A passenger safety monitoring early warning method and device, electronic equipment, computer readable medium and program product

CN122511046APending Publication Date: 2026-08-04INNER MONGOLIA UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610464983.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-09
Publication Date
2026-08-04

AI Technical Summary

Technical Problem

但在实际运营环境中,驾驶员需同时关注路况、信号及上下客等多重信息,难以持续追踪个别乘客的细微动作;车厢内环境嘈杂,乘客口头呼喊往往难以有效传达

Benefits of technology

本申请通过乘客的位姿信息与目标车辆的触发信号相融合,实现了对乘客安全状态的精准、可靠判定。在此基础上,利用直观的预警信息提醒司机乘客的安全状态,进而构建了一套高效、低负担的司乘双向交互机制。该机制在不增加司机额外操作负担的前提下,使得年老或行动不便乘客的上下车需求能够被及时、准确地传达,降低了因为司乘沟通不畅问题,而导致的乘客的安全风险。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122511046A_ABST
    Figure CN122511046A_ABST
Patent Text Reader

Abstract

This invention provides a passenger safety monitoring early warning method and device, electronic equipment, computer-readable medium, and program product, belonging to the technical field of safety monitoring. The early warning method includes: determining a target vehicle from multiple vehicles corresponding to multiple vehicle-mounted terminals based on prior route information, mobile terminal status information, and broadcast signals from vehicle-mounted fixed terminals. The prior route information includes route geometry and station information pre-stored in the mobile terminal; generating passenger pose information based on inertial measurement data and satellite observation data from the mobile terminal, as well as route and station constraint information corresponding to the target vehicle; determining the passenger's safety status based on the trigger signal and pose information from the vehicle-mounted fixed terminal corresponding to the target vehicle; and sending a prompt command to the vehicle-mounted fixed terminal corresponding to the target vehicle based on the passenger's safety status, causing the vehicle-mounted fixed terminal to output corresponding early warning information. This application improves the reliability and accuracy of passenger safety monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the technical field of safety monitoring, and specifically relates to an early warning method and device for passenger safety monitoring, electronic equipment, computer-readable medium, and program product. Background Technology

[0002] Public transportation, especially buses, is an important mode of transportation for the elderly and people with mobility impairments. The applicant of this application found that in actual operation, safety mechanisms for this group still have the following significant deficiencies: During the boarding process, elderly people and those with mobility impairments often need a considerable amount of time to complete a series of actions, including boarding, swiping their cards, finding seats, and stabilizing themselves. Because drivers cannot monitor the readiness of these passengers in real time, the vehicle often starts moving before the passengers are fully seated or have a firm grip on the handrails. The acceleration generated at the moment of vehicle start-up can easily cause passengers to lose their balance, especially in rainy or snowy weather when the passenger compartment floor is slippery, significantly increasing the risk of falls.

[0003] During passenger disembarkation, elderly people and those with mobility issues often need to get up in advance and move slowly towards the door area while the vehicle is in motion. Due to the swaying of the vehicle and the slippery ground, this movement itself poses a safety hazard. At the same time, due to the driver's blind spot, it is difficult for the driver to continuously observe the movement of passengers in the rear door area. This may result in the door being closed and the vehicle starting before passengers have reached the door area or completed their disembarkation preparations, leaving passengers stranded inside the vehicle or forced to continue moving while the vehicle is in motion, increasing the risk of collisions and injuries.

[0004] Current technologies primarily rely on driver visual observation and passenger verbal commands for information exchange between drivers and passengers. However, in actual operating environments, drivers need to simultaneously monitor multiple pieces of information, including road conditions, traffic signals, and passenger pick-up and drop-off times, making it difficult to continuously track the subtle movements of individual passengers. Furthermore, the noisy environment inside the vehicle often makes it difficult to effectively convey passenger verbal commands. Therefore, there is currently a lack of technology that can automatically send a safe departure signal to the driver when passengers have completed their boarding preparations, or proactively remind the driver to extend the stop time when passengers request to disembark.

[0005] The content of the background section is merely the technology known to the inventor and does not necessarily represent the prior art in this field. Summary of the Invention

[0006] The present invention aims to provide a method and device for passenger safety monitoring, an electronic device, a computer-readable medium, and a program product to solve at least one of the above-mentioned technical problems.

[0007] According to one aspect of this application, a passenger safety monitoring and early warning method is provided, executed by a mobile terminal worn by the passenger and communicatively connected to an in-vehicle fixed terminal. Each in-vehicle fixed terminal corresponds to a specific vehicle. The early warning method includes: determining a target vehicle from among multiple vehicles corresponding to multiple in-vehicle fixed terminals based on prior route information, the mobile terminal's status information, and broadcast signals from the in-vehicle fixed terminal; generating passenger pose information based on inertial measurement data and satellite observation data from the mobile terminal, as well as the route and station constraint information corresponding to the target vehicle; determining the passenger's safety status based on the trigger signal and pose information from the in-vehicle fixed terminal corresponding to the target vehicle; and sending a prompt command to the in-vehicle fixed terminal corresponding to the target vehicle based on the passenger's safety status, causing the in-vehicle fixed terminal to output corresponding early warning information.

[0008] According to some embodiments of this application, generating passenger pose information based on inertial measurement data and satellite observation data of a mobile terminal and route and station constraint information corresponding to the target vehicle includes: generating fused positioning information based on inertial measurement data and satellite observation data; adjusting the fused positioning information based on route and station constraint information corresponding to the target vehicle to generate real-time positioning and attitude information of the passenger as pose information.

[0009] According to some embodiments of this application, generating fused positioning information based on inertial measurement data and satellite observation data includes: determining an adaptive weight of the satellite observation data based on the satellite signal quality corresponding to the satellite observation data; and fusing the inertial measurement data and the satellite observation data weighted by the adaptive weight to generate fused positioning information.

[0010] According to some embodiments of this application, the early warning method further includes: determining a compensation factor for satellite observation data based on satellite signal quality; and fusing inertial measurement data with satellite observation data corrected by the compensation factor to generate fused positioning information.

[0011] According to some embodiments of this application, the fused positioning information is adjusted based on the route and station constraint information corresponding to the target vehicle, including at least one of the following methods: when it is determined that the target vehicle is in a stopped state, the fused positioning information is adjusted based on the location information of the current station corresponding to the target vehicle; when it is determined that the target vehicle is in a driving state, the fused positioning information is adjusted based on the projection distance error of the fused positioning information on the preset route path; when it is determined that the target vehicle is in a stopped state, the speed observation value is set to zero to adjust the fused positioning information.

[0012] According to some embodiments of this application, determining a target vehicle from vehicles corresponding to multiple vehicle-mounted fixed terminals based on route prior information, mobile terminal status information, and broadcast signals from vehicle-mounted fixed terminals includes: parsing route identifiers from broadcast signals; filtering multiple candidate vehicles from vehicles corresponding to multiple vehicle-mounted fixed terminals based on broadcast signals; determining the relative distance between the mobile terminal and candidate vehicles based on the received signal strength and mobile terminal status information; determining the matching degree between candidate vehicles and expected routes based on route prior information corresponding to route identifiers; and determining the target vehicle from multiple candidate vehicles based on the relative distance and matching degree.

[0013] According to another aspect of this application, a passenger safety monitoring early warning device is also provided. The early warning device is worn by the passenger and is communicatively connected to an on-board fixed terminal. Each on-board fixed terminal corresponds to a vehicle. The early warning device includes a vehicle identification module, a pose generation module, a safety status determination module, and a command sending module. The vehicle identification module is used to determine the target vehicle from among multiple vehicles corresponding to multiple on-board fixed terminals based on prior route information, the status information of the early warning device, and the broadcast signal from the on-board fixed terminal. The prior route information includes route geometry and station information pre-stored in the early warning device. The pose generation module is used to generate the passenger's pose information based on the inertial measurement data and satellite observation data of the early warning device, as well as the route and station constraint information corresponding to the target vehicle. The safety status determination module is used to determine the passenger's safety status based on the trigger signal and pose information of the on-board fixed terminal corresponding to the target vehicle. The command sending module is used to send a prompt command to the on-board fixed terminal corresponding to the target vehicle based on the passenger's safety status, so that the on-board fixed terminal outputs corresponding early warning information.

[0014] According to another aspect of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the warning methods described above.

[0015] According to another aspect of this application, a computer-readable medium having processor-executable non-volatile program code is also provided, the program code causing the processor to perform any of the warning methods described above.

[0016] According to another aspect of this application, a computer program product is also provided, including a computer program stored on a computer-readable medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform any of the warning methods described above.

[0017] The beneficial effects of the technical solution provided by the embodiments of the present invention are as follows: This application achieves accurate and reliable judgment of passenger safety status by fusing passenger position information with the trigger signal of the target vehicle. Based on this, intuitive warning information is used to remind the driver and passengers of their safety status, thus constructing an efficient and low-burden two-way interaction mechanism between driver and passenger. This mechanism ensures that the boarding and alighting needs of elderly or mobility-impaired passengers are communicated promptly and accurately without increasing the driver's additional operational burden, reducing passenger safety risks caused by poor driver-passenger communication. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart of an early warning method according to an embodiment of this application is shown; Figure 2 A flowchart illustrating step S200 of an embodiment of this application is shown; Figure 3 A flowchart illustrating step S210 of an embodiment of this application is shown; Figure 4 This illustration shows yet another flowchart of the early warning method according to an embodiment of this application; Figure 5 A flowchart illustrating step S100 of an embodiment of this application is shown; Figure 6 A schematic diagram of the structure of the early warning device according to an embodiment of this application is shown.

[0020] Explanation of reference numerals in the attached figures: Early warning device 1; vehicle identification module 11; pose generation module 12; safety status determination module 13; command sending module 14. Detailed Implementation

[0021] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. Various examples are provided by way of explanation and not by way of limitation. Indeed, those skilled in the art will recognize that modifications and variations can be made to the invention without departing from its scope or spirit. For example, a feature represented or described as part of one embodiment may be used in another embodiment to produce yet another embodiment. Therefore, it is desirable that the present invention encompass such modifications and variations falling within the scope of the appended claims and their equivalents.

[0022] The accompanying drawings illustrate one or more examples of the invention. The detailed description uses numerals and letters to refer to features in the drawings. Similar or analogous reference numerals in the drawings and description have been used to refer to similar or analogous parts of the invention. As used herein, the terms “first,” “second,” “third,” and “fourth,” etc., are used interchangeably to distinguish one component from another and are not intended to indicate the location or importance of a single component.

[0023] The accompanying drawings in the following embodiments clearly and completely describe the technical solutions of this application. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] According to one aspect of this application, a passenger safety monitoring and early warning method is provided, executed by a mobile terminal worn by the passenger. The mobile terminal is communicatively connected to an in-vehicle fixed terminal, and the in-vehicle fixed terminal corresponds one-to-one with the vehicle. Figure 1 A flowchart illustrating an embodiment of the early warning method of this application is shown. According to an example embodiment, such as… Figure 1 As shown, the warning method includes steps S100-S400. Exemplarily, this warning method is performed by a warning device. For example, the warning device is a hardware or firmware unit with satellite positioning, inertial measurement, wireless communication, and haptic feedback functions. For example, the warning device is a mobile terminal worn by a passenger. Exemplarily, the mobile terminal is in the style of a badge and is worn on the passenger's clothing using a magnetic snap fastener.

[0025] For example, the vehicle is a bus, and each bus is equipped with a fixed onboard terminal that corresponds one-to-one with the mobile terminal. Although the flowchart shows the logical sequence of the warning method, under default conditions, the steps shown or described may be executed in a different order than that shown in the flowchart.

[0026] In step S100, the target vehicle is determined from the vehicles corresponding to multiple vehicle-mounted fixed terminals based on the route prior information, the status information of the mobile terminal, and the broadcast signal of the vehicle-mounted fixed terminal. The route prior information includes the route geometry and station information pre-stored in the mobile terminal.

[0027] In the embodiments of this application, the mobile terminal continuously scans for Bluetooth Low Energy (BLE) broadcast signals emitted by the fixed terminals on surrounding buses. Each fixed terminal broadcasts a message containing information such as route identifier, vehicle identifier, transmit power (TxPower), and real-time received signal strength (RSSI) at a period of 20-200ms. For example, the mobile terminal's status information includes its own Global Navigation Satellite System (GNSS) position, heading, speed, and timestamp. Prior route information is pre-stored in the mobile terminal, including the geographic geometry of each bus route in the pre-stored bus routes, as well as the latitude and longitude, stopping direction, and timing of all stops along the route.

[0028] For example, the target vehicle is the bus that the mobile terminal ultimately locks onto and confirms from multiple surrounding buses, the bus the passenger is currently about to board or has already boarded. Target vehicle identification is not based on a single broadcast frame, but rather by aggregating multiple broadcast samples from the BLE broadcast signal within a sliding time window (e.g., the most recent 2-5 seconds). The mobile terminal estimates the distance between itself and the bus that issued the signal based on the received BLE broadcast signal strength. If the estimated distance exceeds a preset range (e.g., 200-250 m), the bus is directly eliminated and not added to the candidate list. In this way, the mobile terminal filters out multiple candidate buses, i.e., candidate vehicles. The mobile terminal then selects the target vehicle from the candidate vehicles. First, the mobile terminal estimates the instantaneous distance di between the mobile terminal and each candidate vehicle based on the Received Signal Strength Indicator (RSSI) and a logarithmic path loss model. k represents the actual physical distance between the mobile terminal and the i-th candidate vehicle at time k. The formula for calculating the received signal strength of the i-th candidate vehicle received by the mobile terminal at time k is: Formula (1) Where RSSIi,k is the received signal strength (in dBm) of the i-th candidate vehicle received by the mobile terminal at time k, ρ0 is the reference received signal strength at a reference distance d0 from the transmitter of the i-th candidate vehicle, n is the path loss exponent, and n is an environmental factor representing the rate attenuation of the received signal strength with increasing distance. εi,k is the noise term. Based on the calculated di... k calculates the observation azimuth pointing to the candidate vehicle and compares it with the tangential direction of the route where the candidate vehicle is located to determine the consistency between the candidate vehicle and the pre-stored route in the prior information of the route. Finally, di is calculated. The orthogonal projection distance from k to the pre-stored line polyline in the prior information of the line is used to evaluate di. k matches the pre-stored line orientation. The mobile terminal determines the compatibility of di with the pre-stored line orientation. The target vehicles were selected based on the analysis of k, RSSIi,k elevation, line consistency, and azimuth compatibility.

[0029] In step S200, the passenger's pose information is generated based on the inertial measurement data of the mobile terminal, the satellite observation data, and the route and station constraint information corresponding to the target vehicle.

[0030] In the embodiments of this application, the route and station constraint information corresponding to the target vehicle, that is, after locking the target vehicle in step S100, the geometric data, station location sequence and station stopping side of the route are loaded from the pre-stored route prior information.

[0031] For example, firstly, the mobile terminal fuses inertial measurement data and satellite observation data to generate fused positioning information for the passenger. The fused positioning information is real-time status information including the passenger's position, velocity, and attitude, calculated by the mobile terminal after deep fusion of inertial measurement data and satellite observation data that has undergone anti-multipath adaptive weighting processing.

[0032] Secondly, route and station constraint information refers to the set of geographic information related to the target vehicle's operating route, retrieved from locally stored prior route information after the mobile terminal successfully locks onto the target vehicle. The mobile terminal uses the route and station constraint information as a strong external constraint to correct and optimize the fused positioning information, ultimately obtaining the passenger's pose information.

[0033] In step S300, the passenger's safety status is determined based on the trigger signal and pose information of the on-board fixed terminal corresponding to the target vehicle.

[0034] In the embodiments of this application, the trigger signal is a digital ride intention reminder signal issued by the vehicle-mounted fixed terminal. The mobile terminal continuously receives the trigger signal from the target vehicle, and at the same time, combines it with the passenger's pose information generated in step S200 to perform a comprehensive status determination to determine the passenger's safety status.

[0035] For example, the safety status of the passenger to be determined includes, but is not limited to, the safety statuses such as "sitting / holding on", "standing up / walking", "arriving at the rear door area" and "accidental touch / no touch".

[0036] For example, the trigger signal is generated by pressing a trigger button on the side of the target vehicle seat. The passenger sends the trigger signal to the vehicle-mounted fixed terminal by physically pressing the trigger button, and the mobile terminal obtains the trigger signal from the vehicle-mounted fixed terminal.

[0037] For example, the trigger signal includes passenger travel request, button number, seat number, timestamp, and target vehicle ID. The in-vehicle fixed terminal sends the trigger signal to the mobile terminal. When the mobile terminal detects that the passenger's pose information shows the passenger's position coincides with the seat area of ​​the target vehicle, and the passenger is in a low-dynamic, stable state (e.g., very small acceleration variance), and the in-vehicle fixed terminal transmits the corresponding seat trigger signal, then the system confirms that the passenger is in a safe "seated and ready" state. Conversely, if the pose information shows that the passenger's position is undergoing continuous changes (e.g., moving towards the rear door area, approaching the rear door area, etc.), or if the passenger travel request included in the trigger signal indicates that the passenger is in a "needs to get off" state, then the passenger is determined to be in an unsafe state, and the driver needs to extend the stop time to ensure passenger safety.

[0038] Mobile terminals avoid misjudgments based on a single information source through a fusion judgment mechanism. For example, if only the seat button is triggered, but the posture information shows that the seat is unoccupied, the mobile terminal may determine it as a "mistaken touch"; if the posture information shows that the passenger has reached the rear door area, even if the passenger's disembarkation request has not been triggered, the mobile terminal may generate a disembarkation request signal based on the passenger's behavior of lingering at the rear door for a long time.

[0039] In step S400, a prompting command is sent to the vehicle-mounted fixed terminal corresponding to the target vehicle based on the passenger's safety status, so that the vehicle-mounted fixed terminal outputs the corresponding warning information.

[0040] In the embodiments of this application, the mobile terminal generates a corresponding prompt instruction based on the passenger's safety status determined in step S300, and sends it to the vehicle-mounted fixed terminal of the target vehicle based on a secure communication protocol. For example, after receiving the prompt instruction, the vehicle-mounted fixed terminal outputs corresponding warning information to the driver through an indicator light panel and / or a buzzer set on the vehicle-mounted fixed terminal.

[0041] For example, a prompt command is a digital control command sent by the mobile terminal to the in-vehicle fixed terminal after fusion judgment. It transforms the abstract safety status of passengers (e.g., passengers have arrived at the door and are waiting to get off) into specific hardware actions (e.g., "red light stays on"). Warning information refers to the intuitive signals that the in-vehicle fixed terminal outputs to the driver through visual (indicator lights) and / or audible (buzzer) means after receiving the prompt command from the mobile terminal, reflecting the safety status and specific needs of the passengers in the vehicle.

[0042] For example, using visual (indicator) indicators, the control panel of the vehicle-mounted terminal is equipped with a three-color indicator light. When the mobile terminal determines that the passenger is "seat-ready," it sends a prompt command to the vehicle-mounted terminal, controlling the yellow light on the control panel to flash (indicating the seat button has been triggered and the passenger has confirmed safety), or the yellow light to remain on (indicating the passenger needs to extend their disembarkation time). When the mobile terminal determines that the passenger needs to disembark, it sends a prompt command, controlling the red light on the control panel to flash (indicating the passenger wearing a badge has boarded or is moving towards the door and requesting a delay), or the red light to remain on (indicating the passenger wearing a badge has reached the door area and still needs a delay). If the mobile terminal is online and has no pending requests, the green light remains on. This warning information based on different modes (flashing / solid) of the three-color indicator lights can intuitively and clearly inform the driver of the current safety status and specific needs of the passengers in the vehicle, without requiring the driver to continuously observe the subtle movements of each passenger, thereby improving the accuracy and reliability of passenger safety monitoring.

[0043] Optionally, the mobile terminal can also interact with passengers through haptic feedback (such as vibration). For example, after locking the target vehicle in step S100, the mobile terminal will remind the passenger that the target vehicle is about to arrive at the station through a short vibration, so that the passenger can prepare in advance; when the passenger successfully triggers the alighting request, the mobile terminal will confirm that the command has been successfully sent through vibration.

[0044] Through the above embodiments, this application achieves accurate and reliable determination of passenger safety status by fusing passenger position information with the trigger signal of the target vehicle. Based on this, intuitive warning information is used to remind the driver and passengers of their safety status, thereby constructing an efficient and low-burden two-way interaction mechanism between driver and passenger. This mechanism, without increasing the driver's additional operational burden, ensures that the boarding and alighting needs of elderly or mobility-impaired passengers can be communicated promptly and accurately, reducing passenger safety risks caused by poor driver-passenger communication.

[0045] Figure 2 A flowchart illustrating step S200 of an embodiment of this application is shown. According to an example embodiment, such as... Figure 2 As shown, step S200 includes steps S210-S220.

[0046] In step S210, fused positioning information is generated based on inertial measurement data and satellite observation data.

[0047] In the embodiments of this application, firstly, the mobile terminal estimates the state vector in a geocentric coordinate system using a filter. Exemplarily, the filter is a Kalman filter. Inertial measurement data is collected by an IMU (Inertial Measurement Unit). Satellite observation data is the positioning information of the mobile terminal obtained via satellite. For example, a mobile terminal is equipped with a Global Navigation Satellite System (GNSS). The state vector is a set of mathematical quantities describing the complete motion state of the mobile terminal at a given moment, including the mobile terminal's position, velocity, quaternion attitude, IMU bias, receiver clock bias, and receiver clock drift. The receiver clock bias is the GNSS receiver clock bias, and the receiver clock drift is the frequency error of the GNSS receiver clock. The passenger's state vector is equivalent to the mobile terminal's state vector. The mathematical formula for the passenger's state vector is as follows: Formula (2) Where, p k v represents the passenger's position in the geocentric coordinate system at time k. k Let q represent the passenger's speed at time k. k Let q represent the quaternion attitude of the passenger at time k. k Used to indicate the orientation of a passenger's body. For accelerometer deviation, This is due to the deviation of the gyroscope. For receiver clock bias, This is for receiver clock drift. After calculation using the above formula (2), the mobile terminal obtains the passenger's state vector. Location information is fused using the passenger's state vector x. k p in k v k and q k It is represented by three components.

[0048] Secondly, the mobile terminal considers the complex dynamic characteristics inside the bus compartment and the urban multipath effect, analyzing parameters such as the signal-to-noise ratio, carrier-to-noise ratio, and multipath indicator of satellite signals in real time. Combined with passenger attitude information and state vectors provided by the IMU, it assesses the reliability of the satellite signals and adjusts the observation weights or introduces compensation factors during the filtering process to suppress positional deviations introduced by multipath interference. The formula for calculating the predicted GNSS pseudorange of the i-th satellite at time k is as follows: Formula (3) in, Let s be the predicted GNSS pseudorange of the i-th satellite at time k. i,kLet T be the three-dimensional position coordinates of the i-th satellite in the Earth-centered Earth-fixed coordinate system, where c represents the speed of light, and T is the distance from T to T. i,k For tropospheric delay, I i,k This is the ionospheric delay. The measurement residual of the GNSS pseudorange is the difference between the actual observed value and the predicted observed value mentioned above. The actual observed value is the GNSS pseudorange actually measured by the GNSS receiver.

[0049] The formula for calculating the GNSS Doppler prediction value of the i-th satellite at time k is as follows: +c Formula (4) in, Let v be the GNSS Doppler prediction value of the i-th satellite at time k. k v represents the speed of the GNSS receiver in the mobile terminal. s,i,k Let x be the velocity of the i-th satellite. The residual of the predicted Doppler of the i-th satellite at time k is the difference between the actual GNSS Doppler observation and the GNSS Doppler prediction. According to the fusion calculation process of the above formulas (1)-(4), the mobile terminal calculates x. k p in k v k and q k The three components are then used to obtain fused positioning information.

[0050] In step S220, the fused positioning information is adjusted according to the route and station constraint information corresponding to the target vehicle to generate the passenger's real-time positioning and attitude information as pose information.

[0051] In the embodiments of this application, the route and station constraint information corresponding to the target vehicle is a set of geographic information related to the route of the target vehicle, retrieved from the locally pre-stored route prior information after the mobile terminal successfully locks the target vehicle. This information acts as an external strong constraint condition in the subsequent positioning process, used to correct and optimize the fused positioning information obtained in step S210. The route and station constraint information includes the broken line of the bus route.

[0052] For example, when a bus stops at a station, theoretically the passengers' speed relative to the ground should be zero. Therefore, at this time, the mobile terminal will... k Set it to zero, thereby resetting the velocity drift of the IMU integral accumulation. Additionally, the mobile terminal will... k Set the station coordinates of the docking station, which are pre-stored coordinates on the mobile terminal.

[0053] For example, the mobile terminal continuously monitors its own acceleration via the IMU and determines that the measured acceleration approaches gravitational acceleration, indicating that the bus and passengers are stationary. Additionally, the mobile terminal can also continuously monitor its own angular velocity via the IMU, determining that the measured angular velocity approaches zero, indicating that the bus and passengers are stationary. When both conditions are met simultaneously and for a preset time period (e.g., 1-2 seconds), the mobile terminal determines that the passengers are at zero speed, at which point the mobile terminal will... k Set p to zero k Set the coordinates of the stop to be used.

[0054] For example, when the mobile terminal determines that the target vehicle is in motion, it adjusts the fused positioning information based on the projection distance error of the fused positioning information on a preset route path. During vehicle movement, the mobile terminal orthogonally projects the passenger's position calculated from the current fused positioning information onto the bus's route curve, calculating the lateral projection distance error. This lateral projection distance error constrains the lateral sway of the trajectory, preventing the passenger's trajectory calculated by the IMU from deviating from the actual route due to drift, thus overcoming the problem of easy deviation from the route when relying solely on IMU or GNSS signals is weak.

[0055] Through the above embodiments, this application first fuses the passenger's inertial measurement data with satellite observation data to obtain the passenger's fused positioning information, and then adjusts the fused positioning information according to the route and station constraint information corresponding to the target vehicle to obtain the passenger's real-time positioning and attitude information as pose information. The strong constraint of the route and station constraint information utilizes the industry characteristics of "fixed routes and fixed stations" of buses, and uses the pre-stored route and station prior information as an external reference, which effectively suppresses the inertial drift of the IMU in the harsh environment of the bus compartment, and ultimately ensures that the system can stably output high-precision pose information that meets the requirements of safety status determination.

[0056] Figure 3 A flowchart illustrating step S210 of an embodiment of this application is shown. According to an example embodiment, such as... Figure 3 As shown, step S210 includes steps S211-S212.

[0057] In step S211, the adaptive weights of the satellite observation data are determined based on the satellite signal quality corresponding to the satellite observation data.

[0058] In the embodiments of this application, the mobile terminal calculates the robust weight of each satellite by analyzing the strength of the satellite signal, the degree of urban multipath interference, and the measurement residual. The robust weight of the i-th satellite is used to characterize the adaptive weight of the satellite observation data, and the calculation formula is as follows: Formula (5) Formula (6) in, For the robust weights of the i-th satellite, Let r be the adaptive standard deviation of the i-th satellite. i denoted as the residual, v is the scaling factor, and v is a constant with a positive value. Let be the carrier-to-noise ratio variance of the i-th satellite, calculated as shown in formula (7). The multipath exponential gain is calculated using the formula shown in formula (8): Formula (7) Formula (8) in, For reference variance, (C / N0) i Let (C / N0)ref be the carrier-to-noise ratio of the i-th satellite, and k be the reference carrier-to-noise ratio. mp This is the multipath gain coefficient. Let be the residual variance of the i-th satellite. Reference residual variance. Adaptive observation covariance R i The calculation formula is shown in formula (9), where Ri is the final covariance used by the i-th satellite in the Kalman filter update step. The larger the value of Ri, the less reliable the observation of the i-th satellite is, and the lower its weight in the filter. ϵ is the minimum weight threshold.

[0059] Formula (9) The mobile terminal uses formulas (5) to (9) to adjust the adaptive weight of the satellite observation data according to the satellite signal quality corresponding to the satellite observation data.

[0060] In step S212, inertial measurement data and satellite observation data after adaptive weighting are fused to generate fused positioning information.

[0061] In the embodiments of this application, the process of fusing inertial measurement data and satellite observation data has been described in detail in step S210, and will not be repeated here.

[0062] Through the above embodiments, this application introduces an adaptive observation covariance adjustment mechanism based on satellite signal quality, which enables dynamic identification and downweighting of interfered GNSS observations in cities and bus carriages where multipath effects are severe, thereby improving the reliability and accuracy of fused positioning information.

[0063] Figure 4This illustration shows another flowchart of the early warning method according to an embodiment of this application. According to the example embodiment, such as... Figure 4 As shown, the early warning method includes steps S500-S600.

[0064] In step S500, the compensation factor for the satellite observation data is determined based on the satellite signal quality.

[0065] In the embodiments of this application, the compensation factor is an error correction amount assessed based on the satellite signal quality, used to directly correct the interfered satellite observations. For example, when a mobile terminal detects that the signal quality of a certain satellite is consistently poor, but its geometric distribution is crucial for positioning calculations, it will not simply discard it completely. Instead, it will determine a corresponding compensation factor based on the degree of signal quality degradation of the satellite to correct the errors in satellite observation data caused by multipath interference.

[0066] In step S600, inertial measurement data and satellite observation data corrected by compensation factors are fused to generate fused positioning information.

[0067] In the embodiments of this application, the process of fusing inertial measurement data and satellite observation data has been described in detail in step S210, and will not be repeated here.

[0068] Through the above embodiments, this application provides another effective technical approach for multipath suppression by introducing a compensation factor to directly correct the interfered satellite observations. Combined with the adaptive weighting method, it constitutes a complete multipath response strategy, improving the accuracy and reliability of fusing positioning data in signal-constrained environments.

[0069] For example, in step S220, adjusting the fused positioning information based on the route and station constraint information corresponding to the target vehicle includes at least one of the following methods: When it is determined that the target vehicle is in a parked state, the fused positioning information is adjusted according to the location information of the current station corresponding to the target vehicle.

[0070] In the embodiments of this application, in step S220, when the bus stops at the station, the mobile terminal will p k The coordinates of the stop are set as the station coordinates, and then the fused positioning information is adjusted according to the current station location information corresponding to the target vehicle. This has been described in detail and will not be repeated here.

[0071] When it is determined that the target vehicle is in motion, the fused positioning information is adjusted according to the projection distance error of the fused positioning information on the preset route path.

[0072] In the embodiments of this application, the prior route information includes a preset route path. The mobile terminal adjusts the fused positioning information based on the projection distance error of the fused positioning information on the preset route path. During vehicle operation, the mobile terminal orthogonally projects the passenger's position calculated from the current fused positioning information onto the bus's route polygonal line and calculates the lateral projection distance error. The lateral projection distance error constrains the lateral sway of the trajectory, preventing the passenger's trajectory calculated by the IMU from deviating from the actual route due to drift.

[0073] When the target vehicle is determined to be parked, the speed observation value is reset to zero to adjust the fused positioning information.

[0074] In embodiments of this application, for example, when a bus stops at a station, theoretically the passenger's speed relative to the ground should be zero. Therefore, at this time, the mobile terminal will... k Set to zero.

[0075] Through the above embodiments, this application constructs a multi-level strongly constrained optimization system by introducing route and station constraint information. Specifically, when the vehicle stops at a station, the precise coordinates of the station are used to strongly correct the passenger position, eliminating the position drift accumulated by the IMU over a long period of integration; during the vehicle's movement, the pre-stored route path is used to apply lateral constraints to the passenger position, continuously suppressing the trajectory from deviating from the actual route; simultaneously, the speed observation value is reset to zero at the moment of stopping, effectively resetting the speed drift of the IMU.

[0076] Figure 5 A flowchart illustrating step S100 of an embodiment of this application is shown. According to an example embodiment, such as... Figure 5 As shown, step S100 includes steps S110-S150.

[0077] In step S110, the line identifier is parsed from the broadcast signal.

[0078] In the embodiments of this application, after the mobile terminal receives the BLE broadcast signal from the vehicle-mounted fixed terminal, it first unpacks the BLE broadcast signal data packet according to a predefined protocol format. From the parsed payload, the line identifier is extracted.

[0079] In step S120, multiple candidate vehicles are selected from the vehicles corresponding to multiple vehicle-mounted fixed terminals based on the broadcast signal. The process of selecting multiple candidate vehicles has been described in detail in step S100 and will not be repeated here.

[0080] In step S130, the relative distance between the mobile terminal and the candidate vehicle is determined based on the received strength of the broadcast signal and the status information of the mobile terminal.

[0081] In the embodiments of this application, the relative distance between the mobile terminal and the candidate vehicle is d as described in step S100. i k In step S100, d has already been processed. i k The calculation process has been described in detail and will not be repeated here.

[0082] In step S140, the degree of matching between the candidate vehicle and the expected route is determined based on the prior information of the route identifier.

[0083] In embodiments of this application, this step aims to assess whether the candidate vehicle is operating normally on its claimed route. By evaluating the degree of matching between the candidate vehicle and the preset route path in the prior information of the route, the mobile terminal can effectively eliminate vehicles that, although broadcasting the correct route number, have actually deviated from the route or have abnormal location information, thereby improving the reliability of target recognition.

[0084] Mobile terminal at location p k The observation azimuth angle pointing towards the candidate vehicle is `wrap` is the angle merging function, used to limit the function's output to the range [-π, π). The tangential direction of the preset route is used as the desired heading direction of the candidate vehicle. The formula for calculating the azimuth difference of the candidate vehicle's heading direction is as follows: wrap [-π,π) ( - ) Formula (10) Among them, the azimuth difference in the direction of the candidate vehicle's front end. The smaller the absolute value, the more consistent the direction of the candidate vehicle with the preset route. The orientation difference of the candidate vehicle's head direction is used to represent the degree of matching between the candidate vehicle and the expected route.

[0085] In step S150, the target vehicle is determined from multiple candidate vehicles based on the relative distance and the degree of matching.

[0086] In the embodiments of this application, the mobile terminal evaluates the candidate vehicles based on the relative distance calculated in step S130 and the degree of matching evaluated in step S140. The evaluation formula is as follows: )+ i = user}+ (cos ) Formula (11) Formula (12) Formula (13) Where w1 is the distance weight, w2 is the RSSI weight, w3 is the line consistency weight, and w4 is the orientation consistency weight. To estimate the distance for RSSI, n is the path loss exponent, and τ d τ is the distance scaling factor. ρ Here, x represents the RSSI scaling factor, e represents the natural constant, and LineID is the RSSI scaling factor. i For candidate vehicle route numbers, LineID user Let be the user's desired route number, and 1{} be an exponential function. The mobile terminal calculates the candidate vehicle's score S using formulas (11)-(13). i,k S i,k The value range is from 0 to w 1+ w 2+ w 3+ Between w4, S i,k The larger the value, the higher the matching degree. The mobile terminal determines the matching degree based on the preset S value. i,k The target vehicle was determined by filtering the numerical range.

[0087] Through the above embodiments, this application achieves accurate identification of target buses in complex urban environments by constructing a multi-dimensional, multi-level comprehensive scoring and time-series fusion model. This provides passengers with ample time to prepare for arrival, while simultaneously improving the reliability and accuracy of the early warning system.

[0088] According to another aspect of this application, a passenger safety monitoring early warning device is also provided. The early warning device is worn by the passenger and is communicatively connected to an on-board fixed terminal, with each on-board fixed terminal corresponding to a vehicle. Figure 6 A schematic diagram of the structure of a warning device according to an embodiment of this application is shown. According to an example embodiment, such as… Figure 6 As shown, the early warning device 1 includes a vehicle identification module 11, a pose generation module 12, a safety status determination module 13, and a command sending module 14.

[0089] The vehicle identification module 11 is used to determine the target vehicle from the vehicles corresponding to multiple vehicle-mounted fixed terminals based on the route prior information, the status information of the warning device 1 and the broadcast signal of the vehicle-mounted fixed terminal. The route prior information includes the route geometry and station information pre-stored in the warning device 1.

[0090] In the embodiments of this application, the vehicle identification module 11 continuously scans for Bluetooth Low Energy (BLE) broadcast signals emitted by the fixed terminals on surrounding buses. Each fixed terminal broadcasts a message containing information such as route identification, vehicle identification, transmit power (TxPower), and real-time received signal strength (RSSI) at a period of 20-200ms. For example, the mobile terminal's status information includes its own Global Navigation Satellite System (GNSS) position, heading, speed, and timestamp. Prior route information is pre-stored in the mobile terminal, including the geographic geometry of each bus route in the pre-stored bus routes, as well as the latitude and longitude, stopping direction, and timing of all stops along the route.

[0091] For example, the target vehicle is the bus that the vehicle identification module 11 ultimately locks onto and confirms from multiple surrounding buses, and which the passenger is currently about to board or has already boarded. Target vehicle identification is not based on a single broadcast frame, but rather by aggregating multiple broadcast samples from the BLE broadcast signal within a sliding time window (e.g., the most recent 2-5 seconds). The vehicle identification module 11 estimates the distance between itself and the bus that emitted the signal based on the received BLE broadcast signal strength. If the estimated distance exceeds a preset range (e.g., 200-250 m), the bus is directly eliminated and not added to the candidate list. In this way, the vehicle identification module 11 filters out multiple candidate buses, i.e., candidate vehicles. The vehicle identification module 11 then selects the target vehicle from the candidate vehicles. First, the instantaneous distance di between the mobile terminal and each candidate vehicle is estimated based on the Received Signal Strength Indicator (RSSI) and a logarithmic path loss model. k represents the actual physical distance between the mobile terminal and the i-th candidate vehicle at time k. The formula for the RSSI-distance logarithmic path loss model is: Formula (1) Among them, RSSI i,k Let ρ be the received signal strength (in dBm) of the i-th candidate vehicle received by vehicle identification module 11 at time k, ρ0 be the reference received signal strength at a reference distance d0 from the transmitter of the i-th candidate vehicle, and n be the path loss exponent, an environmental factor representing the rate attenuation of the received signal strength with increasing distance. i,k This is the noise term. Based on the calculated d... i kThe observation azimuth pointing to the candidate vehicle is calculated and compared with the tangential direction of the route where the candidate vehicle is located to determine the consistency between the candidate vehicle and the pre-stored route in the prior information of the route. Finally, d is calculated. i k The orthogonal projection distance of the pre-stored line polyline in the prior information of the line is evaluated as d. i k Matching accuracy with pre-stored route location. Vehicle identification module 11 based on d i k RSSI i,k Target vehicles were selected through analysis of elevation, route consistency, and orientation compatibility.

[0092] The pose generation module 12 is used to generate passenger pose information based on the inertial measurement data and satellite observation data of the early warning device 1, as well as the route and station constraint information corresponding to the target vehicle.

[0093] First, the pose generation module 12 fuses inertial measurement data and satellite observation data to generate fused positioning information for the passenger. The fused positioning information is real-time status information including the passenger's position, velocity, and attitude, calculated by the mobile terminal through deep fusion of inertial measurement data and satellite observation data after anti-multipath adaptive weighting processing.

[0094] Secondly, the route and station constraint information refers to the set of geographic information related to the target vehicle's operating route, retrieved from the locally stored prior route information after the mobile terminal successfully locks onto the target vehicle. The pose generation module 12 uses the route and station constraint information as an external strong constraint condition to correct and optimize the fused positioning information, ultimately obtaining the passenger's pose information.

[0095] The safety status determination module 13 is used to determine the passenger's safety status based on the trigger signal and pose information of the on-board fixed terminal corresponding to the target vehicle.

[0096] In the embodiments of this application, the trigger signal is a digital ride intention reminder signal issued by the vehicle-mounted fixed terminal. The mobile terminal continuously receives the trigger signal from the target vehicle, and at the same time, combines it with the passenger's pose information generated in step S200 to perform a comprehensive status determination to determine the passenger's safety status.

[0097] For example, the safety status of the passenger to be determined includes, but is not limited to, the safety statuses such as "sitting / holding on", "standing up / walking", "arriving at the rear door area" and "accidental touch / no touch".

[0098] For example, the trigger signal is issued by pressing the trigger button on the side of the target vehicle seat. The passenger sends the trigger signal to the vehicle-mounted fixed terminal by physically pressing the trigger button, and the safety status determination module 13 obtains the trigger signal from the vehicle-mounted fixed terminal.

[0099] For example, the trigger signal includes passenger travel request, button number, seat number, timestamp, and target vehicle ID. The in-vehicle fixed terminal sends the trigger signal to the safety status determination module 13. When the safety status determination module 13 receives passenger pose information indicating that the passenger's position coincides with the seat area of ​​the target vehicle, and the passenger is in a low-dynamic stable state (e.g., with a small acceleration variance), and the in-vehicle fixed terminal transmits the corresponding seat trigger signal, the system confirms that the passenger is in a "seated and ready" safe state. Conversely, if the pose information indicates that the passenger's position is undergoing continuous changes (e.g., moving towards the rear door area, approaching the rear door area, etc.), or if the passenger travel request included in the trigger signal indicates that the passenger is in a "needs to get off" state, the system determines that the passenger is in an unsafe state, and the driver needs to extend the stop time to ensure passenger safety.

[0100] The safety status determination module 13 avoids misjudgment from a single information source through a fusion judgment mechanism. For example, if only the seat button is triggered, but the posture information shows that the seat is unoccupied, the mobile terminal may determine it as a "mistaken touch"; if the posture information shows that the passenger has reached the rear door area, even if the passenger's disembarkation request has not been triggered, the mobile terminal may generate a disembarkation request signal based on the passenger's prolonged stay at the rear door.

[0101] The instruction sending module 14 is used to send a prompt instruction to the vehicle-mounted fixed terminal corresponding to the target vehicle according to the passenger's safety status, so that the vehicle-mounted fixed terminal outputs the corresponding warning information.

[0102] In the embodiments of this application, the instruction sending module 14 generates a corresponding prompt instruction based on the passenger's safety status determined in step S300, and sends it to the vehicle-mounted fixed terminal of the target vehicle based on a secure communication protocol. For example, after receiving the prompt instruction, the vehicle-mounted fixed terminal outputs corresponding warning information to the driver through an indicator light panel and / or a buzzer set on the vehicle-mounted fixed terminal.

[0103] For example, a prompt instruction is a digital control command sent by the instruction sending module 14 to the vehicle-mounted fixed terminal after fusion judgment. It transforms the abstract safety status of passengers (e.g., passengers have arrived at the door and are waiting to get off) into specific hardware actions (e.g., "red light is always on"). Warning information refers to the intuitive signals that the vehicle-mounted fixed terminal outputs to the driver through visual (indicator light) and / or auditory (buzzer) means after receiving the prompt instruction from the mobile terminal, reflecting the safety status and specific needs of the passengers in the vehicle.

[0104] For example, using visual (indicator) indicators, the control panel of the vehicle-mounted terminal is equipped with a three-color indicator light. When the mobile terminal determines that the passenger is "seat-ready," the instruction sending module 14 sends a prompt instruction to the vehicle-mounted terminal, controlling the yellow light on the control panel to flash (indicating that the seat button has been triggered and the passenger has confirmed safety), or the yellow light to remain on (indicating that the passenger needs to extend their disembarkation time). When the mobile terminal determines that the passenger needs to disembark, the instruction sending module 14 sends a prompt instruction, controlling the red light on the control panel to flash (indicating that the passenger wearing the badge has boarded or is moving towards the door and requesting a delay), or the red light to remain on (indicating that the passenger wearing the badge has reached the door area and still needs a delay). If the instruction sending module 14 is online and there are no pending requests, the green light remains on. This warning information based on different modes (flashing / solid) of the three-color indicator lights can intuitively and clearly inform the driver of the current safety status and specific needs of the passengers in the vehicle, without requiring the driver to continuously observe the subtle movements of each passenger, thereby improving the accuracy and reliability of passenger safety monitoring.

[0105] Optionally, the mobile terminal may also interact with passengers through haptic feedback (such as vibration). For example, after locking the target vehicle in step S100, the mobile terminal will remind the passenger that the target vehicle is about to arrive at the station through a short vibration, so that the passenger can prepare in advance; when the passenger successfully triggers the alighting request, the mobile terminal will confirm that the command has been sent successfully through vibration.

[0106] Through the above embodiments, this application achieves accurate and reliable determination of passenger safety status by fusing passenger position information with the trigger signal of the target vehicle. Based on this, intuitive warning information is used to remind the driver and passengers of their safety status, thereby constructing an efficient and low-burden two-way interaction mechanism between driver and passenger. This mechanism, without increasing the driver's additional operational burden, ensures that the boarding and alighting needs of elderly or mobility-impaired passengers can be communicated promptly and accurately, reducing passenger safety risks caused by poor driver-passenger communication.

[0107] According to another aspect of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the warning methods described above.

[0108] According to another aspect of this application, a computer-readable medium having processor-executable non-volatile program code is also provided, the program code causing the processor to perform any of the warning methods described above.

[0109] According to another aspect of this application, a computer program product is also provided, including a computer program stored on a computer-readable medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform any of the warning methods described above.

[0110] As is known from common technical knowledge, this invention can be implemented through other embodiments that do not depart from its spirit or essential characteristics. Therefore, the disclosed embodiments described above are merely illustrative and not exhaustive. All modifications within the scope of this invention or its equivalents are included in this invention.

Claims

1. A passenger safety monitoring and early warning method, characterized in that, The warning method is executed by a mobile terminal worn by the passenger and communicatively connected to a vehicle-mounted fixed terminal, which corresponds one-to-one with each vehicle. Based on prior route information, the status information of the mobile terminal, and the broadcast signal of the vehicle-mounted fixed terminal, a target vehicle is determined from the vehicles corresponding to the multiple vehicle-mounted fixed terminals. The prior route information includes route geometry and station information pre-stored in the mobile terminal. The passenger's pose information is generated based on the inertial measurement data and satellite observation data of the mobile terminal, as well as the route and station constraint information corresponding to the target vehicle. The passenger's safety status is determined based on the trigger signal of the on-board fixed terminal corresponding to the target vehicle and the pose information. Based on the passenger's safety status, a prompt instruction is sent to the vehicle-mounted fixed terminal corresponding to the target vehicle, so that the vehicle-mounted fixed terminal outputs the corresponding warning information.

2. The early warning method according to claim 1, characterized in that, The step of generating the passenger's pose information based on the inertial measurement data and satellite observation data of the mobile terminal, as well as the route and station constraint information corresponding to the target vehicle, includes: Based on the inertial measurement data and the satellite observation data, fused positioning information is generated; The fused positioning information is adjusted according to the route and station constraint information corresponding to the target vehicle to generate the passenger's real-time positioning and posture information as the pose information.

3. The early warning method according to claim 2, characterized in that, The step of generating fused positioning information based on the inertial measurement data and the satellite observation data includes: Based on the satellite signal quality corresponding to the satellite observation data, an adaptive weight for the satellite observation data is determined; The fused positioning information is generated by fusing the inertial measurement data with the satellite observation data after adaptive weighting.

4. The early warning method according to claim 3, characterized in that, The method further includes: The compensation factor for the satellite observation data is determined based on the satellite signal quality. The fused positioning information is generated by fusing the inertial measurement data with the satellite observation data corrected by the compensation factor.

5. The early warning method according to claim 2, characterized in that, The adjustment of the fused positioning information based on the route and station constraint information corresponding to the target vehicle includes at least one of the following methods: When it is determined that the target vehicle is in a parked state, the fused positioning information is adjusted according to the location information of the current station corresponding to the target vehicle. When it is determined that the target vehicle is in motion, the fused positioning information is adjusted according to the projection distance error of the fused positioning information on the preset route path. When the target vehicle is determined to be parked, the speed observation value is reset to zero to adjust the fused positioning information.

6. The early warning method according to claim 1, characterized in that, The step of determining the target vehicle from the vehicles corresponding to multiple vehicle-mounted fixed terminals based on prior route information, the status information of the mobile terminal, and the broadcast signal of the vehicle-mounted fixed terminal includes: The line identifier is parsed from the broadcast signal; Based on the broadcast signal, multiple candidate vehicles are selected from the vehicles corresponding to the multiple vehicle-mounted fixed terminals; Based on the received strength of the broadcast signal and the status information of the mobile terminal, the relative distance between the mobile terminal and the candidate vehicle is determined. Based on the prior information of the route corresponding to the route identifier, the degree of matching between the candidate vehicle and the expected route is determined; The target vehicle is determined from the plurality of candidate vehicles based on the relative distance and the degree of matching.

7. A passenger safety monitoring and early warning device, characterized in that, The warning device is worn by the passenger and is communicatively connected to an on-board fixed terminal. Each on-board fixed terminal corresponds to a specific vehicle. The warning device includes: The vehicle identification module is used to determine the target vehicle from the vehicles corresponding to multiple vehicle-mounted fixed terminals based on route prior information, the status information of the warning device, and the broadcast signal of the vehicle-mounted fixed terminal. The route prior information includes route geometry and station information pre-stored in the warning device. The pose generation module is used to generate the passenger's pose information based on the inertial measurement data and satellite observation data of the early warning device and the route and station constraint information corresponding to the target vehicle. The safety status determination module is used to determine the safety status of the passenger based on the trigger signal of the on-board fixed terminal corresponding to the target vehicle and the pose information; The instruction sending module is used to send a prompt instruction to the vehicle-mounted fixed terminal corresponding to the target vehicle based on the safety status of the passenger, so that the vehicle-mounted fixed terminal outputs the corresponding warning information.

8. An electronic device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the early warning method according to any one of claims 1-6.

9. A computer-readable medium having processor-executable non-volatile program code, characterized in that, The program code causes the processor to execute the early warning method according to any one of claims 1-6.

10. A computer program product, characterized in that, It includes a computer program stored on a computer-readable medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the early warning method as described in any one of claims 1-6.