Vehicle-mounted toilet demand prediction method

Abstract

The invention discloses a vehicle-mounted defecation demand prediction method, and relates to the technical field of vehicle-mounted human physiological monitoring, and the method comprises the steps: collecting a bladder region echo signal of a passenger in a vehicle through a millimeter wave radar, and obtaining original bladder monitoring data; processing the original bladder monitoring data to obtain a bladder volume, judging a defecation demand grade according to the bladder volume, and generating a defecation demand grade signal; and according to the different defecation demand level signals, vehicle response is carried out, and passenger defecation suggestions are output. According to the invention, physical quantification of the bladder volume of the passenger is realized; graded defecation demand judgment considering early warning and false alarm suppression; physiological early warning is effectively converted into executable travel suggestions, and driving safety is guaranteed; and the system can be individually optimized step by step along with the monitored object or the use environment. Quantification accuracy and early warning timeliness can be improved, and privacy and engineering deployment feasibility are considered.

Description

Technical Field

[0001] This invention relates to the field of vehicle-mounted human physiological monitoring technology, and in particular to a method for predicting vehicle-mounted toilet needs. Background Technology

[0002] In recent years, non-contact physiological signal monitoring and in-vehicle driver / occupant perception technologies have developed rapidly. Multimodal sensors, such as millimeter-wave radar, ultrasound, infrared, and visual sensors, have been widely researched and engineered in the fields of vital sign detection (respiration, heart rate, body movement) and behavior recognition. Among them, millimeter-wave radar, with its advantages of penetrating obstructions, resisting changes in lighting, and high temporal resolution, is gradually becoming the core sensing method for in-vehicle non-contact physiological monitoring. Simultaneously, the increasing demands of intelligent cockpits and advanced driver assistance systems (ADAS) for occupant status perception, comfort management, and travel experience have driven research into physiological event prediction and proactive interaction strategies based on sensor fusion, enabling occupant health and interactive assistance functions to evolve towards real-time and personalized features.

[0003] Despite advancements in existing technologies across several scenarios, significant shortcomings remain. Vision-based monitoring is susceptible to occlusion and privacy limitations. While seat pressure or wearable sensors can reflect body posture and short-term load, they struggle to directly quantify bladder capacity and pose challenges to long-term comfort and maintenance. Ultrasonic measurement offers advantages in volume estimation accuracy, but its application in vehicle environments is constrained by installation space, coupling, and continuity limitations, hindering seamless, all-weather monitoring. Furthermore, current in-vehicle systems typically focus on anomaly detection or single-threshold alarms, lacking hierarchical predictive capabilities based on dynamic changes in bladder volume and closed-loop response strategies for navigation and cockpit interaction. This reduces practicality and responsiveness in long-distance travel and elderly / childcare scenarios. Summary of the Invention

[0004] In view of the problems existing in current methods for predicting in-vehicle toilet demand, this invention is proposed. Therefore, the problem this invention aims to solve is how to provide a method for predicting in-vehicle toilet demand.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for predicting the need for toilet use in a vehicle, which includes acquiring echo signals of the bladder region of a passenger in the vehicle using millimeter-wave radar to obtain raw bladder monitoring data. The raw bladder monitoring data is processed to obtain bladder volume. Based on the bladder volume, the level of toilet need is determined, and a toilet need level signal is generated, which includes a level 1 warning, a level 2 warning, and a level 3 warning. The vehicle responds to signals indicating different levels of toilet demand and provides toilet suggestions to passengers.

[0006] As a preferred embodiment of the vehicle-mounted toilet demand prediction method of the present invention, the step of obtaining raw bladder monitoring data includes: The millimeter-wave radar is fixed in the seat or ceiling according to the designed posture, and a rigid transformation relationship is established with the vehicle coordinate system to record the sensor posture. After power-on, a static self-test is performed and the unloaded background echo is collected to obtain the noise power and reference clutter spectrum; Select the transmission bandwidth, carrier frequency, transmission waveform, and number of echo samples per cycle according to the required distance resolution and velocity resolution, and record the values ​​and units of the parameters used. Configure the transmit pulse or pulse repetition frequency, and determine the duration and sampling rate of each pulse; Before starting the acquisition, the antenna array or phased array unit is calibrated and the beam direction is set to cover the spatial sector of the occupant's abdomen-bladder area. After performing time-domain DC removal and window function processing on each frame of raw data, a fast Fourier transform is used to obtain the range spectrum. An inter-pulse FFT or STFT is then performed in the Doppler dimension to obtain the range-Doppler two-dimensional spectrum. In the range-Doppler domain, constant false alarm rate detection is used to extract echo peaks from candidate targets. By transforming the coordinates with the sensor pose and the cockpit geometry model, the detected echoes are located in the spatial grid of the bladder region inside the vehicle, and the echo set falling within the bladder region ROI is selected. The original complex waveform and extracted temporal features are preserved for the continuous frame echoes within the ROI to obtain the original bladder monitoring data.

[0007] As a preferred embodiment of the in-vehicle toilet demand prediction method of the present invention, the step of obtaining bladder volume includes: The distance-Doppler echo detected in each frame is mapped to a point cloud in the in-vehicle coordinate system, and the point cloud is first subjected to temporal and spatial noise suppression. For points falling within the bladder ROI in consecutive frames, calculate the instantaneous phase change or amplitude envelope, use adaptive thresholding or CFAR detection to obtain a set of candidate boundary points, and perform edge extraction on the grid. Geometric fitting is performed on the set of contour points in each frame to obtain the spatial domain. The spatial domain is divided into voxels, and the bladder volume and information entropy are calculated based on the voxel occupancy probability. The information entropy is mapped to a normalized score to obtain the confidence level.

[0008] In a preferred embodiment of the in-vehicle toilet demand prediction method of the present invention, the expression for the bladder volume is: ; in: This represents the volume of the bladder. The volume of the monomer. For the first Probability of individual element occupancy; The expression for the information entropy is: ; in: For information entropy, The number of voxels.

[0009] As a preferred embodiment of the in-vehicle toilet demand prediction method of the present invention, the step of determining the toilet demand level based on bladder volume includes: The instantaneous rate of change of bladder volume is calculated based on bladder volume and confidence level, and is expressed as follows: ; in: for The instantaneous rate of change of volume at time t. for Bladder volume at any given time for Bladder volume at any given time To estimate the time window; Preset grading thresholds, define three levels of bladder volume thresholds, and define for each level: continuous trigger duration, instantaneous volume change rate trigger threshold, and minimum confidence threshold; If the instantaneous bladder volume Greater than the Bladder volume threshold If the continuous duration exceeds the duration of continuous triggering, and the confidence level is greater than the minimum confidence threshold, then the toilet need level is determined to be [level]. Level 1 warning; If the instantaneous volume change rate Greater than the Level instantaneous volume change rate trigger threshold Furthermore, if the confidence level is greater than the minimum confidence threshold, the toilet need level is directly upgraded to the [number]th [level]. Level 1 warning; If the confidence level is less than the minimum confidence threshold, a confidence level prompt is generated and the data is marked as data that needs to be reviewed. At the same time, a driving log is recorded while the vehicle is in motion, and a toilet demand level signal is output after the judgment.

[0010] As a preferred embodiment of the vehicle-mounted toilet demand prediction method of the present invention, the step of responding to the vehicle based on different toilet demand level signals includes: When the toilet need level is a Level 2 warning, the system first assesses the current driving situation. If the driving situation allows, the system informs the passenger of the current toilet need level via voice system, recommends the nearest toilet candidate, suggests arranging toilet use as soon as possible, and waits for user confirmation. Navigation is then initiated after user confirmation. If the user refuses to confirm or remains silent, the system records the information and prompts the passenger again at a predetermined time. When the toilet need level is three, the voice system will clearly indicate that the current toilet need level is three emergency warning. At the same time, the ambient light in the car will be activated to warn of the emergency. The system will adopt a predefined driving vision mode and adjust the flashing frequency and brightness according to the current level. It will automatically mark the nearest toilet on the map and plan the route, prioritizing the shortest arrival time. If the confidence level is less than the minimum confidence threshold, only a voice prompt will be issued asking for confirmation and the passenger to manually confirm whether navigation is needed.

[0011] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of a vehicle-mounted toilet demand prediction method.

[0012] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements the steps of a method for predicting in-vehicle toilet demand.

[0013] The beneficial effects of this invention are as follows: This method achieves physical quantification of passenger bladder volume; it provides a tiered toilet demand determination that balances early warning and false alarm suppression; it effectively transforms physiological warnings into actionable travel suggestions while ensuring driving safety; and it allows the system to be gradually personalized and optimized according to the monitored object or usage environment. It can improve quantification accuracy and warning timeliness, while also considering privacy and engineering deployment feasibility. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart of a method for predicting the demand for toilet use in vehicles. Detailed Implementation

[0016] To make the above-mentioned objects, features, and advantages of the present invention more readily understood, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0018] Secondly, the term "one embodiment" or "example" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the invention. An embodiment appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment that selectively excludes other embodiments.

[0019] Reference Figure 1 This is the first embodiment of the present invention, which provides a method for predicting in-vehicle toilet demand, including: S1. Obtain raw bladder monitoring data by collecting echo signals of the bladder area of ​​the occupants inside the vehicle using millimeter-wave radar; Specifically, the millimeter-wave radar is first fixed in the seat or roof according to the design posture, a rigid transformation relationship is established with the vehicle coordinate system and the sensor posture is recorded; After power-on, a static self-test is performed and an unloaded background echo is acquired to estimate the noise baseline and static clutter profile, and to obtain the noise power and reference clutter spectrum. Select the transmission bandwidth, carrier frequency, transmission waveform, and number of echo samples per cycle according to the required distance resolution and velocity resolution, and record the values ​​and units of the parameters used. Configure timing parameters such as transmit pulse / frequency modulated continuous wave (FMCW) or pulse repetition frequency (PRF) to determine the duration of each pulse and the ADC sampling rate to ensure that the echo sampling covers the desired distance window; Before starting acquisition, the antenna array or phased array unit is calibrated and the beam pointing or digital beamforming parameters are set to cover or focus on the spatial sector of the occupant's abdomen-bladder approximation area; continuous acquisition is started, and the original complex I / Q echo samples corresponding to each transmission, as well as the precise timestamp, chirp index, sensor pose, environmental measurements (temperature, power supply voltage) and configuration metadata are saved; After performing time-domain DC removal and window function processing on each frame of raw data, the distance spectrum is obtained by fast Fourier transform. Perform inter-pulse FFT or STFT in the Doppler dimension to obtain the distance-Doppler two-dimensional spectrum to separate slow breathing / bladder micromotion from the vehicle's global motion; In the range-Doppler domain, constant false alarm rate detection (CFAR) is used to extract echo peaks from candidate targets. By transforming the coordinates with the sensor pose and the cabin geometry model, the detected echoes are located in the spatial grid of the bladder region inside the vehicle, and the echo set falling within the bladder region ROI is selected. The original complex waveform and extracted temporal features of the continuous frame echoes within the ROI are preserved to obtain the original bladder monitoring data.

[0020] S2. Process the raw bladder monitoring data to obtain bladder volume, determine the level of toilet need based on bladder volume, and generate a toilet need level signal. Specifically, the distance-Doppler echo detected in each frame is mapped into a point cloud in the in-vehicle coordinate system using the calibrated sensor pose and cockpit geometry model; For each point, retain the amplitude, phase, and timestamp for subsequent processing. Perform temporal and spatial noise suppression on the point cloud: apply bandpass or lowpass filtering to each spatial cell in the time domain to remove large-scale vehicle motion and high-frequency noise. The commonly used time window length is determined by the sampling interval Deltat and the desired smoothness. Neighborhood smoothing (such as weighted moving average or Gaussian filtering) and morphological opening and closing operations are used in the spatial domain to eliminate isolated noise and fill small holes.

[0021] Based on phase and amplitude changes, instantaneous phase changes or amplitude envelopes are calculated for points falling within the bladder ROI in consecutive frames to enhance bladder boundary contrast.

[0022] Candidate boundary point sets are obtained by using adaptive thresholding or CFAR detection. Then, edge extraction is performed on the grid (e.g., based on gradient or magnitude abrupt change), and small targets unrelated to the bladder are removed by connected component analysis. Candidate contour attributes such as area, centroid, and principal direction are retained as the basis for quality judgment.

[0023] Geometric fitting is performed on the set of contour points in each frame to obtain the spatial domain. The spatial domain is divided into voxels, and the voxel occupancy probability is calculated (obtained by normalized amplitude mapping). The bladder volume is summed by voxel count and expressed as: ; in: This represents the volume of the bladder. The volume of the monomer. For the first Probability of individual element occupancy; Confidence scores are generated based on voxel occupancy probabilities. Low-confidence points have their weights reduced in subsequent curve construction. The information entropy of the voxel occupancy probability set is calculated and represented as: ; in: Information entropy; The number of voxels.

[0024] The information entropy is mapped to a normalized score to obtain the confidence level.

[0025] The instantaneous rate of change of bladder volume is calculated based on bladder volume and confidence level, and is expressed as follows: ; in: for The instantaneous rate of change of volume at time t. for Bladder volume at any given time for Bladder volume at any given time To estimate the time window; The system presets tiered thresholds, defines three levels of bladder volume thresholds, and defines for each level: continuous trigger duration, instantaneous volume change rate trigger threshold, and minimum confidence threshold.

[0026] Generate a grading signal, if the instantaneous bladder volume Greater than the Bladder volume threshold If the continuous duration exceeds the duration of continuous triggering, and the confidence level is greater than the minimum confidence threshold, then the toilet need level is determined to be [level]. Level 1 warning; If the instantaneous volume change rate Greater than the Level instantaneous volume change rate trigger threshold Furthermore, if the confidence level is greater than the minimum confidence threshold, the toilet need level is directly upgraded to the [number]th [level]. Level 1 warning; If the confidence level is less than the minimum confidence threshold, a confidence level prompt is generated and the data is marked as data that needs to be reviewed. At the same time, a driving log is recorded while the vehicle is in motion, and a toilet demand level signal is output after the judgment. The toilet demand level signal includes Level 1 warning, Level 2 warning, and Level 3 warning.

[0027] S3. The vehicle responds to different levels of toilet demand signals and outputs toilet suggestions for passengers.

[0028] Specifically, upon receiving a signal indicating the level of need for restroom access, the system executes the following response logic according to the level. All actions are taken with the premise of not compromising driving safety and with a driving-priority suppression strategy in place.

[0029] When the toilet need level is a Level 2 warning, the system first assesses the current driving situation. If the driving situation allows, the system informs the passenger of the current toilet need level via voice system, recommends the nearest toilet candidate, suggests arranging toilet use as soon as possible, and waits for user confirmation. Navigation is then initiated after user confirmation. If the user refuses to confirm or remains silent, the system records the information and prompts the passenger again at a predetermined time.

[0030] When the toilet need level is three, the voice system will clearly indicate that the current toilet need level is three emergency warning. At the same time, the ambient light in the car will be activated to warn of the emergency. The system will adopt a predefined driving vision mode and adjust the flashing frequency and brightness according to the current level. It will automatically mark the nearest toilet on the map and plan the route, prioritizing the shortest arrival time.

[0031] If the confidence level is less than the minimum confidence threshold, only a voice prompt will be issued asking for confirmation and the passenger to manually confirm whether navigation is needed.

[0032] This embodiment also provides a computer device applicable to a vehicle-mounted toilet demand prediction method, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement all or part of the steps of the method described in the above embodiments of the present invention.

[0033] This embodiment also provides a storage medium storing a computer program thereon. When the computer program is executed by a processor, it performs the method in any optional implementation of the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0034] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0035] In summary, this method achieves physical quantification of passenger bladder volume; it provides a tiered approach to toilet needs assessment, balancing early warning and false alarm suppression; it effectively translates physiological alerts into actionable travel recommendations while ensuring driving safety; and it allows the system to be progressively optimized to suit different monitored individuals or usage environments. It improves quantification accuracy and timely warnings while also considering privacy and engineering deployment feasibility.

[0036] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for predicting vehicle-mounted toilet demand, characterized in that: include, Raw bladder monitoring data is obtained by collecting echo signals from the bladder area of ​​the occupants inside the vehicle using millimeter-wave radar. The raw bladder monitoring data is processed to obtain bladder volume, and the level of toilet need is determined based on the bladder volume to generate a toilet need level signal. The vehicle responds to signals indicating different levels of toilet demand and provides toilet suggestions to passengers.

2. The method for predicting vehicle-mounted toilet demand as described in claim 1, characterized in that: The obtained raw bladder monitoring data includes: The millimeter-wave radar is fixed in the seat or ceiling according to the designed posture, and a rigid transformation relationship is established with the vehicle coordinate system to record the sensor posture. After power-on, a static self-test is performed and the unloaded background echo is collected to obtain the noise power and reference clutter spectrum; Select the transmission bandwidth, carrier frequency, transmission waveform, and number of echo samples per cycle according to the required distance resolution and velocity resolution, and record the values ​​and units of the parameters used. Configure the transmit pulse or pulse repetition frequency, and determine the duration and sampling rate of each pulse; Before starting the acquisition, the antenna array or phased array unit is calibrated and the beam direction is set to cover the spatial sector of the occupant's abdomen-bladder area. After performing time-domain DC removal and window function processing on each frame of raw data, a fast Fourier transform is used to obtain the range spectrum. An inter-pulse FFT or STFT is then performed in the Doppler dimension to obtain the range-Doppler two-dimensional spectrum. In the range-Doppler domain, constant false alarm rate detection is used to extract echo peaks from candidate targets. By transforming the coordinates with the sensor pose and the cockpit geometry model, the detected echoes are located in the spatial grid of the bladder region inside the vehicle, and the echo set falling within the bladder region ROI is selected. The original complex waveform and extracted temporal features are preserved for the continuous frame echoes within the ROI to obtain the original bladder monitoring data.

3. The method for predicting vehicle-mounted toilet demand as described in claim 2, characterized in that: The method of obtaining bladder volume includes: The distance-Doppler echo detected in each frame is mapped to a point cloud in the in-vehicle coordinate system, and the point cloud is first subjected to temporal and spatial noise suppression. For points falling within the bladder ROI in consecutive frames, calculate the instantaneous phase change or amplitude envelope, use adaptive thresholding or CFAR detection to obtain a set of candidate boundary points, and perform edge extraction on the grid. Geometric fitting is performed on the set of contour points in each frame to obtain the spatial domain. The spatial domain is divided into voxels, and the bladder volume and information entropy are calculated based on the voxel occupancy probability. The information entropy is mapped to a normalized score to obtain the confidence level.

4. The method for predicting vehicle-mounted toilet demand as described in claim 3, characterized in that: The expression for the bladder volume is: in: This represents the volume of the bladder. The volume of the monomer. For the first Probability of individual element occupancy; The expression for the information entropy is: in: For information entropy, The number of voxels.

5. The method for predicting vehicle-mounted toilet demand as described in claim 4, characterized in that: The method of determining the level of urination need based on bladder volume includes: The instantaneous rate of change of bladder volume is calculated based on bladder volume and confidence level, and is expressed as follows: in: for The instantaneous rate of change of volume at time t. for Bladder volume at any given time for Bladder volume at any given time To estimate the time window; Preset grading thresholds, define three levels of bladder volume thresholds, and define for each level: continuous trigger duration, instantaneous volume change rate trigger threshold, and minimum confidence threshold; If the instantaneous bladder volume Greater than the Bladder volume threshold If the continuous duration exceeds the duration of continuous triggering, and the confidence level is greater than the minimum confidence threshold, then the toilet need level is determined to be [level]. Level 1 warning; If the instantaneous volume change rate Greater than the Level instantaneous volume change rate trigger threshold Furthermore, if the confidence level is greater than the minimum confidence threshold, the toilet need level is directly upgraded to the [number]th [level]. Level 1 warning; If the confidence level is less than the minimum confidence threshold, a confidence level prompt is generated and the data is marked as data that needs to be reviewed. At the same time, a driving log is recorded while the vehicle is in motion, and a toilet demand level signal is output after the judgment. The toilet demand level signal includes Level 1 warning, Level 2 warning, and Level 3 warning.

6. The method for predicting vehicle-mounted toilet demand as described in claim 5, characterized in that: The vehicle response based on different levels of toilet demand signals includes: When the toilet need level is a Level 2 warning, the system first assesses the current driving situation. If the driving situation allows, the system informs the passenger of the current toilet need level via voice system, recommends the nearest toilet candidate, suggests arranging toilet use as soon as possible, and waits for user confirmation. Navigation is then initiated after user confirmation. If the user refuses to confirm or remains silent, the system records the information and prompts the passenger again at a predetermined time. When the toilet need level is three, the voice system will clearly indicate that the current toilet need level is three emergency warning. At the same time, the ambient light in the car will be activated to warn of the emergency. The system will adopt a predefined driving vision mode and adjust the flashing frequency and brightness according to the current level. It will automatically mark the nearest toilet on the map and plan the route, prioritizing the shortest arrival time. If the confidence level is less than the minimum confidence threshold, only a voice prompt will be issued asking for confirmation and the passenger to manually confirm whether navigation is needed.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the in-vehicle toilet demand prediction method according to any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the in-vehicle toilet demand prediction method according to any one of claims 1 to 6.

Images