Uplink and downlink floor judgment method and device, electronic equipment and storage medium

Abstract

The invention relates to an ascending and descending floor judgment method and device, electronic equipment and a storage medium, and the method comprises the steps that current motion parameters of an elevator are obtained, the elevator operation state of the elevator is judged according to the current motion parameters, the elevator operation state is a motion state or a stop state, and the current motion parameters comprise the vertical axis acceleration; when the running state of the elevator is a moving state, the current air pressure change rate is obtained, and the floor where the elevator is located is judged according to the current air pressure change rate and the vertical axis acceleration; and when the elevator operation state is a stopping state, the current air pressure height is obtained, and the floor where the elevator is located is judged according to the current air pressure height and a preset floor Map. According to the scheme, accurate judgment of the elevator floor is achieved by fusing IMU and barometer data, an elevator control system does not need to be transformed, and the method has the advantages of being low in deployment cost, high in adaptability, high in precision, high in anti-drifting capacity and the like, supports self-calibration and online updating and can be widely applied to scenes such as security monitoring and intelligent elevator taking.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method, apparatus, electronic device, and storage medium for determining up and down floors. Background Technology

[0002] Existing solutions mostly rely on the on / off status of floor buttons, facial recognition outside the turnstile / car, or historical elevator usage to trigger elevator access or infer the floor, which has the following limitations: It requires users to operate it actively or rely on external turnstiles, which is not user-friendly for the elderly, children, and people carrying items, and poses a risk of contact.

[0003] It is difficult to accurately determine the floor where the "capture moment" is when the elevator is running across floors using only facial or behavioral data, which often requires additional data points or modifications to the elevator control system.

[0004] Barometer-based floor estimation is susceptible to temperature and humidity drift, resulting in large errors when directly converting floors, making it difficult to meet the needs of accurate image capture and security evidence collection.

[0005] Examples of related technologies: Contactless elevator access and destination floor inference based on facial recognition (historical behavior / reservation). Based on facial recognition and elevator control linkage using external call / car camera footage; Floor detection based on air pressure and time (exhibits drift and threshold dependence). Elevator state and position estimation based on acceleration / pressure fusion (non-intrusive, online learning floor map).

[0006] The existing technical problems include: How to accurately determine the floor level at the time of elevator up / down and capture in the absence of elevator protocol access; How to suppress the effects of air pressure drift, start-stop vibration, and short-term stillness on floor estimation; How to ensure the consistency between face capture quality and floor labeling in scenarios with multiple people, obstructions, and low light? Summary of the Invention

[0007] The technical problem to be solved by the present invention is to provide a method, device, electronic device and storage medium for determining the up and down floors, in order to solve at least one of the above-mentioned technical problems.

[0008] In a first aspect, the technical solution of the present invention to solve the above-mentioned technical problem is as follows: a method for determining the up and down floors, the method comprising: Obtain the current motion parameters of the elevator, and determine the elevator's operating status based on the current motion parameters. The elevator's operating status is either in motion or stopped. The current motion parameters include the vertical axis acceleration. When the elevator is in motion, the current air pressure change rate is obtained, and the floor where the elevator is located is determined based on the current air pressure change rate and the vertical axis acceleration. When the elevator is in a stopped state, the current air pressure altitude is obtained, and the floor where the elevator is located is determined based on the current air pressure altitude and the preset floor map.

[0009] The beneficial effects of this invention are: by combining vertical axis acceleration and the current rate of change of air pressure, the floor position of the elevator can be accurately determined while the elevator is in motion. Simultaneously, by matching the air pressure height during the stationary state with a preset floor map, stable and accurate floor determination is achieved. This method does not require connection to the elevator control system, has the characteristics of low deployment cost and strong applicability, and can be widely applied to various elevator scenarios to meet the needs of security monitoring, intelligent elevator operation, and other applications.

[0010] Based on the above technical solution, the present invention can be further improved as follows.

[0011] Furthermore, the above-mentioned acquisition of the elevator's current motion parameters includes: acquiring the elevator's current motion parameters through an inertial measurement unit installed on a shock-absorbing bracket on the top of the elevator car; the current motion parameters also include angular velocity.

[0012] Furthermore, the above-mentioned determination of the elevator's operating status based on current motion parameters includes: Obtain the current air pressure change rate corresponding to the elevator; Determine the elevator's operating status based on current motion parameters and current air pressure change rate.

[0013] Furthermore, the method also includes: When the elevator is in motion and its direction of travel does not change within a first set time, acquire an image inside the elevator that meets the quality requirements. When the elevator is in a stopped state and its height has not changed within a second set time, an image of the elevator that meets the quality requirements is acquired.

[0014] Furthermore, the method also includes: The acquired images and metadata that meet the quality requirements inside the elevator are packaged and asynchronously reported to the cloud platform via the MQTT protocol.

[0015] Furthermore, the metadata of the aforementioned elevator images that meet the quality requirements includes the timestamp of the image acquisition, the floor, the elevator's direction of travel, and the confidence level.

[0016] Secondly, in order to solve the above-mentioned technical problems, the present invention also provides an up and down floor determination system, including a processing module, as well as an inertial measurement unit and an atmospheric pressure sensor installed in the elevator car; An inertial measurement unit is used to acquire the elevator's current motion parameters, including the vertical axis acceleration. Atmospheric pressure sensor, used to obtain the atmospheric pressure value of the elevator in real time; The processing module is used to determine the elevator's operating status based on the current motion parameters, indicating whether the elevator is in motion or stopped; and to determine the current air pressure change rate and current air pressure altitude based on the real-time atmospheric pressure value. When the elevator is in motion, the current air pressure change rate is obtained, and the floor where the elevator is located is determined based on the current air pressure change rate and the vertical axis acceleration. When the elevator is in a stopped state, the current air pressure altitude is obtained, and the floor where the elevator is located is determined based on the current air pressure altitude and the preset floor map.

[0017] Thirdly, in order to solve the above-mentioned technical problems, the present invention also provides an up / down floor determination device, the device comprising: The acquisition module is used to acquire the current motion parameters of the elevator and determine the elevator's operating status based on the current motion parameters. The elevator's operating status is either in motion or stopped. The current motion parameters include the vertical axis acceleration. The first judgment module is used to obtain the current air pressure change rate and the elevator's vertical acceleration when the elevator is in motion, and to determine the floor the elevator is on based on the current air pressure change rate and the elevator's vertical acceleration; The second judgment module is used to obtain the current air pressure height when the elevator is in a stopped state, and to determine the floor where the elevator is located based on the current air pressure height and the preset floor map.

[0018] Fourthly, in order to solve the above-mentioned technical problems, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the up / down floor determination method of the present application.

[0019] Fifthly, in order to solve the above-mentioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the up / down floor determination method of the present application.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below.

[0022] Figure 1 A flowchart illustrating an up / down floor determination method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an up / down floor determination device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0023] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0024] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0025] The solution provided in this invention can be applied to any application scenario that requires up / down floor determination. The solution provided in this invention can be executed by any electronic device, such as a user's terminal device, including at least one of the following: smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, smart TV, or smart in-vehicle device.

[0026] This invention provides a possible implementation, such as... Figure 1 The diagram shows a flowchart of a method for determining up and down floors. This method can be executed by any electronic device, such as a terminal device, or jointly by a terminal device and a server. For ease of description, the method provided in this embodiment will be described below using a terminal device as the execution subject. Figure 1 The flowchart shown indicates that the method may include the following steps: S10, obtain the current motion parameters of the elevator, and determine the elevator running state based on the current motion parameters. The elevator running state is either in motion or stopped. The current motion parameters include the vertical axis acceleration. S20: When the elevator is in motion, obtain the current air pressure change rate, and determine the floor the elevator is on based on the current air pressure change rate and vertical axis acceleration; S30: When the elevator is in a stopped state, obtain the current air pressure altitude and determine the floor where the elevator is located based on the current air pressure altitude and the preset floor map.

[0027] The method of this invention, by combining vertical axis acceleration and the current rate of change of air pressure, can accurately determine the floor of the elevator while it is in motion. Simultaneously, it matches the air pressure height during the stationary state with a preset floor map to achieve stable and accurate floor determination. This method does not require integration with the elevator control system, and features low deployment cost and wide applicability. It can be widely applied to various elevator scenarios to meet the needs of security monitoring, intelligent elevator operation, and other applications.

[0028] The following specific embodiments further illustrate the solution of the present invention. In these embodiments, the pain point addressed by the present invention is: without modifying the elevator control system, to achieve accurate determination of up and down directions and precise floor marking during face capture by utilizing the fusion of gyroscope, barometer, and vision, while also considering robustness, low power consumption, and deployability. This solution borrows from the floor detection approach of barometer and time, but significantly suppresses drift errors through the fusion of rate of change threshold and IMU; it employs UKF / EKF + floor map to achieve robust cross-floor displacement estimation and floor alignment; and it introduces a face capture trigger mechanism with dual confirmation of direction and floor on the application side, achieving "floor knowledge upon capture," complementing existing technologies such as contactless elevator access / elevator control linkage.

[0029] Based on this, the up / down floor determination method provided in this embodiment may include the following steps: S10: Obtain the current motion parameters of the elevator, and determine the elevator's operating status based on the current motion parameters. The elevator's operating status is either in motion or stopped; where the motion status is either upward or downward. Optionally, obtaining the current motion parameters of the elevator includes: obtaining the current motion parameters of the elevator through an inertial measurement unit installed on a shock-absorbing bracket on the top of the elevator car, wherein the current motion parameters include vertical axis acceleration and angular velocity.

[0030] The inertial measurement unit is mounted on a shock-absorbing bracket to prevent resonance with the gantry crane.

[0031] An Inertial Measurement Unit (IMU) is an electronic device used to measure and report the three-axis attitude angles (or angular rates) and acceleration of an object. It typically consists of three orthogonally mounted accelerometers (for measuring acceleration along the three axes) and three orthogonally mounted gyroscopes (for measuring angular velocity about the three axes), providing real-time information on the object's motion in three-dimensional space, including acceleration, angular velocity, and attitude changes. In elevator systems, IMUs can be used to detect the elevator's operating status (such as upward, downward, start / stop vibrations, etc.) and use their measurement data to assist in accurate floor determination and direction of travel monitoring.

[0032] Optionally, determining the elevator's operating status based on current motion parameters includes: Obtain the current air pressure change rate corresponding to the elevator, where the current air pressure change rate refers to the amount of air pressure change per unit time; Determine the elevator's operating status based on current motion parameters and current air pressure change rate.

[0033] The current rate of change of atmospheric pressure is calculated by dividing the difference between continuously measured atmospheric pressure values ​​by the corresponding time interval. The specific calculation formula is as follows: in, This represents the atmospheric pressure value measured at the current moment. This represents the atmospheric pressure value measured at the previous moment of the current time. The timestamp represents the current moment. The timestamp representing the moment preceding the current moment. This represents the pressure difference between two measurements. This indicates the time interval between two measurements.

[0034] As an example, one way to determine the elevator's operating status based on current motion parameters and the current rate of change of air pressure is as follows: Motion State (A): When the elevator starts moving upward or downward from a certain floor, changes in vertical axis acceleration and air pressure change rate are detected, and the elevator is determined to be in motion state.

[0035] Stopped State (B): When the elevator reaches a certain floor and stops, the vertical axis acceleration and air pressure change rate are close to zero, and the door is open, the system determines that the elevator is in a stopped state.

[0036] Specifically, the motion state (A) is determined by whether the vertical axis acceleration (|a|>0.1g) or the current rate of change of air pressure (|vh|>0.2Pa / s) meets the threshold condition. The angular velocity (|ω|>5° / s) can be used as an auxiliary criterion to detect slight vibrations or rotations of the elevator.

[0037] Docked Status (B): Vertical axis acceleration (|a|<0.1g) and current air pressure change rate (|vh|<0.2Pa / s) are both close to zero. The door open / close signal (if connected) indicates that the elevator door is open, further confirming the docked status.

[0038] S20: When the elevator is in motion, obtain the current air pressure change rate, and determine the floor the elevator is on based on the current air pressure change rate and vertical axis acceleration; S30: When the elevator is in a stopped state, obtain the current air pressure altitude and determine the floor where the elevator is located based on the current air pressure altitude and the preset floor map.

[0039] The floor map is a discrete set containing barometric pressure information for each floor of the elevator, used to record and map the relationship between the elevator's stops and their corresponding barometric pressure. It is typically generated through a floor-by-floor learning process, recording the barometric pressure values ​​for each floor as the elevator stops and storing them as an ordered set. During elevator operation, the floor map is used to match the estimated current barometric pressure with the floor heights in the map to determine the specific floor the elevator is currently stopping at. This provides an accurate reference for floor determination and supports dynamic updates and anomaly detection of floor heights.

[0040] Alternatively, one way to determine the floor where the elevator is located based on the current rate of change of air pressure and vertical axis acceleration is as follows: The elevator's vertical velocity and displacement are estimated in real time by fusing the current rate of change of air pressure with the vertical acceleration (vertical axis acceleration) provided by the IMU (Inertial Measurement Unit) using either the Unscented Kalman Filter (UKF) or Extended Kalman Filter (EKF) algorithm. When the elevator is in motion, the current height of the elevator car can be determined based on the displacement. By comparing this height with discrete floor heights in the floor map, the current floor can be identified. Specifically, when the elevator's vertical velocity approaches zero and its height falls within the floor map's capture threshold (e.g., ±0.4–0.6 m), the current estimate is aligned to the nearest floor, thus determining the elevator's current floor, and the corresponding confidence level is also output.

[0041] If the height deviates from all floors and remains greater than Ns (e.g., 3–5s), an abnormal docking / location loss alarm will be generated.

[0042] When the elevator is in a stopped state, execute S30. Specifically, match the estimated current air pressure height with the floor map (set of floor heights). When the current air pressure height falls within the capture threshold range of a certain floor in the floor map, align the current height to that floor and output the floor determination result and confidence level.

[0043] Optionally, the method further includes: When the elevator is in motion and its direction of travel remains unchanged within a predetermined time period, it indicates stable direction. This means the elevator's direction (up or down) must remain consistent across multiple consecutive frames (e.g., 3 frames). This implies that the elevator has not experienced any directional changes during this period (e.g., suddenly changing from up to down). At this point, images of the elevator's interior that meet quality requirements can be acquired. When the elevator is in a stopped state and its height remains unchanged within a second set time period, it indicates that the floor is stable, meaning the estimated floor height remains stable over multiple consecutive frames. This typically indicates that the elevator has reached and stopped at a floor, or that there has been no significant change in floor height within a short period. At this point, images of the elevator interior that meet quality requirements can be acquired.

[0044] The combination of these two conditions ensures that the elevator is in a relatively stable operating state, making it easier to accurately determine the floor information at the moment of image capture. For example, if the elevator frequently starts and stops or vibrates during operation, causing unstable floor height estimation, or if its direction changes frequently, then the image capture conditions may not be met.

[0045] Specifically, meeting the quality requirements means detecting valid faces; more specifically, it means detecting face images that meet the quality requirements through the camera. This includes indicators such as facial sharpness, occlusion level, pose, and size. For example, facial sharpness must be above a certain threshold (e.g., 30 points), occlusion area must be less than a certain percentage (e.g., 30%), and facial size must be within a reasonable range (e.g., 80-240 pixels). These quality indicators ensure that the captured face images can be used for subsequent analysis and recognition.

[0046] In this application, a preset capture strategy is used to capture facial images. Specifically, ROIs are set for the door area and the middle part of the car, and facial quality scoring (clarity, brightness, occlusion, face size) and deduplication (cross-frame NMS) strategies are adopted. The output image + metadata (timestamp, floor, direction, confidence, camera ID, capture area) is output.

[0047] Optionally, the above-mentioned capture strategy also includes a cross-frame deduplication strategy, which uses the non-maximum suppression (NMS) algorithm to filter the overlapping areas of the same face in consecutive frames.

[0048] Optionally, the method further includes: The acquired images and metadata that meet the quality requirements inside the elevator are packaged and asynchronously reported to the cloud platform via the MQTT protocol.

[0049] Each frame of an image corresponds to metadata, which records the timestamp, floor, elevator direction of travel, and confidence level of the image.

[0050] The confidence level is a value between 0 and 1 (usually expressed as a percentage), used to measure the reliability of the system's determination of the current floor and direction. Specifically: High confidence (close to 1 or 100%): This indicates that the system is very confident in its determination of the current floor and direction, and the accuracy of the determination result is very high.

[0051] Low confidence (close to 0): This indicates that the system is not very certain about the current judgment result, and there may be errors or uncertainties.

[0052] Within a window where direction is confirmed and floor is stable, face capture is triggered. The captured image and metadata that meet the quality requirements are packaged and asynchronously reported to the cloud platform via the MQTT protocol, supporting multi-target tracking and duplicate removal.

[0053] Optionally, after determining the floor, the floor map is updated with the current air pressure height corresponding to that floor.

[0054] Optionally, the real-time acquired motion parameters, atmospheric pressure values, and images can be preprocessed, for example, by performing zero-drift calibration and filtering on the inertial measurement unit (IMU) and temperature compensation and smoothing on the atmospheric pressure values.

[0055] Optionally, when the elevator is in a stopped state, g-vector and barometric pressure reference self-calibration can be triggered; layer-by-layer learning of the map and online updates are supported. Triggering g-vector and barometric pressure reference self-calibration refers to an automatic calibration process executed after the elevator has stopped and remained stationary for a period of time. This process updates the gravitational acceleration vector (g-vector) and the barometric pressure reference altitude value to ensure the accuracy and stability of the sensor data. This process corrects errors caused by environmental changes (such as temperature and humidity) or sensor drift, ensuring the accuracy of subsequent floor determination and operational status monitoring. Supporting layer-by-layer learning of the map and online updates refers to the ability to automatically learn and generate a set of floor heights (floor map) during the elevator's stop-at-each-floor process, and to dynamically update the floor map based on actual operating conditions to adapt to changes in floor height (such as minor changes caused by building renovations or environmental factors), ensuring the accuracy of floor determination and the long-term stability of the system.

[0056] As an example, each time the vehicle stops and remains stationary for ≥2 seconds, a small correction to the g-vector and air pressure baseline is performed; the floor map is periodically reviewed, and if a change in floor height (renovation / remodeling) is detected, relearning is triggered.

[0057] Based on and Figure 1 Based on the same principle as the method shown, this embodiment of the invention also provides an up and down floor determination system, including a processing module (also known as an edge computing device), and an inertial measurement unit and an atmospheric pressure sensor installed in the elevator car; An inertial measurement unit is used to acquire the elevator's current motion parameters, including the vertical axis acceleration. Atmospheric pressure sensor, used to obtain the atmospheric pressure value of the elevator in real time; The processing module is used to determine the elevator's operating status based on the current motion parameters, indicating whether the elevator is in motion or stopped; and to determine the current air pressure change rate and current air pressure altitude based on the real-time atmospheric pressure value. When the elevator is in motion, the current air pressure change rate is obtained, and the floor where the elevator is located is determined based on the current air pressure change rate and the vertical axis acceleration. When the elevator is in a stopped state, the current air pressure altitude is obtained, and the floor where the elevator is located is determined based on the current air pressure altitude and the preset floor map.

[0058] The aforementioned up / down floor determination system also includes an image acquisition module (camera device) installed in the car, which can be a wide-angle / infrared supplementary light camera. The image acquisition module is specifically used for: When the elevator is in motion and its direction of travel does not change within a first set time, acquire an image inside the elevator that meets the quality requirements. When the elevator is in a stopped state and its height has not changed within a second set time, an image of the elevator that meets the quality requirements is acquired.

[0059] The aforementioned up and down floor determination system also includes an edge computing box installed in the elevator car, which is used to package and cache the acquired images and metadata that meet the quality requirements inside the elevator, and asynchronously report them to the cloud platform via the MQTT protocol.

[0060] The aforementioned processing module is specifically used for: determining the elevator's upward / downward / stopping direction based on the vertical acceleration and angular velocity output by the three-axis gyroscope / accelerometer and the rate of change of atmospheric pressure; estimating the car's displacement based on the fusion of the rate of change of atmospheric pressure and vertical acceleration, and determining the floor at the moment of capture by combining the floor height set; and triggering the camera device to capture the face after the direction and floor are determined, and outputting capture metadata including timestamp, floor, direction, and confidence level.

[0061] In the system described in this application, the installation and initialization of each piece of hardware includes: The IMU and barometer (for collecting atmospheric pressure values) are fixed to the vibration-damping bracket on the top of the car to avoid resonance with the door operator; the camera faces the door area and the middle of the car to ensure coverage of a height of 1.2–2.0 m; and the door magnetic sensor / floor button light signal is connected. After the equipment is powered on, it completes g-vector initialization and atmospheric pressure reference altitude acquisition within ≥2 seconds of being stationary; if floor-by-floor stops are detected, floor map learning is automatically performed (recording the displacement between adjacent stops to generate a discrete set of floor heights).

[0062] The IMU's three-axis acceleration and angular velocity are collected in real time and decomposed into the vertical direction; when the door is detected to be closed and the vertical acceleration shows a continuous non-zero trend, it enters the "motion state".

[0063] Calculate the rate of change of air pressure vh; if |vh| is lower than the drift threshold T_drift (e.g., 0.3–0.5 Pa / s), it is determined to be drift, and the drift data is replaced with the current air pressure height; if |vh| is higher than the threshold, it is determined to be cross-floor movement, and the floor estimation process is initiated.

[0064] Specifically, the IMU should be a low-noise, high-stability MEMS sensor (such as the Bosch BMI088) supporting sampling rates above 200Hz. The barometer should be a high-precision, low-drift sensor (such as the Bosch BMP390) ​​with a resolution ≤0.01hPa. The camera should be a 1080P resolution, 120° wide-angle webcam with infrared illumination (such as the Hikvision DS-2CD3346WD-I). The edge computing box should have a computing power ≥4 TOPS (such as the NVIDIA Jetson Nano / Xavier NX) supporting concurrent multi-channel data processing.

[0065] Combine the vertical acceleration sign with the air pressure change trend (upward air pressure decreases, downward air pressure increases) to confirm upward / downward movement, and output the direction event when the door opens.

[0066] Optionally, the aforementioned processing modules may include a direction determination module, a barometric altitude calculation and drift suppression module, a floor map learning module, an event-triggered capture and face quality assessment module, and a floor labeling and reporting module. These modules work together to achieve accurate elevator status perception and intelligent capture functions. Specifically, the direction determination module determines the elevator's operating status based on current motion parameters. The barometric altitude calculation and drift suppression module determines the current barometric altitude based on real-time atmospheric pressure values, using the rate of change of air pressure to detect and suppress drift, ensuring the accuracy of altitude estimation. Simultaneously, this barometric altitude calculation and drift suppression module matches the calculated current barometric altitude with the floor height set (floor map) to determine the elevator's stopping floor and triggers self-calibration and anomaly alarms when necessary, providing reliable altitude information support for elevator floor determination and operating status monitoring.

[0067] The floor map learning module automatically learns and generates a set of floor heights during the elevator's stop-at-each-floor process, recording the air pressure height differences between adjacent floors to form a discrete floor height mapping relationship. By continuously updating the floor map, this module can adapt to changes in floor height (such as minor changes caused by building renovations or environmental factors), providing an accurate reference benchmark for elevator floor determination and ensuring that the system can achieve accurate floor identification and height alignment in different scenarios.

[0068] The event-triggered capture and face quality assessment module triggers face capture when the elevator's direction of travel is confirmed and the floor level is stable. It evaluates face image clarity, occlusion level, pose, and size, selecting high-quality face images that meet requirements for saving and annotation. Duplicate captures are removed to ensure accuracy and reliability, providing high-quality data support for subsequent security monitoring, behavior analysis, and other applications. This is identical to the image acquisition module. The floor annotation and reporting module, similar to the edge computing box, associates captured face images with corresponding floor information, timestamps, direction of travel, and confidence levels. The annotated data is then asynchronously uploaded to the cloud platform via a network protocol (such as MQTT), enabling accurate floor annotation and efficient transmission of face capture data in elevator scenarios. This provides accurate spatiotemporal information support for subsequent security monitoring, data analysis, and intelligent applications.

[0069] Optionally, the above processing module is also used to: initialize the gravitational acceleration vector and the air pressure reference altitude when the elevator stops and is stationary, and periodically make small corrections during operation.

[0070] Optionally, the above-mentioned processing module is also used to distinguish between the elevator’s cross-floor movement and air pressure drift based on the air pressure change rate threshold. That is, when the air pressure change rate exceeds the preset threshold, the elevator is judged to be in cross-floor movement state, while when the air pressure change rate is lower than the threshold, it is judged to be air pressure drift, so as to take corresponding processing strategies to ensure the accuracy of floor determination and the stability of the system.

[0071] Optionally, the aforementioned processing module is also used to enable displacement estimation using IMU integration and air pressure fusion during the cross-floor movement phase, estimating the elevator's vertical velocity and displacement. During the drift phase, the drift data is replaced with the current air pressure height, thereby suppressing the impact of drift on floor determination and ensuring that the system can stably and accurately estimate the elevator's displacement and floor position under different operating conditions. The drift phase refers to the phenomenon where the air pressure sensor output data deviates from the true value due to environmental factors (such as changes in temperature and humidity) or the characteristics of the sensor itself. In this state, the air pressure change rate is low and insufficient to reflect the elevator's cross-floor movement, instead manifesting as slow, non-motion-related air pressure fluctuations.

[0072] Optionally, the above processing module automatically learns and updates the set of floor heights during the floor-by-floor docking process to adapt to changes in floor height.

[0073] Optionally, in this application, the acquisition of various data must be time-synchronized: the IMU, barometer, camera, and door sensor use a unified clock source (such as PTP / hardware timer) to ensure event alignment.

[0074] Optionally, in this application, the atmospheric pressure value can be sampled using a moving average / median filter; the IMU uses a Kalman filter for noise reduction; and the door magnetic jitter is debounced using a state machine.

[0075] Optionally, the solution in this application locally saves captured images to disk with metadata; asynchronously reports anomalies and events to the platform; and supports offline caching and resume interrupted downloads.

[0076] Optionally, in this application, the target floor or door-opening hold instruction is issued after authorization confirmation.

[0077] Optionally, in this application, multiple cameras are synchronized with the same time and floor map, supporting cross-elevator trajectory stitching and abnormal personnel tracking.

[0078] Optionally, the proposed solution provides on-demand maintenance early warning based on the horizontal vibration baseline and start-stop anomalies.

[0079] Optionally, the solution in this application constructs a user elevator behavior profile based on captured facial and floor data, supporting passenger flow statistics, peak warning, and abnormal behavior identification (such as prolonged stay or frequent floor crossing).

[0080] Optionally, in this application's solution, real-time capture and basic analysis are completed at the edge, while big data training and model iteration are performed in the cloud, supporting online algorithm upgrades and parameter optimization.

[0081] To better illustrate and understand the principle of the method provided by this invention, the following description uses an optional specific embodiment to illustrate the solution of this invention. It should be noted that the specific implementation of each step in this specific embodiment should not be construed as a limitation of the solution of this invention. Other implementations that can be conceived by those skilled in the art based on the principle of the solution provided by this invention should also be considered within the scope of protection of this invention.

[0082] Test scenario: A 30-story residential elevator, with a floor height of approximately 3.0 m; equipment installation complies with recommendations in Chapter 4; parameters: IMU 200Hz, air pressure 10 Hz, T_drift 0.4 Pa / s, capture threshold ±0.5 m, stable frame rate 5 frames. Key parameters involved in the implementation process: Sampling frequency: IMU ≥ 200 Hz, air pressure ≥ 10 Hz; Drift threshold T_drift: 0.3–0.5 Pa / s; Floor capture threshold: ±0.4–0.6 m; Stable frame rate for snapshot triggering (M): 3–5 frames; Face quality thresholds: clarity >30, occlusion <30%, face size 80–240 px (normalized by resolution).

[0083] Parameter optimization methods: Grid search or Bayesian optimization is used to adaptively adjust parameters such as drift threshold, capture threshold, and stable frame count, combined with field test data.

[0084] Conclusions obtained from implementing the proposed solution: Direction determination accuracy: ≥99.2% (including start-stop jitter and short-term static scenarios); Floor determination accuracy (at the moment of capture): ≥98.5% (for scenarios involving crossing floors, lingering at doorways, and air pressure disturbances); Capture trigger delay: 80–150 ms (from direction + floor double confirmation to the first frame being dropped); Drift suppression: Activated after 30 minutes of settling, there were 0 instances of floor misjudgment caused by air pressure drift; Note: Experimental data are used to illustrate feasibility and parameter selection range. Specific values ​​vary depending on the building and equipment and should be based on on-site calibration.

[0085] Compared with the prior art, the solution of the present invention has the following beneficial effects: 1. Combining the air pressure change rate threshold with IMU vertical acceleration for orientation determination significantly reduces drift misjudgment; 2. A robust estimation of cross-floor displacement and docking floor alignment is achieved by using UKF / EKF + floor map fusion; 3. Introduce dual confirmation of direction and floor in the snapshot triggering logic to ensure that "the floor is known immediately upon snapshot"; 4. Supports non-intrusive deployment and online self-calibration without protocol modifications, and is compatible with multiple elevator brands.

[0086] Based on and Figure 1 Based on the same principle as the method shown, this embodiment of the invention also provides an up / down floor determination device 20, such as... Figure 2 As shown, the up / down floor determination device 20 may include an acquisition module 210, a first determination module 220, and a second determination module 230, wherein: The acquisition module 210 is used to acquire the current motion parameters of the elevator and determine the elevator's running state based on the current motion parameters. The elevator's running state is either in motion or stopped. The current motion parameters include the vertical axis acceleration. The first judgment module 220 is used to obtain the current air pressure change rate when the elevator is in motion, and to determine the floor where the elevator is located based on the current air pressure change rate and the vertical axis acceleration; The second judgment module 230 is used to obtain the current air pressure height when the elevator is in a stopped state, and to determine the floor where the elevator is located based on the current air pressure height and the preset floor map.

[0087] Optionally, when acquiring the current motion parameters of the elevator, the acquisition module 210 is specifically used to: acquire the current motion parameters of the elevator through an inertial measurement unit installed on the shock-absorbing bracket at the top of the elevator car, the current motion parameters also including angular velocity.

[0088] Optionally, when the acquisition module 210 determines the elevator's operating status based on the current motion parameters, it is specifically used for: Obtain the current air pressure change rate corresponding to the elevator; Determine the elevator's operating status based on current motion parameters and current air pressure change rate.

[0089] Optionally, the above-mentioned device further includes: The image capture module is used to capture images that meet quality requirements inside the elevator when the elevator is in motion and the direction of travel of the elevator does not change within a first set time period; and to capture images that meet quality requirements inside the elevator when the elevator is in a stopped state and the height of the elevator does not change within a second set time period.

[0090] Optionally, the above-mentioned device further includes: The reporting module is used to package the acquired images and metadata that meet the quality requirements inside the elevator and report them asynchronously to the cloud platform via the MQTT protocol.

[0091] Optionally, the metadata of the aforementioned elevator images that meet the quality requirements includes the timestamp of the image acquisition, the floor, the elevator's direction of travel, and the confidence level.

[0092] The up and down floor determination device of the present invention can execute the up and down floor determination method provided in the present invention. The implementation principle is similar. The actions performed by each module and unit in the up and down floor determination device in each embodiment of the present invention are corresponding to the steps in the up and down floor determination method in each embodiment of the present invention. For detailed functional descriptions of each module of the up and down floor determination device, please refer to the descriptions in the corresponding up and down floor determination methods shown above. They will not be repeated here.

[0093] The aforementioned up / down floor determination device can be a computer program (including program code) running on a computer device, such as an application software; the device can be used to execute the corresponding steps in the method provided in the embodiments of the present invention.

[0094] In some embodiments, the uplink / downlink floor determination device provided in this invention can be implemented using a combination of hardware and software. As an example, the uplink / downlink floor determination device provided in this invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the uplink / downlink floor determination method provided in this invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0095] In other embodiments, the up / down floor determination device provided in this invention can be implemented in software. Figure 2 An up / down floor determination device stored in a memory is shown. It can be software in the form of programs and plug-ins, and includes a series of modules, including an acquisition module 210, a first determination module 220 and a second determination module 230, for implementing the up / down floor determination method provided in the embodiments of the present invention.

[0096] The modules described in the embodiments of the present invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0097] Based on the same principles as the methods shown in the embodiments of the present invention, the embodiments of the present invention also provide an electronic device, which may include, but is not limited to: a processor and a memory; the memory for storing computer programs; and the processor for executing the methods shown in any embodiment of the present invention by invoking the computer programs.

[0098] In one alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0099] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0100] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0101] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0102] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0103] Among these, electronic devices can also be terminal devices. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0104] This invention provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0105] According to another aspect of the present invention, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various embodiments described above.

[0106] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0107] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0108] The computer-readable storage medium provided in this invention can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0109] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0110] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. An up-and-down floor determination method characterized by comprising: The method comprises: obtaining current motion parameters of the elevator, determining the elevator running state of the elevator according to the current motion parameters, the elevator running state being a motion state or a stop state, and the current motion parameters comprising vertical axis acceleration; when the elevator running state is the motion state, obtaining a current air pressure change rate, and determining the floor where the elevator is located according to the current air pressure change rate and the vertical axis acceleration; when the elevator running state is the stop state, obtaining a current air pressure height, and determining the floor where the elevator is located according to the current air pressure height and a preset floor map.

2. The method of claim 1, wherein, The current motion parameters of the elevator are obtained by an inertial measurement unit arranged on a damping support at the top of the elevator car, and the current motion parameters further comprise angular velocity.

3. The method of claim 1, wherein, The determination of the elevator running state of the elevator according to the current motion parameters comprises: obtaining a current air pressure change rate corresponding to the elevator; determining the elevator running state of the elevator according to the current motion parameters and the current air pressure change rate.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: when the elevator running state is the motion state and the running direction of the elevator does not change within a first set time, obtaining an image in the elevator that meets the quality requirements; when the elevator running state is the stop state and the height of the elevator does not change within a second set time, obtaining an image in the elevator that meets the quality requirements.

5. The method of claim 4, wherein, The method further comprises: packaging the obtained image in the elevator that meets the quality requirements and metadata, and reporting the image and the metadata to a cloud platform asynchronously through an MQTT protocol.

6. The method of claim 4, wherein, The metadata of the image in the elevator that meets the quality requirements comprises a timestamp, a floor, a running direction and a confidence degree of the image.

7. An up-and-down floor determination system characterized by comprising: The processing module, the inertial measurement unit arranged on the elevator car and the atmospheric pressure sensor are included. The inertial measurement unit is configured to obtain current motion parameters of the elevator, and the current motion parameters comprise vertical axis acceleration. The atmospheric pressure sensor is configured to obtain an atmospheric pressure value of the elevator in real time. The processing module is configured to determine the elevator running state of the elevator according to the current motion parameters, the elevator running state being a motion state or a stop state, and determine a current air pressure change rate and a current air pressure height according to the atmospheric pressure value obtained in real time. when the elevator running state is the motion state, obtaining a current air pressure change rate, and determining the floor where the elevator is located according to the current air pressure change rate and the vertical axis acceleration; when the elevator running state is the stop state, obtaining a current air pressure height, and determining the floor where the elevator is located according to the current air pressure height and a preset floor map.

8. An up-and-down floor determination device characterized by comprising: The method comprises: an obtaining module configured to obtain current motion parameters of the elevator, determine the elevator running state of the elevator according to the current motion parameters, the elevator running state being a motion state or a stop state, and the current motion parameters comprising vertical axis acceleration. The first judging module is configured to, when the elevator operation state is a moving state, acquire a current air pressure change rate, and judge the floor where the elevator is located according to the current air pressure change rate and the vertical axis acceleration. The second judging module is configured to, when the elevator operation state is a stopping state, acquire a current air pressure height, and judge the floor where the elevator is located according to the current air pressure height and a preset floor map.

9. An electronic device, comprising: The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1-6.

Images