Whole-course logistics tracing method and system based on head-mounted device

Abstract

The invention provides a whole-course logistics tracing method and system based on head-mounted equipment, and belongs to the technical field of human-computer interaction. According to the method, the sight behavior of a person wearing the head-mounted equipment is perceived in real time by determining the accurate coordinate of a fixation point; according to the target identification information and the geographic position coordinate data, a superposition display instruction sequence and a semitransparent lamination area are generated, and visual navigation guidance is realized on the premise that the attention of a person wearing the head-mounted equipment is not dispersed; by generating the gazing intention confirmation signal, accurate recognition of the operation intention is ensured, and additional operation is not needed; and finally, a fixation record data set is determined according to the operation intention information and the identity label, and a complete logistics traceability chain is formed in combination with a historical logistics operation chain, so that the traceability record can accurately reflect the circulation of logistics nodes, and the continuity, credibility and integrity of the logistics traceability chain are ensured.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction technology, specifically to a method and system for end-to-end logistics traceability based on head-mounted devices. Background Technology

[0002] Currently, logistics traceability is a key area for ensuring supply chain security and achieving end-to-end traceability of goods. Its importance lies in its ability to promptly identify problematic links, improve operational efficiency, and meet stringent compliance requirements. In modern warehouse and distribution environments, end-to-end logistics traceability relies on the accurate recording of the operational intent, time, and location of each operational node to form a reliable traceability chain. Current logistics traceability methods based on head-mounted devices mostly use manual touch control, voice commands, or gesture recognition to complete information entry and task confirmation. As a result, operators need to frequently interrupt direct handling of goods when sorting or loading / unloading, and instead trigger scanning, confirmation, and recording by touching the screen, issuing voice commands, or making specific gestures. This causes operators' attention to repeatedly switch between goods and equipment, easily leading to operational delays or omissions. Especially in complex warehouses with dense goods and confined spaces, this distraction further amplifies the risk of recording errors.

[0003] The information provided in the background section of this application is only for enhancing the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] In view of this, this application provides a method and system for end-to-end logistics tracking based on head-mounted devices, which can process logistics information without distracting attention.

[0005] In a first aspect, embodiments of this application provide a method for end-to-end logistics traceability based on a head-mounted device. The method includes: real-time acquisition of biometric interaction data and geographic location coordinate data of a person wearing the head-mounted device; the biometric interaction data includes pupil center pixel coordinates, corneal reflector pixel coordinates, pupil diameter variation range, eye movement trajectory, and head posture data; determining precise coordinates of the gaze point based on the biometric interaction data and the geographic location coordinate data; determining whether the precise coordinates of the gaze point are located within a target recognition area; if determined to be within the target recognition area, acquiring an image of the target recognition area and determining target identification information based on the target recognition area image; and determining the head-mounted device wearer's location based on the target identification information and the geographic location coordinate data. The system generates a navigation instruction sequence for personnel to reach a target location; determines an overlay display instruction sequence based on the geographic location coordinates and the navigation instruction sequence, and generates a semi-transparent overlay area based on the overlay display instruction sequence; determines whether the continuous gaze time of the gaze point's precise coordinates within the semi-transparent overlay area exceeds a preset time threshold within a preset time period; if it exceeds the preset time threshold, generates a gaze intent confirmation signal, and obtains the operation intent information corresponding to the gaze intent confirmation signal and the identity identifier corresponding to the person wearing the head-mounted device; determines a gaze record dataset based on the operation intent information and the identity identifier, obtains a historical logistics operation chain, and determines a complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain.

[0006] Secondly, embodiments of this application provide a full-process logistics traceability system based on a head-mounted device. This system includes: an acquisition module, a first determination module, a first judgment module, a second determination module, a third determination module, a second judgment module, and a fourth determination module. The acquisition module is used to acquire in real-time biometric interaction data and geographic location coordinate data of the person wearing the head-mounted device. The biometric interaction data includes pupil center pixel coordinates, corneal reflection point pixel coordinates, pupil diameter variation range, eye movement trajectory, and head posture data. The first determination module is used to determine the precise coordinates of the gaze point based on the biometric interaction data and geographic location coordinate data. The first judgment module is used to determine whether the precise coordinates of the gaze point are located within the target recognition area. If it is determined to be within the target recognition area, an image of the target recognition area is acquired, and target identification information is determined based on the target recognition area image. The second determination module is used to determine the navigation route from the person wearing the head-mounted device to the target location based on the target identification information and geographic location coordinate data. The system comprises four modules: a command sequence, a third determining module (used to determine the overlay display command sequence based on geographic location coordinates and navigation command sequence, and to generate a semi-transparent overlay area based on the overlay display command sequence), a second judging module (used to determine whether the continuous gaze time within the semi-transparent overlay area at the precise coordinates of the gaze point exceeds a preset time threshold; if the determination exceeds the preset time threshold, a gaze intent confirmation signal is generated, and the operation intent information corresponding to the gaze intent confirmation signal and the identity identifier corresponding to the person wearing the head-mounted device are obtained respectively), and a fourth determining module (used to determine the gaze record dataset based on the operation intent information and identity identifier, obtain the historical logistics operation chain, and determine the complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain).

[0007] This application provides a method and system for end-to-end logistics traceability based on a head-mounted device. By determining the precise coordinates of the gaze point, real-time perception of the gaze behavior of the person wearing the head-mounted device is achieved. A navigation instruction sequence is determined based on target identification information and geographic location coordinate data, and an overlay display instruction sequence and a semi-transparent layered area are generated based on the geographic location coordinate data and navigation instruction sequence, achieving intuitive navigation guidance without distracting the person wearing the head-mounted device. A gaze intent confirmation signal is generated by determining whether the continuous gaze time within the semi-transparent layered area exceeds a preset threshold, ensuring accurate recognition of the operation intent without additional operation. Finally, a gaze record dataset is determined based on the operation intent information and identity identifier, and combined with historical logistics operation chains to form a complete logistics traceability chain. This solves the problems of operation delay, recording error, and node misalignment in existing methods, ensuring that the traceability records accurately reflect the flow of logistics nodes, guaranteeing the continuity, reliability, and integrity of the logistics traceability chain, and significantly improving the efficiency and accuracy of operations such as goods sorting and loading / unloading, meeting supply chain security and compliance requirements. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating an exemplary embodiment of the present application of a method for end-to-end logistics traceability based on a head-mounted device.

[0010] Figure 2 This is a flowchart illustrating a head-mounted device-based end-to-end logistics traceability method provided in another exemplary embodiment of this application.

[0011] Figure 3 This is a flowchart illustrating a method for end-to-end logistics traceability based on a head-mounted device, provided in another exemplary embodiment of this application.

[0012] Figure 4 This is a flowchart illustrating a method for end-to-end logistics traceability based on a head-mounted device, provided in another exemplary embodiment of this application.

[0013] Figure 5 This is a flowchart illustrating a method for end-to-end logistics traceability based on a head-mounted device, provided in another exemplary embodiment of this application.

[0014] Figure 6 This is a flowchart illustrating a method for end-to-end logistics traceability based on a head-mounted device, provided in another exemplary embodiment of this application.

[0015] Figure 7 This is a flowchart illustrating a method for end-to-end logistics traceability based on a head-mounted device, provided in another exemplary embodiment of this application.

[0016] Figure 8 This is a flowchart illustrating a method for end-to-end logistics traceability based on a head-mounted device, provided in another exemplary embodiment of this application. Detailed Implementation

[0017] 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 examples set forth herein; rather, they are provided so that this application will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this application.

[0018] The terms “a,” “one,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended inclusion and that other elements / components / etc. may exist in addition to those listed. The terms “first” and “second” are used only as markers and are not a limitation on the number of objects.

[0019] Currently, logistics traceability is a key area for ensuring supply chain security and achieving end-to-end traceability of goods. Its importance lies in its ability to promptly identify problematic links, improve operational efficiency, and meet stringent compliance requirements. In modern warehouse and distribution environments, end-to-end logistics traceability relies on the accurate recording of the operational intent, time, and location of each operational node to form a reliable traceability chain. Using human-computer interaction technologies, such as head-mounted devices, logistics traceability methods often employ manual touch, voice commands, or gesture recognition for information entry and task confirmation. This necessitates operators frequently interrupting direct handling of goods during sorting or loading / unloading, resorting to touch screens, issuing voice commands, or making specific gestures to trigger scanning, confirmation, and recording. This causes operators' attention to repeatedly switch between goods and equipment, easily leading to operational delays or omissions, especially in complex warehouses with dense goods and confined spaces, where this distraction further amplifies the risk of recording errors.

[0020] For example, when an operator looks at a barcode or label, existing methods cannot immediately detect this gaze and automatically trigger the corresponding scanning and data entry. They can only associate the intent, time, and location data after the operator completes additional manual or verbal actions. This delay and disconnect means that the operation nodes recorded by the system often have a time lag between the actual gaze and processing moment, making it difficult for traceability records to accurately reflect the true logistics process sequence and responsibility attribution.

[0021] For example, in actual sorting scenarios, operators need to look at the cargo label to determine the destination, but at the same time they need to look away or free their hands to confirm the scan. This not only prolongs the processing time of a single item, but may also cause node record misalignment during peak periods, causing the destination information that should belong to the current item to be incorrectly associated with the next item, thereby undermining the continuity and reliability of the logistics traceability chain.

[0022] Therefore, how to capture operational intentions in real time by directly utilizing the operator's gaze behavior with the support of head-mounted devices, and complete information locking, input, and recording without distraction, has become a technical problem that needs to be solved in realizing a head-mounted device-based end-to-end logistics traceability method and system.

[0023] This application provides a method for end-to-end logistics traceability based on a head-mounted device, such as... Figure 1The illustrated method is a full-process logistics traceability method based on a head-mounted device. This method may include the following steps: Step S110: Real-time acquisition of biometric interaction data and geographic location coordinate data of the person wearing the head-mounted device. The biometric interaction data includes pupil center pixel coordinates, corneal reflection point pixel coordinates, pupil diameter variation range, eye movement trajectory, and head posture data. Step S120: Determine the precise coordinates of the gaze point based on biometric interaction data and geographic location coordinate data; Step S130: Determine whether the precise coordinates of the gaze point are within the target recognition area. If it is determined that the gaze point is within the target recognition area, acquire the target recognition area image and determine the target identification information based on the target recognition area image. Step S140: Determine the navigation instruction sequence for the person wearing the head-mounted device to reach the target location based on the target identification information and geographic location coordinate data; Step S150: Determine the overlay display instruction sequence based on the geographic location coordinate data and navigation instruction sequence, and generate a semi-transparent overlay area based on the overlay display instruction sequence; Step S160: Determine whether the continuous gaze time within the semi-transparent overlay area within the preset time limit exceeds the preset time threshold. If the gaze point's precise coordinates exceed the preset time threshold, generate a gaze intent confirmation signal and obtain the operation intent information corresponding to the gaze intent confirmation signal and the identity identifier corresponding to the person wearing the head-mounted device. Step S170: Determine the gaze record dataset based on the operation intent information and identity identifier, obtain the historical logistics operation chain, and determine the complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain.

[0024] According to the end-to-end logistics traceability method based on head-mounted devices provided in this application, this method can achieve real-time perception of the gaze behavior of people wearing head-mounted devices by determining the precise coordinates of the gaze point; it determines the navigation instruction sequence based on target identification information and geographic location coordinate data, and generates an overlay display instruction sequence and a semi-transparent layered area based on the geographic location coordinate data and navigation instruction sequence, achieving intuitive navigation guidance without distracting the attention of the person wearing the head-mounted device; it generates a gaze intent confirmation signal by judging whether the continuous gaze time of the precise coordinates of the gaze point in the semi-transparent layered area exceeds a preset threshold, ensuring accurate recognition of the operation intent without additional operation; finally, it determines the gaze record dataset based on the operation intent information and identity identification, and forms a complete logistics traceability chain by combining it with the historical logistics operation chain, solving the problems of operation delay, recording error, and node misalignment in existing methods, ensuring that the traceability record can accurately reflect the flow of logistics nodes, guaranteeing the continuity, credibility, and integrity of the logistics traceability chain, and significantly improving the efficiency and accuracy of operations such as cargo sorting and loading and unloading, meeting the requirements of supply chain security and compliance.

[0025] The following is a detailed description of each step of the end-to-end logistics traceability method based on head-mounted devices provided in the embodiments of this application: In one embodiment of this application, step S110 involves acquiring real-time biometric interaction data and geographic location coordinate data of the person wearing the head-mounted device. The biometric interaction data includes the pupil center pixel coordinates, corneal reflector pixel coordinates, pupil diameter variation range, eye movement trajectory, and head posture data. Specifically, the biometric interaction data is acquired by observing the eye state and head posture of the person wearing the head-mounted device. This data can be collected at a fixed frequency using dedicated sensors and cameras to ensure real-time performance and accuracy. The pupil center pixel coordinates can be obtained by capturing real-time eye images using the infrared camera built into the head-mounted device, and then locating the pupil center pixel position within the image frame using an image recognition algorithm. For example, in a certain image frame, the pupil center pixel coordinates might be (320, 240), and based on a 1920x1080 resolution image, the pixel coordinate range is adapted to the screen size. The corneal reflector pixel coordinates are obtained by illuminating the cornea with infrared light emitted from the infrared camera to form a reflective point. The pixel coordinates of this reflective point within the image frame are recorded synchronously to assist in calibrating the pupil center position and compensating for errors caused by head movement. For example, the corneal reflection point pixel coordinates, acquired synchronously with the aforementioned pupil center coordinates, are (322, 243). The range of pupil diameter variation can be obtained by measuring the pupil diameter value from continuously captured eye images by an infrared camera. This range can be from 2.0 to 8.0 mm, reflecting the attention level of the person wearing the head-mounted device. For example, when the person wearing the head-mounted device is focused on a cargo label, their pupil diameter remains stable at 3.0 mm; when switching operating scenes, their attention is diverted, and the pupil diameter increases to 6.0 mm. Eye movement trajectory can be formed based on the pupil center pixel coordinates and corneal reflection point pixel coordinates of consecutive frames, creating a trajectory vector of eye movement that records the direction and path of eye movement. For example, when the person wearing the head-mounted device moves their gaze from cargo label A to cargo label B, the resulting eye movement trajectory vector is (160, 120). This trajectory can be used to determine the continuity of gaze and target switching. Head posture data can be collected by the IMU (Inertial Measurement Unit) sensor built into the head-mounted device, recording attitude parameters such as pitch angle, yaw angle, and roll angle of the person wearing the device. For example, when a person wearing the head-mounted device looks down at goods, the pitch angle is -15 degrees; when turning to one side of the aisle, the yaw angle is 30 degrees.

[0026] Specifically, geographic coordinate data is used to accurately locate the actual spatial position of personnel wearing head-mounted devices in the work environment. This data can be obtained through a GPS (Global Navigation Satellite System) module or a SLAM (Simultaneous Localization and Mapping) algorithm to ensure that the coordinate accuracy meets the traceability requirements of logistics operations. For example, when personnel wearing head-mounted devices are working in the warehouse sorting area, the GPS module collects the latitude and longitude coordinates as 39.9042 degrees north latitude and 116.4074 degrees east longitude. After entering the warehouse's internal passageway, the SLAM algorithm calculates the 3D spatial coordinates as (10.5, 8.3, 1.2) meters, where the X-axis represents the length of the passageway, the Y-axis represents the width of the passageway, and the Z-axis represents the height.

[0027] In one embodiment of this application, step S120, which determines the precise coordinates of the gaze point based on biometric interaction data and geographic location coordinate data, further includes the following steps: Figure 2 As shown, the specific content is as follows: Step S210: Synchronize and align the biometric interaction data and geographic coordinate data in time to generate a synchronized interaction sequence; Step S220: Based on the synchronous interaction sequence, the gaze duration and gaze direction vector are determined using an interaction recognition algorithm; Step S230: Determine the precise coordinates of the gaze point based on the gaze duration and gaze direction vector.

[0028] Specifically, biometric interaction data collected by the built-in camera and IMU sensor of the head-mounted device can be aligned with geographic coordinate data collected by GPS / modules using a unified timestamp to reduce time errors and form a synchronized interaction sequence. Next, the relative vector between the pupil center and the corneal reflection point in the synchronized interaction sequence is calculated and mapped to an initial gaze direction vector. Then, a quadratic polynomial regression model is used to optimize the initial direction vector, compensating for head-mounted device calibration deviations, to obtain a precise gaze direction vector (θ is the horizontal deflection angle, φ is the vertical deflection angle). The gaze direction vectors of consecutive frames are sorted by timestamp to form a gaze direction vector sequence. A valid gaze is defined as a state where the angle change between two adjacent frames is less than 1.0 degree and the duration of this state exceeds 200 milliseconds. Timing begins from the first frame that satisfies the angle change < 1.0 degree, and the number of frames is accumulated for each subsequent frame that satisfies this condition. If a frame does not satisfy the condition (angle change ≥ 1.0 degree), timing is interrupted and restarted. The accumulated duration of this state is the gaze duration. By combining environmental images captured by the head-mounted device's camera with a 3D point cloud model of the working environment constructed using the SLAM algorithm, the fused gaze direction vector is used as a scene ray and its intersection with the 3D point cloud model is calculated. The coordinates of the intersection point are the three-dimensional coordinates of the gaze point in the real environment. At the same time, by combining synchronized geographic location coordinate data, the absolute spatial position of the gaze point is calibrated to ensure coordinate accuracy and generate precise coordinates of the gaze point.

[0029] For example, the head-mounted device collects biometric data at a frequency of 120Hz. A typical frame of data might include: timestamp 2023-10-15T14:30:25.000Z, pupil center (320, 240), corneal reflector (322, 243), and head posture (-15 degrees, 30 degrees, 0 degrees). Simultaneously, it collects geographic coordinates at a frequency of 1Hz, such as: timestamp 2023-10-15T14:30:25.000Z, coordinates (10.5, 8.3, 1.2) meters. After alignment via the NTP protocol, the single-frame structure of the generated synchronous interaction sequence is as follows: [Timestamp 2023-10-15T14:30:25.000Z, Pupil center (-0.2, 0.1) (normalized), Corneal reflector vector (0.005, 0.003), Head pose vector (-15, 30, 0), Geographic location (10.5, 8.3, 1.2)]. Interpolated frames are added at a 60Hz sampling rate to form a continuous synchronous interaction sequence. The synchronous interaction sequence is parsed, and the relative vector between the pupil center and the corneal reflector in a certain segment is obtained using the PCCR method as (0.02, 0.01). After optimization using a quadratic polynomial regression model, the output gaze direction vector is (θ = 30 degrees, φ = 15 degrees). Further analysis using the I-DT (Improved Dense Trajectories) algorithm revealed that the angle change of the direction vector over 30 consecutive frames (corresponding to 0.5 seconds, 60Hz sampling rate) was less than 0.8 degrees, meeting the valid gaze determination criteria. Therefore, the duration of this gaze was determined to be 0.5 seconds, the gaze direction vector to be (30 degrees, 15 degrees), and the synchronized geographic location coordinates to be (10.5, 8.3, 1.2) meters. After fusing the head pose data using Kalman filtering, the gaze direction vector offset was compensated to (30.1 degrees, 14.9 degrees). The gaze direction vector was then used as a scene ray and intersected with the 3D point cloud model of the warehouse constructed using SLAM, yielding an intersection point coordinate of (11.2, 9.5, 1.2) meters. After geographic location coordinate calibration, the final precise coordinates of the gaze point were determined to be (11.2, 9.5, 1.2) meters (accuracy up to 2.0 centimeters), which corresponds to the label location of a specific item in the warehouse.

[0030] In the above method, by accurately extracting the duration and direction vector of effective gaze, invalid saccades and effective gazes are successfully distinguished, avoiding misidentification of non-gaze behavior. Through Kalman filter fusion and 3D point cloud spatial mapping, the abstract vector parameters are transformed into the precise coordinates of the three-dimensional gaze point in the real working environment, solving the problems of untimely gaze behavior capture, inaccurate gaze direction judgment, and insufficient gaze point positioning accuracy in the existing technology. Personnel wearing the head-mounted device do not need to perform additional operations and will not be distracted from handling goods. In addition, through an efficient human-computer interaction mechanism, the linkage between gaze behavior and device response is realized.

[0031] In one embodiment of this application, in step S130, it is determined whether the precise coordinates of the gaze point are located within the target recognition area. If it is determined that the gaze point is located within the target recognition area, an image of the target recognition area is acquired. Specifically, the spatial range of the target recognition area can be predefined based on the work layout. By calculating the distance between the precise coordinates of the gaze point and the center of the target recognition area, it is determined whether the gaze point falls within the effective range, ensuring that subsequent operations are triggered only when the person wearing the head-mounted device actively gazes at the target area.

[0032] For example, the preset target recognition area is a spherical region containing the label of a certain layer of goods on a warehouse shelf, with its center coordinates at (15.2, 8.5, 1.3) meters and a preset threshold (radius) of 0.3 meters. The precise coordinates of the gaze point of the person wearing the head-mounted device are (15.3, 8.4, 1.3) meters. Using the Euclidean distance formula, the distance d between the precise coordinates of the gaze point and the center of the target recognition area is calculated to be 0.14 meters < 0.3 meters. Therefore, the precise coordinates of the gaze point are determined to be within the target recognition area. Then, the high-resolution camera built into the head-mounted device is activated, focusing on the spherical region centered at (15.2, 8.5, 1.3) meters, capturing 3 frames of raw images. For example, a clear image of the target recognition area showing the goods label (including QR code and part number) can be obtained.

[0033] In one embodiment of this application, step S130, determining the target identification information based on the target recognition region image, further includes the following steps: Figure 3 As shown, the specific content is as follows: Step S310: Based on the target recognition region image, determine the target bounding box using a target detection algorithm; Step S320: Determine the target image based on the target bounding box, and determine the text recognition result of the target image using an optical character recognition algorithm based on the target image; Step S330: Determine the target identification information based on the text recognition results.

[0034] Specifically, pre-trained deep learning object detection algorithms can be used to accurately locate and select target regions containing identification information (such as cargo labels, QR codes, and part number carriers) from pre-processed target recognition region images, eliminating background interference. The YOLOv5 deep learning model can be used to adapt to the recognition needs of various labels in logistics scenarios. By analyzing the texture, contour, and contrast features of pixels in the target recognition region image, target regions that conform to the label template (such as rectangular labels and QR code outlines) are identified, and the coordinates of the two-dimensional bounding box of this region (x1, y1, x2, y2) are output, where (x1, y1) are the pixel coordinates of the upper left corner of the bounding box, and (x2, y2) are the pixel coordinates of the lower right corner. The bounding box will closely fit the edge of the target label, avoiding the inclusion of unnecessary background. Simultaneously, the confidence score of the bounding box (the probability that the target is the identification information) is output. If the confidence score is ≥0.8, it is determined to be a valid bounding box; if the confidence score is <0.8, an image enhancement algorithm (such as contrast adaptive histogram equalization) is automatically called to reprocess the target recognition region image, and detection is performed again until a valid bounding box is obtained or recognition is determined to have failed. Based on the target bounding box, a target image containing only the identification information is cropped, and then the text content (such as part number, destination keywords, QR code decoded text) in the image is extracted by an Optical Character Recognition (OCR) algorithm, converting the image information into machine-readable text data. The text recognition results are structured and uniquely matched, and combined with a preset identification template library, target identification information is generated.

[0035] For example, the target recognition region image is a label image of a product on a warehouse shelf. Using the YOLOv5 algorithm, the rectangular label area containing the part number and QR code is identified. The output bounding box coordinates are (120, 80, 380, 220), with a confidence score of 0.93 ≥ 0.8, indicating a valid bounding box. This target bounding box accurately selects the entire label area and does not include background content such as shelves or other goods. The target recognition region image is cropped based on the bounding box coordinates (120, 80, 380, 220) to obtain a target image containing only the part label (size 260×140 pixels, no background interference). After binarization correction of this target image, the OCR algorithm recognizes the text on the label (P-2024) and the decoded text of the QR code (Destination: Packaging Area, Priority: 3). The output text recognition result is: {“Part Number”:“P-2024”,“Destination”:“Packaging Area”,“Priority”:“3”}. The text recognition results were structured and supplemented with a YOLOv5 detection confidence score of 0.93 and an OCR recognition confidence score of 0.91. After comparison with a pre-established identifier template library, "P-2024" had a 100% similarity to the part number template "P-based full-process logistics traceability method X" and "packaging area" had a 90% similarity to the destination template "XX area". Both met the threshold requirement of ≥80%. Finally, standardized target identifier information was generated: {"Unique Identifier ID":"P-2024","Business Attribute":{"Destination":"Packaging Area","Priority":3,"Destination Coordinates":null},"Identification Confidence":0.92,"Bounding Box Information":"(120,80,380,220)","Collection Timestamp":"2023-10-15T14:35:12.000Z"}.

[0036] In the above method, the YOLOv5 target detection algorithm is used to accurately select the identification area, crop the target image to remove background interference, and then the OCR algorithm is used to extract the text and organize it in a structured manner to finally generate standardized and highly reliable target identification information. The whole process is automated and does not require personnel to wear head-mounted devices to perform manual scanning, input or other additional operations. This solves the problems of operation delay, attention distraction and recording error caused by manual triggering recognition in the existing technology.

[0037] In one embodiment of this application, step S140, which determines the navigation instruction sequence for the person wearing the head-mounted device to reach the target location based on the target identification information and geographic location coordinate data, further includes the following steps: Figure 4 As shown, the specific content is as follows: Step S410: Determine the target location coordinates and target priority attributes based on the target identification information; Step S420: Based on geographic location coordinate data, target location coordinates, and target priority attributes, use the A* algorithm to determine the optimal set of path points from the person wearing the head-mounted device to the target location; Step S430: Determine the navigation instruction sequence based on the optimal path point set.

[0038] Specifically, logistics attribute fields, including the destination name and initial priority, can be directly extracted from the target identification information. These fields are the core search keywords for the logistics database query. Using SQL fuzzy queries, the destination name is matched against a pre-built logistics database. The database table contains logistics-related fields such as target ID, destination name, target location coordinates (X, Y, Z), target priority attribute, warehouse aisle width, and cargo transfer priority. The matching rule is a string similarity of ≥80%, ensuring unique identification of the logistics target. After a successful query, the precise target location coordinates and explicit target priority attributes (e.g., 1 for urgent delivery priority, 2 for regular sorting priority, 3 for low-priority transfer) are extracted as the core input parameters for logistics route calculation. Using the real-time geographic coordinates of personnel wearing head-mounted devices as the starting point of the logistics operation and the target location coordinates as the ending point, combined with the target priority attribute and the real-time status of the logistics warehouse aisles (e.g., sorting busyness, aisle congestion), an A* navigation algorithm is used to construct a logistics warehouse scene grid model. The optimal path that avoids congested aisles and adapts to logistics priorities is calculated and output as a set of path points to support efficient logistics operations. The discrete set of optimal waypoints is transformed into continuous, executable structured logistics navigation instructions. Each instruction includes the coordinates of the next waypoint and the direction offset, forming a parsable sequence format that is adapted to head-mounted displays and the movement understanding of personnel wearing head-mounted displays, ensuring that navigation guidance is accurate and fits the logistics scenario.

[0039] For example, the target identification information includes: unique identifier ID: W-202405, logistics attributes: {destination: sorting area A, priority: 2}. By retrieving the logistics business database through an SQL query, the record corresponding to sorting area A is matched as follows: logistics target ID=LD-012, target location coordinates are (20.0, 15.0, 1.3) meters, target priority attribute=2 (regular sorting priority). The string similarity calculation shows a matching degree of 92%≥80%, thus determining the target location coordinates and target priority attribute. At this time, the real-time geographical coordinates of the person wearing the head-mounted device are (3.0, 2.0, 1.3) meters. The system constructs a 40x40 logistics warehouse grid map, sets the movement cost of the busy sorting aisle (15-20, 10-15) to 2.5, configures the A* algorithm heuristic function, and converges after iterating through the queue for about 280 nodes. The system obtains the optimal set of path points with a total path length of about 22.0 units and containing 20 path points, which are (3.0, 2.0), (4.0, 2.0), (5.0, 3.0), ..., (20.0, 15.0) (the Z-axis coordinates are all 1.3 meters). Based on this optimal set of waypoints, 19 logistics navigation instructions are generated sequentially from adjacent waypoints and integrated into a JSON format navigation instruction sequence: [{"move_to": (4.0,2.0,1.3), "offset": (1.0,0.0,0.0)}, {"move_to": (5.0,3.0,1.3), "offset": (1.0,1.0,0.0)}, …, {"move_to": (20.0,15.0,1.3), "offset": (1.0,0.5,0.0)}]. Each instruction specifies the next moving coordinates and directional offset for the personnel wearing the head-mounted device in the logistics operation.

[0040] The above method solves the problems of low efficiency and large errors caused by manually inputting the destination in logistics scenarios by obtaining the target location coordinates and target priority attributes. By using the A* algorithm to integrate geographic location coordinate data, logistics target parameters and real-time warehouse channel status, a grid map adapted to the logistics warehouse is constructed. The optimal set of path points that avoids congested channels and takes into account logistics priorities is calculated, ensuring the scientific and efficient nature of the navigation path and adapting to the actual needs of logistics operations. Finally, the path points are transformed into a structured and executable sequence of navigation instructions, which associates the personnel location with the target location and realizes human-computer interactive path planning.

[0041] In one embodiment of this application, step S150, which determines the overlay display instruction sequence based on geographic location coordinate data and navigation instruction sequence, further includes the following steps: Figure 5 As shown, the specific content is as follows: Step S510: Synchronize and align the geographic location coordinate data with the navigation instruction sequence using timestamps, and determine whether the deviation between the aligned geographic location coordinate data and the aligned navigation instruction sequence exceeds a preset deviation threshold. Step S520: If the deviation exceeds the preset threshold, the A* algorithm is used again to optimize the optimal path point set. Step S530: If it is determined that the preset deviation threshold is not exceeded, the aligned geographic location coordinate data and the aligned navigation command sequence are fused to determine the superimposed display command sequence.

[0042] Specifically, a time synchronization protocol is used to uniformly calibrate the timestamps of the geographic location coordinates data collected by the head-mounted device's sensors with the navigation command sequence, ensuring a one-to-one correspondence between geographic location coordinates and corresponding navigation path points at the same timestamp. For each set of aligned data (geographic location coordinates and navigation path point coordinates at the same timestamp), the Euclidean distance formula is used to calculate the deviation between the real-time geographic location coordinates and the coordinates of the corresponding path point in the navigation command sequence. When the person wearing the head-mounted device deviates from the navigation route (deviation exceeding the threshold), the A* algorithm is invoked again based on the current real-time geographic location coordinates, the original target location coordinates, and the target priority attribute to avoid the deviation area and potential congestion points, generating a new set of optimal path points to ensure that the navigation guidance always closely matches the actual location. When the person wearing the head-mounted device moves along the navigation route (deviation not exceeding the threshold), the aligned geographic location coordinate data is deeply integrated with the navigation command sequence, supplementing visualization parameters to generate an overlay display command sequence that can be directly rendered by the head-mounted device, ensuring intuitive and accurate guidance.

[0043] For example, in a navigation instruction sequence, the pathpoint coordinates corresponding to the timestamp `2023-10-15T14:30:25.000Z` are (5.0, 5.0, 1.2) meters. After aligning with the real-time geographic coordinates of the same timestamp via a time synchronization protocol, if the real-time geographic coordinates are (5.2, 5.3, 1.2) meters, the deviation calculated using the Euclidean distance formula is approximately 0.36 meters, exceeding the preset deviation threshold of 0.3 meters. In this case, the starting point is updated to the real-time geographic coordinates, while the target location coordinates remain (15.0, 10.0, 1.2) meters, and the target priority attribute remains at level 3. The logistics warehouse grid map is updated, and the movement cost of the surrounding channels in the deviation area is set to 1.5. The A* algorithm is called again and iterates for approximately 150 nodes before converging, generating a new optimal pathpoint set containing (5.2, 5.3), (6.0, 5.5), ..., (15.0, 10.0) (all Z-axis coordinates are 1.2 meters). If the aligned real-time geographic location coordinates are (5.1, 5.1, 1.2) meters, and the calculated deviation is approximately 0.14 meters, which does not exceed the preset deviation threshold, then the real-time geographic location coordinates are merged with the corresponding navigation path points and integrated into a JSON format overlay display instruction sequence, providing direct support for head-mounted device rendering.

[0044] In one embodiment of this application, step S150, generating a semi-transparent overlay region according to the overlay display instruction sequence, further includes the following steps: Figure 6 As shown, the specific content is as follows: Step S610: Determine the visualization area parameters according to the overlay display instruction sequence. The visualization area parameters include display positioning parameters, display direction parameters, and display style parameters. Step S620: Based on the visualization region parameters, use an augmented reality algorithm to generate a semi-transparent overlay region.

[0045] Specifically, the structured overlay display instruction sequence can be transformed into a semi-transparent overlay area that is intuitive and does not interfere with the operation within the field of vision of the person wearing the head-mounted device. By clarifying the visualization parameters and using augmented reality algorithms, the effect of overlaying graphic guidance with the actual scene can be achieved, matching the logistics operation scenario and ensuring that the person wearing the head-mounted device can intuitively obtain navigation information without leaving the operation environment.

[0046] For example, the visualization area parameters are as follows: The display positioning parameters are: 2D mapping coordinates of the center of the head-mounted device screen (960, 540), corresponding to 3D coordinates (6.0, 6.0, 1.2). The display direction parameters are: horizontally upward to the right, pointing at a 45-degree angle. The display style parameters are: 50% transparency, blue color, graphic length 8px (path spacing 1.3 meters), refresh rate 60Hz, and text moved to (6.0, 6.0, 1.2), with 10 meters remaining to reach the packaging area. Augmented reality algorithms are used to fuse a 1920x1080 resolution warehouse environment image captured by the built-in camera of the head-mounted device with the above parameters. A blue semi-transparent arrow (8px long, 50% transparency, pointing at 45 degrees) is rendered at the center of the screen (960, 540). At the same time, a 2px wide light gray line connects the current path point (5.1, 5.1, 1.2) with the target path point (6.0, 6.0, 1.2) to form a basic path trajectory. The preset task text is displayed below the arrow. The graphics and text are updated in real time at a refresh rate of 60Hz to ensure that the person wearing the head-mounted device can clearly perceive the navigation guidance when handling goods. In this way, the navigation information is naturally integrated with the person's field of vision through a human-computer interaction visualization method, which improves the intuitiveness and ease of use of the navigation guidance.

[0047] In one embodiment of this application, in step S160, it is determined whether the continuous gaze duration within the semi-transparent overlay area within a preset time exceeds a preset time threshold. If the determination exceeds the preset time threshold, a gaze intent confirmation signal is generated, and the operation intent information corresponding to the gaze intent confirmation signal and the identity identifier of the person wearing the head-mounted device are obtained respectively. Specifically, by monitoring the gaze behavior of the person wearing the head-mounted device in real time, it is possible to accurately determine whether they actively accept the navigation guidance in the semi-transparent overlay area. If the continuous gaze condition is met, a gaze intent confirmation signal is automatically generated and associated with the corresponding operation intent information and the person's identity identifier. The entire process requires no additional manual or voice operation and does not distract the person wearing the head-mounted device from the logistics operation.

[0048] It should be noted that the screen display area of ​​the semi-transparent overlay region can be 5% of the screen's center area. This area completely overlaps with the rendered graphics and text display area, and the pixel coordinate boundaries of this area are pre-stored as a detection standard. The head-mounted device's built-in eye-tracking camera captures eye movement trajectories at a 120Hz sampling rate, and combines this with a pupil positioning algorithm to calculate the precise coordinates of the real-time gaze point (with an error controlled within 0.5 degrees). Each frame of data is compared with the pixel boundaries of the semi-transparent overlay region to determine whether the gaze point falls within the region. Timing begins from the first frame where the gaze point is detected to be within the semi-transparent overlay region. In subsequent frames, if the gaze point remains within the region, the duration is continuously accumulated to determine the continuous gaze time. If the gaze point moves out of the region in a frame or a gaze interruption is detected (such as closing the eyes), the timer is reset to zero, and the counting restarts.

[0049] It should be noted that when the sustained gaze duration exceeds a preset time threshold, a gaze intent confirmation signal is generated. This signal includes information such as a timestamp and a gaze area association identifier. The triggering condition for generating the gaze intent confirmation signal is that two conditions must be met simultaneously: the sustained gaze duration is >3 seconds and the pupil diameter change is <0.2 mm. This avoids misjudgment (such as unintentionally scanning an area and causing the duration to exceed the threshold).

[0050] For example, the screen pixel range of the semi-transparent overlay area is (910-1010, 510-570), and the precise coordinates of the real-time gaze point of the person wearing the head-mounted device are calculated to be (980, 545). When the gaze point falls within the area, the continuous gaze time is accumulated starting at a sampling rate of 120Hz. For the next 240 frames (corresponding to 2 seconds), the gaze point does not move out of the area, and the pupil diameter remains stable at 3.1-3.2 mm (a change of 0.1 mm < 0.2 mm, meeting the attention verification requirements). After monitoring for another 60 frames (0.5 seconds), the total accumulated time reaches 3.5 seconds, exceeding the preset time threshold of 3 seconds. The system automatically generates a gaze intent confirmation signal in JSON format, and then extracts the operation intent information by querying and overlaying the instruction sequence: confirming to go to the packaging area (coordinates 15.0, 10.0, 1.2 meters) to perform the sorting and transfer task of part P-2023, priority level 3. At the same time, the identity identifier pre-stored on the head-mounted device and verified by biometrics is read: Operator ID: A123456, team: sorting group 3. Finally, the operation intent information and identity identifier are accurately bound together.

[0051] In one embodiment of this application, in step S170, a gaze recording dataset is determined based on the operation intent information and the identity identifier. Specifically, the operation intent information of the person wearing the head-mounted device can be deeply correlated with the identity identifier, and key data such as the time and location collected in real time can be integrated. Through standardized processing, verification, and structured encapsulation, a complete and traceable gaze recording dataset is generated. This provides core data support for the subsequent integration with historical logistics operation chains to build a complete traceability chain. The entire process is automated and requires no additional operation from the person wearing the head-mounted device.

[0052] For example, the operator's intention information while wearing the head-mounted device is: confirming to proceed to the packaging area (coordinates 15.0, 10.0, 1.2 meters) to perform the sorting and transfer task of part P-2023, priority level 3, identification: operator ID: A123456, team: sorting group 3. First, collect the associated core data: operation intention timestamp (2023-10-15T14:35:42.000Z), real-time geographic location coordinates (14.8, 9.9, 1.2 meters), gaze point screen pixel coordinates (980, 545), gaze duration 3.5 seconds, gaze intention confirmation signal strength 92%, pupil diameter variation range 3.1-3.2 mm. The data was then standardized, and the data integrity check code was calculated by concatenating the strings of all standardized fields using the SHA-256 hash algorithm, such as e4f2a9c7d1b6g8h3i5j0k9l2m7n4p1q8. Finally, the data was structured and encapsulated into a JSON-formatted gaze record dataset that includes dimensions of identity identification, operational intent, spatiotemporal data, gaze parameters, and verification.

[0053] In one embodiment of this application, after determining the gaze recording dataset based on the operation intent information and identity identifier in step S170, the following steps are further included: Figure 7 As shown, the specific content is as follows: Step S710: Obtain the preset checksum, gaze record timestamp, and gaze record location coordinates for each gaze record in the gaze record dataset; Step S720: Based on the gaze record timestamp and gaze record location coordinates, use a hash algorithm to determine the current checksum of each gaze record data; Step S730: Determine whether the current check code is the same as the preset check code. If they are not the same, mark the current gaze record data as abnormal data. Step S740: If the determination is the same, then determine whether the current gaze recording data and the gaze recording data adjacent to the current gaze recording data have temporal and positional consistency; Step S750: If it is determined that there is consistency in time and location, then mark the current gaze recording data as verified; if it is determined that there is no consistency in time and location, then mark the current gaze recording data as verified.

[0054] Specifically, dual verification logic can be performed on the generated gaze record dataset. By comparing check codes to prevent tampering and verifying continuity based on time and location consistency, real, complete, and logically coherent gaze record data can be selected. This provides reliable data support for the subsequent integration with historical logistics operation chains to build a complete traceability chain. The entire process is automated and requires no manual intervention.

[0055] It should be noted that checksum matching only proves that a single gaze record has not been tampered with. Further verification of the spatiotemporal logical coherence between this record and adjacent records is required to ensure that the record conforms to the actual scenario of logistics operations (e.g., reasonable personnel movement speed and operation time intervals) and avoid invalid records with spatiotemporal misalignment. Using the timestamp of the current gaze record data as a benchmark, the preceding gaze record with the immediately adjacent timestamp in the gaze record dataset is selected as the adjacent record (if it is the first record, this step is skipped, and the time-location consistency is directly determined). The timestamp difference between the current gaze record and the adjacent gaze record (e.g., current timestamp - adjacent timestamp) is calculated. If the timestamp difference is within the reasonable time interval range of logistics operations (preset to 10 seconds to 5 minutes, adapting to the time consumption of sorting, transfer, and other operations), then the time is determined to be consistent. Simultaneously, the Euclidean distance formula is used to calculate the movement distance of the position coordinates of the two gaze records, and the average movement speed is calculated in combination with the time difference. If the movement distance is within a reasonable range (e.g., ≤50 meters) and the average speed is ≤5 km / h (meeting the upper speed limit for personnel walking operations), then the location is determined to be consistent. Only when both of the above conditions are met can it be determined that there is consistency in time and location.

[0056] For example, the preset checksum of a gaze record extracted from the gaze record dataset is: e4f2a9c7d1b6g8h3i5j0k9l2m7n4p1q8, the gaze record timestamp of this gaze record is: 2023-10-15T14:35:42.000Z, and the gaze record location coordinates are: (14.8, 9.9, 1.2) meters. Simultaneously, the timestamp of its adjacent preceding gaze record is extracted as: 2023-10-15T14:35:12.000Z, and the location coordinates are (10.5, 8.3, 1.2) meters. The timestamp and location coordinates of the current record are concatenated into a string: 2023-10-15T14:35:42.000Z(14.8,9.9,1.2). The current checksum, e4f2a9c7d1b6g8h3i5j0k9l2m7n4p1q8, is calculated using the SHA-256 hash algorithm. This checksum is completely consistent with the preset checksum, thus the checksum is considered a match. The time difference between this record and its adjacent records is calculated to be 30 seconds (within a reasonable range of 10 seconds to 5 minutes). Using the Euclidean distance formula, the movement distance is calculated to be approximately 4.59 meters, the average movement speed is 0.55 km / h (≤5 km / h), and the angle between the movement direction and the navigation path direction is 30 degrees (≤45 degrees). Therefore, the time and location are considered consistent, and this gaze record is marked as verified. If the current checksum of another record is e4f2a9c7d1b6g8h3i5j0k9l2m7n4p1q9 (the last character is different), then the checksum is determined to be mismatched, and the watch record is marked as abnormal data.

[0057] In one embodiment of this application, step S170, which involves obtaining the historical logistics operation chain and determining the complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain, further includes the following steps: Figure 8 As shown, the specific content is as follows: Step S810: Perform multi-dimensional rule matching between the gaze record dataset and the historical logistics operation chain to determine the initial logistics traceability chain; Step S820: Determine whether the data sequence of the initial logistics traceability chain satisfies the data continuity of the entire process. If the data continuity of the entire process is satisfied, then the initial logistics traceability chain is regarded as the complete logistics traceability chain. Step S830: If it is determined that the continuity of data throughout the entire process is not met, the initial logistics traceability chain is marked as an abnormal traceability chain.

[0058] Specifically, matching rules can be established between the gaze record dataset and historical logistics operation chains. Through multi-dimensional cross-validation, correlated gaze records can be selected and spliced ​​together to form an initial logistics traceability chain, ensuring the relevance and accuracy of the correlated data. Next, the record order of the initial logistics traceability chain undergoes full-process data continuity verification to ensure that the time sequence, location movement, and task flow in the chain conform to the actual logic of logistics operations, without gaps or misalignments, thus guaranteeing the integrity and reliability of the traceability chain. If the initial logistics traceability chain fails to meet the full-process data continuity requirements in any dimension of time sequence, location movement, or task flow, it indicates that the chain has data gaps or misalignments and cannot reflect the actual logistics operation process. This chain is marked as an abnormal traceability chain to prevent invalid data from entering the traceability application.

[0059] It should be noted that the dimensions for judging the continuity of data throughout the entire process include temporal continuity, locational movement continuity, and task flow continuity. Temporal continuity means that the timestamps of all records in the initial logistics traceability chain are arranged in ascending order, and the difference between the timestamps of adjacent records is within a reasonable range (the preset time for connecting each logistics link is 5-30 minutes, adapting to the typical operation time of warehousing, temporary storage, sorting, and packaging), with no time reversals or excessively long intervals (exceeding 60 minutes). Locational movement continuity means that the average movement speed obtained by calculating the movement distance of adjacent records using Euclidean distance and combining it with the time difference is ≤5km / h (consistent with the walking speed of personnel), and the movement direction is consistent with the logistics operation flow (e.g., from the warehousing area → temporary storage area → packaging area), with no reverse or abrupt movement. Task flow continuity means that the task links in the initial logistics traceability chain must follow the preset standard logistics flow (e.g., warehousing → temporary storage → sorting → transfer → packaging → outbound), with no missing links, duplications, or logical inversions (e.g., packaging before warehousing).

[0060] For example, the validated gaze record dataset includes: target cargo ID=P-2023, operation intent timestamp=2023-10-15T14:35:42.000Z, real-time geographic coordinates=(14.8,9.9,1.2) meters, and operator ID=A123456. This dataset is matched against the record of cargo P-2023 in the historical logistics operation chain in four dimensions: cargo identification, timestamp, geographic location, and operator identity. Because the cargo identification is consistent, the gaze timestamp falls between the temporary storage and packaging stages, the geographic location deviation from the packaging area is 0.3 meters ≤ 1.0 meter, and the operator identity is consistent, the association is deemed successful. This gaze record (operation stage: sorting and transfer confirmation) is then inserted into the corresponding position, forming the initial logistics traceability chain: [warehousing → temporary storage → sorting and transfer confirmation → packaging]. The initial chain undergoes a full-process data continuity check. The timestamps are sequentially 14:00→14:20→14:35→14:45, with adjacent time differences all within the 5-30 minute range. The average speed of movement is ≤5km / h and the direction is towards the packaging area. The task steps follow the standard process of warehousing→temporary storage→sorting and transfer→packaging. If continuity is satisfied, this initial chain is considered a complete logistics traceability chain. If an initial logistics traceability chain is [warehousing→packaging→sorting and transfer confirmation→temporary storage], and there is a logical reversal of the task steps, or an adjacent record time difference of 90 minutes, or a positional jump causing an average speed of 13.4km / h>5km / h, then the full-process data continuity is not satisfied. This chain is marked as an abnormal traceability chain, the abnormality type is recorded, and an alarm is triggered.

[0061] This application also provides a full-process logistics traceability system based on a head-mounted device. This system may include an acquisition module, a first determination module, a first judgment module, a second determination module, a third determination module, a second judgment module, and a fourth determination module. The acquisition module is used to acquire in real-time biometric interaction data and geographic location coordinate data of the person wearing the head-mounted device. The biometric interaction data includes pupil center pixel coordinates, corneal reflection point pixel coordinates, pupil diameter variation range, eye movement trajectory, and head posture data. The first determination module is used to determine the precise coordinates of the gaze point based on the biometric interaction data and geographic location coordinate data. The first judgment module is used to determine whether the precise coordinates of the gaze point are located within the target recognition area. If it is determined to be within the target recognition area, an image of the target recognition area is acquired, and target identification information is determined based on the target recognition area image. The second determination module is used to determine the navigation route from the person wearing the head-mounted device to the target location based on the target identification information and geographic location coordinate data. The system comprises four modules: a command sequence, a third determining module (used to determine the overlay display command sequence based on geographic location coordinates and navigation command sequence, and to generate a semi-transparent overlay area based on the overlay display command sequence), a second judging module (used to determine whether the continuous gaze time within the semi-transparent overlay area at the precise coordinates of the gaze point exceeds a preset time threshold; if the determination exceeds the preset time threshold, a gaze intent confirmation signal is generated, and the operation intent information corresponding to the gaze intent confirmation signal and the identity identifier corresponding to the person wearing the head-mounted device are obtained respectively), and a fourth determining module (used to determine the gaze record dataset based on the operation intent information and identity identifier, obtain the historical logistics operation chain, and determine the complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain).

[0062] It should be noted that the embodiments of the end-to-end logistics traceability system based on head-mounted devices provided in this application can be used to execute the processing flow of the embodiment of the end-to-end logistics traceability method based on head-mounted devices in the above embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above method embodiments.

[0063] This application also provides an electronic device, which includes one or more processors and memory resources represented by a memory for storing instructions executable by the processor, such as application programs. The application programs stored in the memory may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor is configured to execute instructions to perform the aforementioned end-to-end logistics traceability method based on a head-mounted device.

[0064] The electronic device may also include a power supply component configured to perform power management of the electronic device, a wired or wireless network interface configured to connect the electronic device to a network, and an input / output (I / O) interface. The electronic device can be operated based on operating devices stored in memory, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0065] In one embodiment, a computer device, which may be a server, is also provided. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device stores data. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for end-to-end logistics traceability based on a head-mounted device.

[0066] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for end-to-end logistics traceability based on a head-mounted device. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0067] This application also provides a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor of the aforementioned electronic device, enables the aforementioned electronic device to execute a full-process logistics traceability method based on a head-mounted device.

[0068] This application may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0069] It should be noted that although the steps of the end-to-end logistics traceability method based on head-mounted devices in this application are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps, such as omitting certain steps, combining multiple steps into one step, and / or breaking down one step into multiple steps, should all be considered part of this application.

[0070] It should be understood that this application is not limited to the detailed structure and arrangement of the modules in the end-to-end logistics traceability system based on head-mounted devices proposed in this specification. This application can have other embodiments and can be implemented and executed in various ways. The foregoing variations and modifications fall within the scope of this application. It should be understood that the application and its definition in this specification extend to all alternative combinations of two or more individual features mentioned or apparent in the text and / or drawings. All these different combinations constitute multiple alternative aspects of this application. The embodiments described in this specification illustrate the best known mode for implementing this application and will enable those skilled in the art to utilize this application.

Claims

1. A method for end-to-end logistics traceability based on a head-mounted device, characterized in that, include: Real-time acquisition of biometric interaction data and geographic location coordinate data of people wearing head-mounted devices. The biometric interaction data includes pupil center pixel coordinates, corneal reflection point pixel coordinates, pupil diameter variation range, eye movement trajectory, and head posture data. The precise coordinates of the gaze point are determined based on the biometric interaction data and the geographic location coordinate data. Determine whether the precise coordinates of the gaze point are located within the target recognition area. If it is determined that the gaze point is located within the target recognition area, then acquire the target recognition area image and determine the target identification information based on the target recognition area image. The navigation instruction sequence for the person wearing the head-mounted device to reach the target location is determined based on the target identification information and the geographic location coordinate data; Based on the geographic location coordinate data and the navigation instruction sequence, a superimposed display instruction sequence is determined, and a semi-transparent overlay area is generated based on the superimposed display instruction sequence; Determine whether the continuous gaze time within the semi-transparent overlay area within a preset time exceeds a preset time threshold. If the determination exceeds the preset time threshold, generate a gaze intent confirmation signal and obtain the operation intent information corresponding to the gaze intent confirmation signal and the identity identifier corresponding to the person wearing the head-mounted device. Based on the operation intent information and the identity identifier, determine the gaze record dataset, obtain the historical logistics operation chain, and determine the complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain.

2. The end-to-end logistics traceability method based on head-mounted devices according to claim 1, characterized in that, Determining the precise coordinates of the gaze point based on the biometric interaction data and the geographic location coordinate data includes: The biometric interaction data and the geographic location coordinate data are synchronized and aligned in time to generate a synchronized interaction sequence; Based on the synchronous interaction sequence, an interaction recognition algorithm is used to determine the gaze duration and gaze direction vector; The precise coordinates of the gaze point are determined based on the gaze duration and the gaze direction vector.

3. The end-to-end logistics traceability method based on head-mounted devices according to claim 1, characterized in that, Determining target identification information based on the target recognition region image includes: Based on the target recognition region image, a target detection algorithm is used to determine the target bounding box; The target image is determined based on the target bounding box, and the text recognition result of the target image is determined based on the target image using an optical character recognition algorithm; The target identification information is determined based on the text recognition results.

4. The end-to-end logistics traceability method based on head-mounted devices according to claim 1, characterized in that, The step of determining the navigation instruction sequence for the person wearing the head-mounted device to reach the target location based on the target identification information and the geographic location coordinate data includes: The target location coordinates and target priority attributes are determined based on the target identification information; Based on the geographic location coordinates, the target location coordinates, and the target priority attribute, the A* algorithm is used to determine the optimal set of path points from the person wearing the head-mounted device to the target location; The navigation instruction sequence is determined based on the optimal path point set.

5. The end-to-end logistics traceability method based on a head-mounted device according to claim 4, characterized in that, The step of determining the overlay display instruction sequence based on the geographic location coordinate data and the navigation instruction sequence includes: The geographic location coordinate data and the navigation instruction sequence are synchronized and aligned using timestamps, and it is determined whether the deviation between the aligned geographic location coordinate data and the aligned navigation instruction sequence exceeds a preset deviation threshold. If the deviation exceeds the preset threshold, the A* algorithm is used again to optimize the set of optimal path points. If it is determined that the deviation does not exceed the preset deviation threshold, the aligned geographic location coordinate data and the aligned navigation instruction sequence are fused together to determine the overlay display instruction sequence.

6. The end-to-end logistics traceability method based on head-mounted devices according to claim 1, characterized in that, The step of generating a semi-transparent overlay region according to the overlay display instruction sequence includes: The visualization area parameters are determined according to the overlay display instruction sequence, and the visualization area parameters include display positioning parameters, display direction parameters, and display style parameters. Based on the visualization region parameters, an augmented reality algorithm is used to generate a semi-transparent overlay region.

7. The end-to-end logistics traceability method based on head-mounted devices according to claim 1, characterized in that, After determining the gaze record dataset based on the operational intent information and the identity identifier, the method further includes: Obtain the preset checksum, gaze record timestamp, and gaze record location coordinates for each gaze record in the gaze record dataset; Based on the gaze record timestamp and the gaze record location coordinates, a hash algorithm is used to determine the current checksum of each gaze record data. Determine whether the current check code is the same as the preset check code. If they are not the same, mark the current gaze record data as abnormal data. If the determination is the same, then determine whether the current gaze recording data and the gaze recording data adjacent to the current gaze recording data have temporal and positional consistency; If the time and location are determined to be consistent, the current gaze recording data is marked as verified; if the time and location are not determined to be consistent, the current gaze recording data is marked as verified as failed.

8. The end-to-end logistics traceability method based on head-mounted devices according to claim 1, characterized in that, Determining the complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain includes: The gaze record dataset is matched with the historical logistics operation chain using multi-dimensional rules to determine the initial logistics traceability chain; Determine whether the data order of the initial logistics traceability chain satisfies the data continuity throughout the entire process. If the data continuity throughout the entire process is satisfied, then the initial logistics traceability chain is regarded as a complete logistics traceability chain. If the requirement for continuous data throughout the entire process is not met, the initial logistics traceability chain will be marked as an abnormal traceability chain.

9. A full-process logistics traceability system based on a head-mounted device, characterized in that, include: The acquisition module is used to acquire biometric interaction data and geographic location coordinate data of the person wearing the head-mounted device in real time. The biometric interaction data includes pupil center pixel coordinates, corneal reflection point pixel coordinates, pupil diameter variation range, eye movement trajectory, and head posture data. The first determining module is used to determine the precise coordinates of the gaze point based on the biometric interaction data and the geographic location coordinate data; The first judgment module is used to determine whether the precise coordinates of the gaze point are located within the target recognition area. If it is determined that the gaze point is located within the target recognition area, the target recognition area image is acquired, and the target identification information is determined based on the target recognition area image. The second determining module is used to determine the navigation instruction sequence from the person wearing the head-mounted device to the target location based on the target identification information and the geographic location coordinate data; The third determining module is used to determine the overlay display instruction sequence based on the geographic location coordinate data and the navigation instruction sequence, and to generate a semi-transparent overlay area based on the overlay display instruction sequence; The second judgment module is used to determine whether the continuous gaze time of the precise coordinates of the gaze point within the semi-transparent overlay area within a preset time exceeds a preset time threshold. If the determination exceeds the preset time threshold, a gaze intention confirmation signal is generated, and the operation intention information corresponding to the gaze intention confirmation signal and the identity identifier corresponding to the person wearing the head-mounted device are obtained respectively. The fourth determining module is used to determine the gaze record dataset based on the operation intention information and the identity identifier, obtain the historical logistics operation chain, and determine the complete logistics traceability chain based on the gaze record dataset and the historical logistics operation chain.

Images