Moving target data analysis method and system based on field environment and storage medium

Abstract

The invention relates to the technical field of intelligent transportation, and discloses a moving target data analysis method and system based on a field environment, and a storage medium, and the method comprises the steps: setting a security code corresponding to the representation of a plurality of color features for a target feature; obtaining a site to which the target feature belongs, and calculating first distribution data of the security code; calculating the dynamic level of the station according to the first distribution data; obtaining an operation platform of the station, and calculating second distribution data of the dynamic level; calculating the risk level of the operation platform according to the second distribution data; label information is obtained in real time, if the content of the label information is illegal, the security level is lowered, the security code is updated according to the security level, and an execution log is generated; the management background updates the dynamic level and the risk level; if the dynamic level is lower than the dynamic reference level, triggering station early warning; if the risk level is lower than the risk reference level, platform early warning is triggered; and the main body of the non-motor vehicle can be systematically managed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation, in particular to a mobile target data analysis method and system based on a field environment and a storage medium. BACKGROUND

[0002] The rapid development of express delivery and take-out industries has made non-motor vehicles the main means of transportation for practitioners, but related illegal behaviors are common. Red light running, reverse driving, and occupying motor vehicle lanes are frequent, not only disrupting the order of urban road traffic, but also easily causing traffic accidents and threatening the safety of pedestrians and other vehicles, becoming a difficult problem for urban traffic management.

[0003] To strengthen the safety management of non-motor vehicles, various measures have been taken: traffic control departments increase road patrol frequency and intensify the handling of illegal behaviors; electronic monitoring and snapshot devices are installed on key road sections to record and punish illegal behaviors; traffic safety propaganda and education is carried out to improve the law-abiding consciousness of practitioners; and industry self-discipline mechanisms are implemented in some areas, requiring enterprises to strengthen the management of employees. These measures have to some extent curbed illegal activities, but there are still problems such as incomplete management coverage and lack of real-time performance.

[0004] Existing management measures mainly rely on on-site discovery and on-site punishment, and lack systematic management intervention means for the relevant subjects of non-motor vehicles. When non-motor vehicles commit illegal acts, practitioners cannot be reminded in time to correct them, resulting in the continuous occurrence of illegal acts and the difficulty of eliminating safety hazards. SUMMARY

[0005] In order to systematically manage and intervene the relevant subjects of non-motor vehicles, the present application provides a mobile target data analysis method and system based on a field environment and a storage medium.

[0006] In a first aspect, the present application provides a mobile target data analysis method based on a field environment, which adopts the following technical solution:

[0007] A mobile target data analysis method based on a field environment, comprising the following steps:

[0008] A safety code corresponding to a plurality of color feature representations is set for a target feature, and each safety code corresponds to a different safety level;

[0009] The site to which the target feature belongs is obtained, and the first distribution data of the safety code corresponding to the target feature owned by the site is calculated;

[0010] The dynamic level corresponding to the site is calculated according to the first distribution data, and the dynamic level has multiple levels;

[0011] acquire a running platform corresponding to the affiliated station, calculate second distribution data of the dynamic level corresponding to the affiliated station owned by the running platform;

[0012] calculate a risk level corresponding to the running platform according to the second distribution data, the risk level having multiple levels;

[0013] acquire a target label of the target feature in real time through label reading auxiliary camera video algorithm recognition, if the content of the label information of the target label corresponds to illegal behavior, reduce the security level of the target feature, update the security code of the target feature according to the security level, and generate an execution log;

[0014] upload the label information and the execution log to a management background;

[0015] the management background updates the dynamic level and the risk level according to the label information and the execution log;

[0016] if the dynamic level is lower than a preset dynamic reference level, trigger a station early warning;

[0017] if the risk level is lower than a preset risk reference level, trigger a platform early warning.

[0018] By adopting the above technical solution, the target feature, the affiliated station and the running platform are automatically rated according to the data indicators of the target feature. Among them, the target feature is marked with a security level by a security code in multiple colors, and the target feature can be queried in the management background, realizing one-to-one code and dynamic traceability. The affiliated station is rated by a multi-level dynamic level. The running platform is rated by multiple risk levels. The related subjects of the non-motor vehicle are systematically managed and intervened.

[0019] Optionally, the step of acquiring the target label of the target feature in real time further includes the following sub-steps:

[0020] acquire a live image through a camera video algorithm, identify a target area from the live image, and identify the target feature based on the target area;

[0021] if the target feature is identified, calculate a target position corresponding to the target feature based on the live image, and perform target early warning;

[0022] calculate a target route and a target direction according to multiple target positions;

[0023] acquire a camera or a label reader located on the target route and in front of the target direction;

[0024] select the camera or the label reader closest to the target position;

[0025] The target label on the target feature is read using a camera or a label reader;

[0026] If the target tag is read, the target data corresponding to the target tag is obtained and the target data is uploaded;

[0027] If the target tag is not read, a message will be displayed indicating that the target feature does not have the target data, and the scene image and the target feature will be uploaded.

[0028] By adopting the above technical solutions, it is possible to identify illegal behaviors of target characteristics (non-motorized vehicles) in real time and issue on-site warnings (on road motorized vehicle lanes), promptly stop violations, reduce safety hazards, and significantly improve management timeliness. Through hierarchical image recognition, location calculation, and route direction analysis, combined with dual verification by tag readers (such as RFID tags), the illegal subject and behavior can be accurately located, greatly improving identification accuracy and reducing the false judgment rate. This method can not only intervene in violations in real time, but also achieve post-event accountability through tag data, and can also record targets without tags, solving the problem of incomplete coverage in traditional management. Moreover, relying on existing monitoring equipment and tag readers, the automated process reduces hardware investment and labor costs, and improves management efficiency.

[0029] Optionally, the step of identifying target features based on the target region further includes the following sub-steps:

[0030] Extract license plate feature information from moving targets within the target area;

[0031] The license plate feature information is analyzed, and the moving target is distinguished as an electric bicycle or a motorcycle according to the license plate coding rules or identification features.

[0032] By adopting the above technical solutions, electric bicycles or motorcycles can be distinguished by license plates, which can improve the precision of target identification and enhance the accuracy of law enforcement management.

[0033] Optionally, the method further includes the following steps:

[0034] If the moving target is an electric bicycle or motorcycle, then obtain the license plate feature information of the electric bicycle or motorcycle;

[0035] Obtain the corresponding ownership information based on the license plate feature information;

[0036] Based on the aforementioned information, query the number of early warning records;

[0037] If the number of warning records associated with the information is greater than the preset warning reference number, then a warning message is sent based on the information associated with the information.

[0038] By adopting the above technical solution, and by linking the warning records with the relevant information (such as the information of the operating company of the delivery and takeout workers when non-motorized vehicles are driven on motorized vehicles), the traffic management department can quickly identify companies with prominent violations in the delivery and takeout industries, making the management measures of the traffic management department more targeted; and sending warning information can help the company's internal management, and educate and restrain illegal behavior.

[0039] Optionally, the step of the method if the target label is not read further includes the following sub-steps:

[0040] Trigger the activation of the next camera or tag reader located on the target route and ahead of the target direction, and read the target tag on the target feature through the next camera or tag reader.

[0041] By adopting the above technical solutions, the success rate of target tag reading can be improved, the information loss caused by single reading failure can be reduced, and the effective capture and recording of non-motorized vehicle violation information can be ensured.

[0042] Optionally, the method further includes the following steps:

[0043] The target speed is calculated based on the target location and the recording time corresponding to the target location;

[0044] The number of cameras or tag readers to be activated is determined based on the target speed, and the number is positively correlated with the target speed; the larger the number, the larger the target speed; the smaller the number, the smaller the target speed.

[0045] Simultaneously, a corresponding number of tag readers located on the target route and in front of the target direction are activated to read the target tags on the target features.

[0046] By adopting the above technical solution and increasing the number of readers activated according to speed, the effective reading range and time window can be expanded through multi-device relay or simultaneous capture, which greatly reduces the risk of missing information due to high speed and ensures that the tag information of high-speed moving targets can be obtained in a timely and accurate manner.

[0047] Optionally, after the step of sending the warning information based on the associated information, the method further includes the following steps:

[0048] Calculate the ratio of the number of warning records to the number of warning references;

[0049] The number of cameras or tag readers that need to be activated is determined based on the warning ratio, and the number is positively correlated with the warning ratio; the larger the number, the larger the warning ratio; the smaller the number, the smaller the warning ratio.

[0050] Simultaneously, a corresponding number of cameras or tag readers located on the target route and in front of the target direction are activated to read the target tags on the target features.

[0051] By adopting the above technical solution, for vehicles of enterprises with a high incidence of violations, increasing the number of tag readers that can be activated simultaneously allows for collaborative reading by multiple devices. This reduces the probability of reading failures caused by factors such as signal interference or angle deviation from a single device, minimizing information loss. This significantly improves the success rate and information integrity of target tag readings.

[0052] Optionally, the step of reading the target tag further includes the following sub-steps:

[0053] All activated tag sensors generate read data, the content of which includes complete reads, partial reads, and no reads.

[0054] Calculate the read completeness rate = number of tag sensors that were fully read / (number of tag sensors that were partially read + number of tag sensors that were not read);

[0055] If the read completeness is greater than the preset reference completeness, then the target tag has been read.

[0056] By adopting the above technical solutions, multi-device redundancy verification avoids misjudgment by a single sensor and reduces the false negative rate; quantitatively assesses reading quality and replaces binary judgment with integrity indicators to improve system fault tolerance; and dynamically adjusts resource allocation in combination with early warning ratios or target speeds to balance regulatory efficiency and cost.

[0057] Secondly, this application provides a mobile target data analysis system based on the field environment, which adopts the following technical solution:

[0058] A mobile target data analysis system based on the field environment includes a processor, wherein the processor performs the steps of the mobile target data analysis method based on the field environment as described in any one of the preceding claims.

[0059] Thirdly, this application provides a storage medium, which adopts the following technical solution:

[0060] A storage medium storing a program that, when executed by a processor, implements the steps of the mobile target data analysis method based on the field environment as described above.

[0061] In summary, this application includes at least one of the following beneficial technical effects: By using on-site image recognition and target location calculation, real-time early warning and prevention of non-motorized vehicle violations can be achieved, significantly improving management efficiency and reducing safety hazards. Combining license plate feature analysis and RFID tag dual verification can distinguish between electric bicycles and motorcycles, accurately pinpoint the violator, greatly reduce the false judgment rate, and enhance the accuracy of law enforcement. Attached Figure Description

[0062] Figure 1 This is a step-by-step diagram of a mobile target data analysis method based on the on-site environment.

[0063] Figure 2 This is a step-by-step diagram showing the movement target as an electric bicycle or motorcycle.

[0064] Figure 3 This is a diagram illustrating the steps involved in reading the target tag. Detailed Implementation

[0065] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0066] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0067] This application discloses a method for analyzing moving target data based on the on-site environment, referring to... Figure 1 It includes the following steps:

[0068] Set security codes corresponding to various color feature representations for the target features, with each security code corresponding to a different security level;

[0069] Obtain the site to which the target feature belongs, and calculate the first distribution data of the security codes corresponding to the target feature owned by the site.

[0070] Calculate the dynamic level corresponding to the site based on the first distribution data;

[0071] Obtain the operating platform corresponding to the site, and calculate the second distribution data of the dynamic level corresponding to the site owned by the operating platform;

[0072] The risk level corresponding to the operating platform is calculated based on the second distribution data;

[0073] The target feature's target label is acquired in real time. If the content of the target label's label information corresponds to illegal behavior, the security level of the target feature is reduced, the security code of the target feature is updated according to the security level, and an execution log is generated.

[0074] Upload the tag information and execution logs to the management backend;

[0075] The management backend updates the dynamic rating and risk level based on the tag information and execution logs;

[0076] If the dynamic level is lower than the preset dynamic reference level, a site warning will be triggered.

[0077] If the risk level is lower than the preset risk reference level, a platform warning will be triggered.

[0078] The target characteristic is delivery riders. Based on data indicators such as the use of rider-specific license plates, handling of traffic violations and accidents, and implementation of traffic safety training, the system can automatically identify loopholes in the implementation of the main responsibilities of enterprises and stations, and automatically assess the safety level of riders, stations, and enterprises. The station to which the rider belongs is the delivery station; the operating platform is the platform enterprise to which the delivery station belongs; and the management backend is an administrative platform, such as the "Suishenban APP". Riders are marked with a three-color "safety code" (green, yellow, red) to indicate their safety level, which riders can also check on the "Suishenban APP," achieving "one code per person, dynamic traceability." Delivery stations are dynamically rated from 1 to 5 stars, with 5 stars being the best. Platform enterprises are assessed with two risk levels: "high risk" and "low risk".

[0079] High-definition surveillance cameras deployed along roads (such as fixed cameras on both sides of the roadway and pole-mounted mobile capture devices) collect real-time images of the surrounding environment. The acquisition frequency can be dynamically adjusted according to traffic flow, set to 25 frames per second during peak hours and 15 frames per second during off-peak hours to ensure clear capture of the dynamic features of moving targets. For example, at the intersection of a main urban road, the cameras can cover a radius of 50 meters including the roadway, non-motorized vehicle lane, and pedestrian walkway, providing a complete image data source for subsequent target recognition.

[0080] Deep learning-based image segmentation algorithms (such as the U-Net model) are used to divide the scene image into regions, extracting the pre-defined target regions from the complex background. The target regions are the motor vehicle lanes requiring key monitoring. Specifically, the model is iteratively optimized using training samples (including motor vehicle lane images under different lighting, weather, and time periods) to enable it to accurately identify features such as lane lines and guardrails, thereby defining the pixel range of the motor vehicle lanes. For example, in the image, the motor vehicle lane area is marked with a red rectangle, while non-motorized vehicle lanes and sidewalks are marked with other colors, clearly distinguishing the target area from non-target areas.

[0081] Within a designated motor vehicle lane area, image scanning algorithms (such as YOLOv5) are used to identify moving targets, such as vehicles and pedestrians, and further extract their features. For non-motorized vehicles, the focus is on identifying their shape, riding status (e.g., whether they are carrying passengers or riding against traffic), and associated markings (e.g., license plate number, vehicle color). For example, when an electric bicycle or motorcycle is detected entering a motor vehicle lane, the system automatically extracts the feature of "no engine exhaust pipe," initially classifying it as a non-motorized vehicle and marking it as a target feature to be verified. Motorcycles include both electric and gasoline motorcycles.

[0082] If a non-motorized vehicle is detected entering the motorized vehicle lane, indicating the presence of a target feature, the actual geographical location of the target feature is calculated using an image coordinate transformation algorithm. Specifically, based on the installation parameters of the surveillance camera (such as altitude, tilt angle, and focal length) and a preset road coordinate system (establishing xy-plane coordinates with the center point of the intersection as the origin), the pixel coordinates of the target feature in the image are converted into actual latitude and longitude coordinates.

[0083] Simultaneously, the system triggers a real-time early warning mechanism: it issues alerts through audible and visual alarms deployed at intersections, such as LED warning screens and loudspeakers at the edge of the motor vehicle lane; for example, the screen displays "Non-motorized vehicles are not allowed to occupy the motor vehicle lane," and the loudspeaker simultaneously broadcasts a voice warning; if the target is an electric bicycle or electric motorcycle, it can also send a text warning through its onboard terminal, such as "You have entered the motor vehicle lane, please pay attention to safety and leave immediately," to achieve immediate intervention in illegal behavior.

[0084] By continuously collecting multiple location coordinates of the target features, such as recording latitude and longitude every second, the system uses trajectory fitting algorithms, such as the least squares method, to generate the target route. For example, if the location coordinates of a non-motorized vehicle within 3 seconds are (x1, y1), (x2, y2), and (x3, y3), the system determines its travel trajectory as east to west along the motor vehicle lane by fitting the straight line formed by these three points.

[0085] At the same time, based on the time sequence of the location coordinates, such as the offset direction of the coordinates at a later time relative to the previous time, the target direction is determined to be "west", providing a directional basis for the selection of subsequent cameras or tag readers.

[0086] Pre-deploy cameras or RFID tag readers along the road, such as installing one every 20 meters at a height of 1.5 meters, covering a radius of 8 meters. Record their location information (latitude and longitude) and coverage area into the system database. After determining the target route and direction, the system filters the database for readers located on that route and ahead of the target direction. For example, if the target route is "from east to west," then all RFID readers distributed along the route to the west of the target's current location will be selected.

[0087] Calculate the straight-line distance between each selected reader and the target's current location (latitude and longitude), and select the one closest as the priority reading device. For example, if the target's current location is (x0, y0), and the three readers on the west side are 5 meters, 10 meters, and 15 meters away respectively, then the reader at a distance of 5 meters will be activated first to ensure that the tag can be read as soon as the target enters its coverage area.

[0088] Target features (such as non-motorized vehicles) are pre-installed with RFID electronic tags, which store unique identification information (such as vehicle number, owner information, etc.). When the target enters the coverage area of ​​the selected reader, the reader emits a radio frequency signal to activate the tag, receives the identification information returned by the tag, and completes the reading operation. For example, after the RFID tag of a delivery vehicle in the express delivery and food delivery industries is activated, the reader can obtain its corresponding data such as "rider ID + affiliated company code + vehicle registration number".

[0089] If the reader successfully acquires the tag information (i.e., returns complete tag data), the system associates this data with the identified target features (such as vehicle shape and driving status) to generate a complete record containing "violation time, violation location, target features, and tag data," and uploads it to the traffic management department's backend database. For example, the record content might be "2023-10-01 09:30, XX intersection, motor vehicle lane, electric bicycle or motorcycle, rider ID: 12345, company code: ABC takeaway."

[0090] If the reader fails to acquire tag information, such as due to a damaged or detached tag, or the target not having a tag installed, the system determines that the target's features lack traceable tag data. In this case, the acquired on-site image (including a close-up of the target), extracted target features (such as license plate number and vehicle color), and calculated location information are packaged and uploaded to the backend. For example, for untagged electric bicycles or motorcycles, the uploaded information includes "a close-up image of the vehicle (including a blurred license plate), the time and location of entering the motor vehicle lane, and the driving trajectory," ensuring that even without a tag, violations can be recorded through image documentation.

[0091] This method can identify illegal non-motorized vehicle behavior in motorized vehicle lanes in real time and issue on-site warnings, promptly stopping violations to reduce safety hazards and significantly enhancing the timeliness of management. Utilizing hierarchical image recognition, location calculation, and route direction analysis, combined with dual verification using RFID and other tag readers, it can accurately pinpoint the violator and their behavior, greatly improving identification accuracy and reducing the probability of misjudgment. This method allows for real-time intervention in violations and post-event accountability using tag data, and can also record targets without tags, solving the problem of incomplete coverage in traditional management. Simultaneously, relying on existing monitoring equipment and tag readers, the automated process reduces hardware investment and labor costs, effectively improving management efficiency.

[0092] The steps for identifying target features based on target regions also include the following sub-steps:

[0093] The system extracts license plate feature information from moving targets within the target area. Using edge detection and contour recognition technologies, the license plate area is selected from the vehicle image, such as the rectangular marking area at the rear or front of an electric bicycle or motorcycle, excluding interfering elements like vehicle advertisements and decorative stickers. For example, for electric bicycles or motorcycles, the license plate is typically a rectangular plate with a blue background and white lettering, fixed to the rear license plate frame; gasoline motorcycles have yellow backgrounds with black or white backgrounds with black lettering. The localization algorithm accurately extracts image segments of this area; the resolution is generally adjusted to 300×100 pixels to ensure clear characters. The localized license plate image undergoes preprocessing, including grayscale conversion, deblurring, and tilt correction. Then, a character segmentation algorithm extracts each character (including numbers, letters, and special symbols) from the license plate, forming structured feature information.

[0094] Based on preset coding rules and an identifier feature library, the extracted license plate information is parsed to accurately distinguish between electric bicycles and motorcycles.

[0095] The system has pre-entered coding rules for non-motorized and motorized vehicle license plates. If the coding rules are ambiguous, such as inconsistencies in license plate formats during the transition period in some areas, the physical characteristics of the license plate will be used for further differentiation.

[0096] ReferenceFigure 2 The method also includes the following steps:

[0097] After identifying the moving target as an electric bicycle or motorcycle, the system retrieves the extracted license plate feature information and performs structured processing to extract key identification fields, including region codes, serial numbers, and unique identifiers. For example, some regions assign unique number ranges to electric vehicles used in industries such as express delivery and food delivery. Specifically, a character matching algorithm is used to filter out core fields associated with the license plate information, providing a data foundation for subsequent association with the relevant information.

[0098] The system has a pre-set "license plate-ownership information" mapping database, which stores the relationship between electric bicycle or motorcycle license plates and their owners (such as operating companies, logistics companies, and individual users in the express delivery and food delivery industries).

[0099] For electric bicycles owned by individuals, the license plate number is linked to the owner's ID card information.

[0100] After the license plate number features are entered, the system uses a combination of fuzzy matching and precise query. For example, it first matches the area code to narrow down the range, and then retrieves the corresponding information by serial number, such as "Company: XX Delivery Co., Ltd., Company Code: WMD001".

[0101] The system backend establishes a database linking ownership information and early warning records, recording in real time the violation warning history of electric bicycles or motorcycles under each entity's name, including warning time, violation location, and violation type, such as "driving in a motor vehicle lane" or "running a red light." After obtaining the ownership information, the system automatically queries the entity's cumulative warning records within a preset period (e.g., the past 30 days). For example, if the system finds that "XX Delivery Co., Ltd." received 15 warnings in the past 30 days for "non-motorized vehicles entering motor vehicle lanes," then the company has 15 warning records.

[0102] The system presets warning reference values ​​for different entities, set according to industry averages and management needs. For example, the warning reference value for companies in industries such as express delivery and food delivery is set to 10 times / 30 days. When the number of queried warning records (e.g., 15 times) exceeds the warning reference value (10 times), an alert information sending mechanism is triggered.

[0103] The notifications can be pushed directly to the company's management backend (such as the enterprise safety management system) and the mobile devices linked to the company's responsible personnel, such as via SMS and a dedicated app. The message content includes "Warning Exceeding Standards Reminder" (e.g., "Your company has recorded 15 warnings in the past 30 days, exceeding the reference value by 10"), "Violation Details," and "Rectification Requirements" (e.g., "Please complete rider safety training within 3 days; failure to do so will result in a joint law enforcement inspection"). A triple push notification system (system pop-up + SMS + email) can be used to ensure timely receipt by the company.

[0104] By linking warning records with their associated information (for example, when delivery and takeout workers are identified driving non-motorized vehicles in motorized vehicle lanes, the system can automatically obtain information about the operating company to which the worker belongs), it is possible to quickly locate companies in the delivery and takeout industries that frequently violate regulations, making traffic management measures more targeted. At the same time, sending warning messages to companies helps to encourage them to strengthen internal management, effectively educate and restrain employees from violating regulations, and reduce the occurrence of violations at the source.

[0105] If the target tag method is not read, the following sub-steps are also included:

[0106] When the camera or tag reader (such as an RFID reader) closest to the target location fails to read the target tag on the target feature, for example, due to the tag signal being blocked, a temporary equipment failure, or the target moving too fast causing a timeout, the system automatically triggers the sequential start mechanism:

[0107] Based on the calculated target route (e.g., "traveling from east to west along the XX main road") and target direction (e.g., "west"), the system selects the next-priority reader from a pre-defined database of camera or tag reader deployments that is located on the target route and in front of the current reader (i.e., the next node in the target direction of travel). For example, if the current reader is device R1 deployed 50 meters west of intersection A, and the target direction is west, then the next-priority reader is device R2 deployed 30 meters west of intersection B (the distance between devices along the target route and R1 is 80 meters).

[0108] The system sends a start command to the next sequential reader via a wired network (such as fiber optic) or a wireless network (such as 4G / 5G). The command includes the real-time location, movement speed, and tag signal characteristics (such as tag frequency and encoding format) of the target feature, so that the reader enters the activation state in advance (such as increasing the receiving sensitivity from the default -85dBm to -90dBm and shortening the signal response time to less than 100ms).

[0109] The target tag is read by the next camera or tag reader in sequence: After receiving the start command, the next reader immediately adjusts the reading parameters according to the target's trajectory.

[0110] Calculate the estimated time for the target to reach the reader's coverage area (radius of 10 meters) based on the target's speed (e.g., 20 km / h). If it takes 14.4 seconds to reach a distance of 80 meters, activate the continuous scanning mode in advance and increase the scanning frequency from 1 Hz to 5 Hz to ensure that the target can be captured instantly when it enters the range.

[0111] The reader transmits radio frequency signals through a directional antenna (along the target route) and records data such as signal strength and reflection time. If a signal that matches the target tag encoding rules is captured three times in a row, such as "a 16-bit binary code with the prefix 'WM'", it is considered a successful read. If it is still not read, the next sequential reader (such as R3) is started until the read is successful or the preset maximum number of sequential reads is reached, such as three times.

[0112] By employing a sequential activation mechanism, information loss due to single reader malfunction or momentary interference is avoided. For high-speed moving non-motorized vehicles, such as delivery vehicles in the express delivery and food delivery industries, a "relay-style" reading system ensures that the target remains within the monitoring coverage area throughout its entire route, solving the "coverage blind spot" problem of traditional single-device reading and making the traceability chain of illegal activities more complete.

[0113] The method also includes the following steps:

[0114] The target velocity is calculated based on the target location and the corresponding recording time. Two sets of continuous position data with a time interval Δt ≥ 1 second are selected (e.g., (x1, y1, t1) and (x2, y2, t2)) to avoid calculation errors caused by overly dense sampling. For example, if the target position is (120.001°) at t1 = 09:00:00.

[0115] Given that the coordinates are (E, 30.001°N) and the position at t2 = 09:00:02 is (120.002°E, 30.001°N), then Δt = 2 seconds. The distance s (in meters) between the two points on the Earth's surface is calculated using a latitude and longitude coordinate transformation formula (such as the Haversine formula). Taking the above coordinates as an example, the calculated s = 111 meters (approximate). The instantaneous speed is converted to km / h using the formula v = (s / Δt) × 3.6. In the above example, v = (111 / 2) × 3.6 = 199.8 km / h. This is an extreme example; the actual speed of non-motorized vehicles is usually ≤40 km / h.

[0116] The number of cameras or tag readers to be activated is determined based on the target speed, and the number is positively correlated with the target speed; the larger the number, the higher the target speed; the smaller the number, the lower the target speed. The specific dynamic relationship is as follows:

[0117] When v≤10 (km / h), activate one camera or tag reader, selecting the camera or tag reader closest to the target location;

[0118] When 10 (km / h) < v ≤ 20 (km / h), activate 2 cameras or tag readers and select the 2 nearest consecutive cameras or tag readers;

[0119] When 20 (km / h) < v ≤ 30 (km / h), activate 3 cameras or tag readers and select the 3 nearest consecutive cameras or tag readers;

[0120] When v > 30 (km / h), activate 4 cameras or tag readers and select the 4 nearest consecutive cameras or tag readers.

[0121] Simultaneously, a corresponding number of cameras or tag readers located on the target route and in front of the target direction are activated to read the target tags on the target features. A synchronous triggering mechanism ensures that the selected N readers enter the active state at the same time (error ≤ 50ms) through a millisecond-level time synchronization protocol (such as NTP protocol), avoiding missed reads due to startup time differences. The readers adjust their operating parameters according to the target speed—for example, for a target with v > 30km / h, the signal transmission power is increased from 1W to 2W, the reading sensitivity is optimized from -85dBm to -90dBm, and the effective identification distance is extended to 15 meters. Multiple readers are deployed at intervals along the target route (e.g., 20 meters each) to form a continuous coverage area. For example, 3 readers can cover a 60-meter section, ensuring that a target traveling at 20km / h (which takes 10.8 seconds to pass 60 meters) has sufficient time to be read by at least one device.

[0122] Increasing the number of readers reduces the missed read rate and improves the efficiency of reading high-speed targets; for low-speed targets, reducing the number of readers can reduce energy consumption and avoid resource waste.

[0123] In other embodiments, after the step of sending the alert information based on the associated information, the following steps are further included:

[0124] The system calculates the warning ratio between the number of warning records and the warning reference number. It retrieves the number of warning records (denoted as A) for the relevant information within a preset statistical period (e.g., the last 30 days) from the system's backend database. For example, a company might have issued 25 warnings in the last 30 days. Simultaneously, it extracts a preset warning reference number (denoted as B), which is dynamically adjusted based on industry averages, company size, and historical violation data. For example, the warning reference number for industries like express delivery and food delivery is set at 10 times per 30 days. The quantitative ratio is calculated using the formula "Warning Ratio R = A / B". In the example above, R = 25 / 10 = 2.5, directly reflecting how many times the company's violation risk exceeds the reference level.

[0125] The number of cameras or tag readers to be activated is determined based on the warning ratio. The number of cameras or tag readers is positively correlated with the warning ratio; the larger the number, the larger the warning ratio; the smaller the number, the smaller the warning ratio. Reading resources are dynamically allocated according to the ratio, with the specific rules as follows (taking an urban main road scenario as an example):

[0126] When 1 < warning ratio R ≤ 2, activate 2 cameras or tag readers, and select the 2 cameras or tag readers that are closest to the target location in consecutive order;

[0127] When 2 < warning ratio R ≤ 3, activate 3 cameras or tag readers, and select the 3 cameras or tag readers that are closest to the target location in consecutive order;

[0128] When 3 < warning ratio R, activate 4 cameras or tag readers, and select the 4 cameras or tag readers that are closest to the target location in a consecutive order.

[0129] Simultaneously, a corresponding number of cameras or tag readers located on the target route and in front of the target direction are activated to read the target tags on the target features. A synchronous start command is sent to the selected N readers via industrial-grade Ethernet or a 5G private network to ensure that all devices enter working status simultaneously within 100ms, avoiding reading gaps caused by start-up time differences. For enterprise vehicles with high warning ratios, the readers automatically adjust their operating parameters, such as extending the signal receiving bandwidth from 2MHz to 4MHz to combat interference and extending the tag response time threshold from 50ms to 100ms to accommodate potential tag aging issues. Multiple readers are deployed in a staggered, complementary manner; for example, three readers are installed at heights of 1.2m, 1.5m, and 1.8m on road poles respectively, forming a three-dimensional coverage area and reducing reading blind spots caused by vehicle tilt or tag obstruction.

[0130] The above methods achieve dynamic matching between regulatory resources and corporate illegal risks, which not only ensures the quality of information capture of high-risk targets, but also improves the overall operational efficiency of the regulatory system.

[0131] Reference Figure 3 The step of reading the target tag also includes the following sub-steps:

[0132] During the process of reading the target tag through the tag reader, all activated tag sensors (such as RFID radio frequency sensors) generate and upload reading data in real time. The data content is divided into three categories based on the completeness of the captured tag information:

[0133] Complete reading: The sensor successfully acquires all identification information of the target tag (such as a 16-bit character code containing a unique device number, the owner's code, and the filing time), and the data is verified to be correct (through CRC cyclic redundancy check).

[0134] Partial reading: The sensor only captures part of the tag information (such as only obtaining the first 8 digits of the number), or the data contains verification errors (such as missing characters or abnormal format);

[0135] Not Read: The sensor did not receive any signal from the tag (e.g., due to signal shielding or tag failure) and returned empty data.

[0136] For example, when three tag sensors are activated, combined data such as "2 complete reads and 1 partial read" or "1 complete read, 1 partial read, and 1 no read" may be generated.

[0137] Calculate the read completeness as follows: (Number of tag sensors that were fully read / (Number of tag sensors that were partially read + Number of tag sensors that were not read)).

[0138] If four sensors are activated in a certain scenario, with three performing "complete readings" and one performing "partial readings", then the reading completeness = 3 / 1 = 3.0;

[0139] If two sensors "read completely", one "read partially", and one "read not", then the reading completeness = 2 / (1+1) = 1.0;

[0140] If there are 0 "complete reads", 2 "partial reads", and 1 "unread", then the read completeness is 0 / 3 = 0.

[0141] This indicator quantifies the effectiveness of multi-sensor collaborative reading; a higher value indicates more reliable capture quality of tag information.

[0142] If the read completeness is greater than the preset reference completeness, then the target tag has been read. The system presets a reference completeness threshold, which is dynamically adjusted according to the application scenario.

[0143] For high-risk scenarios, such as enterprise vehicles with a warning ratio R > 3 and high-speed moving targets with a target speed v > 30 km / h, the reference completeness is set to 2.0, meaning that the number of complete reads must be at least twice the number of incomplete reads.

[0144] For typical scenarios, such as ordinary non-motorized vehicles and low-speed moving targets, the reference integrity is set to 1.0, meaning that the number of complete reads is no less than the number of incomplete reads.

[0145] When the calculated read completeness is greater than the preset reference completeness, it is determined that "the target tag has been read" and the system accepts the completely read tag information; otherwise, it is determined that "the read is not effective" and the next sequential reader is triggered.

[0146] Multi-sensor redundancy verification avoids misjudgments caused by single device failure or transient interference. A completeness index replaces the traditional binary "success / failure" judgment, allowing for a certain percentage of abnormal sensor readings. The reference completeness threshold is adjusted by combining parameters such as the warning ratio and target speed, achieving high standards for high-risk situations and moderately relaxed standards for low-risk situations.

[0147] This application also discloses a mobile target data analysis system based on the field environment, including a processor, wherein the processor executes the steps of the mobile target data analysis method based on the field environment as described in any of the above embodiments.

[0148] This application also discloses a storage medium storing a program that, when executed by a processor, implements the steps of the above-described method for analyzing mobile target data based on the field environment.

[0149] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for analyzing moving target data based on the on-site environment, characterized in that, Includes the following steps: A security code corresponding to multiple color feature representations is set for the target feature, and each security code corresponds to a different security level; Obtain the site to which the target feature belongs, and calculate the first distribution data of the security code corresponding to the target feature owned by the site; The dynamic level corresponding to the site is calculated based on the first distribution data; Obtain the operating platform corresponding to the site, and calculate the second distribution data of the dynamic level corresponding to the site owned by the operating platform; The risk level corresponding to the operating platform is calculated based on the second distribution data; The target feature is identified in real time by using a tag-reading auxiliary camera video algorithm. If the content of the tag information of the target feature corresponds to illegal behavior, the security level of the target feature is reduced, the security code of the target feature is updated according to the security level, and an execution log is generated. Upload the tag information and execution logs to the management backend; The management backend updates the dynamic level and the risk level based on the tag information and the execution log; If the dynamic level is lower than the preset dynamic reference level, a site warning is triggered; If the risk level is lower than the preset risk reference level, a platform warning will be triggered.

2. The method for analyzing moving target data based on the on-site environment according to claim 1, characterized in that, The step of acquiring the target label of the target feature in real time also includes the following sub-steps: Acquire on-site images; The target area is identified from the scene image using a camera video algorithm; Identify target features based on the target region; If a target feature is identified, the target location corresponding to the target feature is calculated based on the scene image, and a target warning is issued. The target route and target direction are calculated based on the multiple target locations; Acquire a camera or tag reader located on the target route and in front of the target direction; Select the camera or tag reader closest to the target location; The target label on the target feature is read using a camera or a label reader; If the target tag is read, the target data corresponding to the target tag is obtained and the target data is uploaded; If the target tag is not read, a message will be displayed indicating that the target feature does not have the target data, and the scene image and the target feature will be uploaded.

3. The method for analyzing moving target data based on the on-site environment according to claim 1, characterized in that, The step of identifying target features based on the target region further includes the following sub-steps: Extract license plate feature information from moving targets within the target area; The license plate feature information is analyzed, and the moving target is distinguished as an electric bicycle or a motorcycle according to the license plate coding rules or identification features.

4. The method for analyzing moving target data based on the on-site environment according to claim 3, characterized in that, The method also includes the following steps: If the moving target is an electric bicycle or motorcycle, then obtain the license plate feature information of the electric bicycle or motorcycle; Obtain the corresponding ownership information based on the license plate feature information; Based on the aforementioned information, query the number of early warning records; If the number of warning records associated with the information is greater than the preset warning reference number, then a warning message is sent based on the information associated with the information.

5. The method for analyzing moving target data based on the on-site environment according to claim 1, characterized in that, The step of the method if the target label is not read also includes the following sub-steps: Trigger the activation of the next camera or tag reader located on the target route and ahead of the target direction, and read the target tag on the target feature through the next camera or tag reader.

6. The method for analyzing moving target data based on the on-site environment according to claim 1, characterized in that, The method also includes the following steps: The target speed is calculated based on the target location and the recording time corresponding to the target location; The number of cameras or tag readers to be activated is determined based on the target speed, and the number is positively correlated with the target speed. The larger the quantity, the greater the target speed; The smaller the quantity, the smaller the target speed; Simultaneously, a corresponding number of cameras or tag readers located on the target route and in front of the target direction are activated to read the target tags on the target features.

7. The method for analyzing moving target data based on the on-site environment according to claim 4, characterized in that, After the step of sending the warning information based on the associated information, the following steps are also included: Calculate the ratio of the number of warning records to the number of warning references; The number of cameras or tag readers that need to be activated is determined based on the warning ratio, and the number is positively correlated with the warning ratio. The larger the quantity, the larger the warning ratio; The smaller the quantity, the smaller the warning ratio; Simultaneously, a corresponding number of cameras or tag readers located on the target route and in front of the target direction are activated to read the target tags on the target features.

8. The method for analyzing moving target data based on the on-site environment according to claim 1, characterized in that, The step of reading the target tag further includes the following sub-steps: All activated tag sensors generate read data, the content of which includes complete reads, partial reads, and no reads. Calculate the read completeness rate = number of tag sensors that were fully read / (number of tag sensors that were partially read + number of tag sensors that were not read); If the read completeness is greater than the preset reference completeness, then the target tag has been read.

9. A mobile target data analysis system based on the on-site environment, characterized in that, The device includes a processor that performs the steps of the mobile target data analysis method based on the field environment as described in any one of claims 1-8.

10. A storage medium, characterized in that, The storage medium stores a program that, when executed by a processor, implements the steps of the mobile target data analysis method based on the field environment as described in any one of claims 1-8.

Images