In-vehicle living being presence detection method and system

Abstract

An in-vehicle living being presence detection method and system, aiming to solve the problems of how to design the in-vehicle living being presence detection process and how to optimize and iterate the detection process on the basis of historical alarm data. In order to achieve the purpose, the in-vehicle living being presence detection method comprises: designing a multi-level determination strategy on the basis of the in-vehicle living being presence determination parameters; and continuously iterating and optimizing related parameters and process on the basis of historical alarm data. By using the multi-level determination strategy, the detection alarm accuracy is improved. On the basis of detection alarm big data generated by collaboration among a vehicle, a cloud and a user, the in-vehicle living being presence determination parameters can be continuously optimized, thereby further improving the detection alarm accuracy, and balancing the false alarm rate and the missing alarm rate, thus providing the user with higher-quality service. Moreover, the in-vehicle living being presence detection method is unrelated to vehicle hardware configurations such as a vehicle model and a living being detection sensor type, and has the advantages of easy deployment and implementation and good universality.

Description

Method and system for monitoring residual life forms in vehicles Technical Field

[0001] The present application relates to the field of automobile technology, and specifically provides a method and system for monitoring the remains of living organisms in a vehicle. Background Art

[0002] The Child Presence Detection (CPD) function uses sensors such as radar and cameras installed in the vehicle to detect living organisms, determine whether children (including other living organisms) have been left in the vehicle, and send alarms to vehicle users, third-party service operators, public rescue centers, etc., to avoid the dangers caused by children being left in closed vehicles for a long time.

[0003] In CPD applications, the diversity of in-vehicle environments, such as obstructions, coverage, and positional variations of life forms, as well as performance variations in life form detection sensors, can affect the accuracy of life form detection, leading to false alarms and missed alarms. Therefore, designing an in-vehicle life form monitoring process and optimizing and iterating the monitoring process based on the large amount of historical life form monitoring alarm data generated during vehicle use, thereby improving monitoring accuracy and achieving a balance between false alarms and missed alarms, has become a pressing issue.

[0004] Accordingly, this field requires a new solution to solve the above problems.

[0005] Summary of the Invention

[0006] This application aims to solve or partially solve the above technical problems, namely, how to design a process for monitoring the residual life forms in a vehicle, and optimize and iterate the monitoring process based on a large amount of historical alarm data of residual life forms generated during the use of the vehicle.

[0007] In a first aspect, the present application proposes a method for monitoring the presence of life forms in a vehicle, the method comprising:

[0008] According to a preset detection period, obtaining the continuous existence time and the cumulative existence time of the living organism within the detection period;

[0009] For the detection period, when the continuous existence time of any of the living organisms is greater than or equal to the second time threshold, or the cumulative existence time of the living organisms is greater than or equal to the third time threshold, the detection period is determined to be a life-existing detection period;

[0010] The accumulated number of the life form detection cycles is obtained, and when the accumulated number of the life form detection cycles is greater than or equal to a first number threshold, a second-level alarm is executed.

[0011] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0012] updating at least one of the parameters for determining whether a life form is left in the vehicle based on historical alarm data of monitoring whether a life form is left in the vehicle;

[0013] Among them, the parameters for judging whether a living being remains in the vehicle include the detection period, the second time threshold, the third time threshold, the first quantity threshold, and the second quantity threshold for judging whether there is no life in the vehicle, and the second time threshold is less than the third time threshold.

[0014] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0015] For the detection period, when the continuous presence time of any of the living organisms is less than the second time threshold, and the cumulative presence time of the living organisms is less than the third time threshold, the detection period is determined to be a detection period in which no living organism exists;

[0016] The continuous number of the life form absence detection cycles is obtained, and when the continuous number of the life form absence detection cycles is greater than or equal to the second number threshold, it is determined that there is no life form in the vehicle.

[0017] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0018] Obtaining correct cases and incorrect cases in the historical alarm data within a set time range;

[0019] Perform at least one of the following update methods:

[0020] obtaining a first mean and a first standard deviation of the continuous existence time of the living being in the error case, and a second mean and a second standard deviation in the correct case, respectively, and updating at least one of the parameters for determining whether a living being remains in the vehicle based on the first mean, the first standard deviation, the second mean, and the second standard deviation;

[0021] A third mean and a third standard deviation of the cumulative existence time of the living body in the error case, and a fourth mean and a fourth standard deviation in the correct case are obtained respectively, and at least one of the parameters for determining whether a living body remains in the vehicle is updated based on the third mean, the third standard deviation, the fourth mean, and the fourth standard deviation.

[0022] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0023] Obtaining a second time threshold lower limit value based on the first mean, the first standard deviation, and a preset first standard deviation coefficient;

[0024] Obtaining a second time threshold upper limit value based on the second mean, the second standard deviation, and a preset second standard deviation coefficient;

[0025] At least one of the parameters for determining whether a living being remains in the vehicle is updated based on the second time threshold lower limit value and the second time threshold upper limit value.

[0026] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0027] When the lower limit value of the second time threshold is less than the upper limit value of the second time threshold, checking whether the second time threshold is within the numerical interval of [the lower limit value of the second time threshold, the upper limit value of the second time threshold];

[0028] When the second time threshold is not within the numerical interval of [the second time threshold lower limit value, the second time threshold upper limit value], any numerical value within the numerical interval of [the second time threshold lower limit value, the second time threshold upper limit value] is selected to update the second time threshold.

[0029] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0030] When the second time threshold lower limit value is greater than the second time threshold upper limit value, at least one of the following updating methods is executed:

[0031] Increase the duration of the detection cycle;

[0032] Updating the second time threshold;

[0033] increasing the first quantity threshold;

[0034] increasing the second quantity threshold;

[0035] The updated second time threshold is one of the second time threshold lower limit value and the second time threshold upper limit value.

[0036] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0037] Obtaining a third time threshold lower limit value based on the third mean, the third standard deviation, and a preset third standard deviation coefficient;

[0038] Obtaining a third time threshold upper limit value based on the fourth mean, the fourth standard deviation, and a preset fourth standard deviation coefficient;

[0039] At least one of the parameters for determining whether a living being remains in the vehicle is updated based on the third lower time threshold value and the third upper time threshold value.

[0040] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0041] When the third time threshold lower limit value is less than the third time threshold upper limit value, checking whether the third time threshold is within the value interval of [the third time threshold lower limit value, the third time threshold upper limit value];

[0042] When the third time threshold is not within the numerical interval of [the lower limit value of the third time threshold, the upper limit value of the third time threshold], any value within the numerical interval of [the lower limit value of the third time threshold, the upper limit value of the third time threshold] is selected to update the third time threshold.

[0043] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0044] When the third time threshold lower limit value is greater than the third time threshold upper limit value, at least one of the following updating methods is executed:

[0045] Increase the duration of the detection cycle;

[0046] Updating the third time threshold;

[0047] increasing the first quantity threshold;

[0048] increasing the second quantity threshold;

[0049] The updated third time threshold is one of the third time threshold lower limit value and the third time threshold upper limit value.

[0050] In one embodiment of the above-mentioned method for monitoring the remains of living organisms in a vehicle, the method further includes at least one of the following methods:

[0051] updating at least one of the parameters for determining whether a living being remains in the vehicle based on the historical alarm data of the vehicle model according to the vehicle model;

[0052] According to the vehicle VIN code, at least one of the parameters for determining whether a living being remains in the vehicle is updated based on the historical alarm data of the vehicle VIN code.

[0053] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0054] When the cumulative number of life body detection cycles is greater than or equal to a third threshold, a third-level alarm is executed; or

[0055] When the duration of the second-level alarm is greater than or equal to the fifth time threshold, a third-level alarm is executed.

[0056] In one embodiment of the above-mentioned method for monitoring the remaining life forms in a vehicle, the method further includes:

[0057] Detecting whether there is a living being in the vehicle within a first preset time;

[0058] Comparing whether the existence time of the living body is greater than or equal to a first time threshold;

[0059] When the existence time of the living organism is greater than or equal to the first time threshold, the first alarm is executed.

[0060] In a second aspect, the present application provides a system for monitoring residual life forms in a vehicle, the system comprising a vehicle and a computing device, wherein the vehicle is configured to perform the following operations:

[0061] According to a preset detection period, obtaining the continuous existence time and the cumulative existence time of the living organism within the detection period;

[0062] For the detection period, when the continuous existence time of any of the living organisms is greater than or equal to the second time threshold, or the cumulative existence time of the living organisms is greater than or equal to the third time threshold, the detection period is determined to be a life-existing detection period;

[0063] The accumulated number of the life form detection cycles is obtained, and when the accumulated number of the life form detection cycles is greater than or equal to a first number threshold, a second-level alarm is executed.

[0064] In one embodiment of the above-mentioned in-vehicle life form monitoring system, the computing device is configured to:

[0065] updating at least one of the parameters for determining whether a life form is left in the vehicle based on historical alarm data of monitoring whether a life form is left in the vehicle;

[0066] Among them, the parameters for judging whether a living being remains in the vehicle include the detection period, the second time threshold, the third time threshold, the first quantity threshold, and the second quantity threshold for judging whether there is no life in the vehicle, and the second time threshold is less than the third time threshold.

[0067] In one embodiment of the above-mentioned in-vehicle life form monitoring system, the vehicle is further configured to perform the following operations:

[0068] For the detection period, when the continuous presence time of any of the living organisms is less than the second time threshold, and the cumulative presence time of the living organisms is less than the third time threshold, the detection period is determined to be a detection period in which no living organism exists;

[0069] The continuous number of the life form absence detection cycles is obtained, and when the continuous number of the life form absence detection cycles is greater than or equal to the second number threshold, it is determined that there is no life form in the vehicle.

[0070] In one embodiment of the above-mentioned in-vehicle life form monitoring system, the computing device is configured to perform the following operations:

[0071] Obtaining correct cases and incorrect cases in the historical alarm data within a set time range;

[0072] Perform at least one of the following update methods:

[0073] obtaining a first mean and a first standard deviation of the continuous existence time of the living being in the error case, and a second mean and a second standard deviation in the correct case, respectively, and updating at least one of the parameters for determining whether a living being remains in the vehicle based on the first mean, the first standard deviation, the second mean, and the second standard deviation;

[0074] A third mean and a third standard deviation of the cumulative existence time of the living body in the error case, and a fourth mean and a fourth standard deviation in the correct case are obtained respectively, and at least one of the parameters for determining whether a living body remains in the vehicle is updated based on the third mean, the third standard deviation, the fourth mean, and the fourth standard deviation.

[0075] In one embodiment of the above-mentioned in-vehicle life form monitoring system, the computing device is configured to perform the following operations:

[0076] Obtaining a second time threshold lower limit value based on the first mean, the first standard deviation, and a preset first standard deviation coefficient;

[0077] Obtaining a second time threshold upper limit value based on the second mean, the second standard deviation, and a preset second standard deviation coefficient;

[0078] At least one of the parameters for determining whether a living being remains in the vehicle is updated based on the second time threshold lower limit value and the second time threshold upper limit value.

[0079] In one embodiment of the above-mentioned in-vehicle life form monitoring system, the computing device is configured to perform the following operations:

[0080] Obtaining a third time threshold lower limit value based on the third mean, the third standard deviation, and a preset third standard deviation coefficient;

[0081] Obtaining a third time threshold upper limit value based on the fourth mean, the fourth standard deviation, and a preset fourth standard deviation coefficient;

[0082] At least one of the parameters for determining whether a living being remains in the vehicle is updated based on the third lower time threshold value and the third upper time threshold value.

[0083] In one embodiment of the above-mentioned in-vehicle life form monitoring system, the computing device is configured to perform the following operations:

[0084] updating at least one of the parameters for determining whether a living being remains in the vehicle based on the historical alarm data of the vehicle model according to the vehicle model;

[0085] According to the vehicle VIN code, at least one of the parameters for determining whether a living being remains in the vehicle is updated based on the historical alarm data of the vehicle VIN code.

[0086] This application designs a multi-level judgment strategy for monitoring the presence of life forms in the vehicle based on the detection period, second time threshold, third time threshold, first quantity threshold, second quantity threshold, and other parameters for judging the presence of life forms in the vehicle, thereby improving the accuracy of monitoring alarms. Furthermore, during the vehicle process, based on the big data generated by the collaboration between the vehicle, cloud, and users during the monitoring of the presence of life forms, the parameters for judging the presence of life forms in the vehicle are optimized, which can not only further improve the accuracy of monitoring alarms, but also achieve a good balance between the false alarm rate and the missed alarm rate, thereby providing users with better service. Furthermore, the method of this application is independent of the vehicle hardware configuration, such as the vehicle model and the type of life form detection sensor, and has the advantages of being easy to deploy and implement and having good versatility. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] The disclosure of this application will become more easily understood with reference to the accompanying drawings. Those skilled in the art will readily understand that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0088] FIG1 is a schematic structural diagram of a system for monitoring residual life forms in a vehicle according to an embodiment of the present application.

[0089] FIG2 is a schematic diagram of the main process steps of the method for monitoring the residual life forms in a vehicle according to an embodiment of the present application.

[0090] FIG3 is a schematic diagram of the main process steps for updating the in-vehicle life form retention judgment parameter based on the continuous presence time of the life form in the historical alarm data according to an embodiment of the present application.

[0091] FIG4 is a flowchart of the specific steps of step S304 in an embodiment of the present application.

[0092] FIG5 is a schematic diagram of the main process steps for updating the parameters for determining whether a living body remains in a vehicle based on the cumulative existence time of the living body in the historical alarm data according to an embodiment of the present application.

[0093] FIG6 is a flowchart of the specific steps of step S504 in an embodiment of the present application.

[0094] FIG7 is a schematic diagram of the main process steps for updating the in-vehicle life form remaining judgment parameter of a vehicle of the vehicle model based on the historical alarm data of the vehicle model according to an embodiment of the present application.

[0095] FIG8 is a schematic diagram of the main process steps for updating the vehicle's in-vehicle life form retention judgment parameters based on the historical alarm data of the vehicle's VIN code according to an embodiment of the present application. DETAILED DESCRIPTION

[0096] To make the objectives, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0097] Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the scope of protection of the present application. Those skilled in the art can make adjustments as needed to adapt to specific applications.

[0098] First, let's look at FIG1 , which is a schematic diagram of the structure of a system for monitoring the remaining life forms in a vehicle according to an embodiment of the present application.

[0099] The in-vehicle life residue monitoring system of the embodiment of the present application includes a vehicle 1 and a cloud server 2. The vehicle 1 can use an on-board T-Box to communicate data with the cloud server 2 via a 4G / 5G or other wireless network provided by a telecommunications operator.

[0100] It should be noted that the vehicle 1 generally includes a large number of vehicles, which may be of the same model or of different models. The specific form of the cloud server is not limited, and may be a dedicated server or a server cluster.

[0101] 2 , which illustrates the in-vehicle life form residue monitoring method of the present application in combination with FIG1 and FIG2 . FIG2 is a schematic diagram of the main steps of the in-vehicle life form residue monitoring method of an embodiment of the present application.

[0102] After the vehicle is parked, the user turns off the vehicle power system and locks the vehicle. The cockpit domain controller immediately automatically starts the life-remaining monitoring and performs the first-level life-remaining monitoring, that is, turning on the life-remaining detection sensor in the vehicle within the first preset time to detect whether there is any life in the vehicle.

[0103] Within the first preset time, if there is a living being in the vehicle and the existence time of the living being is greater than or equal to the first time threshold, the first alarm is executed and the second-level living being residual monitoring is started.

[0104] The main function of the first-level life form retention monitoring is to make a preliminary judgment on whether a life form is left in the vehicle when the user has just left the vehicle and has not walked far away, and to promptly notify users near the vehicle to check the situation inside the vehicle based on the judgment results.

[0105] As an example, the first preset time can be set to 30 seconds. Since the first time threshold is only for filtering out interference signals of the life detection sensor, the first time threshold can be set to a smaller value, such as 1 second.

[0106] When the first alarm is executed, the vehicle can sound a specific sound from the onboard horn, control the headlights to display a specific color and flashing frequency, etc. to issue an alarm, thereby prompting users who may not have left the vehicle to check whether there is any living organism in the vehicle in time.

[0107] If there is no living being in the vehicle within the first preset time, it is determined that there is no living being left in the vehicle, and the monitoring of the remaining living being in the vehicle is exited.

[0108] When secondary life presence monitoring is enabled, the in-vehicle life presence monitoring system of the present embodiment performs continuous monitoring over multiple detection cycles. Using the preset detection cycle as the statistical unit, the system records the duration of each life presence signal output by the life presence detection sensor during each detection cycle, i.e., the continuous life presence time. The cumulative life presence time is then calculated by summing the recorded continuous life presence times for each detection cycle.

[0109] For a detection cycle, if the continuous existence time of any life form is greater than or equal to the second time threshold, or the cumulative existence time of the life form is greater than or equal to the third time threshold, then the detection cycle can be determined as a life form presence detection cycle; otherwise, the detection cycle is a life form non-existence detection cycle.

[0110] As an example, the detection period may be set to 60 seconds, the second time threshold may be set to 10 seconds, and the third time threshold may be set to 20 seconds.

[0111] For example, within a certain detection cycle, the three detected life forms have a continuous existence time of 8 seconds, 6 seconds, and 9 seconds respectively. These three life form continuous existence times are all less than the second time threshold, but the cumulative existence time of the life form (8+6+9=23 seconds) is greater than the third time threshold (20 seconds). At this time, the detection cycle is determined to be a life form detection cycle.

[0112] For example, within a certain detection cycle, the continuous existence time of two detected life forms is 15 seconds and 4 seconds respectively. The cumulative existence time of the life forms (15+4=19 seconds) is less than the third time threshold (20 seconds). However, the continuous existence time of one of the life forms is 15 seconds, which is greater than the second time threshold (10 seconds). At this time, the detection cycle is determined to be a life form detection cycle.

[0113] The number of detection periods in which life forms are present and the number of detection periods in which no life forms are present are further counted and updated.

[0114] The cumulative number of life body detection cycles is compared with a first number threshold. When the cumulative number of life body detection cycles is greater than or equal to the first number threshold, a secondary alarm is executed. As an example, the first number threshold can be set to 10.

[0115] When a Level 2 alarm is activated, the user has typically been away from the vehicle for an extended period of time and is therefore no longer aware of the vehicle's sounds, lights, and other signals. Therefore, a Level 2 alarm can be used to remotely notify the user, the vehicle owner, and other personnel involved in the vehicle via text messages, mobile device app notifications, or phone calls, indicating the presence of a living being inside the vehicle.

[0116] After the vehicle activates the Level 2 alarm, it continues monitoring for remaining life forms according to the preset detection cycles, counting the cumulative number of detection cycles in which life forms are present. A Level 3 alarm is activated when the cumulative number of detection cycles in which life forms are present is greater than or equal to a third threshold. For example, the third threshold can be set to 20.

[0117] In another embodiment, after the second-level alarm is triggered, the duration of the second-level alarm can also be counted, and the third-level alarm can be triggered based on the duration of the second-level alarm. Specifically, the third-level alarm is triggered when the duration of the second-level alarm is greater than or equal to a fifth time threshold. As an example, the fifth time threshold can be set to 30 minutes.

[0118] When a Level 3 alarm is executed, a living being has been left in the vehicle for a long time. Therefore, in addition to continuing to send alarm information to users and other vehicle-related personnel through remote notification, the vehicle's eCall system (emergency call) can also be triggered to seek help from a public rescue center.

[0119] It can also perform one or more of the following actions based on the vehicle's surrounding and interior conditions, such as activating the ventilation system, opening windows, and starting the vehicle's air conditioning system to improve the interior environment. It can also continuously sound alarms through the vehicle's horn and lights, and open the doors to attract the attention of nearby personnel and rescue any remaining life forms.

[0120] After executing the third-level alarm, the vehicle can be set to continue monitoring for remaining life forms according to the preset detection cycle until the alarm information is manually released or the monitoring result changes to no remaining life forms in the vehicle.

[0121] When the vehicle counts the cumulative number of life presence detection cycles, it also counts the number of life absence detection cycles. When the consecutive number of life absence detection cycles (the consecutive number of life absence detection cycles will be reset to zero after the detection cycle is determined to be a life presence detection cycle) is greater than or equal to a second threshold (for example, the second threshold can be set to 3), it is determined that no life remains in the vehicle and the vehicle life presence detection is exited. When the consecutive number of life absence detection cycles is less than the second threshold, the life presence monitoring system will continue to detect the presence of life in the vehicle according to the preset detection cycle.

[0122] After a vehicle generates an alarm, the alarm data from the in-vehicle life-presence monitoring is uploaded to a cloud server. This data includes the continuous presence time of each segment of life-presence detected by the life-presence detection sensor during each detection cycle, the cumulative presence time of each life-presence detected during each detection cycle, user information such as whether the user / owner remotely canceled the alarm using a mobile device such as a phone, and vehicle information such as whether the door was opened.

[0123] The cloud server stores the alarm data of the in-vehicle life-remaining monitoring, and regularly checks whether the in-vehicle life-remaining judgment parameters such as the detection period, the second time threshold, the third time threshold, the first quantity threshold, and the second quantity threshold need to be updated based on the historical alarm data of the in-vehicle life-remaining monitoring.

[0124] Continuing with FIG3 , FIG3 is a schematic diagram of the main process steps for updating the in-vehicle life form retention determination parameter based on the continuous presence time of the life form in the historical alarm data according to an embodiment of the present application. The main process steps include:

[0125] Step S301: Acquire correct cases and incorrect cases from historical alarm data in the vehicle within a set time range;

[0126] Step S302: Obtain a first mean and a first standard deviation of the continuous existence time of the living body in the error case;

[0127] Step S303: Obtaining the second mean and second standard deviation of the continuous existence time of the living body in the correct cases;

[0128] Step S304: updating at least one of the parameters for determining whether a living being remains in the vehicle based on the first mean, the first standard deviation, the second mean, and the second standard deviation, wherein the parameters for determining whether a living being remains in the vehicle include a detection period, a second time threshold, a third time threshold, a first quantity threshold, and a second quantity threshold, and the second time threshold is less than the third time threshold.

[0129] In step S301, the alarm data of the in-vehicle life-remaining monitoring within the time range from the execution time of the previous inspection of whether the in-vehicle life-remaining judgment parameters need to be updated to the current time is usually selected as the historical alarm data of the in-vehicle life-remaining monitoring for this inspection and update.

[0130] First, the historical alarm data is analyzed to distinguish which historical alarm data belong to correct cases and which historical alarm data belong to incorrect cases. Specifically, the judgment method of incorrect cases includes the following situations.

[0131] The historical alarm data corresponding to the secondary alarm or tertiary alarm that was remotely canceled by the user, that is, the alarm of life remaining in the car has been generated, but the user may know for sure that there is no life remaining in the car, and directly operate electronic devices such as smartphones and mobile terminals to directly cancel the secondary alarm or tertiary alarm through APP, reply to messages, etc.

[0132] If there is no historical alarm data for a user-inactive period greater than or equal to the fourth time threshold, this means that a life-in-vehicle residual alarm has occurred, but the user has neither returned to the vehicle to unlock or open the door directly using the smart key nor remotely canceled the alarm within the fourth time threshold. For example, the fourth time threshold can be set to 120 minutes.

[0133] The final monitoring result of the secondary life-remaining monitoring is the historical alarm data indicating no life-remaining in the vehicle. That is, after vehicle 1 triggers its first alarm, secondary life-remaining monitoring is initiated. The final result of secondary life-remaining monitoring is that no life-remaining in the vehicle is detected, automatically exiting the current secondary life-remaining monitoring session. Furthermore, during this monitoring session, the user does not perform any operations such as unlocking or opening the vehicle doors.

[0134] After the error cases are determined, the remaining historical alarm data can be considered as correct alarm data, that is, correct cases.

[0135] After obtaining the correct cases and the incorrect cases, the continuous existence time of the living organism is statistically analyzed based on the correct cases and the incorrect cases.

[0136] Since this application checks and updates the parameters for judging the presence of living things in the vehicle based on big data of historical alarm data, the distribution of the continuous existence time of living things in correct cases and incorrect cases can be considered to be approximately in line with the normal distribution.

[0137] Accordingly, in this application, the parameters for judging whether a living being is left in the vehicle are checked and updated based on the mean μ, standard deviation σ of the normal distribution and the characteristics of the probability density function - the 68-95-99.7 rule (empirical rule).

[0138] Among them, the 68-95-99.7 rule is: if a set of data has a probability distribution that is close to the normal distribution, then approximately 68.3% of the values ​​are distributed within 1 standard deviation from the mean, approximately 95.4% of the values ​​are distributed within 2 standard deviations from the mean, and approximately 99.7% of the values ​​are distributed within 3 standard deviations from the mean.

[0139] In step S302 , a first mean μ1 and a first standard deviation σ1 of the continuous existence time of the living body in the error case are obtained.

[0140] In step S303 , a second mean μ2 and a second standard deviation σ2 of the continuous existence time of the living body in the correct case are obtained, and μ1 is smaller than μ2.

[0141] Continue reading Figure 4 to explain the specific steps of step S304 in conjunction with Figure 4. Figure 4 is a flow chart of the specific steps of step S304 in the embodiment of the present application.

[0142] The first standard deviation coefficient is set based on the expected false negative rate of the in-vehicle life form monitoring system. For the probability density function of the approximate normal distribution of the continuous presence time of the life form in the error case, if the false negative rate is A%, then the multiple of σ1 corresponding to the probability value (1-A)% is the first standard deviation coefficient.

[0143] The second standard deviation coefficient is set based on the expected false alarm rate of the in-vehicle life form detection system. For the approximate normal distribution probability density function of the continuous presence time of the life form in the correct case, if the false alarm rate is B%, then the multiple of σ2 corresponding to the probability value (1-B)% (accuracy) is the second standard deviation coefficient.

[0144] As an example, the expected false negative rate of the system is 0.3%, so the standard deviation corresponding to the probability value (1-0.3%)=99.7% is 3 times σ1 (ie "3*σ1" or "3σ1"), and the first standard deviation coefficient is 3.

[0145] The expected false alarm rate of the system is 0.3%, so the standard deviation corresponding to the probability value (1-0.3%)=99.7% is 3 times σ2 (ie "3*σ2" or "3σ2"), and the second standard deviation coefficient is 3.

[0146] After obtaining the first mean, the first standard deviation, and the first standard deviation coefficient, μ1+3σ1 is selected as the lower limit of the second time threshold.

[0147] After obtaining the second mean, the second standard deviation, and the second standard deviation coefficient, μ2-3σ2 is selected as the upper limit of the second time threshold.

[0148] Comparing the lower limit value of the second time threshold and the upper limit value of the second time threshold, if μ1+3σ1 is less than μ2-3σ2, when the second time threshold is between [μ1+3σ1,μ2-3σ2], the missed alarm rate and the false alarm rate will be able to meet the system requirements at the same time.

[0149] Therefore, check whether the second time threshold is between [μ1+3σ1,μ2-3σ2]. If so, the second time threshold does not need to be updated; if not, select any value in [μ1+3σ1,μ2-3σ2] to update the second time threshold.

[0150] If μ1+3σ1 is equal to μ2-3σ2, the second time threshold may be updated with μ1+3σ1 or μ2-3σ2.

[0151] If μ1+3σ1 is greater than μ2-3σ2, it means that the current parameters cannot simultaneously meet the preset missed alarm rate and false alarm rate. In this case, at least one of the following methods can be used to update the parameters for determining whether a living being remains in the vehicle.

[0152] When the system's detection result (such as detecting a living being or detecting the absence of a living being) is consistent with the actual result in the car, the detection result is a true detection result. Considering that there is a limit to the accuracy of the system's single detection that can obtain a true detection result (C%, the false alarm rate is 1-C%), in order to improve the accuracy of the monitoring system, so that the monitoring system can eventually output a reliable detection result and correctly issue a corresponding alarm or exit the monitoring of the remaining living things in the car, the condition for judging the system's correct detection result can be set to n consecutive single detections that are all true detection results. In this way, the detection accuracy of the system will become (1-(1-C%) n ), the corresponding system false alarm rate becomes (1-C%) n .

[0153] For example, if the single accuracy rate C% is 95%, the single false alarm rate is (1-C%) = 5%. The condition for judging the system as a correct detection result is set to that two consecutive single detections are true detection results. At this time, the system false alarm rate is (1-C%) 2=(5%) 2 =0.25%, the system detection accuracy is (1-(1-C%) 2 )=1-0.0025=99.75%.

[0154] Therefore, when the accuracy of a single detection cannot meet the requirements of a higher system detection accuracy or a lower system false alarm rate, the accuracy of the system can be improved by setting results based on multiple correct detections.

[0155] The "number of times" mentioned above can be either consecutive or cumulative. When the values ​​for the consecutive and cumulative values ​​are the same, the accuracy corresponding to the consecutive values ​​will be higher than the accuracy corresponding to the cumulative values. The specific choice of whether to use the consecutive or cumulative value is generally based on the characteristics of the data and the accuracy requirements of the system.

[0156] Accordingly, increasing the first quantity threshold can reduce the false alarm rate.

[0157] Similarly, increasing the second quantity threshold can reduce the false negative rate.

[0158] Increase the duration of the detection cycle, increase the base duration of a single statistic, and improve the detection rate of life remains. For example, increase the duration of the detection cycle from 60 seconds to 90 seconds.

[0159] Setting the second time threshold to the second time threshold lower limit value can meet the requirement of missed alarm rate; or setting the second time threshold to the second time threshold upper limit value can meet the requirement of false alarm rate.

[0160] Furthermore, when the second time threshold is set to the second time threshold lower limit, the first quantity threshold can also be increased simultaneously. In this case, the second time threshold lower limit meets the requirement for the missed alarm rate. Increasing the first quantity threshold can reduce the false alarm rate, thereby ensuring that both the missed alarm rate and the false alarm rate meet the system requirements. Alternatively, when the second time threshold is set to the second time threshold upper limit, the second quantity threshold can also be increased simultaneously. In this case, the second time threshold upper limit meets the requirement for the false alarm rate. Increasing the second quantity threshold can reduce the missed alarm rate, thereby ensuring that both the missed alarm rate and the false alarm rate meet the system requirements.

[0161] Next, referring to FIG. 5 , FIG. 5 is a schematic diagram illustrating the main process steps for updating the in-vehicle life form retention determination parameter based on the cumulative existence time of the life form in the historical alarm data according to an embodiment of the present application. The main process steps include:

[0162] Step S501: Acquire correct cases and incorrect cases from historical alarm data in the vehicle within a set time range;

[0163] Step S502: Obtaining the third mean and third standard deviation of the cumulative existence time of the living body in the error case;

[0164] Step S503: Obtain the fourth mean and fourth standard deviation of the cumulative existence time of the living body in the correct cases;

[0165] Step S504: updating at least one of the parameters for determining whether a living being remains in the vehicle based on the third mean, the third standard deviation, the fourth mean, and the fourth standard deviation, wherein the parameters for determining whether a living being remains in the vehicle include a detection period, a second time threshold, a third time threshold, a first quantity threshold, and a second quantity threshold, and the second time threshold is less than the third time threshold.

[0166] The method of step S501 is the same as that of step S301. In actual application, it is only necessary to execute step S501 or step S301 each time the parameters for determining whether a living body remains in the vehicle are checked and updated.

[0167] When statistically analyzing the cumulative existence time of living organisms based on correct cases and incorrect cases, it can also be considered that the distribution of the cumulative existence time of living organisms in correct cases and incorrect cases approximately conforms to the normal distribution.

[0168] Accordingly, the parameters for judging the presence of living beings in the vehicle can be checked and updated based on the mean μ, standard deviation σ of the approximate normal distribution of the cumulative existence time of the living beings in correct cases and incorrect cases, and the characteristics of the probability density function - the 68-95-99.7 rule (empirical rule).

[0169] In step S502 , a third mean μ3 and a third standard deviation σ3 of the cumulative existence time of the living body in the error case are obtained.

[0170] In step S503 , a fourth mean μ4 and a fourth standard deviation σ4 of the cumulative existence time of the living body in the correct cases are obtained, and μ3 is smaller than μ4.

[0171] Continue reading Figure 6 to explain the specific steps of step S504 in conjunction with Figure 6. Figure 6 is a flow chart of the specific steps of step S504 in the embodiment of the present application.

[0172] The third standard deviation coefficient is set based on the expected false negative rate of the in-vehicle life form monitoring system. For an approximate normal distribution probability density function of the cumulative presence time of life forms in error cases, if the false negative rate is D%, then the third standard deviation coefficient is the multiple of σ3 corresponding to the probability value 1-D%.

[0173] The fourth standard deviation coefficient is set based on the expected false alarm rate of the in-vehicle life form detection system. For the probability density function of the approximate normal distribution of the cumulative presence time of life forms in correct cases, if the false alarm rate is E%, then the multiple of σ4 corresponding to the probability value 1-E% (accuracy rate) is the fourth standard deviation coefficient.

[0174] As an example, the expected false negative rate of the system is 0.3%, so the standard deviation corresponding to the probability value (1-0.3%)=99.7% is 3 times σ3 (ie "3*σ3" or "3σ3"), and the third standard deviation coefficient is 3.

[0175] The expected false alarm rate of the system is 0.3%, so the standard deviation corresponding to the probability value (1-0.3%)=99.7% is 3 times σ4 (ie "3*σ4" or "3σ4"), and the fourth standard deviation coefficient is 3.

[0176] After obtaining the third mean, the third standard deviation, and the third standard deviation coefficient, μ3+3σ3 is selected as the lower limit of the third time threshold.

[0177] After obtaining the fourth mean, the fourth standard deviation, and the fourth standard deviation coefficient, μ4-3σ4 is selected as the upper limit of the third time threshold.

[0178] Compare the lower limit value of the third time threshold and the upper limit value of the third time threshold. If μ3+3σ3 is less than μ4-3σ4, when the third time threshold is between [μ3+3σ3,μ4-3σ4], the missed alarm rate and the false alarm rate will be able to meet the system requirements at the same time.

[0179] Check whether the third time threshold is between [μ3+3σ3,μ4-3σ4]. If so, the third time threshold does not need to be updated; if not, any value in [μ3+3σ3,μ4-3σ4] can be selected to update the third time threshold.

[0180] If μ3+3σ3=μ4-3σ4, the third time threshold can be updated with μ3+3σ3 or μ4-3σ4.

[0181] If μ3+3σ3 is greater than μ4-3σ4, it means that the current parameters may not meet both the missed alarm rate and the false alarm rate. In this case, at least one of the following methods can be used to update the parameters for determining whether a living being remains in the vehicle.

[0182] Increase the detection cycle length, increase the base time of a single statistical analysis, and improve the detection rate of life remains. For example, increase the detection cycle length from 60 seconds to 90 seconds.

[0183] Setting the third time threshold to the third time threshold lower limit value can meet the requirement of missed alarm rate; or setting the third time threshold to the third time threshold upper limit value can meet the requirement of false alarm rate.

[0184] Increasing the first quantity threshold can reduce the false alarm rate.

[0185] Increasing the second quantity threshold can reduce the false negative rate.

[0186] In addition, when the third time threshold is set to the third time threshold lower limit value and the first quantity threshold value is increased; in this case, the third time threshold lower limit value meets the requirement for the missed alarm rate, and increasing the first quantity threshold value can reduce the false alarm rate, so that both the missed alarm rate and the false alarm rate meet the system requirements. Alternatively, when the third time threshold is set to the third time threshold upper limit value and the second quantity threshold value is increased; in this case, the third time threshold upper limit value meets the requirement for the false alarm rate, and increasing the second quantity threshold value can reduce the missed alarm rate, so that both the missed alarm rate and the false alarm rate meet the system requirements.

[0187] It should be noted that, in actual applications, it is possible to check whether the parameters for determining whether a living body remains in the vehicle need to be updated based only on the statistical analysis results of the continuous existence time of the living body, or it is possible to check whether the parameters for determining whether a living body remains in the vehicle need to be updated based only on the statistical analysis results of the cumulative existence time of the living body, or it is possible to check whether the parameters for determining whether a living body remains in the vehicle need to be updated based on the statistical analysis results of both the continuous existence time of the living body and the cumulative existence time of the living body.

[0188] When updating parameters for determining whether a life form has been detected in a vehicle, users can choose to update only one parameter or multiple parameters simultaneously, and the second time threshold must be less than the third time threshold. By continuously iteratively updating parameters for determining whether a life form has been detected in a vehicle, the accuracy of monitoring for the presence of a life form in the vehicle can be further improved, while also achieving a good balance between false positives and false negatives.

[0189] The specific data statistical analysis results used to check whether the parameters for judging whether the remaining life forms in the vehicle need to be updated, and which parameters to update each time, can be set by those skilled in the art according to actual conditions.

[0190] Furthermore, the life form is set as a child, and information about whether there is a child in the car is obtained based on the life form detection sensor, and child left in the car is monitored based on the life form left monitoring method described in the above embodiment.

[0191] It should be noted that this application does not limit the method of obtaining living organisms and identifying the categories of living organisms. As an example, living organism information can be obtained through image sensors, millimeter-wave radar sensors, etc., and the categories of living organisms can be judged, where the categories of living organisms include children, adults, pets, etc.

[0192] In another embodiment, as shown in FIG7 , for a specific vehicle model, in step S701, the vehicle model is obtained. In step S702, based on all historical alarm data corresponding to the vehicle model, at least one of the vehicle's remaining life-form detection parameters is updated for the vehicle model. The vehicle's remaining life-form detection parameters include a detection period, a second time threshold, a third time threshold, a first quantity threshold, and a second quantity threshold, with the second time threshold being less than the third time threshold. In this case, since vehicles of the same model have essentially the same life-form detection sensors and environments, the iteratively optimized vehicle's remaining life-form detection parameters will be more suitable for that vehicle model, further improving the accuracy of vehicle remaining life-form detection.

[0193] In another embodiment, as shown in FIG8 , for a vehicle with a high false alarm rate, in step S801, the vehicle's VIN code is obtained; in step S802, at least one of the vehicle's in-vehicle life form retention judgment parameters can be updated based solely on all historical alarm data corresponding to the vehicle's VIN code. The in-vehicle life form retention judgment parameters include a detection period, a second time threshold, a third time threshold, a first quantity threshold, and a second quantity threshold, and the second time threshold is less than the third time threshold. This provides a feasible solution for individual cases.

[0194] Furthermore, the present application also provides a system for monitoring the remaining life forms in a vehicle, which includes a vehicle and a computing device.

[0195] This application does not limit the location and form of the computing device. The computing device can be a cloud server in the embodiment of this application as shown in Figure 1, or a local dedicated server. The computing device can obtain the alarm data of the in-vehicle life-remaining monitoring of the vehicles in the system, and regularly update the in-vehicle life-remaining judgment parameters based on the historical alarm data of the in-vehicle life-remaining monitoring.

[0196] In some special embodiments, the computing device may also be a vehicle controller, which stores the alarm data of the in-vehicle life-remaining monitoring generated by the vehicle, and periodically updates the in-vehicle life-remaining judgment parameters of the vehicle based on the historical alarm data of the in-vehicle life-remaining monitoring of the vehicle.

[0197] The relevant user personal information that may be involved in the various embodiments of this application is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy and necessity, and based on the reasonable purposes of business scenarios, to process the personal information that users actively provide during the use of products / services or generated due to the use of products / services, as well as the personal information obtained with the user's authorization.

[0198] The personal information processed by the Applicant will vary depending on the specific product / service scenario and will be based on the specific scenario in which the user uses the product / service. This may involve the user's account information, device information, driving information, vehicle information, or other related information. The Applicant will treat the user's personal information and its processing with a high degree of diligence.

[0199] The Applicant attaches great importance to the security of user personal information and has taken reasonable and feasible security measures that comply with industry standards to protect user information and prevent personal information from being accessed, disclosed, used, modified, damaged or lost without authorization.

[0200] It should be noted that the terms "first," "second," and other ordinal numbers in the specification and claims of this application and the accompanying drawings are used only to distinguish similar objects, and are not used to describe or indicate a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0201] Thus far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present application.

Claims

1. A method for monitoring the presence of living beings left in a vehicle, characterized in that, The method includes: Obtaining the continuous presence time of the living body and the cumulative presence time of the living body within the detection period according to a preset detection period; For the detection period, when the continuous presence time of any one of the living bodies is greater than or equal to the second time threshold, or the cumulative presence time of the living body is greater than or equal to the third time threshold, determining that the detection period is a detection period with a living body present; Obtaining the cumulative quantity of the detection periods with a living body present, and when the cumulative quantity of the detection periods with a living body present is greater than or equal to the first quantity threshold, performing a secondary alarm.

2. The in-vehicle vital-sign residue monitoring method according to claim 1, wherein The method further includes: Updating at least one of the judgment parameters for the presence of a living body left in the vehicle based on the historical alarm data of the monitoring of the presence of a living body left in the vehicle; Wherein, the judgment parameters for the presence of a living body left in the vehicle include the detection period, the second time threshold, the third time threshold, the first quantity threshold, and a second quantity threshold for judging that there is no life in the vehicle, and the second time threshold is less than the third time threshold.

3. The in-vehicle living body residue monitoring method according to claim 2, wherein, The method further includes: For the detection period, when the continuous presence time of any one of the living bodies is less than the second time threshold and the cumulative presence time of the living body is less than the third time threshold, determining that the detection period is a detection period without a living body present; Obtaining the continuous quantity of the detection periods without a living body present, and when the continuous quantity of the detection periods without a living body present is greater than or equal to the second quantity threshold, determining that there is no living body in the vehicle.

4. The in-vehicle vital sign detection method according to claim 2, wherein The method further includes: Obtaining the correct cases and incorrect cases in the historical alarm data within a set time range; Performing at least one of the following update methods: Respectively obtaining a first mean value and a first standard deviation of the continuous presence time of the living body in the incorrect cases, and a second mean value and a second standard deviation of the continuous presence time of the living body in the correct cases, and updating at least one of the judgment parameters for the presence of a living body left in the vehicle based on the first mean value, the first standard deviation, the second mean value, and the second standard deviation; Respectively obtaining a third mean value and a third standard deviation of the cumulative presence time of the living body in the incorrect cases, and a fourth mean value and a fourth standard deviation of the cumulative presence time of the living body in the correct cases, and updating at least one of the judgment parameters for the presence of a living body left in the vehicle based on the third mean value, the third standard deviation, the fourth mean value, and the fourth standard deviation.

5. The in-vehicle living body left-behind monitoring method according to claim 4, wherein, The method further includes: Obtaining a lower limit value of the second time threshold based on the first mean value, the first standard deviation, and a preset first standard deviation coefficient; Obtaining an upper limit value of the second time threshold based on the second mean value, the second standard deviation, and a preset second standard deviation coefficient; Updating at least one of the judgment parameters for the presence of a living body left in the vehicle based on the lower limit value of the second time threshold and the upper limit value of the second time threshold.

6. The in-vehicle vital sign left-behind monitoring method according to claim 5, characterized in that, The method further includes: When the lower limit value of the second time threshold is less than the upper limit value of the second time threshold, checking whether the second time threshold is within the numerical range of [the lower limit value of the second time threshold, the upper limit value of the second time threshold]; When the second time threshold is not within the numerical range of [the lower limit value of the second time threshold, the upper limit value of the second time threshold], select any value within the numerical range of [the lower limit value of the second time threshold, the upper limit value of the second time threshold] to update the second time threshold.

7. The in-vehicle living body left-behind monitoring method according to claim 5, characterized in that The method further includes: When the lower limit value of the second time threshold is greater than the upper limit value of the second time threshold, perform at least one of the following update methods: Increase the duration of the detection period; Update the second time threshold; Increase the first quantity threshold; Increase the second quantity threshold; Wherein, the updated second time threshold is one of the lower limit value of the second time threshold and the upper limit value of the second time threshold.

8. The in-vehicle living body residue monitoring method according to claim 4, characterized in that, The method further includes: Obtain a lower limit value of the third time threshold based on the third mean, the third standard deviation, and a preset third standard deviation coefficient; Obtain an upper limit value of the third time threshold based on the fourth mean, the fourth standard deviation, and a preset fourth standard deviation coefficient; Update at least one of the in-vehicle living body left-behind judgment parameters based on the lower limit value of the third time threshold and the upper limit value of the third time threshold.

9. The in-vehicle vital sign residue monitoring method according to claim 8, characterized in that, The method further includes: When the lower limit value of the third time threshold is less than the upper limit value of the third time threshold, check whether the third time threshold is within the numerical range of [the lower limit value of the third time threshold, the upper limit value of the third time threshold]; When the third time threshold is not within the numerical range of [the lower limit value of the third time threshold, the upper limit value of the third time threshold], select any value within the numerical range of [the lower limit value of the third time threshold, the upper limit value of the third time threshold] to update the third time threshold.

10. The in-vehicle living body residue monitoring method according to claim 8, wherein The method further includes: When the lower limit value of the third time threshold is greater than the upper limit value of the third time threshold, perform at least one of the following update methods: Increase the duration of the detection period; Update the third time threshold; Increase the first quantity threshold; Increase the second quantity threshold; Wherein, the updated third time threshold is one of the lower limit value of the third time threshold and the upper limit value of the third time threshold.

11. The method for monitoring the presence of a living being left in a vehicle according to claim 2, wherein The method further includes at least one of the following methods: Update at least one of the in-vehicle living body left-behind judgment parameters based on the historical alarm data of the vehicle model according to the vehicle model; Update at least one of the in-vehicle living body left-behind judgment parameters based on the historical alarm data of the vehicle VIN according to the vehicle VIN.

12. The in-vehicle vital sign monitoring method according to claim 1, characterized in that, The method further includes: When the cumulative quantity of the presence-of-living-body detection period is greater than or equal to the third quantity threshold, perform a third-level alarm; or, When the duration of the second-level alarm is greater than or equal to the fifth time threshold, perform a third-level alarm.

13. The method for monitoring the presence of a living being left in a vehicle according to claim 1, wherein, The method further includes: Detect whether there is a living body in the vehicle within a first preset time; Compare whether the living body presence time is greater than or equal to the first time threshold; When the living body presence time is greater than or equal to the first time threshold, perform a first alarm.

14. An in-vehicle living body left-behind monitoring system, characterized in that, The system includes a vehicle and a computing device, and the vehicle is configured to perform the following operations: Obtain the continuous presence time and cumulative presence time of the living body within the detection period according to a preset detection period; For the detection period, when the continuous presence time of any one of the living bodies is greater than or equal to the second time threshold, or the cumulative presence time of the living body is greater than or equal to the third time threshold, determine that this detection period is a detection period with a living body present; Obtain the cumulative quantity of the detection periods with a living body present. When the cumulative quantity of the detection periods with a living body present is greater than or equal to the first quantity threshold, execute a secondary alarm.

15. The in-vehicle living body residue monitoring system according to claim 14, wherein The computing device is configured to: Update at least one of the in-vehicle living body left-behind judgment parameters based on the historical alarm data of in-vehicle living body left-behind monitoring; Wherein, the in-vehicle living body left-behind judgment parameters include the detection period, the second time threshold, the third time threshold, the first quantity threshold, and a second quantity threshold for judging that there is no life in the vehicle, and the second time threshold is less than the third time threshold.

16. The in-vehicle vital sign monitoring system according to claim 15, characterized in that, The vehicle is further configured to perform the following operations: For the detection period, when the continuous presence time of any one of the living bodies is less than the second time threshold and the cumulative presence time of the living body is less than the third time threshold, determine that this detection period is a detection period without a living body present; Obtain the consecutive quantity of the detection periods without a living body present. When the consecutive quantity of the detection periods without a living body present is greater than or equal to the second quantity threshold, determine that there is no living body in the vehicle.

17. The in-vehicle vital-sign residue monitoring system according to claim 15, wherein The computing device is configured to perform the following operations: Obtain the correct cases and wrong cases in the historical alarm data within a set time range; Execute at least one of the following update methods: Respectively obtain the first mean and the first standard deviation of the continuous presence time of the living body in the wrong cases, and the second mean and the second standard deviation in the correct cases, and update at least one of the in-vehicle living body left-behind judgment parameters based on the first mean, the first standard deviation, the second mean, and the second standard deviation; Respectively obtain the third mean and the third standard deviation of the cumulative presence time of the living body in the wrong cases, and the fourth mean and the fourth standard deviation in the correct cases, and update at least one of the in-vehicle living body left-behind judgment parameters based on the third mean, the third standard deviation, the fourth mean, and the fourth standard deviation.

18. The in-vehicle vital-sign residue monitoring system according to claim 17, wherein The computing device is configured to perform the following operations: Obtain a lower limit value of the second time threshold based on the first mean, the first standard deviation, and a preset first standard deviation coefficient; Obtain an upper limit value of the second time threshold based on the second mean, the second standard deviation, and a preset second standard deviation coefficient; Update at least one of the in-vehicle living body left-behind judgment parameters based on the lower limit value of the second time threshold and the upper limit value of the second time threshold.

19. The in-vehicle living body residue monitoring system according to claim 17, characterized in that, The computing device is configured to perform the following operations: Obtain a lower limit value of the third time threshold based on the third mean, the third standard deviation, and a preset third standard deviation coefficient; Obtain an upper limit value of the third time threshold based on the fourth mean, the fourth standard deviation, and a preset fourth standard deviation coefficient; Update at least one of the in-vehicle living body left-behind judgment parameters based on the lower limit value and the upper limit value of the third time threshold.

20. The in-vehicle vital sign residue monitoring system according to claim 15, wherein The computing device is configured to perform the following operations: Based on the vehicle model, update at least one of the in-vehicle living body left-behind judgment parameters according to the historical alarm data of the vehicle model; Based on the vehicle VIN code, update at least one of the in-vehicle living body left-behind judgment parameters according to the historical alarm data of the vehicle VIN code.

Images