A warehouse material detection method, device, equipment and storage medium

Abstract

The application provides a warehouse material detection method, device and equipment and a storage medium, and relates to the technical field of intelligent warehousing. The warehouse material detection method comprises the following steps: acquiring current material state information of a plurality of warehouse locations to determine an abnormal warehouse location in the plurality of warehouse locations; acquiring personnel activity video corresponding to the abnormal warehouse location; analyzing the personnel activity video by using a preset identification model to obtain an operation suspicion score; and generating a detection traceability report of the abnormal warehouse location based on the operation suspicion score. According to the embodiment of the application, accurate time positioning of an abnormal event of warehouse materials can be realized.

Description

Technical Field

[0001] This application relates to the field of intelligent warehousing technology, and more specifically, to a method, apparatus, equipment, and storage medium for detecting stored materials. Background Technology

[0002] At present, the inventory systems used by companies (such as warehouses) in the logistics and warehousing industry are basically visual inventory systems. They can only detect anomalies at a certain point in time (such as missing, misplaced, or damaged goods), but cannot determine the specific time when the anomaly occurred, the cause of the anomaly (who caused it), or the process of the anomaly (how it happened).

[0003] Furthermore, warehouses are typically equipped with independent video surveillance and access control systems, but these systems are isolated from the inventory system and have no logical connection to each other. They cannot automatically establish a causal link between "abnormal materials" and "specific actions of specific personnel." When anomalies are discovered during inventory, administrators need to manually review massive amounts of video footage, guess the time range based on experience, and conduct visual screening, which is extremely inefficient and prone to missing crucial footage. Summary of the Invention

[0004] According to one aspect of this application, a method for detecting stored materials is provided, comprising: acquiring current material status information of multiple storage locations to identify abnormal storage locations among the multiple storage locations; acquiring personnel activity videos corresponding to the abnormal storage locations; parsing the personnel activity videos using a preset recognition model to obtain an operation suspicion score; and generating a detection and traceability report of the abnormal storage locations based on the operation suspicion score.

[0005] According to some embodiments, obtaining the current material status information of multiple storage locations to identify abnormal storage locations among the multiple storage locations includes: obtaining the expected material status information of multiple storage locations; comparing the current material status information and the expected material status information; and determining the abnormal storage locations and their corresponding information based on the comparison results. The information corresponding to the abnormal storage locations includes the identifier of the abnormal storage location and the time of abnormal determination.

[0006] According to some embodiments, obtaining personnel activity videos corresponding to abnormal storage locations includes: obtaining the last successful inventory count time of the abnormal storage location, and calculating an abnormal time window based on the abnormality determination time and the last successful inventory count time; determining a list of personnel entering and exiting the abnormal storage location within the abnormal time window based on the identifier of the abnormal storage location; and obtaining personnel activity videos of each person in the list of personnel entering and exiting the abnormal storage location within the abnormal time window based on the identifier of the abnormal storage location.

[0007] According to some embodiments, personnel activity videos are analyzed using a preset recognition model to obtain an operation suspicion score, including: obtaining a preset abnormal behavior mapping library, which includes the correspondence between abnormal material types and operation actions; analyzing personnel activity videos using the recognition model to identify the sequence of operation actions performed by each person entering and leaving the personnel list on materials stored in abnormal storage locations; and matching the operation action sequence with the abnormal material type based on the abnormal behavior mapping library to obtain an operation suspicion score.

[0008] According to some embodiments, based on an abnormal behavior mapping library, the sequence of operation actions is matched with the type of material abnormality to obtain an operation suspicion score, including: obtaining the occurrence time of each person's operation action; determining the matching degree between each person's operation action and the material abnormality type, the time proximity between the occurrence time and the abnormality determination time, and the degree of abnormality of each person's operation action based on the matching result between the operation action sequence and the material abnormality type; and calculating the operation suspicion score based on the matching degree, time proximity, and degree of abnormality, combined with preset weights.

[0009] According to some embodiments, generating a detection and traceability report for abnormal storage locations based on an operation suspicion score includes: sorting the operation actions corresponding to the operation suspicion scores in a preset order based on the operation suspicion scores; and generating a detection and traceability report based on the sorted operation actions.

[0010] According to some implementations, the detection and traceability report includes links to videos of personnel activities corresponding to abnormal storage locations.

[0011] According to one aspect of this application, a detection device for stored goods is provided, comprising: a status determination module for acquiring current material status information of multiple storage locations to identify abnormal storage locations among the multiple storage locations; a video acquisition module for acquiring video of personnel activities corresponding to the abnormal storage locations; a data analysis module for parsing the personnel activity video through a preset recognition model to obtain an operation suspicion score; and a report generation module for generating a detection and traceability report of the abnormal storage locations based on the operation suspicion score.

[0012] According to one aspect of this application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to perform the method as described above.

[0013] According to one aspect of this application, a computer-readable storage medium is provided that stores a computer program or instructions thereon, which, when executed by a processor, implement the method as described above.

[0014] According to the embodiments of this application, key events and video evidence leading to material anomalies can be identified in a very short time, enabling more precise traceability of material anomaly detection. This provides an objective and visual chain of evidence for determining responsibility for issues such as inventory discrepancies and cargo damage, avoiding shirking of responsibility and improving the intelligence and security of warehouse management.

[0015] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application.

[0017] Figure 1 A flowchart illustrating a method for detecting stored goods according to an example embodiment of this application is shown.

[0018] Figure 2 A schematic diagram of a detection device for stored goods according to an example embodiment of this application is shown.

[0019] Figure 3 A block diagram of an electronic device according to an example embodiment of this application is shown. Detailed Implementation

[0020] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this application will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0021] The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of these specific details, or other methods, components, materials, apparatus, or operations may be employed. In these cases, well-known structures, methods, apparatuses, implementations, materials, or operations will not be shown or described in detail.

[0022] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0023] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0024] This application provides a method, apparatus, equipment, and storage medium for detecting stored materials, which can achieve precise traceability of material anomaly detection.

[0025] The following will describe in detail, with reference to the accompanying drawings, a method, apparatus, equipment, and storage medium for detecting stored materials according to embodiments of this application.

[0026] Figure 1 A flowchart illustrating a method for detecting stored goods according to an example embodiment of this application is shown.

[0027] like Figure 1 As shown, in step S100, the current material status information of multiple storage locations is obtained to identify abnormal storage locations among the multiple storage locations.

[0028] For example, in step S100, the detection device compares the current material status information and expected material status information of multiple storage locations to identify abnormal storage locations.

[0029] The detection device acquires the expected status information of materials in multiple storage locations.

[0030] According to some embodiments, the detection device can obtain expected material status information for multiple storage locations through a warehouse management system (WMS). For example, whether storage location 1, ..., storage location N contains materials.

[0031] The detection device acquires current material status information from multiple storage locations.

[0032] According to some embodiments, the detection device can obtain the current material status information of multiple storage locations through an automated inventory system (such as a stacker crane vision inventory system). Specifically, the automated inventory system can use intelligent inventory functions to photograph and identify multiple storage locations to obtain the current material status of each location.

[0033] The detection device compares the current status information of materials with the expected status information of materials, and determines the abnormal storage locations and their corresponding information based on the comparison results.

[0034] For example, suppose the detection device obtains the current material status information for storage locations 1-10 as follows: storage locations 1-9 contain materials, and storage location 10 contains no materials. However, the expected material status information for storage locations 1-10 is shown as: each storage location contains materials. Therefore, the detection device determines storage location 10 as an abnormal storage location and uses the current time as the abnormality determination time T for storage location 10. d .

[0035] In step S200, video footage of personnel activities corresponding to the abnormal storage location is obtained.

[0036] For example, in step S200, the detection device calculates the abnormal time window and determines the list of personnel entering and leaving the abnormal storage location within the abnormal time window and the corresponding personnel activity video.

[0037] The detection device obtains the last successful inventory count time of the abnormal storage location, and calculates the abnormal time window based on the abnormality determination time and the last successful inventory count time.

[0038] According to some embodiments, the detection device obtains the time T of the last successful inventory count for abnormal storage locations. ok And determine time T based on the anomaly. d Calculate the abnormal time window ΔT=T d -T ok If the last successful inventory count for the storage location does not exist, the detection device uses a default traceability period (e.g., 24 hours) instead of the abnormal time window.

[0039] Based on the identification of abnormal storage locations, the detection device determines the list of personnel who entered and exited the abnormal storage locations within the abnormal time window.

[0040] According to some embodiments, the detection device can obtain a list of all personnel entering and exiting the abnormal storage location area within the abnormal time window ΔT through the access control system based on the identification of the abnormal storage location.

[0041] Based on the identification of abnormal storage locations, the detection device acquires video footage of the activities of each person in the list of personnel entering and exiting the warehouse within the abnormal time window.

[0042] According to some embodiments, the detection device can acquire video of each person in the abnormal storage location area within an abnormal time window by using a video storage system, based on the identification of the abnormal storage location and the obtained list of people entering and leaving the abnormal storage location area.

[0043] In step S300, the video of personnel activity is analyzed using a preset recognition model to obtain an operation suspicion score.

[0044] For example, in step S300, the detection device analyzes the video of personnel activities through a preset recognition model to identify the sequence of personnel's actions on materials in abnormal storage locations, and matches the sequence of actions with the abnormal types of materials according to a preset abnormal behavior mapping library to obtain an operation suspicion score.

[0045] The detection device acquires a preset abnormal behavior mapping library.

[0046] According to some embodiments, the abnormal behavior mapping library includes a correspondence between material abnormality types and operational actions, so as to associate material abnormality types with operational actions that may cause the abnormality.

[0047] For example, Material Anomaly Type 1 is a decrease in the quantity of Goods A, and its associated operations include "removing Goods A" and "moving the entire pallet of Goods A." Material Anomaly Type 2 is an exchange of positions between Goods A and Goods B, and its associated operations include "placing Goods A in the storage location corresponding to Goods B" and "placing Goods B in the storage location corresponding to Goods A." Material Anomaly Type 3 is damage to the outer packaging of goods, and its associated operations include "throwing goods" and "colliding with shelves."

[0048] The detection device analyzes the video of personnel activities using a preset recognition model to identify the sequence of actions performed by each person in the personnel list on materials stored in abnormal storage locations.

[0049] According to some embodiments, the recognition model may employ the SlowFast deep learning-based behavior recognition network. The detection device analyzes the video of personnel activity for each person in the list of personnel entering and exiting abnormal storage locations within the abnormal time window using the recognition model, and obtains the sequence of operational actions of each person in the list of personnel entering and exiting abnormal storage locations.

[0050] For example, the detection device first uses a recognition model to identify whether any personnel have entered the abnormal storage location area in the personnel activity video. If it confirms that personnel have entered the area, it continues to identify the personnel's actions. Suppose the detection device first identifies that personnel M from the personnel list lingered in storage location area 10, and then uses the recognition model to identify that personnel M reached into storage location area 10 to retrieve materials. In this manner, the detection device can obtain the sequence of actions performed by each person in the personnel list at the abnormal storage location.

[0051] Based on the abnormal behavior mapping library, the detection device matches the sequence of operation actions with the abnormal types of materials.

[0052] According to some embodiments, based on the correspondence between material anomaly types and operation actions in the abnormal behavior mapping library, the detection device will match the operation action sequence obtained by the recognition model with the material anomaly type and obtain the matching result.

[0053] Furthermore, the detection device acquires the time of each person's operational actions.

[0054] According to some embodiments, the time T0 of each person's action in the list of personnel entering and leaving abnormal storage locations can be obtained during the analysis of personnel activity videos through a recognition model.

[0055] Based on the matching results between the sequence of operational actions and the types of material anomalies, the detection device determines the degree of matching between the operational actions of each person in the list of personnel entering and leaving the abnormal storage location and the types of material anomalies, the time proximity between the occurrence time and the time of anomaly determination, and the degree of abnormality of each person's operational actions.

[0056] According to some embodiments, based on the matching results between operational actions and material anomaly types, the detection device can determine the matching degree score between each person's operational actions and material anomaly types according to preset rules. For example, if the operational action and the material anomaly type match completely, the matching degree score is high (e.g., 100 points); if the operational action and the material anomaly type match partially, the matching degree score is low (e.g., 50 points); and if the operational action and the material anomaly type do not match, the matching degree score is 0.

[0057] Similarly, based on the matching results between operational actions and material anomaly types, the detection device can determine the occurrence time T0 of each person's operational action and the anomaly determination time T of the abnormal storage location according to preset rules. d The time proximity score. Where T0 and T... d The closer they are, the higher their corresponding time proximity score.

[0058] Similarly, based on the matching results between operational actions and material anomaly types, the detection device can determine the degree of abnormality score of each person's operational actions according to preset rules. For example, the degree of abnormality score for normal picking up and placing of goods is low, while the degree of abnormality score for throwing or trampling of goods is high.

[0059] Based on the matching degree between each person's operation and the abnormality type of the materials, the time proximity between the occurrence time of each person's operation and the time of abnormality determination of the abnormal storage location, and the degree of abnormality of each person's operation, the detection device calculates the operation suspicion score by combining preset weights.

[0060] According to some embodiments, preset weights include w1, w2, and w3, which can be adjusted according to the actual application scenario. Based on the matching degree between each person's operation and the abnormality type of the materials (referred to as matching degree), the time proximity between the occurrence time of each person's operation and the time of abnormality determination of the abnormal storage location (referred to as time proximity), and the degree of abnormality of each person's operation (referred to as degree of abnormality), the detection device calculates the operation suspicion score S = w1. Match degree +w2 Time proximity +w3 The degree of abnormality in the movement.

[0061] In step S400, an investigation and traceability report of the abnormal storage location is generated based on the operation suspicion score.

[0062] For example, in step S400, the detection device sorts the operation actions of each person in the list of personnel entering and leaving the abnormal storage location according to the operation suspicion score, and generates a detection traceability report.

[0063] Based on the suspicion score, the detection device sorts the operation actions corresponding to the suspicion scores in a preset order.

[0064] According to some embodiments, the detection device sorts all the operation actions of each person in the list of personnel entering and leaving the abnormal storage location according to the operation suspicion score, and selects multiple operation actions with higher operation suspicion scores (such as Top 5) in a preset order (such as from high to low) as events that may lead to the occurrence of abnormal storage locations.

[0065] Then, the detection device generates a detection and traceability report for abnormal storage locations based on the ordered operation actions.

[0066] According to some embodiments, the detection and traceability report includes the identification of the abnormal storage location, the type of abnormal material, the time of abnormality determination, the associated personnel, the description of the operation, the time of occurrence of the operation, the suspicion score of the operation, and a link to the video of the personnel activity corresponding to the abnormal storage location.

[0067] According to the embodiments of this application, key events and video evidence that lead to material anomalies can be identified in a very short time, enabling more accurate traceability of material anomaly detection and improving the intelligence and security of warehouse management.

[0068] Figure 2 A schematic diagram of a detection device for stored goods according to an example embodiment of this application is shown.

[0069] like Figure 2 As shown, the detection device 100 includes a status determination module 110, a video acquisition module 120, a data analysis module 130, and a report generation module 140.

[0070] The status determination module 110 obtains the expected material status information of multiple storage locations.

[0071] The status determination module 110 obtains the current material status information of multiple storage locations.

[0072] The status determination module 110 compares the current material status information with the expected material status information, and determines the abnormal storage location and its corresponding information based on the comparison results.

[0073] The video acquisition module 120 acquires the last successful inventory count time of the abnormal storage location, and calculates the abnormal time window based on the abnormality determination time and the last successful inventory count time.

[0074] Based on the identification of the abnormal storage location, the video acquisition module 120 determines the list of personnel entering and exiting the abnormal storage location within the abnormal time window.

[0075] Based on the identification of abnormal storage locations, the video acquisition module 120 acquires video of the activities of each person in the list of personnel entering and exiting the warehouse within the abnormal time window.

[0076] The data analysis module 130 obtains a preset abnormal behavior mapping library.

[0077] The data analysis module 130 analyzes the video of personnel activities using a preset recognition model to identify the sequence of actions performed by each person in the personnel list on materials stored in abnormal storage locations.

[0078] Based on the abnormal behavior mapping library, the data analysis module 130 matches the sequence of operation actions with the abnormal types of materials.

[0079] The data analysis module 130 obtains the time of each person's operation.

[0080] Based on the matching results between the sequence of operational actions and the types of material anomalies, the data analysis module 130 determines the degree of matching between the operational actions of each person in the list of personnel entering and leaving the abnormal storage location and the types of material anomalies, the time proximity between the occurrence time and the time of anomaly determination, and the degree of abnormality of each person's operational actions.

[0081] Based on the matching degree between each person's operation and the abnormality type of the materials, the time proximity between the occurrence time of each person's operation and the time of abnormality determination of the abnormal storage location, and the degree of abnormality of each person's operation, the data analysis module 130 calculates the operation suspicion score by combining preset weights.

[0082] Based on the suspicion score, the report generation module 140 sorts the operation actions corresponding to the suspicion scores in a preset order.

[0083] The report generation module 140 generates a detection and traceability report for abnormal storage locations based on the sorted operation actions.

[0084] Figure 3 A block diagram of an electronic device according to an example embodiment of this application is shown.

[0085] like Figure 3 As shown, the electronic device 600 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0086] like Figure 3 As shown, the electronic device 600 is manifested in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc. The storage unit stores program code, which can be executed by the processing unit 610, causing the processing unit 610 to perform the methods described in this specification according to the various exemplary embodiments of this application. For example, the processing unit 610 can perform, for example... Figure 1 The method shown.

[0087] Storage unit 620 may include readable media in the form of volatile storage units, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include read-only memory (ROM) 6203.

[0088] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0089] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0090] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0091] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. The technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0092] Software products may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0093] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0094] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0095] The aforementioned computer-readable medium carries one or more programs, which, when executed by a device, cause the computer-readable medium to perform the aforementioned functions.

[0096] Those skilled in the art will understand that the above modules can be distributed in the device as described in the embodiments, or they can be modified accordingly and placed in one or more devices that are unique to this embodiment. The modules in the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0097] The embodiments of this application have been described in detail above. These descriptions are solely for the purpose of helping to understand the method and core ideas of this application. Furthermore, any changes or modifications made by those skilled in the art based on the ideas of this application, its specific implementation methods, and its application scope, are all within the scope of protection of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for detecting stored goods, characterized in that, include: Obtain the current material status information of multiple storage locations to identify abnormal storage locations among the multiple storage locations; Obtain video footage of personnel activities corresponding to the abnormal storage locations; The video of the personnel's activities is analyzed using a preset recognition model to obtain a score indicating the degree of suspicion of the operation. Based on the suspected operation score, a detection and traceability report for the abnormal storage location is generated.

2. The method according to claim 1, characterized in that, Obtain the current material status information of multiple storage locations to identify abnormal storage locations among the multiple storage locations, including: Obtain the expected material status information of the multiple storage locations; The current material status information and the expected material status information are compared; Based on the comparison results, the abnormal storage location and its corresponding information are determined. The information corresponding to the abnormal storage location includes the identifier of the abnormal storage location and the time when the abnormality was determined.

3. The method according to claim 2, characterized in that, Obtain video footage of personnel activities corresponding to the abnormal storage locations, including: Obtain the last successful inventory count time of the abnormal storage location, and calculate the abnormal time window based on the abnormality determination time and the last successful inventory count time; Based on the identifier of the abnormal storage location, determine the list of personnel entering and exiting the abnormal storage location within the abnormal time window; Based on the identifier of the abnormal storage location, obtain the video of each person's activity in the abnormal time window from the list of people entering and exiting the warehouse.

4. The method according to claim 3, characterized in that, The video of the personnel's activities is analyzed using a preset recognition model to obtain a suspicion score, including: Obtain a preset abnormal behavior mapping library, which includes the correspondence between material abnormality types and operation actions; The identification model is used to analyze the video of personnel activities to identify the sequence of actions performed by each person in the list of personnel entering and exiting the abnormal storage location on the materials stored therein. Based on the abnormal behavior mapping library, the sequence of operation actions is matched with the abnormal material type to obtain the operation suspicion score.

5. The method according to claim 4, characterized in that, Based on the abnormal behavior mapping library, the sequence of operation actions is matched with the abnormal material types to obtain the operation suspicion score, including: Obtain the time of occurrence of each person's action; Based on the matching results between the sequence of operational actions and the types of material anomalies, determine the degree of matching between each person's operational actions and the types of material anomalies, the time proximity between the occurrence time and the anomaly determination time, and the degree of abnormality of each person's operational actions; The suspicion score of the operation is calculated based on the matching degree, the time proximity, and the degree of abnormality of the action, combined with preset weights.

6. The method according to claim 5, characterized in that, Based on the operational suspicion score, a detection and traceability report for the abnormal storage location is generated, including: Based on the suspected operation score, the operation actions corresponding to the suspected operation score are sorted in a preset order; The detection and tracing report is generated based on the sorted operation actions.

7. The method according to claim 6, characterized in that, The detection and traceability report includes a link to the video of the personnel activity corresponding to the abnormal storage location.

8. A detection device for stored materials, characterized in that, include: The status determination module is used to obtain the current material status information of multiple storage locations in order to identify abnormal storage locations among the multiple storage locations; The video acquisition module is used to acquire video of personnel activities corresponding to the abnormal storage location; The data analysis module is used to analyze the video of the personnel's activities using a preset recognition model to obtain a score indicating the degree of suspicion of the operation. The report generation module is used to generate a detection and traceability report for the abnormal storage location based on the operation suspicion score.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the method as described in any one of claims 1-7.

Images