, a center point is randomly selected, and a circular area is constructed with the center point as the center and an initial radius of 0. Then the initial radius is gradually increased by one pixel unit distance to expand the circular area. Initially, the radius is small, and the pixel differences in the circular area may be relatively consistent. As the radius increases, the pixel differences in the area gradually contain more difference information.

[0035] After each expansion, the recognition feature evaluation value of the corresponding circular area is calculated. When the recognition feature evaluation value decreases for the first time, the expansion of the circular area radius is stopped, and the circular area after the expansion is stopped is used as the initial recognition area of ​​the difference map.

[0036] The identification feature evaluation value of the circular area is calculated by analyzing the distribution of pixel values ​​in the circular area, that is, the relationship is satisfied:

[0037] In the formula, Expand the radius of the circular area The corresponding circular area recognition feature evaluation value is Expand the radius of the circular area Pixel difference The probability of occurrence, Expand the radius of the circular area The mean of the absolute values ​​of all pixel differences at this time, Expand the radius of the circular area The corresponding value at this time is is the hyperbolic tangent function.

[0038] in, It is used to calculate the entropy of the probability distribution of pixel differences in a circular area. The larger the entropy, the more uniform the distribution of pixel differences, the higher the amount of information in the area, and the higher the degree of distinction. The mean of the absolute values ​​of all pixel differences in the circular area is normalized so that the feature evaluation varies within a certain range; The radius of the circular area is normalized so that the feature evaluation is not only related to the distribution of pixel differences in the area, but also to the size of the area, avoiding feature evaluation deviation caused by the area being too large or too small.

[0039] As the radius increases, the pixel difference in the area gradually contains more difference information, and the recognition feature evaluation also changes accordingly. When the recognition feature evaluation decreases for the first time, it means that the pixel value difference information in the circular area has tended to saturation. Continuing to expand the area will not bring more effective feature information, but may introduce noise or irrelevant information. Stopping the expansion at this time can ensure that the initial recognition area has a higher feature significance and discrimination, providing a reliable basis for subsequent cargo identification.

[0040] If the pixel differences within the circular area are evenly distributed and consistent, then its recognition feature evaluation value may be low. On the contrary, if the pixel differences within the circular area have large fluctuations, changes, or heterogeneity (for example, containing multiple colors, textures, or brightness changes), then its recognition feature evaluation value may be high. A high feature evaluation value may mean that the circular area contains more information or details.

[0041] By determining the initial recognition area of ​​one difference map as described above, the initial recognition areas corresponding to other difference maps can be obtained in the same way.

[0042] In summary, one target image corresponds to five difference images, each difference image corresponds to an initial recognition region, and then all the initial recognition regions in the target image are obtained.

[0043] Traverse all the marked initial identification areas and detect the overlap between them. For each pair of areas, calculate their overlapping parts. This can be achieved using geometric algorithms or functions in the image processing library.

[0044] For each pair of overlapping initial recognition areas, their overlapping parts are taken as a new intersection area. If multiple areas overlap, their overlapping parts can be merged into a larger intersection area. For example, there are 8 initial recognition areas, and there are two initial recognition areas with overlapping parts, then there is 1 intersection area, and the number of initial recognition areas with intersections in this intersection area is 2; or there are three initial recognition areas with overlapping parts, then there is 1 intersection area, and the number of initial recognition areas with intersections in this intersection area is 3.

[0045] All the intersection areas of the target map are counted, and the significance and discrimination of the intersection areas are further analyzed by calculating the prominence index of the intersection areas.

[0046] Specifically, the number of initial recognition areas contained in the intersection area, the mean of all pixel values ​​in the intersection area, and the mean of all pixel values ​​in the target image are obtained, and the prominence index of the intersection area is calculated according to the number of initial recognition areas contained in the intersection area, the mean of all pixel values ​​in the intersection area, and the mean of all pixel values ​​in the target image, that is, the relationship is satisfied:

[0047] In the formula, is the prominence index of the intersection area, is the number of initial recognition areas contained in the intersection area, is the mean value of all pixel values ​​in the intersection area, is the mean value of all pixel values ​​in the target image, is the hyperbolic tangent function.

[0048] in, The relative difference between the average pixel value of the intersection area and the average pixel value of the entire target image is calculated. If the pixel values ​​of the intersection area and the entire target image are very close, then this value will be close to 0; if the difference is large, this value will be close to 1.

[0049] By combining the number of initial recognition regions and the pixel value difference between the intersection region and the entire target image, this index provides a quantitative indicator to assess the significance of a region in the target image. A high value indicates that the region is more prominent or significant in the target image, perhaps because it contains multiple initial recognition regions and its pixel values ​​are significantly different from the background.

[0050] Furthermore, the prominence indexes of all the intersection areas of the target graph are calculated, and the top 10 intersection areas with larger prominence indexes are retained (it should be noted that in practical applications, the number of intersection areas to be retained can be dynamically adjusted according to the actual situation of the goods and the recognition requirements). The corresponding intersection areas constitute the recognition area set of the target graph, which means that for each target graph, only those areas that are most likely to provide useful recognition information are focused on.

[0051] In summary, for each target image of the goods, 10 intersection areas with higher prominence indexes are selected as the recognition area set, so 60 recognition areas can be obtained by adding them up.

[0052] Furthermore, in these recognition areas, there may be overlapping images or data (i.e., intersections) of multiple categories of goods, and the categories of goods that can be distinguished in these recognition areas are recorded, which means that if one recognition area contains image features of two or more goods at the same time, for example, if one recognition area appears in images of multiple goods, and these goods belong to different categories, then this recognition area contains multiple categories of goods.

[0053] In general, the above S2 operation utilizes the differences and significance of image features to construct an effective recognition area set by calculating and screening the intersection areas with larger prominence indexes, thereby helping to distinguish and identify different categories of goods.

[0054] S3: The identification area set of each target image of the goods is put into the neural network for training, and a multi-classification network is obtained after the training is completed; the grayscale image of the goods collected in real time is put into the multi-classification network to obtain an output set containing probability values ​​of each category of goods.

[0055] In practical applications, cargo images may be affected by many factors, such as lighting changes, image quality, occlusion, etc. The neural network can learn the features in the recognition area through training, which are essential for distinguishing objects of different categories. During the training process, the neural network will continuously adjust its internal parameters (such as weights and biases) so that it can produce the desired output when given input. This learning process enables the neural network to gradually improve its recognition accuracy of the recognition area.

[0056] Specifically, the identification area set of each target image of the goods is put into the neural network for training, and a multi-classification network is obtained after the training is completed. It should be noted that neural network training and multi-classification network are existing technologies and will not be described in detail here.

[0057] According to the operation of S1 above, the grayscale image of the goods collected in real time is input into the multi-classification network to obtain an output set containing probability values ​​of each category of goods.

[0058] S4: Based on the output set, the goods are stored in designated storage locations or shelves by category.

[0059] First, a first classification threshold is set (set to 0.8 in the embodiment of the present invention). The first classification threshold is used to distinguish whether the cargo image can be clearly classified into a certain cargo category.

[0060] Then, the maximum probability value of the cargo category is found in the output set obtained in the above S3. If the maximum probability value is greater than the first classification threshold, it is considered that the cargo image can be clearly classified into the cargo category corresponding to the maximum probability value.

[0061] Next, according to this cargo category, the corresponding cargo is stored in the designated storage location or shelf.

[0062] It should be considered that, usually in classification tasks, a threshold is set to determine whether the prediction result is reliable. The common threshold is 0.5, but in the embodiment of the present invention, the above value is selected as 0.8 as a stricter threshold. In this case, if the maximum probability value is within the classification threshold interval of [0.5, 0.8], it means that although the probability of this category is the highest, it still does not meet the set standard, so it cannot be determined that the input cargo image belongs to this category.

[0063] In addition, for the judgment of not belonging to a certain category, this threshold is usually relatively low. For example, if the set threshold is 0.2, then when the probability value of a certain category is lower than this threshold, it can be considered that the product image does not belong to this category. Therefore, the second classification threshold is set to 0.2.

[0064] Therefore, in order to improve the accuracy of judgment, the goods whose maximum probability value of the goods category is between [0.5, 0.8] are regarded as high-probability goods, and the goods whose maximum probability value of the goods category is less than 0.2 are regarded as low-probability goods.

[0065] For each high-probability cargo, the area containing only low-probability cargo categories is removed from its recognition area set to obtain a new recognition area set. In the new recognition area set, if a certain recognition area contains high-probability cargo, the maximum probability value corresponding to the high-probability cargo plus 1 is used as the mark value of the recognition area. If the recognition area does not contain high-probability cargo, 1 is used as the mark value of the recognition area. Then all the mark values ​​are weighted to obtain the weight of each recognition area in the new recognition area set.

[0066] Each identification area in the new identification area set is encoded to obtain a corresponding encoding vector, all encoding vectors are accumulated to obtain a discriminant vector, and training is performed based on the discriminant vector to obtain a judgment network for high-probability goods. In the judgment network training process, a cross entropy loss function is used. When the preset number of training times is reached or the loss function value is less than the preset loss threshold (the loss threshold is set to 0.5 in the embodiment of the present invention), the judgment network training is completed.

[0067] Specifically, the above discriminant vector satisfies the relationship:

[0068] In the formula, is the discriminant vector of high probability goods, New identification areas for high probability goods are concentrated The weight of the recognition area, New identification areas for high probability goods are concentrated The encoding vector of the identified region, The total number of identification areas in the new identification area set for high-probability goods.

[0069] The above S4 screens out goods with certain and uncertain classification through a preliminary multi-classification network, and further trains a special judgment network for the uncertain goods to improve the accuracy of classification.

[0070] The present invention can accurately determine the key feature areas of the goods by obtaining grayscale images of each side of the goods, marking the initial recognition area in the target image, and then calculating the prominence index of the intersection area. These feature areas contain significant information about the appearance of the goods, such as shape, texture, etc. When these recognition area sets are put into the neural network for training, the neural network can learn the characteristic patterns of different categories of goods. For example, in a logistics warehouse, there are various kinds of goods, such as electronic product packaging boxes and packaging boxes. This process can quickly identify the regular shape of the packaging box and features such as metal accessories on the packaging box, so as to quickly determine the category of the goods when the goods are put into storage, avoiding the tedious process of manually checking the goods one by one, and greatly improving the recognition efficiency.

[0071] An embodiment of the present invention further discloses an artificial intelligence-based supply chain management system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an artificial intelligence-based supply chain management method according to the present invention is implemented.

[0072] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0073] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0074] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0075] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A supply chain management method based on artificial intelligence, characterized in that: include: Obtain grayscale images of each side of the goods when they enter the warehouse; Selecting a grayscale image of any surface as a target image, marking all the initial recognition areas in the target image, obtaining the intersection area of ​​all the initial recognition areas, calculating the prominence index of the intersection area, and forming the intersection area whose prominence index is greater than a preset prominence threshold into a recognition area set of the target image; the recognition area set includes multiple cargo categories; The identification area set of each target image of the goods is put into the neural network for training, and a multi-classification network is obtained after the training is completed; the grayscale image of the goods collected in real time is put into the multi-classification network to obtain an output set containing probability values ​​of each category of the goods; Based on the output collection, the goods are stored by category in the designated storage locations or shelves.

2. The supply chain management method based on artificial intelligence according to claim 1, characterized in that: The step of marking all the initially identified areas in the target map comprises: Subtract the target image from all other grayscale images to obtain multiple difference images; A center point is randomly selected on the difference map, and a circular area is constructed with the center point as the center and an initial radius of 0. Based on the preset expansion conditions, the initial radius is gradually increased to obtain a circular area of ​​the corresponding radius. The recognition feature evaluation value of each circular area is calculated until the recognition feature evaluation value decreases for the first time, then the radius increase is stopped. The circular area after the increase in the stop radius is used as the initial recognition area of ​​the difference map, and then all the initial recognition areas in the target map are obtained.

3. The supply chain management method based on artificial intelligence according to claim 2, characterized in that: The protrusion index satisfies the relationship: ; In the formula, is the prominence index of the intersection area, is the number of initial recognition areas contained in the intersection area, is the mean value of all pixel values ​​in the intersection area, is the mean value of all pixel values ​​in the target image, is the hyperbolic tangent function.

4. The supply chain management method based on artificial intelligence according to claim 3 is characterized in that: According to the output set, storing the goods by category in the designated storage location or shelf includes: A first classification threshold is set. If the maximum probability value of the goods category in the output set is greater than the first classification threshold, the input goods image is determined to belong to the goods category corresponding to the maximum probability value, and the corresponding goods are stored in the designated storage location or shelf according to the goods category.

5. The supply chain management method based on artificial intelligence according to claim 4, characterized in that: According to the output set, storing the goods by category in the designated storage location or shelf also includes: Setting a classification threshold interval, and treating goods with the maximum probability value within the classification threshold interval as high-probability goods; For each high-probability cargo, the judgment network is trained, and the real-time cargo image is input into all the trained judgment networks to obtain the output probability values ​​of multiple judgment networks. The judgment network corresponding to the maximum output probability value is found. The high-probability cargo corresponding to the judgment network is the cargo category to which the real-time collected cargo image belongs.

6. The supply chain management method based on artificial intelligence according to claim 5, characterized in that: The training process of the judgment network includes: A second classification threshold is set, and the goods whose maximum probability value is less than the second classification threshold are regarded as low-probability goods; for each high-probability goods, the area containing only the low-probability goods category is eliminated from its recognition area set to obtain a new recognition area set; in the new recognition area set, if any recognition area contains high-probability goods, the maximum probability value corresponding to the high-probability goods is added by 1 as the mark value of the recognition area, otherwise 1 is used as the mark value of the recognition area; all the mark values ​​are weighted to obtain the weight of each recognition area in the new recognition area set; each recognition area in the new recognition area set is encoded to obtain the corresponding encoding vector, all the encoding vectors are accumulated to obtain the discriminant vector, and training is performed according to the discriminant vector to obtain a judgment network for high-probability goods.

7. The supply chain management method based on artificial intelligence according to claim 6, characterized in that: The cross entropy loss function is used in the judgment network training process. When the preset training times are reached or the loss function value is less than the preset loss threshold, the judgment network training is completed.

8. A supply chain management system based on artificial intelligence, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the artificial intelligence-based supply chain management method according to any one of claims 1 to 7 is implemented.

Images