Intelligent warehouse sorting and carrying system and method based on storage robot

Abstract

The invention relates to the technical field of warehouse picking and carrying, and particularly discloses an intelligent warehouse picking and carrying system and method based on a storage robot. The storage robot is used for carrying goods to an identification conveyor, a goods identification code image is collected, image identification is conducted, and goods information is obtained; meanwhile, cargo weight data are obtained through a weight sensor, low-dimensional embedded coding is conducted on the cargo weight data and the cargo weight data through a data analysis technology based on deep learning, cargo weight dominant modeling features are constructed, and the accuracy of cargo identification information is intelligently judged by analyzing interaction between the cargo weight dominant modeling features and the embedded weight features; and in response to the accuracy of the goods identification information, the goods are conveyed through the robot. According to the method and the device, the correctness of the cargos can be verified by utilizing more information sources through combining double mechanisms of image recognition (obtaining the types and the quantity of the cargos) and weight sensor data, so that the cargos with similar labels can be effectively distinguished, and misrecognition is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of warehouse picking and handling, and more specifically, to an intelligent warehouse picking and handling system and method based on a warehouse robot. Background Art

[0002] With the rapid development of e-commerce and modern logistics, the demand for intelligent warehousing systems is increasing. As an automated device used in the field of warehousing and logistics, warehousing robots can autonomously or semi-autonomously complete tasks such as cargo handling, storage and picking, greatly improving the efficiency and accuracy of warehousing management.

[0003] Patent CN118479184A proposes a picking system for a stereoscopic warehouse based on an intelligent robot and its control method. First, the transport robot delivers the goods to the identification conveyor to scan the code and enter the information; then the double-track and single-track mobile robots cooperate to store the goods in the storage shelves; when taking the goods from the deep shelf, the relevant components are first prepared for staggered movement, and then the goods on the outside are taken; then the deep goods and the outer goods are exchanged; finally, the picking mechanism delivers the goods to the transport robot via the identification conveyor, and the robot avoids obstacles and delivers them to the designated location.

[0004] In this process, when the goods are transported to the identification conveyor and the code is scanned, the information obtained by scanning the code needs to be checked for accuracy. Only in this way can the information be guaranteed to be accurate. However, in actual application scenarios, due to the high similarity of labels or insufficient accuracy of scanning equipment, misidentification may occur, that is, mistaking one item for another. This misidentification not only affects the accuracy of inventory management, but may also lead to order processing errors and reduced customer satisfaction.

[0005] Therefore, an optimized intelligent warehouse picking and handling solution based on storage robots is desired. Summary of the invention

[0006] The present application provides an intelligent warehouse picking and handling system and method based on a storage robot, which can utilize more information sources to verify the correctness of the goods by combining the dual mechanisms of image recognition (obtaining the type and quantity of goods) and weight sensor data (obtaining the weight of goods), thereby being able to effectively distinguish goods with similar labels and reduce the occurrence of misidentification.

[0007] According to one aspect of the present application, a control method for an intelligent warehouse picking and handling system based on a storage robot is provided, comprising: transporting goods to an identification conveyor by a storage robot; collecting an identification code image of the goods by a code scanning device of the identification conveyor; performing image recognition on the identification code image to obtain goods identification information, the goods identification information including the type of goods, the quantity of goods and the destination; obtaining the weight data of the goods collected by a weight sensor; performing encoding verification on the type of goods and the quantity of goods in the goods identification information and the weight data of the goods to obtain a verification result indicating whether the goods identification information is accurate, comprising: performing low-dimensional embedding and core feature cross-modal goods information verification on the type of goods, the quantity of goods and the weight data of the goods to obtain the verification result; in response to the accuracy of the goods identification information, transporting the goods to the destination by a storage robot.

[0008] According to another aspect of the present application, there is provided an intelligent warehouse picking and handling system based on a storage robot, comprising: a cargo handling module, used to transport cargo to an identification conveyor through a storage robot; an identification code image acquisition module, used to acquire an identification code image of the cargo through a code scanning device of the identification conveyor; a cargo identification information acquisition module, used to perform image recognition on the identification code image to obtain cargo identification information, wherein the cargo identification information includes cargo type, cargo quantity and destination; a cargo weight data acquisition module, used to acquire cargo weight data acquired by a weight sensor; a verification result determination module, used to perform encoding verification on the cargo type and cargo quantity in the cargo identification information and the cargo weight data to obtain a verification result indicating whether the cargo identification information is accurate, including: performing low-dimensional embedding and core feature cross-modal cargo information verification on the cargo type, the cargo quantity and the cargo weight data to obtain the verification result; a cargo delivery module, used to deliver the cargo to the destination through a storage robot in response to the cargo identification information being accurate.

[0009] The present application provides an intelligent warehouse picking and handling system and method based on a storage robot, which collects the identification code image of the goods by transporting the goods to the identification conveyor through the storage robot, and performs image recognition on the goods to obtain the goods information (goods type, goods quantity and destination), and obtains the goods weight data collected by the weight sensor at the same time, and uses the data analysis and coding technology based on deep learning to perform low-dimensional embedding encoding on the goods type and goods quantity and goods weight data in the goods identification information, and then constructs the goods weight explicit modeling features based on the embedded goods type low-dimensional embedding features and goods quantity low-dimensional embedding features, so as to intelligently judge whether the object identification information is accurate according to the core feature response interaction between the goods weight explicit modeling features and the embedded goods weight low-dimensional embedding features, and in response to the accuracy of the goods identification information, the goods are transported by the robot. By combining the dual mechanisms of image recognition (obtaining the type and quantity of goods) and weight sensor data (obtaining the weight of goods), the present application can use more information sources to verify the correctness of the goods, so as to effectively distinguish goods with similar labels and reduce the occurrence of misidentification. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0011] Figure 1 This is a schematic flowchart of a control method for an intelligent warehouse picking and handling system based on a storage robot according to an embodiment of the present application.

[0012] Figure 2 This is a schematic flowchart of step S5 in the control method of the intelligent warehouse picking and handling system based on the storage robot according to an embodiment of the present application.

[0013] Figure 3 This is a data flow diagram of step S5 in the control method of the intelligent warehouse picking and handling system based on the storage robot in an embodiment of the present application.

[0014] Figure 4 This is a schematic flowchart of step S54 in the control method of the intelligent warehouse picking and handling system based on the storage robot according to an embodiment of the present application.

[0015] Figure 5 This is a schematic block diagram of an intelligent warehouse picking and handling system based on a storage robot according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0017] Based on this, the technical concept of the present application is to collect the identification code image of the goods by transporting the goods to the identification conveyor through a warehouse robot, and perform image recognition on it to obtain the goods information (goods type, quantity and destination), and at the same time obtain the goods weight data collected by the weight sensor, and use the data analysis and coding technology based on deep learning to perform low-dimensional embedding encoding on the goods type and quantity and the goods weight data in the goods identification information, and then construct the explicit modeling features of the goods weight based on the embedded low-dimensional embedding features of the goods type and the low-dimensional embedding features of the goods quantity, so as to intelligently judge whether the object identification information is accurate according to the core feature response interaction representation between the explicit modeling features of the goods weight and the embedded low-dimensional embedding features of the goods weight, and in response to the accuracy of the goods identification information, the goods are transported by the robot. By combining the dual mechanisms of image recognition (obtaining the type and quantity of goods) and weight sensor data (obtaining the weight of goods), the present application can use more information sources to verify the correctness of the goods, so as to effectively distinguish goods with similar labels and reduce the occurrence of misidentification.

[0018] Specifically, in the technical solution of this application, Figure 1 Schematic flow chart of the control method of the intelligent warehouse picking and handling system based on the storage robot in the embodiment of the present application. Figure 1 As shown, the control method of the intelligent warehouse picking and handling system based on the storage robot includes: S1, transporting the goods to the identification conveyor by the storage robot; S2, collecting the identification code image of the goods by the scanning device of the identification conveyor; S3, performing image recognition on the identification code image to obtain the goods identification information, and the goods identification information includes the type of goods, the quantity of goods and the destination; S4, obtaining the goods weight data collected by the weight sensor; S5, encoding and verifying the type of goods and the quantity of goods in the goods identification information and the weight data of the goods to obtain a verification result indicating whether the goods identification information is accurate; S6, in response to the accuracy of the goods identification information, transporting the goods to the destination by the storage robot.

[0019] Exemplarily, in step S1, the goods are transported to the identification conveyor by the storage robot. It should be understood that the identification conveyor is equipped with a special code scanning device that can collect and identify the goods in a centralized manner. The storage robot transports the goods to the identification conveyor, and can collect and process information such as the identification code image of the goods in a centralized location, thereby improving the efficiency and accuracy of information processing. Specifically, using the storage robot to complete this handling task not only improves the operating efficiency, but also enhances the flexibility and adaptability of the system. Specifically, the storage robot can autonomously navigate and avoid obstacles according to the instructions of the controller, and safely transport the goods from the storage location to the identification conveyor. In a specific example, the storage robot includes multiple precision components such as a dual-track mobile robot, a single-track mobile robot, and various motor and belt components. These components work together to accurately locate and transport goods. The dual-track mobile robot can move horizontally on parallel ground rails, while the single-track mobile robot can move left and right on the top rail. The combination of the two can cover most areas of the warehouse. In addition, the first belt assembly and the transmission belt assembly on the guide rod drive the position adjustment component, so that the cargo transfer component and the transfer component can move according to the preset path, and finally the cargo is placed smoothly on the identification conveyor. In the whole process, the controller plays a vital role. It is not only responsible for coordinating the actions of various mechanical components, but also synchronizes the data update through the built-in preset program and the database of the warehouse management system to facilitate subsequent inventory management, order processing and logistics tracking. In this way, whether the goods are in or out of the warehouse, seamless docking can be achieved, which greatly improves the operating efficiency and service quality of the entire warehousing system. Therefore, using a warehouse robot to move goods to the identification conveyor is not only a technical requirement, but also an important means to improve the level of modern logistics warehousing management.

[0020] Exemplarily, in step S2, the identification code image of the goods is collected by the code scanning device of the identification conveyor. It should be understood that by collecting the identification code image of the goods by the code scanning device of the identification conveyor, efficient and accurate acquisition of the goods information can be achieved. When the goods are transported to the identification conveyor, the code scanning device (such as a barcode scanner or RFID reader) on the identification conveyor can automatically scan the goods, read its identification code, and transmit this information to the controller in real time. This step ensures that key information such as the type, quantity and destination of the goods can be recorded quickly and accurately. Compared with manual input, this method greatly reduces the possibility of human error and improves the reliability of the data. At the same time, this automated method also improves the processing speed, allowing the warehouse to process more goods in a shorter time, thereby improving the overall operational efficiency.

[0021] In a specific example, the process of collecting the identification code image of the goods by the scanning device of the identification conveyor is as follows: when the warehouse robot places the goods on the identification conveyor, the identification conveyor will drive the goods on its top to move horizontally in the front-back direction. During this process, the scanning device on the identification conveyor will automatically start to scan the identification code on the goods. The scanning device is usually installed on the top or side of the conveyor to ensure that all possible positions can be covered.

[0022] Exemplarily, in step S3, the identification code image is subjected to image recognition to obtain cargo identification information, and the cargo identification information includes cargo type, cargo quantity and destination. It should be understood that, considering that the identification code image contains key attribute information of the cargo, such as cargo type, cargo quantity and destination, this information provides basic data for subsequent judgment of the accuracy of this information. Based on this, in the technical solution of the present application, the identification code image is subjected to image recognition to obtain cargo identification information, and the cargo identification information includes cargo type, cargo quantity and destination. That is, the identification code, as an information carrier, usually integrates the key information of the cargo in a coded form. By parsing the identification code image through image recognition technology, the information integrated in the identification code can be accurately extracted. In this way, they can be analyzed and compared with the actual data to verify the correctness of the information and send the goods to the correct destination.

[0023] In a specific example, the process of image recognition of the identification code image is as follows: when the goods are placed on the identification conveyor, the identification conveyor will start the scanning device (such as a barcode scanner or RFID reader) installed on its top or side to scan the identification code on the goods. The identification code usually contains basic information about the goods, such as a barcode or a QR code. The scanning device captures the images of these identification codes and transmits them to the controller. The controller has built-in advanced image recognition algorithms that can analyze and decode these images to extract detailed information such as the type, quantity and destination of the goods. During the image recognition process, the controller first pre-processes the identification code image, such as denoising, enhancing contrast, etc., to improve the image quality. Then, optical character recognition (OCR) technology or other specialized decoding algorithms are used to parse out the specific data in the identification code.

[0024] Exemplarily, in step S4, the cargo weight data collected by the weight sensor is obtained. It should be understood that the cargo weight data is obtained to further confirm the accuracy of the cargo identification information. Although image recognition technology can efficiently read the barcode or QR code of the cargo and extract information such as the cargo type, quantity and destination, there may still be errors in this information. For example, the label may be incorrectly pasted or damaged, resulting in inaccurate scanning results. The actual weight data of the cargo is obtained by the weight sensor, and it is compared with the expected weight, which can effectively verify the correctness of the cargo identification information. If the actual weight does not match the expected weight, the system can promptly discover and handle abnormal situations to avoid inventory confusion and order processing errors caused by erroneous information. In addition, weight data can also help optimize warehouse management and logistics operations. For example, in a high-density storage stereoscopic warehouse, there are many types of goods and a large number of goods, and different types of goods have different weight characteristics. Through the data provided by the weight sensor, the system can more accurately allocate storage locations, reasonably plan handling routes, and ensure that the goods can be stored and transported safely and efficiently. At the same time, weight data also provides an important reference for subsequent logistics distribution, ensuring that each piece of goods can be delivered to the designated location on time and accurately.

[0025] In a specific example, the process of obtaining the cargo weight data collected by the weight sensor is as follows: When the cargo is placed on the identification conveyor, the identification conveyor activates its built-in weight sensor. These sensors are usually installed at key locations on the conveyor, such as under the cargo bracket, to ensure that the weight of the cargo can be accurately measured. When the cargo passes through the sensor, the sensor captures the cargo weight data in real time and transmits the data to the controller.

[0026] Exemplarily, in step S5, the type and quantity of goods in the goods identification information and the weight data of the goods are coded and verified to obtain a verification result indicating whether the goods identification information is accurate. It should be understood that, first of all, coding verification can effectively prevent the problem of misidentification caused by high label similarity or insufficient accuracy of scanning equipment. Although image recognition technology is very mature, in actual operation, there may still be situations such as damaged, blurred or pasted labels, which will affect the accuracy of the recognition results. For example, two different types of goods may have similar barcodes or QR codes, and relying solely on image recognition technology may lead to misjudgment. By combining the actual weight data obtained by the weight sensor, the system can compare and verify in multiple dimensions, thereby greatly reducing the probability of misidentification. If the expected weight of a piece of goods does not match the actual measured weight, the system can promptly discover and correct the error to ensure the accuracy of the goods information. Secondly, coding verification helps to improve the accuracy of inventory management. Modern warehousing systems usually need to handle a large number of goods of various types and large quantities, and accurate inventory management is essential for the smooth operation of the supply chain. By coding and verifying the cargo type, quantity and weight data, the system can update and verify inventory information in real time to avoid inventory confusion caused by inconsistent information.

[0027] In one embodiment, encoding verification is performed on the cargo type and cargo quantity in the cargo identification information and the cargo weight data to obtain a verification result indicating whether the cargo identification information is accurate, including: performing low-dimensional embedding and core feature cross-modal cargo information verification on the cargo type, the cargo quantity and the cargo weight data to obtain the verification result.

[0028] In one embodiment, Figure 2 This is a schematic flowchart of step S5 in the control method of the intelligent warehouse picking and handling system based on the storage robot according to an embodiment of the present application. Figure 3 Schematic diagram of data flow in step S5 of the control method of the intelligent warehouse picking and handling system based on the storage robot in the embodiment of the present application. Figure 2 and Figure 3As shown, the cargo type, cargo quantity and cargo weight data are subjected to low-dimensional embedding and core feature cross-modal cargo information verification to obtain the verification result, including: S51, respectively performing low-dimensional embedding coding on the cargo type and the cargo quantity to obtain a cargo type low-dimensional embedding coding vector and a cargo quantity low-dimensional embedding coding vector; S52, performing low-dimensional embedding coding on the cargo weight data to obtain a cargo weight low-dimensional embedding coding vector; S53, constructing a cargo weight explicit modeling coding vector based on the cargo type low-dimensional embedding coding vector and the cargo quantity low-dimensional embedding coding vector; S54, performing core feature cross-modal cargo information verification on the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector to obtain a cargo information heterogeneous feature response interaction coding vector; S55, obtaining the verification result based on the cargo information heterogeneous feature response interaction coding vector.

[0029] Exemplarily, in step S51, the cargo type and the cargo quantity are respectively subjected to low-dimensional embedding coding to obtain a cargo type low-dimensional embedding coding vector and a cargo quantity low-dimensional embedding coding vector. It should be understood that, in order to convert the cargo type and the cargo quantity into a form that can be processed by a computer and capture the intrinsic characteristics of each data to provide support for subsequent analysis and processing, the present application performs low-dimensional embedding coding on the cargo type and the cargo quantity to map these data to a low-dimensional space, thereby obtaining a cargo type low-dimensional embedding coding vector and a cargo quantity low-dimensional embedding coding vector. In particular, in a specific example of the present application, the cargo type and the cargo quantity are respectively subjected to low-dimensional embedding coding to obtain a cargo type low-dimensional embedding coding vector and a cargo quantity low-dimensional embedding coding vector, including: using an embedding layer to respectively encode the cargo type and the cargo quantity to obtain a cargo type low-dimensional embedding coding vector and a cargo quantity low-dimensional embedding coding vector. The cargo type and the cargo quantity can be respectively encoded using an embedding layer to obtain a cargo type low-dimensional embedding coding vector and a cargo quantity low-dimensional embedding coding vector. That is, the low-dimensional vector generated by the embedding layer can more effectively represent the characteristics of the type and quantity of goods. Compared with the original simple encoding method, the low-dimensional embedded coding vector can more accurately capture the essential attributes of goods, provide a more reliable information basis for subsequent operations such as the accuracy of goods identification information, inventory management, and path planning of warehouse robots, and improve the system's ability to understand and process goods information.

[0030] Exemplarily, in step S52, the cargo weight data is subjected to low-dimensional embedding coding to obtain a cargo weight low-dimensional embedding coding vector. It should be understood that the cargo weight data is subjected to low-dimensional embedding coding to map the cargo weight data to a low-dimensional space to obtain a cargo weight low-dimensional embedding coding vector. In particular, in a specific example of the present application, the cargo weight data is subjected to low-dimensional embedding coding to obtain a cargo weight low-dimensional embedding coding vector, including: using the embedding layer to embed the cargo weight data to obtain the cargo weight low-dimensional embedding coding vector. That is, through the embedding vector, the intrinsic structure and pattern of the weight data can be better represented in the low-dimensional space, so that the model can more effectively utilize this information.

[0031] Exemplarily, in step S53, based on the low-dimensional embedding coding vector of the cargo type and the low-dimensional embedding coding vector of the cargo quantity, an explicit modeling coding vector of cargo weight is constructed. It should be understood that there is an inherent logical connection between the cargo type and the cargo quantity and the cargo weight. Different types of cargo usually have their own relatively fixed unit weights, and the number of cargo directly affects the total weight. Therefore, in order to dig out the associated information hidden behind the data, so as to more accurately understand the formation mechanism of cargo weight, the present application constructs an explicit modeling coding vector of cargo weight based on the low-dimensional embedding coding vector of the cargo type and the low-dimensional embedding coding vector of the cargo quantity. In particular, in a specific example of the present application, based on the low-dimensional embedding coding vector of the cargo type and the low-dimensional embedding coding vector of the cargo quantity, an explicit modeling coding vector of cargo weight is constructed, including: multiplying the low-dimensional embedding coding vector of the cargo type and the low-dimensional embedding coding vector of the cargo quantity by position points to obtain the explicit modeling coding vector of cargo weight. Specifically, the low-dimensional embedded coding vector of the cargo type and the low-dimensional embedded coding vector of the cargo quantity are multiplied by position to reflect this inherent logical connection at the vector level. For example, the embedded vector elements corresponding to a certain type of fragile goods may represent some characteristic weights of this type of goods. After being multiplied by the cargo quantity vector, it can comprehensively reflect the expected weight characteristics based on the type and quantity to obtain the cargo weight explicit modeling coding vector. In this way, by constructing the cargo weight explicit modeling coding vector and comparing and verifying it with the actual weight detection results, the accuracy of the item identification information can be more effectively judged.

[0032] Exemplarily, in step S54, the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector are subjected to core feature cross-modal cargo information verification to obtain a response interaction coding vector between heterogeneous features of cargo information. It should be understood that, considering that the cargo weight low-dimensional embedding coding vector is obtained by directly performing low-dimensional embedding coding on the actual weight data of the cargo, it reflects the actual weight characteristics of the cargo; and the cargo weight explicit modeling coding vector is obtained by a specific operation (such as point multiplication by position) based on the low-dimensional embedding coding vector of the cargo type and quantity, and contains weight-related features inferred according to the cargo type and quantity. There may be potential relationships and differences between the two. Therefore, in order to verify the feature information from these two different sources and to more accurately judge the identification information, in this application, the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector are subjected to core feature cross-modal cargo information verification to obtain a response interaction coding vector between heterogeneous features of cargo information. That is, by verifying these two vectors, these potential relationships can be deeply explored, such as discovering the deviation law between the actual weight and the expected weight under certain cargo type and quantity combinations. This mining helps to better understand the properties and characteristics of the goods, providing more valuable information for subsequent analysis and decision-making.

[0033] In one embodiment, Figure 4 FIG. 5 is a schematic flow chart of step S54 in the control method of the intelligent warehouse picking and handling system based on the storage robot in the embodiment of the present application. Figure 4 As shown, the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector are subjected to core feature cross-modal cargo information verification to obtain a cargo information heterogeneous feature response interaction coding vector, including: S541, extracting core features from the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector to obtain a cargo weight low-dimensional embedding feature core information anchor coding vector and a cargo weight explicit modeling feature core information anchor coding vector; S542, S543, interactively encode the cargo information feature granularity response of the cargo weight low-dimensional embedding feature core information anchor coding vector and the cargo weight explicit modeling feature core information anchor coding vector to obtain the cargo information core feature value granularity response interactive coding vector; S544, fuse the cargo information core feature granularity response interactive coding vector and the cargo information core feature value granularity response interactive coding vector to obtain the cargo information heterogeneous feature response interactive coding vector.

[0034] In one embodiment, in step S541, core features are extracted from the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector to obtain the cargo weight low-dimensional embedding feature core information anchor coding vector and the cargo weight explicit modeling feature core information anchor coding vector, including: constructing the autocorrelation association matrix of the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector respectively to obtain the cargo weight low-dimensional embedding autocorrelation association matrix and the cargo weight explicit modeling autocorrelation association matrix. Specifically, the process is expressed by the formula: ;in, is the low-dimensional embedding encoding vector of the cargo weight, An encoding vector explicitly modeling the cargo weight, is the transpose operation, and is a feature mapping function, such as a linear mapping or a nonlinear kernel function, is the low-dimensional embedding autocorrelation matrix of cargo weight, is the autocorrelation matrix of cargo weight explicit modeling.

[0035] Cargo information autocorrelation core information anchoring is performed on the cargo weight low-dimensional embedding autocorrelation association matrix and the cargo weight explicit modeling autocorrelation association matrix respectively to obtain the cargo weight low-dimensional embedding feature core information anchoring encoding vector and the cargo weight explicit modeling feature core information anchoring encoding vector. Specifically, the process is expressed by the formula: ;in, To anchor the core information, For feature decoupling operations, and They are respectively Each row vector of and They are The corresponding cargo weight low-dimensional embedding weight matrix and cargo weight low-dimensional embedding bias vector, is matrix multiplication, is the low-dimensional embedding score weight vector of the cargo weight, It is the first significant factor in the low-dimensional embedding of cargo weight. The cargo weight is embedded in the low-dimensional salient factor, is the normalization function, is the set of significant factors of the low-dimensional embedding of normalized cargo weight. Normalized cargo weight low-dimensional embedding significant factors, is the The number of row vectors in is the low-dimensional embedding feature core information anchor encoding vector of cargo weight, and They are respectively Each row vector of and They are The corresponding cargo weight explicit weight matrix and cargo weight explicit bias vector, is the explicit scoring weight vector of cargo weight, It is the first factor in the set of dominant and significant factors of cargo weight. The cargo weight is a dominant factor. is the first in the set of normalized cargo weight dominant and significant factors Normalized cargo weight dominant factor, is the The number of row vectors in , and and The number of It is the anchor coding vector of the core information of explicit modeling features of cargo weight.

[0036] It should be understood that the purpose of constructing the autocorrelation matrix of the low-dimensional embedding coding vector of the cargo weight and the explicit modeling coding vector of the cargo weight and performing the core information anchoring operation on them is to ensure the high accuracy of the cargo identification information and the intelligence level of the system. This process can effectively improve the reliability and efficiency of the entire warehouse management system through multi-level data processing and feature extraction. First, the autocorrelation matrix of the low-dimensional embedding coding vector of the cargo weight and the explicit modeling coding vector of the cargo weight is constructed to make explicit the mutual correlation between the components within these feature vectors. Specifically, the low-dimensional embedding coding vector of the cargo weight is obtained by low-dimensional embedding coding of the actual measured cargo weight data, which reflects the actual weight characteristics of the cargo; while the explicit modeling coding vector of the cargo weight is generated based on the low-dimensional embedding coding vector of the cargo type and quantity through specific operations (such as point multiplication by position), reflecting the expected weight characteristics inferred from the cargo type and quantity. Through feature mapping, the system can generate the autocorrelation matrix of the two feature vectors, thereby revealing the relationship between their internal components. Next, the generated low-dimensional embedding autocorrelation association matrix of cargo weight and the autocorrelation association matrix of cargo weight explicit modeling are anchored with the autocorrelation core information of cargo information in order to further refine and purify the key information in the feature vector. This step highlights the parts of the feature vector that are highly related to the core semantics, removes redundant information and reduces noise through means such as feature distillation. Specifically, the system uses a core information anchoring network based on autocorrelation decoupling to process the internal information of the feature and generate a core anchor point representation with refined structure. In addition, the core information anchoring operation also has the function of constraining the semantic consistency of feature representation in the compressed space. By constraining the information entropy, the system can improve the generalization ability of the model and ensure that it can maintain high accuracy in different situations. For example, when dealing with a large number of different types and quantities of goods, the system needs to have sufficient flexibility and adaptability. By anchoring the core information, the system can maintain stable performance in a complex and changing environment and avoid misjudgments caused by data fluctuations or noise interference.

[0037] Exemplarily, in step S542, by performing cargo information feature granularity response interactive coding on the cargo weight low-dimensional embedding feature core information anchor coding vector and the cargo weight explicit modeling feature core information anchor coding vector, the system can understand the various attributes of the cargo at a more detailed level. This coding method not only focuses on the point-to-point comparison of individual feature sub-items, but also involves their overall behavior patterns in the entire feature set. For example, when processing a batch of electronic products, the system will not only analyze the specific weight differences of each product, but also consider the behavior patterns of the batch of products as a whole, such as the total weight distribution law and its potential correlation. In this process, the system uses cargo information feature granularity response interactive coding to capture the subtle differences and dependencies between the two feature vectors. The core of cargo information feature granularity response interactive coding is to reveal the deep semantic coupling within the feature vector. In this way, the system can discover hidden patterns and associations in cargo weight data. For example, the system can identify that there is a systematic deviation between the actual weight and the expected weight of certain goods, which may be due to changes in packaging materials, the presence of additional accessories, or weight deviations of certain products. These subtle differences are crucial for optimizing inventory management and path planning. Specifically, the calculation process of step S542 is expressed by the formula: ;in, It is added by location point. and are the response weight matrix and response bias vector, respectively. is the hyperbolic tangent function, It is the granular response interaction encoding vector of the core feature of cargo information.

[0038] Exemplarily, in step S543, by interactively encoding the cargo information feature value granularity response of the cargo weight low-dimensional embedded feature core information anchor coding vector and the cargo weight explicit modeling feature core information anchor coding vector, the system can understand the various attributes of the cargo more carefully at the numerical level. This encoding method not only focuses on the overall weight difference, but also details the specific weight value of each individual cargo. In this process, the system uses element-by-element operations to characterize the interdependence between feature values. This method enables the system to connect the semantic abstraction layer with the data numerical layer, thereby enriching the representation dimension of interactive modeling. Specifically, the system can reveal the specific numerical difference between the actual weight and the expected weight through element-by-element operations, and further analyze which specific cargoes cause this deviation. Specifically, the calculation process of step S543 is expressed by the formula: ;in, It is the granular response interaction coding vector of the core feature value of cargo information.

[0039] Exemplarily, in step S544, during the interactive coding of the granular response of the cargo information feature, the system explores the response relationship between the two feature vectors on the semantic unit and captures the semantic coupling at the micro level. This coding method not only focuses on the point-to-point comparison of individual feature sub-vectors, but also involves their overall behavior patterns in the entire feature set. During the interactive coding of the granular response of the cargo information feature value, the system returns to the lower-level numerical operation, and the element-by-element operation is used to characterize the interdependence between the feature values. This method enables the system to connect the semantic abstraction layer with the data numerical layer, thereby enriching the representation dimension of the interactive modeling. The specific numerical difference between the actual weight and the expected weight is revealed through the element-by-element operation, and further analysis is performed on which specific goods cause this deviation. Next, the system fuses the two encoding vectors to generate a unified encoding vector with multi-granular information expression-the interactive encoding vector of the response between heterogeneous features of cargo information. This process is not just a simple cascade operation, but also includes the integration and optimization of feature information to ensure that the final generated vector can fully reflect the various attributes and states of the goods. Through this multi-level information integration, the system can make more accurate decisions in a complex warehousing environment. The fused encoding vector contains not only the overall semantic information of the goods, but also the specific numerical differences. This comprehensive information enables the system to better understand and process various information of the goods, reduce the possibility of human errors, and improve overall operational efficiency. Specifically, the calculation process of step S544 is expressed as: ;in, For cascade operation, It is the response interaction encoding vector between heterogeneous features of the cargo information.

[0040] Preferably, in another embodiment of the present application, in step S544, the cargo information core feature granularity response interactive coding vector and the cargo information core eigenvalue granularity response interactive coding vector are fused to obtain the cargo information heterogeneous feature response interactive coding vector, including: performing cargo information growth distribution interactive gradient correction on the cargo information core feature granularity response interactive coding vector and the cargo information core eigenvalue granularity response interactive coding vector to obtain a corrected cargo information core feature granularity response interactive coding vector composed of multiple corrected cargo information core feature granularity eigenvalues ​​and a corrected cargo information core eigenvalue granularity response interactive coding vector composed of multiple corrected cargo information core eigenvalue granularity eigenvalues; and fusing the corrected cargo information core feature granularity response interactive coding vector and the corrected cargo information core eigenvalue granularity response interactive coding vector to obtain the cargo information heterogeneous feature response interactive coding vector. The process is expressed by the formula: ;in, yes Middle The eigenvalues ​​at the positions, yes Middle The eigenvalues ​​at the positions, is the cosine function, yes The corrected eigenvalues, yes The corrected eigenvalues, is the corrected cargo information core feature granularity response interaction encoding vector, is the corrected cargo information core feature value granularity response interactive coding vector, It is the response interaction encoding vector between heterogeneous features of the cargo information.

[0041] Here, considering the difference between the modeling representation of the core feature granularity response interaction coding vector of the cargo information and the core eigenvalue granularity response interaction coding vector of the cargo information, which may cause unstable perturbations in the characteristic manifold interface of the fused heterogeneous feature response interaction coding vector of the cargo information with multi-granularity information expression, the core eigenvalue granularity response interaction coding vector of the cargo information is represented as an extensibility constraint, and the overall characteristic interactive distribution growth under the eigenvalue diffusion process is used to model the interface shape perturbation deviation of the overall distribution of the core feature granularity response interaction coding vector of the cargo information based on the growth exponent representation under the extensibility constraint. That is, the interaction interface gradient under the eigenvalue granularity is used as the perturbation contribution factor, and the growth exponent stabilization contribution of the gradient diffusion under the eigenvalue mutual dependence is determined, so as to realize the growth mode gradient correction under the dominance of perturbation stabilization, and improve the manifold interface stability of the heterogeneous feature response interaction coding vector of the cargo information.

[0042] Exemplarily, in step S55, the verification result is obtained based on the response interaction coding vector between heterogeneous features of the cargo information. In one embodiment, the verification result is obtained based on the response interaction coding vector between heterogeneous features of the cargo information, including: inputting the response interaction coding vector between heterogeneous features of the cargo information into a cargo information verifier based on a classifier to obtain the verification result. That is, the response interaction coding vector between heterogeneous features of the cargo information obtained by cross-domain response interaction of the core features using the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector is classified to automatically determine whether the cargo identification information is accurate. In particular, the classifier can learn the mapping relationship between different feature patterns and specific categories after training with a large amount of data. The response interaction coding vector between heterogeneous features of the cargo information contains rich information after the actual weight feature of the cargo interacts with the expected weight feature inferred based on type and quantity. The cargo information verifier based on the classifier can analyze and identify these complex feature patterns to determine whether they meet the accurate pattern of cargo identification information. For example, during the training process, the classifier learns that when the actual weight matches the expected weight within a certain range, the cargo identification information is accurate, then it can judge whether the current cargo belongs to this accurate mode based on the interaction coding vector. In a specific example of the present application, the fused interaction coding vector of the response between heterogeneous features of cargo information is input into a pre-trained Softmax classifier. The classifier calculates the unnormalized score of each category based on the input features and converts it into a probability distribution through the Softmax function. The probability distribution output by the classifier represents the possibility of each category. The cargo information verifier based on the classifier has two types of labels: "cargo identification information is accurate" and "cargo identification information is inaccurate". For example, the result output by the classifier may be: the probability of the "cargo identification information is accurate" category is 0.95, and the probability of the "cargo identification information is inaccurate" category is 0.05, so the output verification result is that the cargo identification information is accurate.

[0043] Exemplarily, in step S6, in response to the cargo identification information being accurate, the cargo is transported to the destination by a storage robot. It should be understood that only when the cargo identification information is accurate can we clearly know what the cargo to be transported is (including cargo type, quantity, etc.) and where it is to be transported (destination). The storage robot operates based on accurate information, which can avoid errors such as taking the wrong cargo or transporting it to the wrong place, thereby ensuring the accuracy of the entire handling process. At the same time, for some special types of cargo, such as fragile goods and dangerous goods, accurate identification information can enable the robot to adopt appropriate handling methods and strengths to ensure the safety of operation, prevent cargo damage or safety accidents, and improve the operating efficiency of the entire warehouse.

[0044] Specifically, in response to the cargo identification information being accurate, the cargo is transported to the destination by a storage robot, including the following steps: First, the system calculates the optimal transportation path according to the destination of the cargo and the current warehouse layout. This step is usually completed by the warehouse management system (WMS), taking into account the traffic conditions, obstacles and other priorities of the handling tasks in the warehouse to ensure that the robot can reach the target location in the shortest time and the safest way. The path planning algorithm will comprehensively consider multiple factors, such as distance, time, energy consumption, etc., to select an optimal path. Then, the system assigns the handling task to the appropriate storage robot. Warehouse robots are usually equipped with a variety of sensors (such as lidar, cameras, etc.) for navigation and obstacle avoidance. These sensors can perceive the surrounding environment in real time to ensure that the robot will not collide or other unexpected situations during the movement. The robot will also go to the location of the cargo along the predetermined path according to the path planning results. After arriving at the location of the cargo, the storage robot uses a robotic arm or other grasping device to take the cargo off the shelf and transport it to the designated destination. During this process, the robot will continuously monitor its status and environmental changes to ensure the safety and accuracy of the handling operation. For example, the robot can detect the status of the goods through sensors to ensure that the goods are not damaged or lost. Finally, after the handling is completed, the system will record the relevant information of the handling (such as time, path, goods status, etc.) and update the inventory information in the warehouse database. These records are not only helpful for subsequent operations and management, but also can serve as the basis for data analysis to help optimize warehouse operation strategies.

[0045] In summary, according to the control method of the intelligent warehouse picking and handling system based on the storage robot of the embodiment of the present application, the storage robot carries the goods to the identification conveyor to collect the identification code image of the goods, and performs image recognition on it to obtain the goods information (goods type, quantity and destination), and obtains the goods weight data collected by the weight sensor at the same time, and uses the data analysis and coding technology based on deep learning to perform low-dimensional embedding encoding on the goods type and quantity and the goods weight data in the goods identification information, and then constructs the explicit modeling feature of the goods weight based on the embedded low-dimensional embedding feature of the goods type and the low-dimensional embedding feature of the goods quantity, so as to intelligently judge whether the object identification information is accurate according to the core feature response interaction representation between the explicit modeling feature of the goods weight and the embedded low-dimensional embedding feature of the goods weight, and in response to the accuracy of the goods identification information, the goods are transported by the robot. By combining the dual mechanisms of image recognition (obtaining the type and quantity of goods) and weight sensor data (obtaining the weight of goods), the present application can use more information sources to verify the correctness of the goods, so as to effectively distinguish goods with similar labels and reduce the occurrence of misidentification.

[0046] Figure 5Schematic block diagram of an intelligent warehouse picking and handling system based on a storage robot according to an embodiment of the present application. Figure 5 As shown, the intelligent warehouse picking and handling system 100 based on the storage robot includes: a cargo handling module 110, which is used to transport the cargo to the identification conveyor through the storage robot; an identification code image acquisition module 120, which is used to collect the identification code image of the cargo through the scanning device of the identification conveyor; a cargo identification information acquisition module 130, which is used to perform image recognition on the identification code image to obtain cargo identification information, and the cargo identification information includes cargo type, cargo quantity and destination; a cargo weight data acquisition module 140, which is used to obtain cargo weight data collected by a weight sensor; a verification result determination module 150, which is used to perform encoding verification on the cargo type and cargo quantity in the cargo identification information and the cargo weight data to obtain a verification result indicating whether the cargo identification information is accurate, including: performing low-dimensional embedding and core feature cross-modal cargo information verification on the cargo type, the cargo quantity and the cargo weight data to obtain the verification result; a cargo transportation module 160, which is used to transport the cargo to the destination through the storage robot in response to the cargo identification information being accurate.

[0047] Here, those skilled in the art can understand that the specific operations of each module in the above-mentioned intelligent warehouse picking and handling system based on the storage robot have been referred to above. Figures 1 to 4 The invention has been introduced in detail in the description of the intelligent warehouse picking and handling method based on a warehousing robot, and therefore, its repeated description will be omitted.

[0048] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0049] It should be understood that the specific examples in this article are only intended to help those skilled in the art better understand the embodiments of the present application, rather than to limit the scope of the embodiments of the present application.

[0050] It should also be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0051] It should also be understood that the various implementation methods described in this specification can be implemented individually or in combination, and the embodiments of the present application are not limited to this.

[0052] Unless otherwise stated, all technical and scientific terms used in the embodiments of the present application are the same as the meanings generally understood by those skilled in the art of the technical field of the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the scope of the present application. The term "and / or" used in the present application includes any and all combinations of one or more related listed items. The singular forms of "a kind of", "above" and "the" used in the embodiments of the present application and the appended claims are also intended to include majority forms, unless the context clearly indicates other meanings. In addition, the terms "first", "second" etc. are only used for description purposes and cannot be understood as indicating or suggesting relative importance.

[0053] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0054] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0055] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0056] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0057] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A control method for an intelligent warehouse picking and handling system based on a storage robot, characterized in that: include: The goods are transported to the identification conveyor by a storage robot; and the identification code image of the goods is collected by a code scanning device of the identification conveyor; Performing image recognition on the identification code image to obtain cargo identification information, the cargo identification information including cargo type, cargo quantity and destination; acquiring cargo weight data collected by a weight sensor; performing coding verification on the cargo type and cargo quantity in the cargo identification information and the cargo weight data to obtain a verification result indicating whether the cargo identification information is accurate, including: performing low-dimensional embedding and core feature cross-modal cargo information verification on the cargo type, cargo quantity and cargo weight data to obtain the verification result; In response to the cargo identification information being accurate, the cargo is transported to the destination by a warehouse robot.

2. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 1 is characterized in that: The cargo type, cargo quantity and cargo weight data are subjected to low-dimensional embedding and core feature cross-modal cargo information verification to obtain the verification result, including: respectively performing low-dimensional embedding coding on the cargo type and the cargo quantity to obtain a cargo type low-dimensional embedding coding vector and a cargo quantity low-dimensional embedding coding vector; performing low-dimensional embedding coding on the cargo weight data to obtain a cargo weight low-dimensional embedding coding vector; constructing a cargo weight explicit modeling coding vector based on the cargo type low-dimensional embedding coding vector and the cargo quantity low-dimensional embedding coding vector; performing core feature cross-modal cargo information verification on the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector to obtain a cargo information heterogeneous feature response interaction coding vector; and obtaining the verification result based on the cargo information heterogeneous feature response interaction coding vector.

3. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 2 is characterized in that: The cargo type and the cargo quantity are respectively low-dimensionally embedded and encoded to obtain a cargo type low-dimensional embedded coding vector and a cargo quantity low-dimensional embedded coding vector, including: using an embedding layer to respectively encode the cargo type and the cargo quantity to obtain a cargo type low-dimensional embedded coding vector and a cargo quantity low-dimensional embedded coding vector.

4. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 3 is characterized in that: The cargo weight data is low-dimensionally embedded and encoded to obtain a cargo weight low-dimensional embedded coding vector, comprising: using the embedding layer to embed the cargo weight data to obtain the cargo weight low-dimensional embedded coding vector.

5. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 4 is characterized in that: Based on the low-dimensional embedded coding vector of the cargo type and the low-dimensional embedded coding vector of the cargo quantity, a cargo weight explicit modeling coding vector is constructed, including: multiplying the low-dimensional embedded coding vector of the cargo type and the low-dimensional embedded coding vector of the cargo quantity by position points to obtain the cargo weight explicit modeling coding vector.

6. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 5 is characterized in that: The core feature cross-modal cargo information verification is performed on the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector to obtain a response interaction coding vector between heterogeneous features of cargo information, including: extracting core features from the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector to obtain a cargo weight low-dimensional embedding feature core information anchor coding vector and a cargo weight explicit modeling feature core information anchor coding vector; performing cargo information feature granularity response interaction coding on the cargo weight low-dimensional embedding feature core information anchor coding vector and the cargo weight explicit modeling feature core information anchor coding vector to obtain a cargo information core feature granularity response interaction coding vector; performing cargo information feature value granularity response interaction coding on the cargo weight low-dimensional embedding feature core information anchor coding vector and the cargo weight explicit modeling feature core information anchor coding vector to obtain a cargo information core feature value granularity response interaction coding vector; fusing the cargo information core feature granularity response interaction coding vector and the cargo information core feature value granularity response interaction coding vector to obtain the cargo information heterogeneous feature response interaction coding vector.

7. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 6 is characterized in that: Extracting core features from the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector to obtain cargo weight low-dimensional embedding feature core information anchor coding vector and cargo weight explicit modeling feature core information anchor coding vector, including: constructing the autocorrelation association matrix of the cargo weight low-dimensional embedding coding vector and the cargo weight explicit modeling coding vector respectively to obtain cargo weight low-dimensional embedding autocorrelation association matrix and cargo weight explicit modeling autocorrelation association matrix; anchoring cargo information autocorrelation core information of the cargo weight low-dimensional embedding autocorrelation association matrix and the cargo weight explicit modeling autocorrelation association matrix respectively to obtain cargo weight low-dimensional embedding feature core information anchor coding vector and cargo weight explicit modeling feature core information anchor coding vector.

8. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 7 is characterized in that: The cargo information core feature granularity response interactive coding vector and the cargo information core eigenvalue granularity response interactive coding vector are integrated to obtain the cargo information heterogeneous feature response interactive coding vector, including: performing cargo information growth distribution interactive gradient correction on the cargo information core feature granularity response interactive coding vector and the cargo information core eigenvalue granularity response interactive coding vector to obtain a corrected cargo information core feature granularity response interactive coding vector composed of multiple corrected cargo information core feature granularity eigenvalues ​​and a corrected cargo information core eigenvalue granularity response interactive coding vector composed of multiple corrected cargo information core eigenvalue granularity eigenvalues; and integrating the corrected cargo information core feature granularity response interactive coding vector and the corrected cargo information core eigenvalue granularity response interactive coding vector to obtain the cargo information heterogeneous feature response interactive coding vector.

9. The control method of the intelligent warehouse picking and handling system based on the storage robot according to claim 8 is characterized in that: The verification result is obtained based on the response interaction coding vector between the heterogeneous features of the cargo information, including: inputting the response interaction coding vector between the heterogeneous features of the cargo information into a cargo information verifier based on a classifier to obtain the verification result.

10. An intelligent warehouse picking and handling system based on a storage robot, characterized in that: include: A cargo handling module, used to carry cargo to an identification conveyor by means of a storage robot; an identification code image acquisition module, used to acquire an identification code image of the cargo by means of a code scanning device of the identification conveyor; a cargo identification information acquisition module, used to perform image recognition on the identification code image to obtain cargo identification information, wherein the cargo identification information includes cargo type, cargo quantity and destination; a cargo weight data acquisition module, used to acquire cargo weight data acquired by a weight sensor; a verification result determination module, used to perform coding verification on the cargo type and cargo quantity in the cargo identification information and the cargo weight data to obtain a verification result indicating whether the cargo identification information is accurate, including: performing low-dimensional embedding and core feature cross-modal cargo information verification on the cargo type, cargo quantity and cargo weight data to obtain the verification result; The cargo delivery module is used to deliver the cargo to the destination by a storage robot in response to the cargo identification information being accurate.

Images