A logistics material traceability management method and device

Abstract

The present invention provides a logistics material tracing management method and device, the method comprising: performing material truck detection based on a logistics video sequence to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate the video data corresponding to the material transported by the material truck at different transportation times in a specific transportation scene; the specific transportation scene includes several base stations; based on the target material truck detection frame, tracking the position information of the target material truck at different transportation times, and outputting the tracking results; when the signal data between the target material truck and the base station is detected, based on the signal data, using several base stations to locate the target material truck, and outputting the position sequence of the target material truck; based on the tracking result of the target material truck, the position sequence is accurately compared, and the real motion state of the target material truck is output. This embodiment realizes the tracing of materials in the logistics process by accurately tracking and locating the target material truck, thereby improving the efficiency and reliability of logistics management.

Description

Technical Field

[0001] The present invention belongs to the technical field of material management, and in particular relates to a logistics material traceability management method and device. Background Art

[0002] Before materials are processed or fully processed, they generally need to be stored in warehouses until they are needed for processing or transshipment, at which point they need to be transported from one destination to another. Of course, transshipment between different warehouses within the same factory also exists, but currently materials cannot be identified or screened during transportation within the same factory. In most cases, there is only a simple warehouse-in and warehouse-out registration for the goods, and it is impossible to clarify the ownership of the goods and the relationship between the periods. Moreover, staff are required to participate in the logistics transportation process, which is time-consuming and labor-intensive, and the material management efficiency is low.

[0003] Therefore, the above problems existing in the prior art easily cause confusion in the transportation and use of materials, and it is impossible to trace them. Summary of the invention

[0004] In view of the above problems existing in the prior art, an embodiment of the present invention provides a logistics material traceability management method and device; the method can realize accurate traceability and positioning of the flow of materials within the factory, thereby improving the efficiency and reliability of logistics management.

[0005] According to a first aspect of an embodiment of the present invention, a logistics material traceability management method is provided, comprising: detecting a material truck based on a logistics video sequence to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate video data corresponding to the material transported by the material truck at different transportation times under a specific transportation scenario; the specific transportation scenario includes a plurality of base stations; based on the target material truck detection frame, tracking the position information of the target material truck at different transportation times, and outputting the tracking results; when signal data between the target material truck and the base station is detected, locating the target material truck based on the signal data using the plurality of base stations, and outputting the position sequence of the target material truck at different detection times; calibrating the position sequence based on the tracking result of the target material truck, and outputting the real motion state of the target material truck.

[0006] Optionally, it also includes: establishing an association between the actual movement state of the target material truck and the virtual scene map, and visually displaying the actual movement state of the target material truck in the form of a digital twin to generate a visualization result; wherein the virtual scene map is used to indicate map information of a virtual scene constructed based on the specific transportation scene.

[0007] Optionally, when the signal data between the target material vehicle and the base station is detected, the target material vehicle is positioned using the several base stations based on the signal data, and a position sequence of the target material vehicle at different detection times is output; including: when the UWB signal transmitted by the target material vehicle to the base station is detected, the current detection time corresponding to the UWB signal is obtained; the base station that can be reached by the UWB signal detected at the current detection time is determined as a candidate base station, and several candidate base stations are obtained; based on the arrival time of the UWB signal at each of the candidate base stations, a reference base station, a first quasi base station, a second quasi base station and a third quasi base station are selected from the several candidate base stations; the UWB signal is determined The first time difference between the UWB signal arriving at the reference base station and the first quasi-base station, the second time difference between the UWB signal arriving at the reference base station and the second quasi-base station, and the third time difference between the UWB signal arriving at the reference base station and the third quasi-base station; based on the location information of the reference base station, the location information of the first quasi-base station, the location information of the second quasi-base station, the location information of the third quasi-base station, the first time difference, the second time difference, the third time difference and the speed of light, determine the positioning position of the target vehicle at the current detection moment; based on the positioning position corresponding to each current detection moment, determine the position sequence of the target vehicle at different detection moments.

[0008] Optionally, the position sequence is calibrated based on the tracking result of the target material vehicle, and the real motion state of the target material vehicle is output; including: for any current detection moment among different detection moments: obtaining the positioning position of the target material vehicle corresponding to the current detection moment from the position sequence; selecting the tracking position corresponding to the current detection moment from the tracking result of the target material vehicle; matching and fusing the tracking position and the positioning position, and outputting the observed position of the target material vehicle corresponding to the current detection moment; obtaining the real position of the target material vehicle at the previous detection moment before the current detection moment and adjacent to the current detection moment; predicting the real position of the target material vehicle at the current detection moment based on the observed position of the target material vehicle at the current detection moment and the real position at the previous detection moment; determining the real position sequence of the target material vehicle corresponding to different detection moments based on the real position corresponding to each current detection moment; determining the real speed sequence of the target material vehicle based on the real position sequence of the target material vehicle corresponding to different detection moments.

[0009] Optionally, the tracking position and the positioning position are matched and fused to output the observed position of the target vehicle at the current detection moment; including: matching the position coordinates of the target vehicle based on the positioning position and tracking position of the target vehicle; if the matching result indicates that the position coordinates of the positioning position and the tracking position of the target vehicle match, obtaining the ID of the target vehicle, and determining a first weight corresponding to the positioning position of the target vehicle and a second weight corresponding to the tracking position of the target vehicle; wherein the first weight is greater than the second weight; based on the first weight and the second weight, weighted processing is performed after applying corresponding weights to the positioning position and the tracking position, and the observed position of the target vehicle at the current detection moment is output.

[0010] Optionally, the selecting the tracking position corresponding to the current detection moment from the tracking results of the target vehicle includes: selecting the target vehicle tracking image corresponding to the current detection moment from the tracking results of the target vehicle; based on the camera parameters for collecting the logistics video sequence, converting the target vehicle tracking image from pixel space to physical space, and generating the tracking position of the target vehicle corresponding to the current detection moment.

[0011] Optionally, based on the target vehicle detection frame, the location information of the target vehicle at different transportation times is tracked, and the tracking result is output; including: based on the detection frame of the target vehicle, a temporary Car ID is assigned to the target vehicle; based on the temporary Car ID of the target vehicle, the location information of the target vehicle at different transportation times is tracked through the DeepSort strategy, and a location tracking sequence is output; the position tracking sequence is determined as the tracking result of the target vehicle.

[0012] Optionally, the method also includes: using different models of material trucks as training samples; performing data enhancement processing on each of the training samples to obtain a training sample data set; performing model training on the training sample data set based on a target detection algorithm to generate a target detection model; performing material truck detection on a logistics video sequence based on the target detection model to obtain a target material truck detection frame.

[0013] Optionally, the method also includes: encoding the material based on material information and material batch to generate a unique material identifier; generating a unique identifier for the material cart based on parameter information of the material cart; a UWB tag is affixed to the material cart, and an ID identifier is set on the UWB tag; the UWB tag on the material cart and the base station are within the same height range; establishing a mapping relationship between the unique identifier of the material cart, the unique identifier of the material and the ID identifier, and generating a binding result.

[0014] According to the second aspect of an embodiment of the present invention, a logistics material traceability management device is also provided, including: a detection module, which is used to detect a material truck based on a logistics video sequence to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate the video data corresponding to the material transported by the material truck at different transportation times under a specific transportation scenario; the specific transportation scenario includes several base stations; a tracking module, which is used to track the position information of the target material truck at different transportation times based on the target material truck detection frame, and output the tracking result; a determination module, which is used to locate the target material truck based on the signal data and using the several base stations when the signal data between the target material truck and the base station is detected, and output the position sequence of the target material truck at different detection times; a calibration module, which is used to calibrate the position sequence based on the tracking result of the target material truck, and output the real motion state of the target material truck.

[0015] According to a third aspect of an embodiment of the present invention, there is also provided an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in the first aspect.

[0016] According to a fourth aspect of an embodiment of the present invention, there is further provided a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect is implemented.

[0017] The present invention provides a logistics material traceability management method, the method comprising: first, performing material truck detection based on a logistics video sequence to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate the video data corresponding to the material transported by the material truck at different transportation times in a specific transportation scenario; the specific transportation scenario includes several base stations; secondly, based on the target material truck detection frame, tracking the position information of the target material truck at different transportation times, and outputting the tracking result; thereafter, when the signal data between the target material truck and the base station is detected, based on the signal data, the target material truck is positioned using the several base stations, and the position sequence of the target material truck at different detection times is output; finally, the position sequence is compared based on the tracking result of the target material truck, and the real motion state of the target material truck is output. This embodiment realizes the traceability of materials in the logistics process within the factory by accurately tracking and positioning the target material truck, thereby improving the efficiency and reliability of logistics management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Hereinafter, some specific embodiments of the present invention will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0019] Figure 1 A flow chart of a logistics material traceability management method provided by an embodiment of the present invention;

[0020] Figure 2 It is a schematic diagram of a flow chart of determining the position sequence of a target material vehicle at different detection times in one embodiment of the present invention;

[0021] Figure 3 It is a schematic diagram of a process of calibrating the position sequence based on the tracking result of the target material vehicle in one embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the structure of a logistics material traceability management device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] In traditional logistics management systems, material traceability often relies on paper records or simple barcode systems, which often have problems such as information entry errors, data loss or difficulty in tracking. The material barcode custom coding module and material coding and material truck binding module of the present invention implement accurate traceability of materials in the logistics process by applying a unique custom code to each material and binding it to the material truck. In a complex logistics environment, accurately locating the position of materials is crucial to improving logistics efficiency. Traditional positioning methods often cannot meet the needs of high-precision positioning. The present invention uses UWB technology, combined with YOLO-v8n and DeepSort, to achieve real-time, high-precision positioning and status tracking of materials in the logistics link. Traditional logistics management usually relies on manual operation and experience-based decision-making, which is inefficient and prone to errors. The present invention uses digital twin technology to establish a virtual model of the factory logistics network. By simulating, optimizing and predicting various situations in the logistics process, it can provide decision support for logistics management, thereby improving the efficiency and reliability of logistics management.

[0025] like Figure 1 As shown, a flow chart of a logistics material traceability management method provided by an embodiment of the present invention.

[0026] A logistics material traceability management method includes at least the following steps:

[0027] S101, performing material truck detection based on a logistics video sequence to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate video data corresponding to materials transported by a material truck at different transportation times in a specific transportation scenario; the specific transportation scenario includes a number of base stations;

[0028] S102, based on the target material vehicle detection frame, tracking the location information of the target material vehicle at different transportation times, and outputting the tracking result;

[0029] S103, when signal data between the target material vehicle and the base station is detected, based on the signal data, the target material vehicle is positioned using a plurality of base stations, and a position sequence of the target material vehicle at different detection times is output;

[0030] S104, calibrate the position sequence based on the tracking result of the target material vehicle, and output the real motion state of the target material vehicle.

[0031] In S101, illustratively, the material is encoded based on the material information and the material batch to generate a material unique identifier; based on the parameter information of the material truck, a material truck unique identifier is generated; and a mapping relationship is established between the material truck unique identifier and the material unique identifier.

[0032] For example: build a special coding management module to manage the generation, allocation, maintenance and query of material codes; implement functions such as automatic generation, manual allocation, and historical record viewing in the coding management module to facilitate the management and traceability of codes. Apply coding to all aspects of material management, including warehousing, inventory, production, etc., to ensure the uniqueness and traceability of materials.

[0033] Customize the material code based on the material type, production date, batch number and other information to generate a unique material identifier. For example, a material's barcode or QR code. A material's unique identifier ensures the accurate association between the material and its information.

[0034] Exemplarily, the sizes and number of all objects in a specific transportation scenario are counted and calculated; base stations are set up on workshop pillars, equipment, and material storage points.

[0035] The positioning of the target material truck based on communication data needs to consider long-distance communication. Reducing signal obstruction can indirectly shorten the effective communication distance. In the specific transportation scenario of logistics, the obstructions are mainly metal and concrete materials. This is because metal and concrete can easily cause signal reflection or diffraction, resulting in multipath effects or non-line-of-sight errors. Therefore, in order to improve the transmission efficiency of signal data and avoid the influence of obstructions on signal data transmission, the height difference between the two base stations should not be too large. A communication tag is affixed to the material truck, and an ID mark is set on the communication tag. The communication tag on the material truck and the base station are within the same height range.

[0036] In a specific transportation scenario, there are several material trucks transporting materials; the logistics video stream of the material trucks transporting materials is collected through the 360-degree panoramic camera deployed in the specific transportation scenario; then the logistics video sequence is used to detect the material trucks and obtain the target material truck detection frame. For example: different types of material trucks are used as training samples; each of the training samples is subjected to data enhancement processing to obtain a training sample data set; the training sample data set is trained based on the target detection algorithm to generate a target detection model; the logistics video sequence is subjected to material truck detection based on the target detection model to obtain the target material truck detection frame.

[0037] Here, the object detection algorithm can be YOLO-v8n.

[0038] In S102, the location information of the target material vehicle at different transportation times is tracked based on the existing tracking algorithm, and the tracking result is output. For example: based on the detection frame of the target material vehicle, a temporary Car ID is assigned to the target material vehicle; based on the temporary Car ID of the target material vehicle, the location information of the target material vehicle at different transportation times is tracked through the DeepSort strategy, and a location tracking sequence is output; the location tracking sequence is determined as the tracking result of the target material vehicle.

[0039] In S103, a communication tag is attached to the material vehicle, and an ID mark is set on the communication tag; the communication tag on the material vehicle and the base station are located in the same height range. The material vehicle communicates with the base station based on the communication tag. Based on the delay difference of the signal data between the target material vehicle and the base station, the positioning position of the target material vehicle in a specific transportation scenario is calculated.

[0040] The detection time is used to indicate the time when the target vehicle successfully transmits the signal data to the base station. The target vehicle has a corresponding positioning position at each detection time; the positioning positions at different detection times are arranged in time order to form a position sequence.

[0041] Here, when the communication tag is a UWB tag, the corresponding signal data is a UWB signal. Compared with WIFI, Bluetooth, ZigBee or RFID technology, UWB positioning technology has the advantages of higher positioning accuracy, strong anti-interference, strong penetration, and long communication distance.

[0042] In S104, the tracking result and position sequence of the target material vehicle are simultaneously input into the prediction model, prediction is performed, and the real motion state of the target material vehicle is output; or, according to a preset rule, the position sequence is calibrated based on the tracking result of the target material vehicle, and the real motion state of the target material vehicle is output. The real motion state of the target material vehicle includes the real position and real speed of the target material vehicle.

[0043] This embodiment uses custom coding of material barcodes and tracking and positioning of material trucks in the logistics process. It can accurately track and position the target material truck to achieve traceability of materials in the logistics process, thereby improving the efficiency and reliability of logistics management.

[0044] In a preferred implementation manner of this embodiment, a logistics material traceability management method also includes: establishing an association between the actual movement state of the target material truck and the virtual scene map, and visually displaying the actual movement state of the target material truck in the form of a digital twin to generate a visualization result; wherein the virtual scene map is used to indicate map information of a virtual scene constructed based on the specific transportation scene.

[0045] Specifically, we build scene modeling within the factory, including virtual entity modeling of building structure, road network, object distribution and other information. The model format is converted into a virtual scene map. The physical workshop is driven by the data model to complete the mapping from the physical workshop to the virtual workshop. The collected data is processed and analyzed, and useful information is extracted and displayed. The target tracked by the DeepSort strategy is associated with the virtual scene map. Through the data twin technology, the location, status, transportation trajectory and other information of the material are displayed in the form of twins to help users manage and monitor the materials.

[0046] This embodiment establishes a virtual model of the logistics network through digital twin technology, so that the real logistics process can be dynamically simulated, predicted and optimized, thereby improving the intelligence level and efficiency of logistics management.

[0047] like Figure 2 As shown, it is a schematic diagram of a flow chart of determining the position sequence of the target material vehicle at different detection times in one embodiment of the present invention.

[0048] The method for determining the position sequence of the target material vehicle at different detection times includes at least the following steps:

[0049] S201, when a UWB signal transmitted by a target material vehicle to a base station is detected, a current detection time corresponding to the UWB signal is obtained;

[0050] S202, determining base stations that can be reached by the UWB signal detected at the current detection time as candidate base stations, and obtaining a plurality of candidate base stations;

[0051] S203, selecting a reference base station, a first quasi-base station, a second quasi-base station, and a third quasi-base station from a number of candidate base stations based on the arrival time of the UWB signal at each candidate base station;

[0052] S204, determining a first time difference between the UWB signal arriving at the reference base station and the first quasi base station, a second time difference between the UWB signal arriving at the reference base station and the second quasi base station, and a third time difference between the UWB signal arriving at the reference base station and the third quasi base station;

[0053] S205, determining the positioning position of the target material vehicle at the current detection time based on the position information of the reference base station, the position information of the first quasi-base station, the position information of the second quasi-base station, the position information of the third quasi-base station, the first time difference, the second time difference, the third time difference and the speed of light;

[0054] S206, based on the positioning position corresponding to each current detection moment, determine the position sequence of the target material vehicle at different detection moments.

[0055] For example, if the workshop space is less than 10,000 square meters and the plane space is a square workshop, four VDU2506 UWB base stations are used in the factory area to simultaneously locate 20 material carts. The four base stations are installed in the four corners of the factory area to form a quadrilateral. This layout ensures that the entire factory area is covered and the distance between the base stations is relatively uniform.

[0056] Assume that the coordinates of the base stations are (Ax, Ay, Az), (Bx, By, Bz), (Cx, Cy, Cz) and (Dx, Dy, Dz), and the coordinates of the target vehicle are (Ux, Uy, Uz) which are unknown. The X-axis represents the left and right direction, the Y-axis represents the front and back direction, and the Z-axis represents the up and down direction. The coordinates of UWB base station A are (0, 0, 2.5), located in the upper left corner of the workshop, the coordinates of UWB base station B are (350, 0, 2.5), located in the upper right corner of the workshop, the coordinates of UWB base station C are (0, 350, 2.5), located in the lower left corner of the workshop, and the coordinates of UWB base station D are (350, 350, 2.5), located in the lower right corner of the workshop. Through the Time Difference of Arrival (TDOA) technology, UWB base station A is selected as the reference base station. The time difference between the target vehicle arriving at two known locations, UWB base station A and UWB base station B, and the distance between the two locations are related to each other; specifically, it is shown in the following formula (1):

[0057] Formula (1);

[0058] Where: c is the speed of light (about 3×10 8 m / s).

[0059] Δt AB It is the time difference between the signal from the target vehicle to UWB base station A and UWB base station B.

[0060] R UA is the distance from the target vehicle to the UWB base station A, and the calculation formula is:

[0061] Formula (2);

[0062] R UB is the distance from the target vehicle to the UWB base station B, and the calculation formula is:

[0063] Formula (3);

[0064] Formula (4);

[0065] The relationship between the time difference between the target vehicle arriving at two known locations, UWB base station A and UWB base station C, and the distance between the two locations is shown in the following formula (5):

[0066] Formula (5);

[0067] The relationship between the time difference of the target vehicle arriving at two known locations, UWB base station A and UWB base station D, and the distance between the two locations is as follows:

[0068] Formula (6);

[0069] The three equations (4), (5), and (6) are nonlinear. The least squares method is used to solve (Ux, Uy, Uz) to obtain the positioning position of the target material vehicle at the current detection time.

[0070] This embodiment uses multiple base stations to locate the target material truck, thereby improving the accuracy of the positioning position calculation of the target material truck, which is beneficial to the accurate tracing of materials.

[0071] like Figure 3 As shown, it is a schematic diagram of the process of calibrating the position sequence based on the tracking result of the target material vehicle in one embodiment of the present invention.

[0072] The position sequence is accurately adjusted based on the tracking result of the target material vehicle, including at least the following steps:

[0073] S301, for any current detection moment among different detection moments: obtain the positioning position of the target material vehicle at the current detection moment from the position sequence; select the tracking position corresponding to the current detection moment from the tracking result of the target material vehicle; match and fuse the tracking position and the positioning position, and output the observed position corresponding to the target material vehicle at the current detection moment; obtain the real position of the target material vehicle at the previous detection moment before the current detection moment and adjacent to the current detection moment; based on the observed position of the target material vehicle at the current detection moment and the real position at the previous detection moment, predict the real position of the target material vehicle at the current detection moment;

[0074] S302, based on the real position corresponding to each current detection moment, determining the real position sequence of the target material vehicle corresponding to different detection moments;

[0075] S303, determining a real speed sequence of the target vehicle based on the real position sequence corresponding to the target vehicle at different detection times.

[0076] Exemplarily, the tracking position and the positioning position are matched and fused to output the observed position of the target vehicle at the current detection moment; including: matching the position coordinates of the target vehicle based on the positioning position and tracking position of the target vehicle; if the matching result indicates that the position coordinates of the positioning position and the tracking position of the target vehicle match, the ID of the target vehicle is obtained, and a first weight corresponding to the positioning position of the target vehicle and a second weight corresponding to the tracking position of the target vehicle are determined; wherein the first weight is greater than the second weight; based on the first weight and the second weight, corresponding weights are applied to the positioning position and the tracking position, and weighted processing is performed to output the observed position of the target vehicle at the current detection moment.

[0077] Exemplarily, selecting the tracking position corresponding to the current detection moment from the tracking results of the target vehicle; including: selecting the target vehicle tracking image corresponding to the current detection moment from the tracking results of the target vehicle; based on the camera parameters for collecting the logistics video sequence, converting the target vehicle tracking image from pixel space to physical space, and generating the tracking position of the target vehicle corresponding to the current detection moment.

[0078] For example, when the target tracking DeepSort algorithm tracks the location information of the target material truck at different transportation times, it assigns a temporary Car ID to it.

[0079] For any current detection moment among different detection moments: the target vehicle tracking image corresponding to the current detection moment is based on image pixels, while the positioning position is based on the actual physical space. The tracking image of the target vehicle is converted from the pixel space to the actual physical space using the camera's internal parameters (such as focal length, principal point, etc.) and external parameters (rotation matrix and translation vector) to generate the tracking position of the target vehicle at the current detection moment; determine whether the absolute value of the difference between the positioning position and the tracking position is less than the preset threshold; if so, determine that the positioning position and tracking position of the target vehicle match successfully; the target tracking DeepSort algorithm obtains the ID of the target vehicle, and uses the ID to replace the temporary Car ID to continue tracking the target vehicle.

[0080] Based on the attention mechanism, different weights are assigned according to the accuracy and reliability of the DeepSort and UWB systems. Since the UWB system has higher accuracy, a greater weight is given to the positioning position. The positioning position with the first weight and the tracking position with the second weight are added together to output the observed position of the target vehicle at the current detection moment. The Kalman filter technology is used to estimate the real position of the target vehicle at the current detection moment based on the real position of the target vehicle at the previous detection moment and the observed position at the current detection moment. Since the real position coordinates contain both the image information provided by DeepSort and the actual physical space information provided by UWB, they are more accurate and reliable.

[0081] This embodiment fuses the UWB positioning results with the DeepSort algorithm tracking results and performs calibration to ensure the accuracy and stability of the target material vehicle positioning, thereby achieving accurate tracing and positioning of materials and improving the efficiency and reliability of logistics management.

[0082] The logistics material traceability management method provided in this embodiment will be described in detail below in conjunction with specific application scenarios.

[0083] A logistics material traceability management method includes: a server, and a user end and a client end connected to the server for communication; the server includes a gateway, a business layer and a cache area;

[0084] S1, taking different types of material trucks as training samples; performing data enhancement processing on each of the training samples to obtain a training sample data set; performing model training on the training sample data set based on the YOLO-v8n algorithm to generate a target detection model; performing material truck detection on the logistics video sequence based on the target detection model to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate the video data corresponding to the material truck transporting materials at different transportation times under a specific transportation scenario; the specific transportation scenario includes several base stations.

[0085] S2, based on the material information and material batch, encode the material to generate a unique material identifier; based on the parameter information of the material cart, generate a unique identifier for the material cart; a UWB tag is affixed to the material cart, and an ID identifier is set on the UWB tag; the UWB tag on the material cart and the base station are within the same height range; establish a mapping relationship between the unique identifier of the material cart, the unique identifier of the material and the ID identifier, and generate a binding result.

[0086] S3, based on the detection frame of the target material vehicle, assign a temporary Car ID to the target material vehicle; based on the temporary Car ID of the target material vehicle, track the location information of the target material vehicle at different transportation times through the DeepSort strategy, and output a location tracking sequence; determine the location tracking sequence as the tracking result of the target material vehicle.

[0087] S4, when the UWB signal transmitted by the target material vehicle to the base station is detected, the current detection time corresponding to the UWB signal is obtained; the base stations that can be reached by the UWB signal detected at the current detection time are determined as candidate base stations to obtain several candidate base stations; based on the arrival time of the UWB signal at each of the candidate base stations, a reference base station, a first quasi-base station, a second quasi-base station and a third quasi-base station are selected from the several candidate base stations; a first time difference between the UWB signal arriving at the reference base station and the first quasi-base station, a second time difference between the UWB signal arriving at the reference base station and the second quasi-base station, and a third time difference between the UWB signal arriving at the reference base station and the third quasi-base station are determined; based on the location information of the reference base station, the location information of the first quasi-base station, the location information of the second quasi-base station, the location information of the third quasi-base station, the first time difference, the second time difference, the third time difference and the speed of light, the positioning position corresponding to the target material vehicle at the current detection time is determined; based on the positioning position corresponding to each of the current detection times, the position sequence of the target material vehicle at different detection times is determined.

[0088] S5, for any current detection moment among different detection moments: obtain the positioning position of the target vehicle at the current detection moment from the position sequence; select the target vehicle tracking image corresponding to the current detection moment from the tracking result of the target vehicle; based on the camera parameters of the logistics video sequence, convert the target vehicle tracking image from pixel space to physical space, and generate the tracking position of the target vehicle at the current detection moment.

[0089] Based on the positioning position and tracking position of the target vehicle, the position coordinates of the target vehicle are matched; if the matching result indicates that the position coordinates of the positioning position and the tracking position of the target vehicle match, the ID of the target vehicle is obtained, and the first weight corresponding to the positioning position of the target vehicle and the second weight corresponding to the tracking position of the target vehicle are determined; wherein the first weight is greater than the second weight; based on the first weight and the second weight, corresponding weights are applied to the positioning position and the tracking position, and weighted processing is performed to output the observed position of the target vehicle at the current detection moment.

[0090] Obtain the real position of the target vehicle at the previous detection moment before the current detection moment and adjacent to the current detection moment; based on the Kalman filtering technology, predict the real position of the target vehicle at the current detection moment according to the observed position of the target vehicle at the current detection moment and the real position at the previous detection moment; determine the real position sequence of the target vehicle at different detection moments based on the real position corresponding to each current detection moment; determine the real speed sequence of the target vehicle based on the real position sequence of the target vehicle at different detection moments.

[0091] S6, establishing an association between the actual movement state of the target material truck and the virtual scene map, and visually displaying the actual movement state of the target material truck in the form of a digital twin to generate a visualization result; wherein the virtual scene map is used to indicate map information of a virtual scene constructed based on the specific transportation scene.

[0092] This embodiment combines the YOLO-v8n and DeepSort algorithms with UWB technology to achieve accurate tracking, positioning, and management of materials by improving the accuracy and reliability of the target material vehicle positioning. It is particularly suitable for tracking and managing targets in dynamic scenarios where high positioning accuracy is required.

[0093] The innovation of this invention lies in the combination of material traceability, positioning and optimization management. The material barcode custom coding realizes the individual identification of the material, and then realizes the real-time tracking and positioning of the material in the logistics link. The virtual model of the logistics network is established through digital twin technology, so that the logistics process can be dynamically simulated, predicted and optimized, thereby improving the intelligence level and efficiency of logistics management. This comprehensive application creates a highly intelligent and efficient logistics management system with high practicality.

[0094] like Figure 4 FIG. 1 is a schematic diagram of the structure of a logistics material traceability management device provided by an embodiment of the present invention.

[0095] A logistics material traceability management device, the device 400 includes: a detection module 401, which is used to detect a material truck based on a logistics video sequence to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate the video data corresponding to the material transported by the material truck at different transportation times in a specific transportation scenario; the specific transportation scenario includes several base stations; a tracking module 402, which is used to track the position information of the target material truck at different transportation times based on the target material truck detection frame, and output the tracking result; a determination module 403, which is used to locate the target material truck based on the signal data and using the several base stations when the signal data between the target material truck and the base station is detected, and output the position sequence of the target material truck at different detection times; a calibration module 404, which is used to calibrate the position sequence based on the tracking result of the target material truck, and output the real movement state of the target material truck.

[0096] In a preferred implementation of this embodiment, the device also includes: a visualization display module, which is used to establish an association between the actual movement state of the target material truck and the virtual scene map, and visualize the actual movement state of the target material truck in the form of a digital twin to generate a visualization result; wherein the virtual scene map is used to indicate map information of a virtual scene constructed based on the specific transportation scene.

[0097] In a preferred implementation manner of this embodiment, the determination module includes: an acquisition unit, which is used to acquire the current detection time corresponding to the UWB signal when the UWB signal transmitted by the target material vehicle to the base station is detected; a first determination unit, which is used to determine the base station that can be reached by the UWB signal detected at the current detection time as a candidate base station, and obtain several candidate base stations; a selection unit, which is used to select a reference base station, a first quasi base station, a second quasi base station and a third quasi base station from the several candidate base stations based on the arrival time of the UWB signal at each of the candidate base stations; a second determination unit, which is used to determine the first time difference between the arrival of the UWB signal at the reference base station and the first quasi base station, The second time difference between the arrival of the UWB signal at the reference base station and the second quasi-base station, and the third time difference between the arrival of the UWB signal at the reference base station and the third quasi-base station; a third determination unit, used to determine the positioning position of the target material vehicle corresponding to the current detection moment based on the position information of the reference base station, the position information of the first quasi-base station, the position information of the second quasi-base station, the position information of the third quasi-base station, the first time difference, the second time difference, the third time difference and the speed of light; a fourth determination unit, used to determine the position sequence of the target material vehicle at different detection moments based on the positioning position corresponding to each current detection moment.

[0098] In a preferred implementation manner of this embodiment, the calibration module includes: a calibration unit, which is used for: for any current detection moment among different detection moments: obtaining the positioning position of the target material vehicle corresponding to the current detection moment from the position sequence; selecting the tracking position corresponding to the current detection moment from the tracking result of the target material vehicle; matching and fusing the tracking position and the positioning position, and outputting the observed position of the target material vehicle corresponding to the current detection moment; obtaining the real position of the target material vehicle at the previous detection moment before the current detection moment and adjacent to the current detection moment; predicting the real position of the target material vehicle at the current detection moment based on the observed position of the target material vehicle at the current detection moment and the real position at the previous detection moment; a first determination unit, which is used to determine the real position sequence corresponding to the target material vehicle at different detection moments based on the real position corresponding to each current detection moment; and a second determination unit, which is used to determine the real speed sequence of the target material vehicle based on the real position sequence corresponding to the target material vehicle at different detection moments.

[0099] In a preferred implementation manner of this embodiment, the calibration unit includes: a position coordinate matching subunit, which is used to perform position coordinate matching on the target trolley based on the positioning position and tracking position of the target trolley; a determination subunit, which is used to obtain the ID identification of the target trolley if the matching result indicates that the position coordinates of the positioning position and the tracking position of the target trolley match, and determine the first weight corresponding to the positioning position of the target trolley and the second weight corresponding to the tracking position of the target trolley; wherein the first weight is greater than the second weight; a weighted processing subunit, which is used to perform weighted processing on the positioning position and the tracking position after applying corresponding weights based on the first weight and the second weight, and output the observed position of the target trolley at the current detection moment.

[0100] In a preferred implementation manner of this embodiment, the calibration unit also includes: a selection subunit, used to select a target material vehicle tracking image corresponding to the current detection moment from the tracking results of the target material vehicle; a generation subunit, used to convert the target material vehicle tracking image from pixel space to physical space based on the camera parameters of the logistics video sequence, and generate a tracking position of the target material vehicle corresponding to the current detection moment.

[0101] In a preferred implementation manner of this embodiment, the tracking module includes: an ID assigning unit, used to assign a temporary Car ID to the target vehicle based on the detection frame of the target vehicle; a tracking unit, used to track the location information of the target vehicle at different transportation times based on the temporary Car ID of the target vehicle through the DeepSort strategy, and output a location tracking sequence; a determination unit, used to determine the position tracking sequence as the tracking result of the target vehicle.

[0102] In a preferred implementation of this embodiment, the device also includes: a training sample module, which is used to use different models of material trucks as training samples; a data enhancement processing module, which is used to perform data enhancement processing on each of the training samples to obtain a training sample data set; a model training module, which is used to perform model training on the training sample data set based on a target detection algorithm to generate a target detection model; a material truck detection module, which is used to perform material truck detection on a logistics video sequence based on the target detection model to obtain a target material truck detection frame.

[0103] In a preferred implementation manner of this embodiment, the device also includes: a first generating module, used to encode the material based on material information and material batch, and generate a unique material identifier; a second generating module, used to generate a unique identifier for the material cart based on the parameter information of the material cart; a setting module, used to affix a UWB tag to the material cart, and the UWB tag is provided with an ID identifier; the UWB tag on the material cart and the base station are located within the same height range; a mapping creation module, used to establish a mapping relationship between the unique identifier of the material cart, the unique identifier of the material and the ID identifier, and generate a binding result.

[0104] The above device can execute the logistics material traceability management method provided by an embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the logistics material traceability management method. For technical details not described in detail in this embodiment, please refer to the logistics material traceability management method provided by an embodiment of the present invention.

[0105] The present invention also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the logistics material traceability management method described in the present invention.

[0106] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0107] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0108] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to the following embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0109] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0110] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0111] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0112] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0113] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0114] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

[0115] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0116] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0117] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A logistics material traceability management method, characterized in that: include: Cart detection is performed based on the logistics video sequence to obtain a target car detection frame; wherein the logistics video sequence is used to indicate the video data corresponding to the material transported by the car at different transport times in a specific transportation scenario; the specific transportation scenario includes a number of base stations; Based on the detection frame of the target vehicle, a temporary Car ID is assigned to the target vehicle; based on the temporary Car ID of the target vehicle, the position information of the target vehicle at different transportation times is tracked by using the DeepSort strategy, and a position tracking sequence is output; the position tracking sequence is determined as the tracking result of the target vehicle; When a UWB signal transmitted by the target material vehicle to the base station is detected, the current detection time corresponding to the UWB signal is obtained; the base stations that can be reached by the UWB signal detected at the current detection time are determined as candidate base stations to obtain several candidate base stations; based on the arrival time of the UWB signal at each of the candidate base stations, a reference base station, a first quasi base station, a second quasi base station and a third quasi base station are selected from the several candidate base stations; a first time difference between the UWB signal arriving at the reference base station and the first quasi base station, a second time difference between the UWB signal arriving at the reference base station and the second quasi base station, and a third time difference between the UWB signal arriving at the reference base station and the third quasi base station are determined; based on the location information of the reference base station, the location information of the first quasi base station, the location information of the second quasi base station, the location information of the third quasi base station, the first time difference, the second time difference, the third time difference and the speed of light, the positioning position of the target material vehicle corresponding to the current detection time is determined; based on the positioning position corresponding to each of the current detection times, the position sequence of the target material vehicle at different detection times is determined; For any current detection moment among different detection moments: obtain the positioning position of the target vehicle at the current detection moment from the position sequence; select the tracking position corresponding to the current detection moment from the tracking result of the target vehicle; based on the positioning position and tracking position of the target vehicle, perform position coordinate matching for the target vehicle; if the matching result indicates that the positioning position and tracking position of the target vehicle match, obtain the ID of the target vehicle, and determine the first weight corresponding to the positioning position of the target vehicle and the second weight corresponding to the tracking position of the target vehicle; wherein the first weight is greater than the second weight; based on the first weight and the second weight, apply corresponding weights to the positioning position and the tracking position, perform weighted processing, and output the observed position of the target vehicle at the current detection moment. Position; obtain the real position of the target material vehicle at the previous detection moment before the current detection moment and adjacent to the current detection moment; predict the real position of the target material vehicle at the current detection moment based on the observed position of the target material vehicle at the current detection moment and the real position at the previous detection moment; determine the real position sequence of the target material vehicle at different detection moments based on the real position corresponding to each current detection moment; determine the real speed sequence of the target material vehicle based on the real position sequence corresponding to different detection moments; wherein a UWB tag is attached to the material vehicle, and an ID mark is set on the UWB tag; the UWB tag on the material vehicle and the base station are located within the same height range; establish a mapping relationship between the material vehicle unique identifier, the material unique identifier and the ID identifier, and generate a binding result.

2. The method according to claim 1, characterized in that Also includes: An association is established between the actual motion state of the target material truck and the virtual scene map, and the actual motion state of the target material truck is visualized in the form of a digital twin to generate a visualization result; wherein the virtual scene map is used to indicate map information of a virtual scene constructed based on the specific transportation scene.

3. The method according to claim 1, characterized in that The step of selecting a tracking position corresponding to the current detection time from the tracking result of the target vehicle comprises: Selecting a target material vehicle tracking image corresponding to the current detection moment from the tracking results of the target material vehicle; Based on the camera parameters for collecting the logistics video sequence, the target vehicle tracking image is converted from pixel space to physical space, and the tracking position of the target vehicle corresponding to the current detection moment is generated.

4. The method according to claim 1, characterized in that: Also includes; Use different types of material trucks as training samples; Performing data enhancement processing on each of the training samples to obtain a training sample data set; Performing model training on the training sample data set based on a target detection algorithm to generate a target detection model; Based on the target detection model, the material truck is detected in the logistics video sequence to obtain the target material truck detection frame.

5. The method according to claim 1, characterized in that Also includes: Based on the material information and material batch, the material is encoded to generate a unique material identifier; Based on the parameter information of the material truck, a unique identification of the material truck is generated.

6. A logistics material traceability management device, characterized in that: include: A detection module is used to detect a material truck based on a logistics video sequence to obtain a target material truck detection frame; wherein the logistics video sequence is used to indicate the video data corresponding to the material truck transporting materials at different transportation times in a specific transportation scenario; the specific transportation scenario includes a number of base stations; A tracking module is used to assign a temporary Car ID to the target vehicle based on the detection frame of the target vehicle; based on the temporary Car ID of the target vehicle, track the location information of the target vehicle at different transportation times through the DeepSort strategy, and output a location tracking sequence; determine the location tracking sequence as the tracking result of the target vehicle; A determination module, for, when detecting a UWB signal transmitted by the target material vehicle to the base station, obtaining a current detection time corresponding to the UWB signal; determining the base station that can be reached by the UWB signal detected at the current detection time as a candidate base station, and obtaining a plurality of candidate base stations; selecting a reference base station, a first quasi base station, a second quasi base station, and a third quasi base station from the plurality of candidate base stations based on the arrival time of the UWB signal at each of the candidate base stations; determining a first time difference between the UWB signal arriving at the reference base station and the first quasi base station, a second time difference between the UWB signal arriving at the reference base station and the second quasi base station, and a third time difference between the UWB signal arriving at the reference base station and the third quasi base station; determining a positioning position corresponding to the target material vehicle at the current detection time based on the position information of the reference base station, the position information of the first quasi base station, the position information of the second quasi base station, the position information of the third quasi base station, the first time difference, the second time difference, the third time difference, and the speed of light; determining a position sequence of the target material vehicle at different detection times based on the positioning position corresponding to each of the current detection times; A calibration module is used for: for any current detection moment among different detection moments: obtaining the positioning position of the target vehicle at the current detection moment from the position sequence; matching the position coordinates of the target vehicle based on the positioning position and tracking position of the target vehicle; if the matching result indicates that the position coordinates of the positioning position and the tracking position of the target vehicle match, obtaining the ID of the target vehicle, and determining a first weight corresponding to the positioning position of the target vehicle and a second weight corresponding to the tracking position of the target vehicle; wherein the first weight is greater than the second weight; based on the first weight and the second weight, weighted processing is performed after applying corresponding weights to the positioning position and the tracking position, and outputting the weight of the target vehicle at the current detection moment. The observed position at a moment; obtain the real position of the target material vehicle at the previous detection moment before the current detection moment and adjacent to the current detection moment; predict the real position of the target material vehicle at the current detection moment based on the observed position of the target material vehicle at the current detection moment and the real position at the previous detection moment; determine the real position sequence of the target material vehicle at different detection moments based on the real position corresponding to each current detection moment; determine the real speed sequence of the target material vehicle based on the real position sequence corresponding to different detection moments; wherein a UWB tag is affixed to the material vehicle, and an ID mark is set on the UWB tag; the UWB tag on the material vehicle and the base station are located within the same height range; establish a mapping relationship between the material vehicle unique identifier, the material unique identifier and the ID identifier, and generate a binding result.

Images