Driver electrocardiosignal analysis method, device and storage medium

Abstract

The application discloses a driver electrocardiosignal analysis method and device and a storage medium. The method comprises the following steps: acquiring a first electrocardiosignal feature of a driver collected in a current baseline updating period; determining whether an electrocardiosignal feature baseline meets an updating condition based on the first electrocardiosignal feature and the electrocardiosignal feature baseline, wherein the electrocardiosignal feature baseline is obtained based on a second electrocardiosignal feature of the driver collected in a historical baseline updating period; and if the electrocardiosignal feature baseline meets the updating condition, updating the electrocardiosignal feature baseline based on the first electrocardiosignal feature, so as to detect the state of the driver through the updated electrocardiosignal feature baseline. The above scheme realizes real-time detection of driver distraction and ensures the accuracy of driver state detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicles, in particular to a driver electrocardiosignal analysis method and device and storage medium. BACKGROUND

[0002] With the continuous development of science, the popularity of automobiles is increasing. When driving a car, the distraction of the driver can cause the driver's field of view to narrow, weaken the driver's response ability and reaction time, etc. At present, the distraction of the driver has become one of the main reasons for road traffic accidents.

[0003] In the prior art, for traffic accidents, the video recorded by the driving recorder is usually used to view the cause of the accident. This method can only be used as a basis for inferring the cause of the accident after the accident occurs, and cannot detect the distraction of the driver before the accident occurs. SUMMARY

[0004] The present application provides a driver electrocardiosignal analysis method and device and storage medium.

[0005] In a first aspect, the present application provides a driver electrocardiosignal analysis method, comprising:

[0006] obtaining a first electrocardiosignal feature of a driver collected in a current baseline update period;

[0007] determining whether an electrocardiosignal feature baseline satisfies an update condition based on the first electrocardiosignal feature and the electrocardiosignal feature baseline, wherein the electrocardiosignal feature baseline is obtained based on a second electrocardiosignal feature of the driver collected in a historical baseline update period;

[0008] if the electrocardiosignal feature baseline satisfies the update condition, updating the electrocardiosignal feature baseline based on the first electrocardiosignal feature, so as to detect the state of the driver through the updated electrocardiosignal feature baseline.

[0009] Optionally, the obtaining of the first electrocardiosignal feature of the driver collected in the current baseline update period comprises:

[0010] obtaining a first electrocardiosignal of the driver collected in the current baseline update period;

[0011] extracting time domain features and frequency domain features of the first electrocardiosignal as the first electrocardiosignal feature.

[0012] Optionally, the electrocardiosignal feature baseline is determined by the following steps:

[0013] obtaining a second electrocardiosignal feature of the driver collected in the historical baseline update period;

[0014] determine the electrocardio feature baseline based on the average value vector and the standard deviation vector corresponding to the second electrocardio feature.

[0015] Optionally, the determining whether the electrocardio feature baseline satisfies the update condition based on the first electrocardio feature and the electrocardio feature baseline comprises:

[0016] performing standardization processing on the first electrocardio feature based on the electrocardio feature baseline;

[0017] inputting the feature after the standardization processing into a preset distraction state discrimination model to output a distraction score sequence of the driver when driving in the current baseline update period;

[0018] determining whether the electrocardio feature baseline satisfies the update condition based on the distraction score sequence and the first electrocardio feature.

[0019] Optionally, the first electrocardio feature comprises a heart rate feature, and the determining whether the electrocardio feature baseline satisfies the update condition based on the distraction score sequence and the first electrocardio feature comprises:

[0020] determining a target proportion of the distraction score sequence that is less than a preset score value;

[0021] performing a DF test on the heart rate feature acquired in the current baseline update period to obtain a target test result;

[0022] if the target proportion is greater than a first threshold value and the target test result is less than a second threshold value, it is determined that the electrocardio feature baseline satisfies the update condition.

[0023] Optionally, after the determining whether the electrocardio feature baseline satisfies the update condition based on the first electrocardio feature and the electrocardio feature baseline, the method further comprises:

[0024] if the electrocardio feature baseline does not satisfy the update condition, entering a next baseline update period to determine whether to update the electrocardio feature baseline in the next baseline update period.

[0025] Optionally, the updating the electrocardio feature baseline based on the first electrocardio feature comprises:

[0026] determining the updated electrocardio feature baseline based on an average value vector and a standard deviation vector corresponding to the first electrocardio feature.

[0027] In a second aspect, the present application further provides a driver electrocardio signal analysis device, comprising:

[0028] an acquisition module configured to acquire a first electrocardio feature of a driver collected in a current baseline update period;

[0029] a processing module configured to determine, based on the first electrocardio feature and an electrocardio feature baseline, whether the electrocardio feature baseline satisfies an update condition, wherein the electrocardio feature baseline is obtained based on second electrocardio features of the driver collected in a historical baseline update period;

[0030] an updating module configured to, if the electrocardio feature baseline satisfies the update condition, update the electrocardio feature baseline based on the first electrocardio feature, so as to detect the state of the driver by using the updated electrocardio feature baseline.

[0031] In a third aspect, an embodiment of the present application provides a driver electrocardio signal analysis device, which comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors to perform operation instructions corresponding to the method provided in the first aspect.

[0032] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement steps corresponding to the driver electrocardio signal analysis method provided in the first aspect.

[0033] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0034] In the embodiments of the present application, the first electrocardio feature of the driver collected in a current baseline update period is obtained, and based on the first electrocardio feature and an electrocardio feature baseline, it is determined whether the electrocardio feature baseline satisfies an update condition, wherein the electrocardio feature baseline is obtained based on second electrocardio features of the driver collected in a historical baseline update period; if the electrocardio feature baseline satisfies the update condition, the electrocardio feature baseline is updated based on the first electrocardio feature, so as to detect the state of the driver by using the updated electrocardio feature baseline. In the above solution, on the one hand, the state of the driver during driving is detected by using the electrocardio feature of the driver, so that whether the driver is distracted can be determined in time; on the other hand, when the state of the driver is detected by using the electrocardio feature, the electrocardio feature baseline is dynamically updated, so that the current electrocardio baseline can be changed with the electrocardio signal of the driver at different times, the consistency between the current electrocardio baseline and the electrocardio signal of the user is ensured, and the accuracy of the state detection of the driver is improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0036] Figure 1 A flow chart of a driver electrocardiosignal analysis method provided for an embodiment of the present specification;

[0037] Figure 2 A schematic diagram of a driver electrocardiosignal analysis device provided for an embodiment of the present specification;

[0038] Figure 3 A schematic diagram of another driver electrocardiosignal analysis device provided for an embodiment of the present specification. DETAILED DESCRIPTION

[0039] Embodiments of the present application provide a driver electrocardiosignal analysis method, device and storage medium.

[0040] The general idea of the technical solutions of the embodiments of the present application is as follows: acquiring a first electrocardiosignal feature of a driver collected in a current baseline updating period; determining whether an electrocardiosignal feature baseline meets an updating condition based on the first electrocardiosignal feature and the electrocardiosignal feature baseline, wherein the electrocardiosignal feature baseline is obtained based on a second electrocardiosignal feature of the driver collected in a historical baseline updating period; and if the electrocardiosignal feature baseline meets the updating condition, updating the electrocardiosignal feature baseline based on the first electrocardiosignal feature, so as to detect the state of the driver by using the updated electrocardiosignal feature baseline.

[0041] In the above-mentioned solution, on the one hand, the state of the driver during driving is detected by the electrocardiosignal feature of the driver, which can timely determine whether the driver is distracted, and on the other hand, the electrocardiosignal feature baseline is dynamically updated when the state of the driver is detected by the electrocardiosignal feature, which can ensure that the current electrocardiosignal baseline can change with the electrocardiosignal of the driver at different times, ensure the consistency between the current electrocardiosignal baseline and the electrocardiosignal of the user, and thus improve the accuracy of the state detection of the driver.

[0042] In order to better understand the above technical solutions, the above technical solutions will be described in detail in combination with the drawings of the specification and specific embodiments.

[0043] Firstly, the term "and / or" appearing in the present document only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present document generally represents an "or" relationship between the front and rear associated objects.

[0044] The embodiments of the present specification provide a driver electrocardiosignal analysis method, as shown in the method, the method comprises the following steps: Figure 1

[0045] Step S101: acquiring a first electrocardiosignal feature of a driver collected in a current baseline update period;

[0046] Step S102: determining whether the electrocardiosignal baseline meets the update condition based on the first electrocardiosignal feature and the electrocardiosignal baseline, wherein the electrocardiosignal baseline is obtained based on a second electrocardiosignal feature of the driver collected in a historical baseline update period;

[0047] Step S103: if the electrocardiosignal baseline meets the update condition, updating the electrocardiosignal baseline based on the first electrocardiosignal feature, to detect the state of the driver through the updated electrocardiosignal baseline.

[0048] The scheme in the embodiments of the present specification can be applied in a vehicle terminal, can be applied in a server capable of communicating with a vehicle, and can be applied in a system composed of a vehicle terminal and a server, which is not limited here.

[0049] In order to collect the electrocardiosignal of the driver, a sensor capable of collecting the electrocardiosignal of the driver can be arranged in the vehicle, for example, a steering wheel, a safety belt, a seat, etc. provided with an electrocardiosignal collector can be installed in the vehicle. In addition, the driver can also wear a device capable of collecting the electrocardiosignal, such as a bracelet, a watch, a heart rate belt, etc.

[0050] ​In step S101, the current baseline update period can be an arbitrary period of time during the driving process of the driver. It should be noted that the lengths of the baseline update periods can be the same or different, which is not limited herein. In an embodiment, the driving process of the driver can be periodically divided according to a preset length, for example, every 5 minutes, every 10 minutes, or every hour. In another embodiment, the lengths of the baseline update periods can be different, for example, the first baseline update period for setting the initial electrocardio feature baseline is 10 minutes, and the baseline update periods for updating the electrocardio feature baseline are 15 minutes. In the embodiments of the present specification, there can be intervals between the periods, for example, entering the next baseline update period every preset time interval, or the periods can be continuous without intervals, which is not limited herein.

[0051] Based on each baseline update period, the electrocardio signal of the driver in the period can be obtained by the electrocardio signal acquisition device, and then the electrocardio signal is preprocessed, such as removing noise, to obtain the preprocessed electrocardio signal. Then, the electrocardio feature corresponding to the preprocessed electrocardio signal is obtained by feature extraction.

[0052] In the embodiments of the present specification, the first electrocardio feature can be obtained by the following steps: obtaining the first electrocardio signal of the driver collected in the current baseline update period; extracting the time domain feature and the frequency domain feature of the first electrocardio signal as the first electrocardio feature.

[0053] Specifically, taking the length of the current baseline update period as 10 minutes as an example, the first electrocardio signal is continuously collected for 10 minutes, which can be a preprocessed signal. Further, the time domain feature and the frequency domain feature of the first electrocardio signal are extracted, and the time window of the feature extraction can be set according to actual needs, for example, 30 seconds, 60 seconds, etc. The time domain feature includes but is not limited to the heart rate feature and the heart rate variability time domain feature, and the heart rate variability feature can include the standard deviation of all sinus RR intervals (SDNN), the root mean square of adjacent RR interval differences (RMSSD), etc. The frequency domain feature can include high frequency feature, low frequency feature, etc. The first electrocardio signal feature can include one or more of the above features, which is not limited herein.

[0054] In step S102, the electrocardio feature baseline can reflect the electrocardio signal state of the driver when the driver is not distracted. Since the electrocardio feature of the driver also changes at different time periods, for example, the electrocardio feature of the driver collected in the morning is different from the electrocardio feature of the driver collected in the evening, and the electrocardio feature of the driver collected at the beginning of the driving is also different from the electrocardio feature of the driver collected after driving for 3 hours. Therefore, if a fixed electrocardio feature baseline is used to determine whether the driver is distracted, it is obviously unreasonable, and the determination result is also inaccurate. Based on this, in the embodiments of the present specification, whether the electrocardio feature baseline satisfies the updating condition is detected to dynamically update the electrocardio feature baseline, so that the electrocardio feature baseline can match the current electrocardio condition of the driver, thereby improving the accuracy of the distraction determination based on the electrocardio feature baseline.

[0055] In the specific implementation process, the electrocardio feature baseline can be obtained by the following steps: obtaining the second electrocardio feature of the driver collected in the historical baseline updating period; and determining the electrocardio feature baseline based on the mean value vector and the standard deviation vector corresponding to the second electrocardio feature.

[0056] Specifically, the historical baseline updating period can be the previous period of the current baseline updating period, or the previous N periods of the current baseline updating period. N is an integer greater than 1. In the specific implementation process, after the driver starts the vehicle, the driver can enter the first baseline updating period, and the mean value vector and the standard deviation vector of the electrocardio feature are used as the initial electrocardio feature baseline for determining whether the driver is distracted by collecting the electrocardio signal and extracting the corresponding electrocardio feature in the period. Since the electrocardio state of the driver changes, in the second baseline updating period, if the initial electrocardio feature baseline satisfies the updating condition, the initial electrocardio feature baseline is updated to obtain a new electrocardio feature baseline. Similarly, in each baseline updating period, the electrocardio feature baseline updated last time is detected, and if it needs to be updated, the electrocardio feature baseline is updated and then enters the next baseline updating period, and if it does not need to be updated, it directly enters the next baseline updating period.

[0057] Therefore, for the current baseline updating period, the electrocardio feature baseline is the baseline determined in the historical baseline updating period. If the electrocardio feature baseline is updated in the previous period of the current updating period, the historical baseline updating period is the previous baseline updating period, and the second electrocardio feature is the electrocardio feature corresponding to the electrocardio signal collected in the previous baseline updating period.

[0058] In the embodiments of the present specification, since the electrocardio feature can include multiple features, such as a heart rate feature, a heart rate variability feature, a frequency domain feature, etc., for each type of feature, there can be a corresponding electrocardio feature baseline. Each type of electrocardio feature baseline includes an average value vector and a standard deviation vector of the feature.

[0059] In the implementation process, the update condition of the electrocardio feature baseline can include multiple conditions, for example, comparing the first electrocardio feature with the electrocardio feature baseline, and when the comparison result meets the preset error range, it is considered that the update condition is met. In the embodiments of the present specification, step S102 can be implemented by the following steps: performing standardization processing on the first electrocardio feature based on the electrocardio feature baseline; inputting the standardized feature into a preset distraction state discrimination model to output a distraction score sequence of the driver when driving in the current baseline update period; and determining whether the electrocardio feature baseline meets the update condition based on the distraction score sequence and the first electrocardio feature.

[0060] Specifically, the preset distraction state discrimination model is used to determine whether the driver is distracted, and the preset distraction state discrimination model can be pre-trained. In one embodiment, for each driver, multiple groups of electrocardio features of the driver in a historical period (such as the past three months, half a year) can be collected, and the electrocardio features corresponding to each collection time are standardized based on the electrocardio feature baseline at the collection time. At the same time, the driver state (including the distraction state and the non-distraction state) corresponding to each group of electrocardio features is recorded as the label of the group of electrocardio features, and the above standardized electrocardio features and the corresponding labels are used as training samples of the model. The initial distraction state discrimination model is trained by using the training samples to obtain a trained model as the preset distraction state discrimination model. The input of the model is the electrocardio feature of the driver, and the output is the distraction score of the driver. In one embodiment, the higher the distraction score, the higher the degree of distraction of the driver.

[0061] Since the electrocardio feature baseline is the baseline of the stable driving of the driver, i.e., the non-distraction state, the driver state corresponding to the first electrocardio feature can be determined by the preset distraction state discrimination model. Specifically, the electrocardio feature baseline in the first electrocardio feature can be standardized, i.e., the first electrocardio feature is standardized, and the standardized feature is output to the preset distraction state discrimination model to obtain a driver distraction score sequence corresponding to the current baseline update period.

[0062] Further, if it is determined that the driver is in the state of distraction based on the distraction score sequence, the first electrocardio feature cannot be used for baseline updating, i.e., the updating condition is not met. If it is determined that the driver is in the state of non-distraction based on the distraction score sequence, i.e., the driver is in the process of stable driving in the current baseline updating period, the baseline updating can be performed by using the first electrocardio feature.

[0063] In the embodiments of the present specification, the first electrocardio feature includes a heart rate feature, and whether the electrocardio feature baseline meets the updating condition can be determined by the following steps: determining a target proportion of the distraction scores less than a preset score in the distraction score sequence; performing DF test on the heart rate feature obtained in the current baseline updating period to obtain a target test result; and if the target proportion is greater than a first threshold and the target test result is less than a second threshold, it is determined that the electrocardio feature baseline meets the updating condition.

[0064] Specifically, the preset score can be set according to actual needs, which is not limited here, such as 30, 40, 50, etc. It should be noted that the lower the preset score, the lower the distraction degree of the driver. The number of scores less than the preset score is counted from the obtained distraction score sequence, and the total number of scores in the sequence is counted, so as to calculate the target proportion of the scores less than the preset score. If the target proportion is greater than the first threshold, it is indicated that the driver is in the state of non-distraction most of the time in the current baseline updating period, wherein the first threshold can be set according to actual needs, such as 90%, 95%, etc.

[0065] In addition, considering that the electrocardio feature baseline needs to reflect the change of the driver in the stable state of electrocardio, in the embodiments of the present specification, DF test is performed on the heart rate feature in the current baseline updating period, and if the target test result is less than the second threshold (such as p value < 0.05), it is indicated that the heart rate feature is in a relatively stable state. Of course, the second threshold can also be set to other values, which is not limited here.

[0066] In the embodiments of the present specification, the electrocardio feature baseline is determined to meet the updating condition only when the target proportion is greater than the first threshold and the target test result is less than the second threshold, which is more strict for updating the electrocardio feature baseline, and can ensure the accuracy and usability of the updated electrocardio feature baseline.

[0067] It should be noted that in addition to using the heart rate feature, other features can also be used for baseline updating judgment, for example, using heart rate variability feature, which is not limited here.

[0068] Further, in step S103, if the electrocardio characteristic baseline satisfies the updating condition, the electrocardio characteristic baseline is updated based on the first electrocardio characteristic. The baseline updating can be implemented in various ways. In one embodiment, the baseline updating can perform the following steps: based on the mean value vector and the standard deviation vector corresponding to the first electrocardio characteristic, the updated electrocardio characteristic baseline is determined.

[0069] Specifically, since the electrocardio characteristic of the driver changes, if the historical determined electrocardio characteristic is used for distraction judgment, the accuracy of the distraction judgment cannot be guaranteed. Therefore, the first electrocardio characteristic obtained in the current baseline updating period can be used to re-determine the electrocardio characteristic baseline, that is, the mean value vector and the standard deviation vector corresponding to the first electrocardio characteristic are used as the updated electrocardio characteristic baseline, and are used in subsequent distraction judgment.

[0070] Of course, the baseline updating can also be implemented in other ways, for example, the current used electrocardio characteristic baseline is corrected based on the mean value vector and the standard deviation corresponding to the first electrocardio characteristic, and the corrected electrocardio characteristic baseline is used as the updated electrocardio characteristic baseline.

[0071] In the embodiments of the present specification, if the electrocardio characteristic baseline does not satisfy the updating condition in the current baseline updating period, the electrocardio characteristic baseline is kept unchanged, and the next baseline updating period is entered, so that the electrocardio characteristic obtained in the next baseline updating period is used to re-determine whether to update the electrocardio characteristic baseline in the next baseline updating period. Through this cyclic manner, the electrocardio characteristic baseline is kept dynamically updated, so that the electrocardio characteristic baseline is most consistent with the current electrocardio characteristic of the driver.

[0072] Further, in the embodiments of the present specification, the distraction state of the driver can be judged in real time based on the electrocardio characteristic baseline. Specifically, the electrocardio signal of the driver is collected and processed in real time, that is, the electrocardio characteristic of the collected signal is extracted, and the extracted electrocardio characteristic is standardized based on the electrocardio characteristic, and the standardized characteristic is input into the preset distraction state discrimination model to output the distraction score at the current time. In order to avoid misjudgment, the target number of distraction scores can be recorded continuously, and if a preset proportion of the target number of distraction scores are greater than a set value, it is considered that the driver is in a distraction state. The set value and the preset proportion can be set according to actual needs, which are not limited here. It should be noted that the distraction state judgment process of the driver and the baseline updating can be two independent processes, and the set value in the distraction state judgment process and the preset value in the baseline updating process for judging whether to satisfy the updating condition can be the same or different, which is not limited here.

[0073] If it is detected that the driver is in a distracted state, the driver can be warned, for example, by a speaker to make a sound warning to the driver, or by a vibration device installed on the steering wheel to make a voice warning to the driver, etc.

[0074] In order to better understand the scheme provided in the embodiments of the present specification, the specific implementation of the driver electrocardio signal analysis method is exemplified as follows:

[0075] In this embodiment, when it is detected that the driver enters the driving process, the first baseline updating period is entered. Since the first baseline updating period corresponds to the initial driving of the driver, distraction driving usually does not occur, and therefore the initial electrocardio feature baseline can be obtained directly according to the electrocardio features obtained in the first baseline updating period.

[0076] After entering the second baseline updating period, the electrocardio features corresponding to the second baseline updating period are obtained. Further, the electrocardio features corresponding to the second baseline updating period are standardized based on the initial electrocardio feature baseline, and the standardized features are input into the preset distraction state discrimination model to obtain a distraction score sequence in the second baseline updating period. If the target proportion of the distraction score sequence that is less than a preset score is greater than 90%, and the p value in the heart rate feature DF test is <0.05, then the mean vector and the standard deviation vector are recalculated based on the electrocardio features of the second baseline updating period to determine a new electrocardio feature baseline. If the above conditions are not met, the baseline is not updated, and the next baseline updating period is entered. The above process is cycled to realize dynamic updating of the electrocardio feature baseline.

[0077] In this embodiment, while the electrocardio feature baseline is updated, the distraction state of the driver can also be detected in real time. Specifically, since the driver usually does not drive distractedly in the initial driving period, the state of the driver does not need to be judged by the preset distraction state discrimination model in the first baseline updating period. After the first baseline updating period, i.e., after the initial electrocardio feature baseline is generated, the distraction score of the driver can be output in real time by the preset distraction state discrimination model. Since the electrocardio feature baseline is constantly updated, after the electrocardio feature baseline is updated each time, the updated electrocardio feature baseline is used to standardize the current electrocardio features obtained, which are used as the input of the preset distraction state discrimination model, greatly improving the accuracy of the distraction state judgment of the driver.

[0078] In summary, the scheme of the embodiments of the present specification can effectively solve the problem of inaccurate prediction of the distraction state of the driver due to the difference in physiological signals of the driver in long-time driving, and can more accurately detect the distraction state of the driver, thereby improving driving safety.

[0079] Based on the same inventive concept, the embodiments of the present specification also provide a driver electrocardiosignal analysis device, as shown in the drawings, which comprises: Figure 2

[0080] The acquisition module 201 is configured to acquire a first electrocardiosignal feature of a driver collected in a current baseline update period.

[0081] The processing module 202 is configured to determine whether the electrocardiosignal feature baseline meets an update condition based on the first electrocardiosignal feature and the electrocardiosignal feature baseline, wherein the electrocardiosignal feature baseline is obtained based on a second electrocardiosignal feature of the driver collected in a historical baseline update period.

[0082] The update module 203 is configured to update the electrocardiosignal feature baseline based on the first electrocardiosignal feature if the electrocardiosignal feature baseline meets the update condition, so as to detect the state of the driver by using the updated electrocardiosignal feature baseline.

[0083] Optionally, the acquisition module 201 is configured to:

[0084] acquire a first electrocardiosignal of the driver collected in the current baseline update period.

[0085] extract time domain features and frequency domain features of the first electrocardiosignal as the first electrocardiosignal feature.

[0086] Optionally, the device further comprises a baseline determination module configured to:

[0087] acquire a second electrocardiosignal feature of the driver collected in the historical baseline update period.

[0088] determine the electrocardiosignal feature baseline based on a mean value vector and a standard deviation vector corresponding to the second electrocardiosignal feature.

[0089] Optionally, the processing module 202 is configured to:

[0090] perform standardization processing on the first electrocardiosignal feature based on the electrocardiosignal feature baseline.

[0091] input the feature after the standardization processing into a preset distraction state discrimination model, and output a distraction score sequence of the driver when driving in the current baseline update period.

[0092] determine whether the electrocardiosignal feature baseline meets the update condition based on the distraction score sequence and the first electrocardiosignal feature.

[0093] Optionally, the first electrocardiosignal feature comprises a heart rate feature, and the processing module 202 is configured to:

[0094] ​Determine the target percentage of the distraction score sequence that is less than a preset score;

[0095] Perform a DF test on the heart rate features obtained in the current baseline update cycle to obtain the target test results;

[0096] If the target proportion is greater than the first threshold and the target test result is less than the second threshold, then the ECG characteristic baseline is determined to meet the update condition.

[0097] Optionally, the device further includes:

[0098] The cycle control module is used to enter the next baseline update cycle if the ECG characteristic baseline does not meet the update conditions, so as to determine whether to update the ECG characteristic baseline in the next baseline update cycle.

[0099] Optionally, update module 203 for:

[0100] Based on the mean vector and standard deviation vector corresponding to the first ECG feature, the updated ECG feature baseline is determined.

[0101] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the driver's electrocardiogram signal analysis method, and will not be elaborated here.

[0102] Based on the same inventive concept, embodiments of this specification also provide a driver's electrocardiogram signal analysis device, such as... Figure 3 As shown, it includes a memory 308, a processor 302, and a computer program stored in the memory 308 and executable on the processor 302. When the processor 302 executes the program, it implements the steps of any of the methods of the driver electrocardiogram signal analysis method described above.

[0103] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 308. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 306 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 308 can be used to store data used by processor 302 during operation.

[0104] Based on the same inventive concept, the present application also provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of any of the driver ECG signal analysis methods described above.

[0105] The specification is presented to enable any person skilled in the art to practice the methods, systems, and computer program products described herein. The computer program Figure 1 one or more functions specified in the flow or flows and / or blocks Figure 1 device that implements the functions specified in the flow or flows and / or blocks.

[0106] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 one or more functions specified in the flow or flows and / or blocks Figure 1 device that implements the functions specified in the flow or flows and / or blocks.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 one or more functions specified in the flow or flows and / or blocks Figure 1 device that implements the functions specified in the flow or flows and / or blocks.

[0108] While preferred embodiments of the application have been described, modifications and variations can be apparent to those skilled in the art once aware of the general underlying concepts. Accordingly, the appended claims intend to embrace all such modifications and variations as fall within the scope of the application.

[0109] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for analyzing driver electrocardiogram signals, characterized in that, include: The driver's first electrocardiogram features collected within the current baseline update cycle are obtained, wherein the driver's driving process is divided into multiple baseline update cycles. Based on the first ECG feature and the ECG feature baseline, determining whether the ECG feature baseline meets the update conditions includes: based on the ECG feature baseline and the first ECG feature, determining the driver's distraction score sequence during driving within the current baseline update cycle; determining the target proportion of the distraction score sequence that is less than a preset score; performing a DF test on the heart rate features obtained in the current baseline update cycle to obtain a target test result; if the target proportion is greater than a first threshold and the target test result is less than a second threshold, then determining that the ECG feature baseline meets the update conditions; wherein, the ECG feature baseline is obtained based on the driver's second ECG feature collected within a historical baseline update cycle, the distraction score sequence is used to characterize the driver's degree of distraction, and the target test result is used to characterize the stability of the driver's heart rate features; If the ECG feature baseline meets the update condition, the ECG feature baseline is updated based on the first ECG feature, so as to detect the driver's state through the updated ECG feature baseline.

2. The method as described in claim 1, characterized in that, The acquisition of the driver's first electrocardiogram features collected within the current baseline update period includes: Acquire the first electrocardiogram signal of the driver collected within the current baseline update cycle; The time-domain and frequency-domain features of the first electrocardiogram (ECG) signal are extracted and used as the first ECG feature.

3. The method as described in claim 1, characterized in that, The baseline characteristics of the electrocardiogram were determined through the following steps: Acquire the second electrocardiogram features of the driver collected within the historical baseline update period; The baseline of the electrocardiogram feature is determined based on the mean vector and standard deviation vector corresponding to the second electrocardiogram feature.

4. The method as described in claim 1, characterized in that, The step of determining the driver's distraction score sequence during driving within the current baseline update period based on the ECG baseline and the first ECG feature includes: Based on the aforementioned ECG feature baseline, the first ECG feature is standardized. The standardized features are input into a preset distraction state discrimination model, and the distraction score sequence of the driver during driving within the current baseline update cycle is output.

5. The method as described in claim 1, characterized in that, After determining whether the ECG feature baseline meets the update conditions based on the first ECG feature and the ECG feature baseline, the method further includes: If the ECG characteristic baseline does not meet the update conditions, the process proceeds to the next baseline update cycle to determine whether to update the ECG characteristic baseline in the next baseline update cycle.

6. The method as described in claim 1, characterized in that, The step of updating the ECG feature baseline based on the first ECG feature includes: Based on the mean vector and standard deviation vector corresponding to the first ECG feature, the updated ECG feature baseline is determined.

7. A driver's electrocardiogram signal analysis device, characterized in that, include: The acquisition module is used to acquire the first electrocardiogram features of the driver collected within the current baseline update cycle; A processing module, configured to determine whether the electrocardiogram (ECG) feature baseline meets the update condition based on the first ECG feature and the ECG feature baseline, comprising: determining a distraction score sequence of the driver during driving in the current baseline update period based on the ECG feature baseline and the first ECG feature; determining a target proportion of the distraction score sequence that is less than a preset score; performing a DF test on the heart rate feature obtained in the current baseline update period to obtain a target test result; if the target proportion is greater than a first threshold and the target test result is less than a second threshold, determining that the ECG feature baseline meets the update condition; wherein the ECG feature baseline is obtained based on the second ECG feature of the driver collected in a historical baseline update period, the distraction score sequence is used to characterize the distraction degree of the driver, and the target test result is used to characterize the stability degree of the heart rate feature of the driver; An update module, configured to update the ECG feature baseline based on the first ECG feature if the ECG feature baseline meets the update condition, so as to detect the state of the driver through the updated ECG feature baseline.

8. A driver's electrocardiogram signal analysis device, characterized in that, It includes a memory and one or more programs, wherein one or more programs are stored in the memory and are configured to be executed by one or more processors to perform the operation instructions corresponding to the method according to any one of claims 1 to 6.

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

Images