An artificial intelligence-based remote warehouse identification method, device and medium

Abstract

The application discloses an artificial intelligence-based remote warehouse goods identification method and device and a medium, and relates to the technical field of data processing based on management purposes. The method comprises the following steps: collecting a goods image of goods to be identified in a warehouse, detecting the goods image to determine whether the goods to be identified meet the storage constraint condition corresponding to the goods type to which the goods to be identified belong; if not, screening out target goods that do not meet the storage constraint condition, generating a remote loading instruction for an image collection device according to the distribution relationship between a key identification area in the target goods and the image collection device arranged in the warehouse; and controlling the image collection device to identify the key identification area based on the remote loading instruction, so as to generate goods evaluation information for the target goods according to the obtained identification result, and giving a warning prompt according to the goods evaluation information.

Description

Technical Field

[0001] The present application relates to the technical field of data processing for management purposes, and specifically to a remote warehouse goods identification method, equipment and medium based on artificial intelligence. Background Art

[0002] In current warehouse management, the product identification process primarily relies on on-site inspections by personnel. However, this traditional method is particularly inconvenient when personnel are far from the warehouse where the goods are stored. Not only is it inefficient, but the information lag caused by distance can also lead to management oversights. While the development of video product identification technology has improved the convenience of product identification, it is limited by video resolution and the human eye's ability to discern. This makes it difficult to ensure accurate identification, especially for certain specialized goods, and poses a significant risk of error. Summary of the Invention

[0003] To solve the above problems, this application proposes a remote warehouse product identification method based on artificial intelligence, including:

[0004] Collecting cargo images of the cargo to be identified in the warehouse and detecting the cargo images to determine whether the cargo to be identified meets the storage constraints corresponding to the cargo type to which it belongs;

[0005] If not, filter out the target goods that do not meet the storage constraint conditions, and generate a remote loading instruction for the image acquisition device according to the distribution relationship between the key identification areas in the target goods and the image acquisition devices set in the warehouse;

[0006] Based on the remote loading instruction, the image acquisition device is controlled to identify the key identification area, so as to generate cargo evaluation information for the target cargo according to the obtained identification result, and to issue an early warning prompt according to the cargo evaluation information.

[0007] In one implementation of the present application, the storage constraints include quality constraints and space constraints. Based on the distribution relationship between the key identification areas in the target goods and the image acquisition devices provided in the warehouse, a remote loading instruction for the image acquisition devices is generated, specifically including:

[0008] If the target goods do not meet the quality constraint conditions, screening designated image acquisition devices within the coverage area of ​​the target goods from the image acquisition devices in the warehouse according to the abnormal risk information corresponding to each key identification area of ​​the target goods;

[0009] generate a first remote loading instruction for the image collection device according to a distribution relationship of spatial positions between the specified image collection device and the target goods and a concentration degree of the target goods around the specified image collection device.

[0010] In an implementation manner of the present application, after the remote loading instruction for the image collection device is generated, the method further includes:

[0011] obtain a frequency of occurrence of the target goods in a preset observation period, and determine an instruction type corresponding to the target goods according to the frequency of occurrence; wherein the instruction type includes a single instruction and a joint instruction;

[0012] In a case where the instruction type of the target goods is the joint instruction, an auxiliary loading instruction sent by a user is identified, and the auxiliary loading instruction is corrected according to a detection requirement required by the key identification area, so that the auxiliary loading instruction and the remote loading instruction are jointly loaded when the key identification area is identified.

[0013] In an implementation manner of the present application, the goods image is detected to determine whether the to-be-identified goods meets a storage constraint condition corresponding to a goods type to which the to-be-identified goods belongs, specifically including:

[0014] The goods image is detected to determine a goods type corresponding to the to-be-identified goods, and a position identification area corresponding to the to-be-identified goods and a quality detection dimension are identified;

[0015] obtain storage information corresponding to the goods type, compare position identification information carried in the position identification area with the storage information to determine whether the position identification information matches the storage information;

[0016] and, based on the quality detection dimension, match the goods image with a standard image of the to-be-identified goods to identify whether there is a quality defect in the goods image;

[0017] In a case where the position identification information does not match the storage information and / or there is a quality defect in the goods image, it is determined that the to-be-identified goods does not meet the storage constraint condition corresponding to the goods type to which the to-be-identified goods belongs.

[0018] In an implementation manner of the present application, after the goods image is matched with the standard image of the to-be-identified goods based on the quality detection dimension, the method further includes:

[0019] determine whether the to-be-identified goods needs to be detected in linkage according to the goods type, and if yes, determine a linkage device corresponding to the to-be-identified goods;

[0020] Obtaining the sensing data collected by the linkage device to identify whether there is a quality defect in the quality detection area through the sensing data and the standard image.

[0021] In an implementation manner of the present application, the remote loading instruction further comprises a second remote loading instruction, and the second remote loading instruction is generated according to a distribution relationship between a key identification area in the target goods and an image collection device arranged in the warehouse, and specifically comprises:

[0022] When the target goods do not satisfy the space constraint condition, a target image collection device closest to the target goods in space is determined, and a second remote loading instruction for the target image collection device is generated according to a distribution relationship between the target image collection device and the key identification area.

[0023] Embodiments of the present application provide a remote warehouse identification device based on artificial intelligence, which comprises:

[0024] at least one processor;

[0025] and a memory in communication connection with the at least one processor;

[0026] wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0027] collect a goods image of a to-be-identified goods in a warehouse, and detect the goods image to determine whether the to-be-identified goods satisfies a storage constraint condition corresponding to a goods type to which the to-be-identified goods belongs;

[0028] if not, a target goods not satisfying the storage constraint condition is screened out, and a remote loading instruction for an image collection device arranged in the warehouse is generated according to a distribution relationship between a key identification area in the target goods and the image collection device;

[0029] based on the remote loading instruction, the image collection device is controlled to identify the key identification area, so as to generate goods evaluation information for the target goods according to an obtained identification result, and a warning prompt is made according to the goods evaluation information.

[0030] In an implementation manner of the present application, the storage constraint condition comprises a quality constraint condition and a space constraint condition, and the processor is further capable of:

[0031] In a case where the target goods do not satisfy the quality constraint condition, according to abnormal risk information corresponding to each key identification region in the target goods, a specified image acquisition device within a region covering the target goods is screened out from the image acquisition devices of the warehouse;

[0032] According to a distribution relationship of spatial positions between the image acquisition device and the target goods, and a concentration degree of the target goods around the specified image acquisition device, a first remote loading instruction for the image acquisition device is generated.

[0033] In an implementation manner of the present application, the processor is further capable of:

[0034] An occurrence frequency of the target goods in a preset observation period is acquired, and according to the occurrence frequency, an instruction type corresponding to the target goods is determined; wherein the instruction type includes a single instruction and a joint instruction;

[0035] In a case where the instruction type of the target goods is the joint instruction, an auxiliary loading instruction sent by a user is identified, and the auxiliary loading instruction is corrected according to detection requirements required by the key identification region, so that the auxiliary loading instruction and the remote loading instruction are jointly loaded when the key identification region is identified.

[0036] The embodiment of the present application provides a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are configured to:

[0037] The method for identifying goods in a remote warehouse based on artificial intelligence according to any one of the above.

[0038] The method for identifying goods in a remote warehouse based on artificial intelligence provided by the present application can bring the following

[0039] Beneficial effects:

[0040] By remotely identifying and evaluating the goods, personnel do not need to go to the site to check, which is especially suitable for the case where personnel are far away from the warehouse, greatly improves the convenience and efficiency of identifying goods. At the same time, based on the preliminary goods image identification result, the image acquisition device controls the secondary detection of the key identification region of the goods within a certain range, compared with the case where the traditional video identification technology is limited by resolution and human eye recognition, the identification accuracy of special goods can be effectively improved, and the error risk is reduced. In addition, the goods evaluation information is generated in time based on the identification result and a warning prompt is made, so that the management personnel can quickly understand the goods situation, timely process problems, avoid management omissions, and enhance the timeliness and accuracy of warehouse management. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0042] Figure 1 A flowchart of a remote warehouse goods identification method based on artificial intelligence provided by an embodiment of the application;

[0043] Figure 2 A schematic diagram of a remote warehouse goods identification device based on artificial intelligence provided by an embodiment of the application. DETAILED DESCRIPTION

[0044] To make the objects, technical solutions and advantages of the application clearer, the technical solutions of the application will be described below in detail with reference to the embodiments of the application and the corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the application, but not all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the application.

[0045] The technical solutions provided by the embodiments of the application will be described in detail below with reference to the drawings.

[0046] As shown in the drawings, the remote warehouse goods identification method based on artificial intelligence provided by an embodiment of the application comprises: Figure 1

[0047] S101: Collecting a goods image of a to-be-identified goods in a warehouse, detecting the goods image to determine whether the to-be-identified goods meets the storage constraint condition corresponding to the goods type to which the to-be-identified goods belongs.

[0048] In the storage management process, the goods in the warehouse will be pasted with various labels, such as two-dimensional codes, bar codes or radio frequency labels, etc. These labels usually contain the identification information of the goods (such as the goods number, name, specification, etc.) and the storage location information (such as the goods shelf number, goods location number, etc.). At the same time, multiple image acquisition devices, such as high-definition cameras, will be installed in the warehouse to collect and monitor the images of the goods. These image acquisition devices are distributed at different positions in the warehouse to ensure that the entire warehouse area can be covered.

[0049] ​Each type of goods in the warehouse has a corresponding warehouse constraint condition, which refers to the restrictions and conditions set for goods storage. One is a quality constraint condition, which is used to determine whether certain special goods (such as fresh food, medicine, textiles, etc.) have quality problems during storage. The other is a space constraint condition, which is used to determine whether the goods are stored in the correct storage location. Therefore, when remotely identifying goods, the image capture device in the warehouse can be called to capture the goods image of the goods to be identified. By detecting the goods image, it is determined whether the goods to be identified meet the warehouse constraint condition corresponding to the goods type to which it belongs, so as to determine whether the currently stored goods to be identified is abnormal.

[0050] Specifically, before identifying the goods image, a pre-trained neural network model is first obtained. The neural network model can use YOLOv8 model, etc. The neural network model detects the goods image to determine the goods type corresponding to the goods to be identified, such as food, electronic products, clothing, etc. through the probability distribution output by the Softmax layer. At the same time, the model can also identify the area containing the goods location identification information, such as a two-dimensional code, an RFID tag, or a text coding area, etc. These location identification areas can determine whether the goods are stored in the correct storage location. In addition, according to the identified goods type, the model can also determine the quality detection dimension of the goods for detection, which includes the integrity, size specification, color, etc. of the goods. Taking steel as an example, the corresponding quality detection dimension may include the length, width, thickness, and surface defects of the steel.

[0051] Therefore, after identifying the location identification area corresponding to the goods to be identified and the quality detection dimension, the goods image is identified based on these two types of information to determine whether the goods to be identified meets the warehouse constraint condition corresponding to the goods type to which it belongs.

[0052] On the one hand, for the space constraint condition, it is necessary to determine whether the current goods to be identified is stored in the correct storage location based on the warehouse information corresponding to the goods type. By searching the database by goods type, the warehouse information corresponding to the goods type can be obtained, which includes the goods number, name, specification, storage location requirement, etc. The storage location requirement limits the storage location of the goods. For example, fragile ceramic products are required to be stored on shelves with low height and good cushioning when warehousing. Therefore, after the goods are matched with the warehouse information corresponding to the goods type, the location identification information carried in the location mark area is compared with the storage location requirement in the warehouse information. By judging whether the location identification information matches the warehouse information, it can be determined whether the goods are stored in the correct location. If they do not match, it means that the goods to be identified does not meet the corresponding space constraint condition, and the storage location of the goods to be identified needs to be changed.

[0053] On the other hand, whether the quality constraint condition is met can be determined only after the quality detection dimension detects the quality of the goods image. First, a standard image corresponding to the to-be-identified goods is obtained, and the standard image refers to a standard appearance image of the goods type when the quality is qualified. Then, the goods image is matched with the standard image, and the corresponding region in the goods image is detected based on the image features in each quality detection dimension. Whether there is a quality defect in the goods image can be identified through feature comparison. If there is a quality defect, it means that the to-be-identified goods does not meet its corresponding quality constraint condition, at this time, the quality of the to-be-identified goods has a certain problem, and the goods need to be processed in time, and at the same time, such goods are avoided to be sold to the outside.

[0054] It should be noted that the quality defect of the goods cannot be comprehensively identified only according to the goods image. Before the quality of the to-be-identified goods is detected through the standard image, it is also necessary to determine whether the to-be-identified goods needs to be detected in combination according to the type of the to-be-identified goods. Different types of goods may have different characteristics and quality detection requirements. Some goods can be more accurately judged in quality through image matching, while some goods need to be combined with other detection means to more comprehensively evaluate their quality status. If it is determined that the to-be-identified goods needs to be detected in combination, the to-be-identified goods corresponding to the linkage equipment is determined, the sensing data collected by the linkage equipment and the standard image are combined, and whether there is a quality defect in the quality detection region is comprehensively analyzed. For example, for fresh goods, in addition to image monitoring, environmental data collected by sensors can also be used to assist in detecting the quality of the goods. If the environmental data does not meet the best storage requirements of the to-be-identified goods, it can be judged that the to-be-identified goods may have a certain quality defect due to the unsuitable environment. The standard image provides the quality standard of the goods in appearance, and the sensing data provides more in-depth quality information. By combining image matching and linkage detection, the quality status of the goods can be comprehensively evaluated from multiple angles and dimensions, avoiding the missed detection or misjudgment that may exist only by relying on single image matching, and improving the accuracy and reliability of quality detection.

[0055] According to the above detection process, when the position identification information does not match the warehouse information, and / or there is a quality defect in the goods image, it means that the to-be-identified goods does not meet the warehouse constraint condition.

[0056] S102: If not, the target goods that do not meet the warehouse constraint condition are screened out, and a remote loading instruction for the image acquisition device is generated according to the distribution relationship between the key identification region in the target goods and the image acquisition device arranged in the warehouse.

[0057] By the foregoing detection method, target goods that do not meet the storage constraint condition can be screened out from the goods to be identified, and these target goods may have abnormalities in the storage position or quality detection. However, this identification method is a global image recognition based on the overall image of the goods to be identified, which can quickly screen out abnormal goods, but is limited by the video resolution, and may not accurately identify some subtle and key part abnormalities, such as small characters on the goods label and small defects on the product surface.

[0058] To solve the problem of limited goods identification accuracy, a remote loading instruction for the image acquisition device can be generated according to the distribution relationship between the key identification area in the target goods and the image acquisition device arranged in the warehouse. The key identification area refers to an area containing important information, such as a position identification area, and a key quality detection area on the surface of the goods, such as an appearance defect area and a size specification detection area. Capturing the key identification area of the goods to be identified and performing secondary identification can obtain clearer images, thereby more accurately determining the storage position and quality of the goods. The remote loading instruction is an instruction for remotely controlling the shooting angle, shooting frequency, resolution, etc. of the image acquisition device. According to the distribution relationship between the key identification area of the target goods and the image acquisition device arranged in the warehouse, the parameters of the image acquisition device are adjusted to obtain clearer image information, improving the accuracy and reliability of remote goods identification. At the same time, the remote loading instruction can automatically adjust the working state of the image acquisition device, and clear images of the key identification area can be obtained without manual intervention. This greatly reduces the time and workload of manual inspection and adjustment, and improves the efficiency of remote goods identification.

[0059] In one embodiment, when the target goods do not meet the quality constraint condition, the specified image acquisition device within the coverage range of the target goods in the image acquisition device of the warehouse needs to be selected based on the abnormal risk information corresponding to each key identification area in the target goods, to ensure that the selected specified image acquisition device can clearly capture the image of the key identification area.

[0060] The abnormal risk information refers to the risk degree of the key identification area, which determines the spatial range that needs to be considered when selecting the specified image acquisition device. The greater the risk, the higher the probability of abnormality of the key identification area. In order to identify whether this area is abnormal, a more extensive and comprehensive area range needs to be considered to capture the key identification area that may have abnormalities from multiple perspectives. When determining the abnormal risk information corresponding to the key identification area, the following steps can be implemented:

[0061] First, historical identification record information of the same type of goods as the target goods in the past period of time is extracted from the warehouse management system or database. The historical identification record information includes various information about the identification of the target goods, such as the appearance of the key identification area of the goods in the image, whether there is an abnormal situation, and abnormal information, etc.

[0062] Then, by analyzing the historical identification record information, the abnormal change rate of each key identification area in the target goods at different time points is calculated. The abnormal change rate represents the development of the abnormality in the key identification area. The larger the abnormal change rate, the faster the abnormal change of the target goods, and the more attention needs to be paid to the abnormal situation in this area.

[0063] Secondly, according to the abnormal change rate, the abnormal risk coefficient corresponding to the key identification area is determined. The abnormal risk coefficient is a quantitative index for measuring the possibility of abnormality in the key identification area in the future warehouse process. For example, for the key identification area on the surface of the electronic product shell, the abnormal change rate is high, and the standard value of the abnormal risk coefficient is 1. After evaluation, its abnormal risk coefficient may be determined as 0.8, indicating a high risk.

[0064] Finally, based on the abnormal risk coefficient, the area range value corresponding to each key identification area in the warehouse space is determined. The area range value is used to define the spatial range related to the key identification area that needs to be considered when selecting the image acquisition device. The abnormal risk coefficient and the area range value are positively correlated. The higher the abnormal risk coefficient, the larger the corresponding area range value, which means that when selecting the image acquisition device, a wider area range needs to be considered, because the key identification area with high risk needs a wider monitoring range to improve the possibility of discovering potential abnormalities, so as to ensure that timely measures can be taken to handle the problem and avoid loss of goods or warehouse management problems caused by abnormal situations.

[0065] After selecting the specified image acquisition device according to the risk information of the key identification area, a first remote loading instruction for the image acquisition device is generated according to the spatial position distribution relationship between the specified image acquisition device and the target goods, and the concentration of the target goods around the specified image acquisition device. The first remote loading instruction is an instruction for precise shooting positioning of the key identification area by controlling the moving route and shooting frequency of the image acquisition device when the goods to be identified do not meet the quality constraint conditions, which is used to verify whether there is a quality abnormality problem in the key identification area. The key identification area here refers to the key quality detection area.

[0066] Specifically, according to the spatial position distribution relationship between the designated image collection device and the target goods in the warehouse, the center collection point in the designated image collection device is taken as a reference, and the moving route of the center collection point from the current position to the target goods is generated according to the spatial position of the target goods, which can ensure that the image collection device can accurately aim at the target goods, and improve the accuracy and effectiveness of image collection. It should be noted that the above process realizes the regulation of the shooting angle of the designated image collection device, and can also adjust the focal length of the designated image collection device during the control of the movement of the designated image collection device, so that the designated image collection device after adjusting the focal length can obtain the enlarged key identification area, and at the same time ensure that the shooting range can contain all the target goods to be collected.

[0067] Through the distribution relationship of the spatial position, the moving route of the designated image collection device is adjusted, and in this process, the working load of each designated image collection device, that is, the distribution of the target goods that need to be covered by the designated image collection device, also needs to be considered. Therefore, the concentration of the target goods around the designated image collection device also needs to be calculated. The concentration refers to the degree of concentration of the target goods around the designated image collection device. The higher the concentration, the more target goods around the designated image collection device, and the more target goods that need to be monitored at the same time. Therefore, according to the concentration, the collection frequency of the designated image collection device can be adjusted. The higher the concentration of the surrounding goods, the higher the collection frequency of the designated image collection device may need to be improved, so as to obtain more image information and timely capture the quality abnormality of the key identification area, and realize more detailed monitoring and analysis of the target goods.

[0068] In one embodiment, when the target goods do not meet the spatial constraint condition corresponding to the type of goods to which they belong, that is, the storage position of the goods does not match the specified storage position, the specific storage position needs to be further determined and the corresponding remote loading instruction is generated.

[0069] Specifically, among all the image collection devices in the warehouse, the target image collection device closest to the target goods in space is selected by calculating the spatial distance between each device and the target goods. This can calculate the straight-line distance from each camera to the target goods according to the installation position coordinates of each camera and the current position coordinates of the target goods, using a spatial distance formula such as the Euclidean distance formula. The camera with the smallest distance is the closest target image collection device.

[0070] According to the distribution relationship between the recent target image acquisition device and the key recognition area of the target goods, such as the field of view range of the device, the relative angle with the goods, the distance, and other factors, a second remote loading instruction for controlling the target image acquisition device is generated. The second remote loading instruction is used to verify whether there is a storage location abnormality problem in the key recognition area when the goods to be identified do not meet the spatial constraint condition. The key recognition area here refers to the position identification area. For example, the second remote loading instruction requires the target image acquisition device to adjust the shooting angle and focal length, so that the key recognition area enters the center of its shooting field of view and achieves the best focus, clearly shooting the image of the area, so as to re-detect and determine whether the actual storage location of the goods is compliant. If it is found that the storage location of the goods is wrong, the quality condition of the goods can also be combined to further decide whether the goods need to be moved to the correct position or other processing is needed.

[0071] In the embodiments of the present application, when the target goods do not meet the spatial constraint condition, i.e., the storage location is wrong, the main task is to quickly determine the actual storage location. The nearest image acquisition device can most directly and quickly capture the image of the target goods, so as to quickly judge the specific location where the goods are located. The quality constraint condition involves comprehensive detection of the quality of the goods, which may need to observe the goods from multiple angles and directions to find potential quality problems. The specified image acquisition device in the surrounding range can shoot the key recognition area of the goods from different angles to provide more comprehensive image information.

[0072] In one embodiment, the above-mentioned remote loading instruction is automatically generated based on the image detection result. In order to ensure that the goods meet the storage constraint condition, the state of the goods needs to be continuously monitored. In a preset observation period, the number of times that the target goods are identified as not meeting the storage constraint condition is called the occurrence frequency. For example, in a warehouse, the system will periodically check the goods within half an hour. If a piece of goods is identified as not meeting the storage constraint condition 5 times within half an hour, then its occurrence frequency is 5 times. According to this occurrence frequency, the instruction type of the target goods can be judged. The instruction type is divided into single instruction and joint instruction. If the occurrence frequency is low, it means that the identification result of the goods has randomness, which may be caused by image quality problems such as image resolution, and the abnormality problem is not serious, which can be automatically identified and processed by the single instruction, i.e., the remote loading instruction. If the occurrence frequency is high, it means that the goods indeed have a more serious abnormality, and at this time, in order to further improve the identification efficiency, the image acquisition device can be jointly loaded and controlled by the auxiliary loading instruction sent by the user.

[0073] When the instruction type of the target goods is a joint instruction, the auxiliary loading instruction sent by the user is identified. The auxiliary loading instruction is a voice instruction issued by a person, which can provide additional information for the operation of the system. For example, the user may tell the system through a voice instruction to perform a more detailed inspection on a specific goods. The voice instruction is converted into text or instruction signals through voice recognition technology, and the system can understand the user's intention. The auxiliary loading instruction is subjected to semantic analysis to extract key instruction information therefrom. For example, the user's voice instruction may be "perform high-precision detection on the packaging box of the target goods on shelf A", and through semantic analysis of this sentence, the key instruction information "shelf A", "packaging box", and "high-precision detection" can be extracted. Next, it is necessary to determine whether the key instruction information is valid information. Valid information refers to information that can actually affect the detection or operation of the goods, such as "packaging box", which tells which area of the target goods needs to be subjected to high-precision detection next, while information such as "just check it" is invalid because it does not provide specific guidance.

[0074] If the key instruction information is valid, the auxiliary loading instruction is corrected according to the matching degree between the key instruction information and the detection requirements of the key recognition area. The higher the matching degree, the more the instruction information conforms to the detection requirements. For example, if the key recognition area needs to detect the quality of the goods, and the user's instruction information is about size detection, then the matching degree is low, and the system may need to correct the instruction to make it more in line with the quality detection requirements. The auxiliary loading instruction after correction will be jointly loaded with the remote loading instruction. Joint loading means that the two instructions will be executed simultaneously to jointly complete the recognition and detection of the key recognition area of the target goods, which can more comprehensively and effectively handle the problems of the goods, improve the efficiency and quality of warehouse management, better adapt to different goods and different detection requirements, and provide more accurate services.

[0075] S103: Based on the remote loading instruction, control the image acquisition device to recognize the key recognition area, to generate goods evaluation information for the target goods according to the obtained recognition result, and to give a warning prompt according to the goods evaluation information.

[0076] Through the remote loading instruction, the remote control system can control the image acquisition device to recognize the key recognition area, and generate goods evaluation information for the target goods according to the recognition result. The remote control system will give a warning prompt according to the generated goods evaluation information. If the goods evaluation information indicates that the goods have quality problems or are stored in the wrong location, the system will promptly issue a warning to remind the staff to take appropriate measures. For example, if it is found that the storage location of the goods does not comply with the regulations, a warning will be issued to prompt the staff to move the goods to the correct location.

[0077] In the embodiment of the present application, only through the cargo image recognition, it may be disturbed by the surrounding environment, other cargos and other factors, resulting in inaccurate recognition, and based on the preliminary image recognition result, through the secondary detection of the key recognition area of the cargos in a certain range by controlling the image acquisition device, the part needing attention can be more accurately positioned, and the accuracy of remote cargo identification is improved.

[0078] The above is the method embodiment of the present application. Based on the same idea, some embodiments of the present application also provide the device and the non-volatile computer storage medium corresponding to the above method.

[0079] Figure 2 A structure diagram of a remote warehouse cargo identification device based on artificial intelligence is provided for the embodiment of the present application. As shown in Figure 2 , it comprises:

[0080] at least one processor; and

[0081] a memory in communication connection with the at least one processor; wherein

[0082] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0083] acquire a cargo image of a cargo to be identified in a warehouse, and detect the cargo image to determine whether the cargo to be identified meets the storage constraint condition corresponding to the cargo type to which the cargo to be identified belongs;

[0084] if not, screening a target cargo that does not meet the storage constraint condition, and generating a remote loading instruction for the image acquisition device according to the distribution relationship between the key identification area in the target cargo and the image acquisition device set in the warehouse;

[0085] controlling the image acquisition device to identify the key identification area based on the remote loading instruction, to generate cargo evaluation information for the target cargo according to the obtained identification result, and to give a warning prompt according to the cargo evaluation information.

[0086] The processor can also:

[0087] in the case that the target cargo does not meet the quality constraint condition, screening a specified image acquisition device within the coverage range of the target cargo from the image acquisition devices in the warehouse according to the abnormal risk information corresponding to each key identification area in the target cargo;

[0088] generating a first remote loading instruction for the image acquisition device according to the distribution relationship of the spatial position between the image acquisition device and the target cargo, and the concentration of the target cargo around the specified image acquisition device.

[0089] The processor is further capable of:

[0090] acquiring a frequency of occurrence of the target goods in a preset observation period, and determining a command type corresponding to the target goods according to the frequency of occurrence, wherein the command type includes a single command and a joint command;

[0091] In a case where the command type of the target goods is the joint command, an auxiliary loading command sent by the user is identified, and the auxiliary loading command is corrected according to a detection requirement of the key identification area, so as to jointly load the corrected auxiliary loading command and the remote loading command when the key identification area is identified.

[0092] The embodiment of the present application provides a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are configured as the method for identifying goods in a remote warehouse based on artificial intelligence.

[0093] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts of each of the embodiments can be referred to each other. Each of the embodiments mainly describes the difference from other embodiments. Especially, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple, and the related parts can be referred to the part of the method embodiment.

[0094] The device and medium provided by the embodiment of the present application are one-to-one corresponding to the method, so the device and medium also have the similar beneficial technical effects as the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and medium will not be described here.

[0095] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0096] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0097] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0098] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0099] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0100] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. The memory is an example of computer-readable media.

[0101] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0102] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0103] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A remote warehouse goods identification method based on artificial intelligence, characterized in that: The method comprises: Collecting images of goods to be identified in the warehouse and detecting the images to determine whether the goods to be identified meet the storage constraints corresponding to the goods type to which they belong; If not, target goods that do not meet the storage constraints are screened out, and remote loading instructions are generated for the image acquisition devices set up in the warehouse based on the distribution relationship between key identification areas in the target goods and the image acquisition devices set up in the warehouse; the key identification areas are areas containing important information, including location identification areas and key quality inspection areas on the surface of the goods; Based on the remote loading instruction, controlling the image acquisition device to identify the key identification area, generating cargo evaluation information for the target cargo according to the obtained identification result, and issuing an early warning prompt according to the cargo evaluation information; Detecting the cargo image to determine whether the cargo to be identified meets the storage constraints corresponding to the cargo type to which it belongs, specifically includes: Detecting the cargo image to determine the cargo type corresponding to the cargo to be identified, and identifying the location identification area and quality detection dimension corresponding to the cargo to be identified; Obtaining warehousing information corresponding to the cargo type, and comparing the location identification information carried in the location identification area with the warehousing information to determine whether the location identification information matches the warehousing information; and, based on the quality detection dimension, matching the cargo image with a standard image of the cargo to be identified to identify whether there are quality defects in the cargo image; In a case where the location identification information does not match the warehousing information and / or there are quality defects in the cargo image, it is determined that the cargo to be identified does not meet the storage constraint conditions corresponding to the cargo type to which it belongs.

2. The method for remote warehouse goods identification based on artificial intelligence according to claim 1, characterized in that: The storage constraints include quality constraints and space constraints. Based on the distribution relationship between the key identification areas in the target goods and the image acquisition devices installed in the warehouse, a remote loading instruction for the image acquisition devices is generated, specifically including: If the target goods do not meet the quality constraint conditions, screening designated image acquisition devices within the coverage area of ​​the target goods from the image acquisition devices in the warehouse according to the abnormal risk information corresponding to each key identification area of ​​the target goods; A first remote loading instruction for the image acquisition device is generated according to the spatial distribution relationship between the designated image acquisition device and the target goods, and the concentration of the target goods around the designated image acquisition device.

3. The method for remote warehouse goods identification based on artificial intelligence according to claim 1, characterized in that: After generating the remote loading instruction for the image acquisition device, the method further includes: Obtaining the occurrence frequency of the target goods within a preset observation period, and determining the instruction type corresponding to the target goods based on the occurrence frequency; wherein the instruction type includes a single instruction and a combined instruction; In the case where the instruction type of the target cargo is the combined instruction, the auxiliary loading instruction sent by the user is identified, and the auxiliary loading instruction is corrected according to the detection requirements required by the key identification area, so that when the key identification area is identified, the corrected auxiliary loading instruction and the remote loading instruction are jointly loaded.

4. The method for remote warehouse goods identification based on artificial intelligence according to claim 1, characterized in that: After matching the cargo image with the standard image of the cargo to be identified based on the quality detection dimension, the method further includes: Determine, based on the type of goods, whether the goods to be identified require linkage detection, and if so, determine the linkage device corresponding to the goods to be identified; The sensor data collected by the linkage device is acquired to identify whether there is a quality defect in the quality inspection area through the sensor data and the standard image.

5. The method for remote warehouse goods identification based on artificial intelligence according to claim 2, characterized in that: The remote loading instruction further includes a second remote loading instruction, which generates a remote loading instruction for the image acquisition device according to the distribution relationship between the key identification area in the target goods and the image acquisition device set in the warehouse, specifically including: When the target cargo does not meet the spatial constraint condition, the target image acquisition device that is closest to the target cargo space is determined, and a second remote loading instruction for the target image acquisition device is generated based on the distribution relationship between the target image acquisition device and the key recognition area.

6. A remote warehouse goods identification device based on artificial intelligence, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Collecting cargo images of the cargo to be identified in the warehouse and detecting the cargo images to determine whether the cargo to be identified meets the storage constraints corresponding to the cargo type to which it belongs; If not, target goods that do not meet the storage constraints are screened out, and remote loading instructions are generated for the image acquisition devices set up in the warehouse based on the distribution relationship between key identification areas in the target goods and the image acquisition devices set up in the warehouse; the key identification areas are areas containing important information, including location identification areas and key quality inspection areas on the surface of the goods; Based on the remote loading instruction, controlling the image acquisition device to identify the key identification area, generating cargo evaluation information for the target cargo according to the obtained identification result, and issuing an early warning prompt according to the cargo evaluation information; Detecting the cargo image to determine whether the cargo to be identified meets the storage constraints corresponding to the cargo type to which it belongs, specifically includes: Detecting the cargo image to determine the cargo type corresponding to the cargo to be identified, and identifying the location identification area and quality detection dimension corresponding to the cargo to be identified; Obtaining warehousing information corresponding to the cargo type, and comparing the location identification information carried in the location identification area with the warehousing information to determine whether the location identification information matches the warehousing information; and, based on the quality detection dimension, matching the cargo image with a standard image of the cargo to be identified to identify whether there are quality defects in the cargo image; In a case where the location identification information does not match the warehousing information and / or there are quality defects in the cargo image, it is determined that the cargo to be identified does not meet the storage constraint conditions corresponding to the cargo type to which it belongs.

7. The artificial intelligence-based remote warehouse goods identification device according to claim 6 is characterized in that: The storage constraints include quality constraints and space constraints. The processor can also: If the target goods do not meet the quality constraint conditions, screening designated image acquisition devices within the coverage area of ​​the target goods from the image acquisition devices in the warehouse according to the abnormal risk information corresponding to each key identification area of ​​the target goods; A first remote loading instruction for the image acquisition device is generated according to the spatial distribution relationship between the image acquisition device and the target goods, and the concentration of the target goods around the designated image acquisition device.

8. The artificial intelligence-based remote warehouse goods identification device according to claim 7, characterized in that: The processor is also capable of: Obtaining the occurrence frequency of the target goods within a preset observation period, and determining the instruction type corresponding to the target goods based on the occurrence frequency; wherein the instruction type includes a single instruction and a combined instruction; In the case where the instruction type of the target cargo is the combined instruction, the auxiliary loading instruction sent by the user is identified, and the auxiliary loading instruction is corrected according to the detection requirements required by the key identification area, so that when the key identification area is identified, the corrected auxiliary loading instruction and the remote loading instruction are jointly loaded.

9. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: An artificial intelligence-based remote warehouse goods identification method as described in any one of claims 1 to 5.

Images