Vehicle-mounted system takeover method, vehicle-mounted system takeover device and readable storage medium

Abstract

The invention belongs to the field of intelligent driving, and particularly relates to a vehicle-mounted system takeover method, a vehicle-mounted system takeover device and a readable storage medium. The method comprises the following steps of: inputting physical sign data into a physical sign model through a physical sign detection module, judging a dangerous driving grade and a first coping strategy through the physical sign model, obtaining a second coping strategy through a man-machine, and further judging according to the current reliability and a preset reliability threshold so as to select the first coping strategy and the second coping strategy. By means of the method, the situation that when the sign data suddenly change, the user judges in combination with reality can be avoided, misjudgment of objective detection of the vehicle is reduced, and meanwhile, when the user has a slight condition, the user can autonomously and safely select a reasonable coping strategy for driving. And the decision of the user can be judged in turn through the setting of the current reliability, so that the problem that the user still drives in danger under high-risk physical sign data is prevented.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent driving, and in particular relates to a vehicle-mounted system takeover method, a vehicle-mounted system takeover device and a readable storage medium. Background Art

[0002] During vehicle driving, some sudden illnesses may cause the driver to lose control of the vehicle, eventually causing the vehicle to enter an uncontrollable driving state and causing serious consequences. Among these diseases, diseases involving the cardiovascular system are particularly serious, which may cause the driver to be unable to drive normally. Among the diseases caused by the cardiovascular system, some sudden illnesses may cause the driver to lose consciousness and fall into a coma when the disease occurs, further putting the driver and the vehicle in a dangerous situation, and more seriously causing an accident caused by the uncontrollable vehicle.

[0003] In the prior art, a detection method and corresponding rescue measures and control methods are also provided. When it is detected that a user is ill, protective measures are immediately executed through the vehicle-mounted system.

[0004] However, the existing technology is very limited when it comes to subjective judgment of the driver and forced takeover of the vehicle. Since the vital sign data is mutagenic, signal deviation may occur at the mutation node, resulting in inaccurate detection; thus, the data and strategy of vehicle judgment are not applicable to the current driving scenario and are inconsistent with the actual situation of the user. At the same time, in some sudden illnesses, when the onset is mild or in the middle stage (such as hypertension, arrhythmia, etc.), the user is still conscious and can still drive safely. At this time, the user can choose a safer driving method, such as pulling over or driving into a service area. If the vehicle is forcibly intervened in the control at this time, it may cause misjudgment of the state on some highway sections, resulting in direct pulling over. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a vehicle system takeover method, a smart bracelet, a driving system and a computer-readable storage medium. After detecting physical signs and judging the current posture danger level and the corresponding first response strategy, the second response strategy is further obtained through human-computer interaction. When selecting the first response strategy and the second response strategy, a current reliability judgment is also provided. The first response strategy designated for the vehicle or the second response strategy selected by the person is further selected through the current reliability judgment. The current reliability is judged by physical sign data, and the signal deviation caused by data mutation is prevented through human judgment, thereby preventing inaccurate vehicle judgment. It can also enable users to independently perform safety control according to actual conditions in some mild physical sign conditions. On the other hand, the accuracy of human judgment can be further judged through the current reliability, thereby preventing users from driving dangerously in high-risk situations.

[0006] The purpose of the present invention is achieved by the following technical means:

[0007] In a first aspect, the present invention provides a vehicle system takeover method, comprising:

[0008] Obtaining the first physical sign data of the target user and inputting it into the physical sign judgment model;

[0009] The physical sign judgment model determines the target user's dangerous driving level and the first response strategy according to the first physical sign data;

[0010] Receive feedback information from the target user, and determine a second response strategy based on the feedback information;

[0011] After obtaining the second coping strategy, obtaining the second vital sign data of the target user to set the current reliability;

[0012] It is determined whether the current reliability is greater than a preset reliability threshold. If so, the second response strategy is selected; otherwise, the first response strategy is selected.

[0013] When driving, the target driver's vital sign data is detected in real time, and the dangerous driving level of the current target driver is obtained by judgment. This method monitors the target vital sign data of the driver in real time when driving to prevent sudden illness, especially cardiovascular disease, so that the vehicle is out of control and causes danger in the driving process; and according to the dangerous driving level, the domain controller queries the first response strategy, and at the same time, through human-computer interaction, manually confirms the second response strategy, and compares the current reliability with the preset reliability threshold to select the first response strategy or the second response strategy. The purpose of this method is to provide two strategies. The first response strategy is a safety strategy preset by the vehicle itself, and the second response strategy is a strategy confirmed or proposed by the target driver itself, so that when the strategy is implemented, the user is first reminded through feedback information, so that the user understands the current situation, and selects an autonomous strategy based on the current situation and the actual situation, so as to prevent unreasonable problems caused by vehicle decisions not being combined with reality. At the same time, it can also enable the vehicle to autonomously drive in combination with actual conditions and experience when the user is in a minor condition. At the same time, the current reliability is used for auxiliary judgment. After the current reliability is judged with the preset reliability threshold, the first response strategy or the second response strategy is selected. When judging, the current reliability is introduced for auxiliary judgment, and the current reliability is analyzed through the vital sign data and adjusted with the vital sign, so that the vehicle is more reasonable when choosing a strategy. The reference of the current reliability can in turn judge the user's behavior and prevent the user from making dangerous driving actions when he is in a high-level vital sign. Among them, the first vital sign data can be obtained through the vehicle's sensors, vehicle vital sign sensing modules and other modules that can perform vital sign detection. When judging the current reliability, the second vital sign data is also obtained. The second vital sign data is the target person's vital sign data obtained by the vehicle after the user makes the second response strategy. The second vital sign data has the same detection items as the first vital sign data, or the second vital sign data adds detection items to the technology of the first vital sign data. Therefore, the acquisition method of the second vital sign data can be the same as the acquisition method of the first vital sign data. The second vital sign data can be verified on the basis of the first vital sign data after the target person has fed back information, so as to prevent the misjudgment of the vehicle caused by the mutant and instantaneous vital sign data in the first vital sign data. At the same time, using the second vital sign data as the current reliability calculation can avoid some dangerous vital sign data that suddenly appear when the first vital sign data is detected. When the judgment is made, the dangerous first vital sign data has been alleviated, and then the second vital sign data becomes normal, resulting in increased reliability and avoiding incorrect takeover of the vehicle.

[0014] In some implementations, after determining the second coping strategy, obtaining second vital sign data of the target user to determine the current reliability includes:

[0015] A fuzzy set is defined, the second vital sign data of the target user is fuzzified to obtain first fuzzy data, and the data is input into the fuzzy set;

[0016] A membership function is defined, and the first fuzzy data is input into the membership function to obtain the membership;

[0017] Define fuzzy rules, and obtain the current reliability through weighted average method based on the fuzzy rules and membership degree.

[0018] The current reliability is fuzzified by the vital sign data, generally multiple vital sign data, and the membership function is set accordingly, and the membership can be calculated, and finally the current reliability is evaluated according to the multiple vital sign data. This technology is essentially a weight distribution technology. According to the combination of multiple vital sign data, the degree of data is judged according to the fuzzy value, and further according to the membership of different data, the contribution value of the data to the current reliability is calculated, so that the current reliability changes, and the current reliability is also affected by multiple vital sign data, so that the current reliability is more reasonable. When calculating the current reliability, first define the fuzzy set, and fuzzify the real-time vital sign data. Fuzzification is also the definition of data. The data is defined as a type according to the data value range and forms the first fuzzy data, and the data is input into the fuzzy set. Then define the membership function, and calculate the membership of a certain data in the membership function, which can also be understood as the proportion of data in a certain range, and further set the fuzzy rules to determine the relationship between the first fuzzy data and the current reliability, and calculate the entire current reliability through the membership. In this method, the current reliability is a variable, which is indirectly affected by the physical sign data, and can further make the current reliability more reasonable when judging the entire strategy based on the physical sign.

[0019] In some implementations, a fuzzy set is defined, the second vital sign data of the target user is fuzzified to obtain first fuzzy data, and the data is input into the fuzzy set; including:

[0020] The value range of the second vital sign data is set to mild, moderate, and severe, and the detected second vital sign data is fuzzily defined as any one of mild, moderate, and severe fuzzy data according to the value range; and the fuzzy data is input into the fuzzy set.

[0021] By fuzzifying the data, the entire current reliability calculation is made relatively simple, especially when multiple vital sign data have different data types, and there is no need for normalization or data processing.

[0022] In some implementations, defining a membership function, inputting the first fuzzy data into the membership function, and obtaining the membership; comprises:

[0023] The membership function of each feature element is determined by triangular fuzzy numbers or Gaussian fuzzy numbers, and then the membership is calculated.

[0024] By using triangular fuzzy numbers or Gaussian fuzzy numbers, the membership function can be defined by using triangular fuzzy numbers or Gaussian fuzzy numbers respectively according to the case where the range of some first fuzzy data is linear or discrete.

[0025] In some implementations, fuzzy rules are defined, and according to the fuzzy rules and the degree of membership, the current reliability is obtained by weighted average method, including:

[0026] When the fuzzy data is mild, the current reliability is high; when the fuzzy data is moderate, the current reliability is medium; when the fuzzy data is severe, the current reliability is low;

[0027] After each fuzzy rule is generated, the fuzzy rule weight level is set so that when multiple fuzzy rules simultaneously point to the same current reliability and calculate the overall current reliability, the overall current reliability is calculated by a weighted average algorithm according to the weight level.

[0028] The fuzzy rule is used to determine the relationship between the first fuzzy data determined by the vital sign data and the current reliability, further classify the data, and judge the level of the current reliability. This method can simplify the judgment of the current reliability and connect the data. When multiple fuzzy rules are set, after each fuzzy rule is generated, the fuzzy rule weight level is set so that when multiple fuzzy rules point to the same current reliability at the same time, when calculating the specific current reliability, the overall current reliability is calculated according to the weight level through the weighted average algorithm.

[0029] In some implementations, the physical sign judgment model determines the target user's dangerous driving level and the first coping strategy based on the first physical sign data, including:

[0030] According to the physical sign data, the overall judgment is made into a slight dangerous driving level, a moderate dangerous driving level, or a high dangerous driving level, and the first response strategy corresponding to the dangerous driving level is queried;

[0031] The first response strategy includes the slightly dangerous driving level strategy, the moderately dangerous driving level strategy, and the highly dangerous driving level strategy.

[0032] By combining multiple vital sign data, the danger level is judged, and the corresponding first response strategy is further obtained, and the second response strategy of the target driver is obtained through human-computer interaction. Through the first response strategy and the second response strategy, the objective first response strategy through vital sign data and the subjective second response strategy are obtained, making the vehicle strategy more reasonable.

[0033] In some implementations, receiving feedback information from the target user and determining a second response strategy according to the feedback information includes:

[0034] The target person provides feedback on the first response strategy, and determines the second response strategy based on the feedback information;

[0035] The feedback information includes the target person's confirmation of the coping strategy, rejection of the coping strategy, and additional coping strategies proposed by the target person.

[0036] The feedback information of the second response strategy can not only serve to remind the target person, but also further provide the target person's subjective strategy when the vehicle selects a response strategy.

[0037] In a second aspect, the present invention provides a vehicle-mounted system takeover device, comprising:

[0038] A physical sign data acquisition module is used to obtain the physical sign data of the target person and input it into the physical sign judgment model;

[0039] A dangerous driving judgment module, used for the physical sign judgment model to determine the dangerous driving level and the first response strategy of the target user according to the first physical sign data;

[0040] A strategy implementation module, used to receive feedback information from target users and determine a second response strategy based on the feedback information;

[0041] The reliability calculation module is used to obtain the second vital sign data of the target user after determining the second coping strategy to determine the current reliability.

[0042] Through various modules, the acquisition of vital sign data, dangerous driving judgment, strategy implementation and current reliability calculation are realized, so that the present invention implements the vehicle system takeover method.

[0043] In some embodiments, the vital sign data acquisition module includes any one or more of a smart bracelet, a camera, a thermal sensor, and an infrared sensor.

[0044] Among them, the smart bracelet is equipped with a vehicle-computer linkage device, which is used to connect to the vehicle and provide human heart blood data.

[0045] In a third aspect, the present invention proposes a computer-readable storage medium, which stores at least one execution instruction. When the executable instruction runs on the vehicle system takeover device of the second aspect, the device executes the vehicle system takeover method of any implementation method of the first aspect.

[0046] Beneficial effects of the vehicle-mounted system takeover method, vehicle-mounted system takeover device and readable storage medium of the present invention:

[0047] The physical sign data of the physical sign detection module is input into the physical sign model, and the physical sign model determines the dangerous driving level and the first response strategy, and obtains the second response strategy through the human-machine interface, and further judges based on the current reliability and the preset reliability threshold to select the first response strategy and the second response strategy. This method can avoid the user's actual judgment when the physical sign data suddenly changes, reduce the misjudgment of the vehicle's objective detection, and at the same time, when the user has a minor condition, the user can autonomously and safely choose a reasonable response strategy for driving. The current reliability setting can also judge the user's decision in turn to prevent the user from still driving dangerously under high-risk physical sign data. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0049] Figure 1 It is the main flow chart of the present invention;

[0050] Figure 2 is the fuzzy logic flow chart of the present invention;

[0051] Figure 3 is a schematic diagram of the driving system of the present invention;

[0052] Figure 4 This is the architecture diagram of the smart bracelet of the present invention;

[0053] Figure 5 This is a secondary confirmation flow chart of the smart bracelet of the present invention;

[0054] Figure 6 This is a diagram of the interactive architecture of the driving system and the smart bracelet of the present invention. DETAILED DESCRIPTION

[0055] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0056] Embodiment 1:

[0057] like Figure 1 As shown, the present invention proposes a vehicle system takeover method, comprising the following steps:

[0058] Step 101: Acquire first physical sign data of a target user and input into a physical sign judgment model;

[0059] Specifically, according to the physical sign detection module, first physical sign data of the target person is obtained, wherein the first physical sign data includes heart rate, diastolic blood pressure, systolic blood pressure and facial features, and the first physical sign data is input into the physical sign judgment model.

[0060] The beneficial effect of this step is that it detects the vital sign data and obtains the vital sign data of the target person in real time, thereby preventing the occurrence of sudden illness, and can analyze abnormal data in advance. Furthermore, the data changes can be recorded so that the data can be uploaded to the system, so that the system can analyze the physical condition of the target person.

[0061] Step 102: The physical sign judgment model determines the target user's dangerous driving level and the first coping strategy according to the first physical sign data;

[0062] Specifically, the dangerous driving level analysis is performed based on the acquired physical sign data. For example, for cardiovascular diseases, when detecting physical sign data, including the detection of heart rate, diastolic pressure and systolic pressure, combined with various existing medical data, the data of heart rate, diastolic pressure and systolic pressure are combined to judge the dangerous driving level, such as mild dangerous driving level, moderate dangerous driving level and deep dangerous driving level; and further, the judgment conditions of the data are set, such as assuming that systolic pressure, diastolic pressure and heart rate are systolic, diastolic, heart_rate respectively; and the judgment conditions are set as:

[0063] if(systolic>140and systolic<=159and diastolic>90and diastolic<=99and heart_rate>=60and heart_rate<100)or(systolic>=90and systolic<=150anddiastolic>=60and diastolic<=100and heart_rate>100)or(systolic>=70andsystolic<90and diastolic>=50and diastolic<60and heart_rate>=95and heart_rate<=100)or(heart_rate>=40and heart_rate<60)or(heart_rate==100):

[0064] Determined as "mildly dangerous driving level"

[0065] elif (systolic >= 160 && systolic <= 179 && diastolic >= 100 && diastolic < 109 && heart_rate >= 60 && heart_rate < 100) || (systolic >= 90 && systolic <= 140 && diastolic >= 60 && diastolic <= 90 && heart_rate >= 40 && heart_rate < 60) || (systolic < 90 && diastolic < 60 && heart_rate > 120) || (systolic >= 60 && systolic < 70 && diastolic >= 40 && diastolic < 50 && heart_rate >= 100 && heart_rate <= 120) || (systolic >= 160 && systolic <= 179) || (diastolic >= 100 && diastolic < 109) || (heart_rate >= 30 && heart_rate < 40) || (heart_rate >= 100 && heart_rate <= 120):

[0066] Determined as "Moderate Risk Driving Level"

[0067] elif (systolic >= 180 && diastolic >= 110 && heart_rate >= 100) || (systolic < 90 && diastolic < 60 && heart_rate < 40) || (systolic < 80 && diastolic < 50 && heart_rate < 60) || (systolic < 60 && diastolic < 40 && (heart_rate > 120 || heart_rate < 30)) || (systolic >= 180) || (diastolic >= 110) || (heart_rate < 30) || (heart_rate > 120):

[0068] Determined as "Severe Risk Driving Level"

[0069] else:

[0070] Determined as "Normal Driving Level"

[0071] Furthermore, different dangerous driving levels are obtained. At the same time, different first response strategies are set for different dangerous driving levels in combination with the facial features of the target person. Among them, the judgment condition is to calibrate the data according to medical data. When judging the dangerous driving level, multiple diseases can be judged according to multiple judgment conditions, such as hypertension, arrhythmia, acute myocardial infarction, shock, etc., so as to judge the dangerous driving level in combination with the physical sign data characteristics of multiple possible diseases.

[0072] The beneficial effect of this step is that a preliminary judgment can be made on the current posture status based on the vital sign data, and by combining multiple judgment conditions and factors, the domain controller can classify the current driving, set different solutions according to different levels, and control other functions of the vehicle, further achieving more intelligent vehicle control and safe driving.

[0073] Step 103: receiving feedback information from the target user, and determining a second response strategy according to the feedback information;

[0074] Specifically, the second response strategy is obtained through human-computer interaction to obtain the subjective judgment strategy of the current target person. The beneficial effect of this step is that through the active confirmation of the target user, while further reminding the user, it is also possible to combine subjective judgment when obtaining the first response strategy.

[0075] Step 104: After obtaining the second coping strategy, obtain the second vital sign data of the target user to set the current reliability;

[0076] Specifically, after obtaining the second coping strategy, the second physical sign data is further obtained by the method of obtaining the first physical sign data, and the second physical sign data has the same items as the original first physical sign data, including heart rate, diastolic blood pressure, systolic blood pressure and facial features. Furthermore, on the basis of the above items, the physical sign data change trend can be added, and the physical sign data change trend can be expressed in the form of aggravation or alleviation.

[0077] The beneficial effect of this step is that the acquisition of the second vital sign data is added, so that the second vital sign data can better represent the subjective judgment state of the current target person. The first vital sign data represents the objective physical state at the previous detection moment. And the first vital sign data can be verified and compared with the second vital sign data to avoid the vehicle erroneous takeover caused by the convex edge of the data, and also to avoid the first response strategy still being implemented in a high-level mode after the target person is relieved.

[0078] Step 105: Determine whether the current reliability is greater than a preset reliability threshold, if so, select the second response strategy, otherwise select the first response strategy.

[0079] Specifically, after the domain controller obtains the first response strategy, the second response strategy is obtained from the target driver through voice or other human-computer interaction methods. Through the second response strategy, the target driver can subjectively judge whether to execute the first response strategy or propose other response strategies. Further, when judging, the subjective judgment conditions of the target driver are added. When judging whether to adopt the first response strategy or the second response strategy, the current reliability is set for judgment, wherein the current reliability is calculated for the vital sign data, and its purpose is to further judge whether the second response strategy proposed by the target driver is an erroneous judgment made by ignoring high-risk vital signs, and to determine the timing of the mandatory execution of the first response strategy of the vehicle through the preset reliability threshold. The reliability threshold can be obtained through the convolutional neural network, after training in multiple scenarios, under a reasonable threshold, the first response strategy of the vehicle intervenes, which can reasonably balance the threshold of the target driver and the vehicle switching. Further, by obtaining the second vital sign data for the second time, the first vital sign data obtained for the first time can also be tested for the second time to prevent data mutation, and the current reliability is judged with the new second vital sign data, which can also be aimed at the current reliability of the user's vital signs when making a decision.

[0080] The beneficial measures of this step, through this method, can make the judgment more humane and more in line with the actual ring, at the same time, can also take into account the operating experience of the target driver, at the same time, through the current reliability setting, the vehicle can further combine subjective judgment to select a response strategy, thereby making the entire vehicle control means more intelligent and more reasonable.

[0081] It should be noted that the above steps are not necessarily required to be performed in order, and some steps can be started when the previous steps have not been completed.

[0082] Furthermore, when setting up the detection of vital signs data, multiple and long-term detections can be carried out. In particular, when the vital signs data is about to enter high-risk areas, repeated confirmations can be carried out to further prevent misjudgments caused by sudden changes in data, thereby affecting driving decisions.

[0083] The beneficial effect of the above process is that, when driving, the target driver's vital sign data is detected in real time, and the dangerous driving level of the current target person is obtained by judgment. This method monitors the target vital sign data of the driver in real time when driving to prevent sudden illness, especially cardiovascular disease, so that the vehicle is out of control and causes danger in the driving process; and according to the dangerous driving level, the domain controller queries the first response strategy, and at the same time, through human-computer interaction, manually confirms the second response strategy, and compares the current reliability with the preset reliability threshold, so as to select the first response strategy or the second response strategy. The purpose of this method is to provide two strategies. The first response strategy is a safety strategy preset by the vehicle autonomously, and the second response strategy is a strategy autonomously confirmed or proposed by the target driver, so that when the strategy is implemented, the user is first reminded through feedback information, so that the user understands the current situation, and selects an autonomous strategy based on the current situation and the actual situation, so as to prevent unreasonable problems caused by vehicle decisions not being combined with reality. At the same time, it can also enable the vehicle to autonomously drive in combination with actual conditions and experience when the user is in a minor condition.

[0084] At the same time, the current reliability is used for auxiliary judgment. After the current reliability is judged with the preset reliability threshold, the first response strategy or the second response strategy is selected. When judging, the current reliability is introduced for auxiliary judgment, and the current reliability is analyzed through the vital sign data and adjusted with the vital sign, so that the vehicle is more reasonable when choosing a strategy. The reference of the current reliability can in turn judge the user's behavior and prevent the user from making dangerous driving actions when he is in a high-level vital sign. Among them, the first vital sign data can be obtained through the vehicle's sensors, vehicle vital sign sensing modules and other modules that can perform vital sign detection. When judging the current reliability, the second vital sign data is also obtained. The second vital sign data is the target person's vital sign data obtained by the vehicle after the user makes the second response strategy. The second vital sign data has the same detection items as the first vital sign data, or the second vital sign data adds detection items to the technology of the first vital sign data. Therefore, the acquisition method of the second vital sign data can be the same as the acquisition method of the first vital sign data. The second vital sign data can be verified on the basis of the first vital sign data after the target person has fed back information, so as to prevent the misjudgment of the vehicle caused by the mutant and instantaneous vital sign data in the first vital sign data. At the same time, using the second vital sign data as the current reliability calculation can avoid some dangerous vital sign data that suddenly appear when the first vital sign data is detected. When the judgment is made, the dangerous first vital sign data has been alleviated, and then the second vital sign data becomes normal, resulting in increased reliability and avoiding incorrect takeover of the vehicle.

[0085] Embodiment 2:

[0086] like Figure 2-3 As shown, this embodiment is based on Embodiment 1 and further optimizes and illustrates the process in Embodiment 1.

[0087] In some embodiments, after determining the second coping strategy, obtaining second vital sign data of the target user to determine the current reliability includes:

[0088] Step 201: define a fuzzy set, fuzzify the second vital sign data to obtain first fuzzy data, and input the data into the fuzzy set;

[0089] Specifically, fuzzy sets are defined, such as heart rate: low, medium, high; diastolic blood pressure: low, medium, high; systolic blood pressure: low, medium, high; similarity between facial features and disease models: low, medium, high; complexion: normal, abnormal; and the current reliability of the output is also set with fuzzy sets including low, medium, high; fuzzy sets of multiple signs, fuzzy sets divided by data value ranges, after defining the fuzzy sets, the detected sign data is fuzzily converted into first fuzzy data, for example, the heart rate data of 169 is converted into the first fuzzy data with the first fuzzy data being "medium", and the first fuzzy data with the heart rate being "medium" is input into the fuzzy set, and finally the fuzzy set is set with multiple first fuzzy data sets of sign data.

[0090] The beneficial effect of this step is that, by using the method of fuzzy data, while combining multiple data, it reduces data processing such as data type conversion and data normalization, thereby reducing the complexity of data combination.

[0091] Step 202: define a membership function, input the first fuzzy data into the membership function, and obtain the membership;

[0092] Specifically, a membership function is defined, which is used to judge the membership of the input data in the set. For example, when the heart rate of 169 is in the "medium" data range, the proportion or degree thereof, so that when the weight is set later, the higher the membership, the higher the influence on the output data, that is, the higher the weight.

[0093] The beneficial effect of this step can be further achieved by setting the degree of membership so that when establishing fuzzy data, the data characteristics of the data itself can also be maintained.

[0094] Step 203: define fuzzy rules, and obtain the current reliability through weighted average method according to the fuzzy rules and membership degree.

[0095] Specifically, fuzzy rules are defined. The method of defining fuzzy rules is similar to the method of defining dangerous driving levels mentioned above. For example, systolic, diastolic, and heart rate are defined as systolic, diastolic, and heart_rate respectively. IF (systolic = "low" and diastolic = "low" and heart_rate = "low") corresponds to the current reliability being "high".

[0096] The beneficial effect of this step is that, through this method, the relationship between multiple first fuzzy data and current reliability is defined, and the relationship between data is made clearer through fuzzy data, without the need for data transformation and without considering the inability to connect due to different data types.

[0097] In essence, the current reliability setting is to adjust the weight ratio of the first coping strategy and the second coping strategy according to the vital sign data, and rationally select the coping strategy through the allocation of weights. There are many methods for practical application of this method, including using rule engines to achieve dynamic weight adjustment, using machine learning models to achieve dynamic weight adjustment, and using fuzzy logic applicable to this case to achieve dynamic weight adjustment.

[0098] In this embodiment, the algorithm is mainly used to perform fuzzy processing and data output on the input data, such as defining fuzzy sets, fuzzifying input, formulating fuzzy rules, fuzzy reasoning, and fuzzy output.

[0099] At the same time, the current reliability is used for auxiliary judgment. After the current reliability is judged with the preset reliability threshold, the first response strategy or the second response strategy is selected. When judging, the current reliability is introduced for auxiliary judgment, and the current reliability is analyzed through the physical sign data and adjusted with the physical sign, so that the vehicle is more reasonable when choosing a strategy. The reference of the current reliability can in turn judge the user's behavior and prevent the user from making dangerous driving actions when he is in a high physical sign. Among them, the current reliability is fuzzy processed through the physical sign data, generally multiple physical sign data, and the membership function is set accordingly, and the membership can be calculated, and finally the current reliability is evaluated according to the multiple physical sign data. This technology is essentially a weight distribution technology. According to the combination of multiple physical sign data, the degree of data is judged according to the fuzzy value, and further according to the membership of different data, the contribution value of the data to the current reliability is calculated, so that the current reliability changes, and the current reliability is also affected by multiple physical sign data, so that the current reliability is more reasonable.

[0100] In some embodiments, a fuzzy set is defined, the second vital sign data is fuzzified to obtain first fuzzy data, and the data is input into the fuzzy set; comprising:

[0101] The value range of the second vital sign data is set to mild, moderate, and severe, and the detected real-time vital sign data is fuzzily defined as any one of mild, moderate, and severe fuzzy data according to the value range; and the fuzzy data is input into the fuzzy set.

[0102] Specifically, when differentiating the vital sign data, it can be classified according to the corresponding dangerous driving level, that is, divided into mild, moderate, and severe, and the data is further input into the fuzzy set.

[0103] By fuzzifying the data, the entire current reliability calculation is made relatively simple, especially when multiple vital sign data have different data types, and there is no need for normalization or data processing.

[0104] In some embodiments, a membership function is defined, and the first fuzzy data is input into the membership function to obtain the membership; comprising:

[0105] The membership function of each feature element is determined by triangular fuzzy numbers or Gaussian fuzzy numbers, and then the membership is calculated.

[0106] Specifically, for example, when establishing the membership function of the heart rate, since the heart rate is linear and continuous data within the value range, the function can be established through the triangle fuzzy number. When partitioning, set the data points of 140, 160, and 180, and divide the heart rate value range into (0, 140], (140, 160], (160, 180], (180, 200), so the following piecewise function is obtained:

[0107]

[0108] Among them, f(x) is the actual value of the heart rate. According to the segmentation, the membership degree of the vital sign data in each segment can be obtained, and then the membership of the data in a certain fuzzy set can be obtained.

[0109] By using triangular fuzzy numbers or Gaussian fuzzy numbers, the membership function can be defined by using triangular fuzzy numbers or Gaussian fuzzy numbers respectively according to the case where the data range of some first fuzzy data is linear or discrete.

[0110] In some embodiments, a fuzzy rule is defined, and the current reliability is obtained by a weighted average method according to the fuzzy rule and the membership degree, including:

[0111] When the fuzzy data is mild, the current reliability is high; when the fuzzy data is moderate, the current reliability is medium; when the fuzzy data is severe, the current reliability is low;

[0112] After each fuzzy rule is generated, the fuzzy rule weight level is set so that when multiple fuzzy rules simultaneously point to the same current reliability and calculate the overall current reliability, the overall current reliability is calculated by a weighted average algorithm according to the weight level.

[0113] Specifically, fuzzy rules are set as in the above embodiment, and connections are established between data according to the fuzzy rules. Since the higher the first fuzzy data of the vital sign data, the more dangerous the vital sign data is, the current reliability and the first fuzzy data generated by the vital sign data are often inversely corresponding.

[0114] If there are multiple vital sign data, multiple fuzzy rules are set to define the relationship between the combination of vital sign data and the current reliability; including:

[0115] After each fuzzy rule is generated, the fuzzy rule weight level is set so that when multiple fuzzy rules point to the same current reliability at the same time, when calculating the specific current reliability, the overall current reliability is calculated by a weighted average algorithm according to the weight level.

[0116] Specifically, the relationship between them can be set as follows:

[0117]

[0118] Among them, N is the membership degree, ∑N is the sum of the membership degrees of all the first fuzzy data, M is the weight level, and f(u) is the current reliability. Since the current reliability is the higher the data, the greater the physical problem, the result obtained during the calculation is often inversely proportional to the data.

[0119] The fuzzy rule is used to determine the relationship between the first fuzzy data determined by the vital sign data and the current reliability, further classify the data, and judge the level of the current reliability. This method can simplify the judgment of the current reliability and connect the data. When multiple fuzzy rules are set, after each fuzzy rule is generated, the fuzzy rule weight level is set so that when multiple fuzzy rules point to the same current reliability at the same time, when calculating the specific current reliability, the overall current reliability is calculated according to the weight level through the weighted average algorithm.

[0120] In some embodiments, the physical sign judgment model determines the target user's dangerous driving level and the first response strategy according to the first physical sign data, including:

[0121] The target person provides feedback on the first response strategy, and determines the second response strategy based on the feedback information;

[0122] The feedback information includes the target person's confirmation of the coping strategy, rejection of the coping strategy, and additional coping strategies proposed by the target person.

[0123] Specifically, it is generally divided into three driving levels, and corresponding strategies of different degrees are set according to the three levels.

[0124] Specifically, the mildly dangerous driving level strategy includes Chinese voice feedback, safe driving touch action confirmation, smart bracelet confirmation, and pull-over confirmation;

[0125] The strategies for the moderately dangerous driving level include Chinese voice feedback, safe driving touch action confirmation, smart bracelet confirmation, pull-over confirmation, pull-over confirmation, emergency distress signal confirmation, and emergency contact number dialing confirmation;

[0126] The highly documented driving level strategy includes Chinese voice feedback, safe driving touch action confirmation, smart bracelet confirmation, pull-over parking confirmation, pull-over parking confirmation, emergency distress signal confirmation, 120 call confirmation, emergency contact number call confirmation, and smart bracelet shared location information confirmation;

[0127] By judging the danger level and further deriving the corresponding first response strategy, different response strategies are set according to different levels, which also makes the vehicle's strategy selection more reasonable.

[0128] In some embodiments, in some implementations, the physical sign judgment model determines the target user's dangerous driving level and the first coping strategy according to the first physical sign data, including:

[0129] The target person provides feedback on the first response strategy, and determines the second response strategy based on the feedback information;

[0130] The feedback information includes the target person's confirmation of the coping strategy, rejection of the coping strategy, and additional coping strategies proposed by the target person.

[0131] Specifically, through vehicle-computer interaction methods such as vehicle-computer screen interaction, voice interaction, and vehicle button interaction, the feedback information of the target person is confirmed, and based on the feedback information, the second response strategy of the target person is formed and determined.

[0132] The beneficial effect of this method is that, through the subjective judgment of the target person and the interaction between the vehicle and the computer, while reminding the target person that there is an abnormality in the vital sign data and that attention should be paid, the subjective judgment of the target person can also be obtained, so that the vehicle can make choices based on the subjective judgment of the target person when making objective judgments.

[0133] Embodiment 3:

[0134] like Figure 3-4 As shown, the present invention further proposes a vehicle-mounted system takeover device 300, comprising:

[0135] The physical sign data acquisition module 301 is used to acquire the physical sign data of the target person and input it into the physical sign judgment model;

[0136] The dangerous driving judgment module 302 is used for the physical sign judgment model to determine the dangerous driving level and the first coping strategy of the target user according to the first physical sign data;

[0137] A strategy implementation module 303 is used to receive feedback information from a target user and determine a second response strategy according to the feedback information;

[0138] The central processing unit 304 is used to process complex algorithms and real-time data to ensure efficient operation and rapid response of the system. These core processors are usually high-performance computing platforms that can support tasks such as multi-sensor data fusion, deep learning algorithm reasoning, real-time decision-making and control. Common processors include chips from manufacturers such as Intel, NVIDIA, and ARM. They have powerful computing power and parallel processing capabilities and are suitable for various complex computing tasks in intelligent driving systems. The core processor plays a vital role in the intelligent driving system and is the cornerstone of the system's high performance and stable operation.

[0139] The control execution module 305 controls the vehicle's steering, acceleration and deceleration according to the decision and planning results to achieve precise control of the vehicle. This module usually includes the vehicle power system, steering system, braking system, etc.

[0140] The data storage and communication module 506 is used to store the data acquired by the sensor and to exchange and communicate data with the vehicle's internal system and the external cloud system.

[0141] The safety system module 307 includes a vehicle safety control unit, a safety sensor, etc., which is used to monitor the vehicle status and ensure the safety and controllability of the system.

[0142] The smart bracelet smart driving module 308 is a module for the intelligent driving system of the car to communicate with the smart bracelet. It is a window for the smart bracelet to access and control the intelligent driving vehicle. The smart bracelet exists as an auxiliary external terminal device of the intelligent driving system of the car. Through this module, it communicates with the vehicle-machine interaction module 301 to realize the connection between the bracelet and the driving system.

[0143] The reliability calculation module 309 is used to obtain the second vital sign data of the target user after determining the second coping strategy to determine the current reliability.

[0144] Embodiment 4:

[0145] like Figures 4 to 6 As shown, based on Example 3, in some embodiments, the vital sign data acquisition module includes any one or more of a smart bracelet, a camera, a thermal sensor, and an infrared sensor.

[0146] Among them, the smart bracelet is equipped with a vehicle-computer linkage device, which is used to connect to the vehicle and provide human heart blood data.

[0147] Specifically, this embodiment provides a smart bracelet 400, which further specifically includes:

[0148] The vehicle-machine interaction module 401 is used to apply the vehicle system takeover method described in any one of Example 1 and Example 2. Its function is to be a module responsible for the communication and docking between the smart bracelet and the car's intelligent driving system. The smart bracelet is connected to the car's intelligent driving system to enable the smart bracelet to send instructions to control the vehicle to start the vital sign detection module.

[0149] The human-computer interaction module 402 is mainly used to allow the driver to interact with the smart bracelet, including voice interaction and touch screen mode. This module enables the user to control the smart bracelet through voice commands or gesture operations to perform functions, message confirmation, information input and other operations, thereby improving the convenience and user experience of the smart bracelet. The existence of the human-computer interaction module allows users to use the smart bracelet more conveniently and achieve safer interactive operations during driving.

[0150] These include response strategies for emergency distress signal confirmation, 120 call confirmation, emergency contact number call confirmation, and smart bracelet shared location information confirmation;

[0151] The GPS communication module 402 is mainly used to realize the positioning tracking and data communication functions. The GPS module is used to obtain the current geographical location information of the smart bracelet, which can be used to locate the driver's position. The communication module is used to exchange and communicate data with external devices or cloud systems, including functions such as transmitting health data, receiving notification reminders, and making emergency calls. The existence of these modules can enable the smart bracelet to have functions such as positioning tracking and remote communication, thereby improving the safety and convenience of users.

[0152] The security authentication module 403 is mainly used to ensure the legal and compliant use of the smart bracelet and provide security. This module usually includes functions such as identity authentication, data encryption and secure communication, which are used to verify the identity of the user, protect personal privacy information, and prevent misoperation or unauthorized access and data leakage. The existence of the security authentication module can effectively prevent information security risks, protect the user's personal information and the normal operation of the bracelet function. A security verification mechanism can be established between the smart bracelet and the vehicle to ensure the legality and security of the instructions.

[0153] The display module 404 is mainly used to display relevant information to the user, including time, health data, notification reminders, touch operations, etc. The existence of the display module can improve the interactivity and practicality of the smart bracelet, allowing users to use the bracelet more conveniently and obtain relevant information.

[0154] The data storage and data processing module is mainly used to store and process various data collected by the smart bracelet, including health detection data, location data, etc. This module usually includes a storage chip, a processor and related algorithms for collecting, storing, analyzing and processing data.

[0155] The power module 405 is mainly used to provide power to the wristband to ensure its normal operation. This module usually includes a battery or a charging circuit to store and provide power to support the various functions of the wristband, such as location tracking, emergency calls, health monitoring, etc. The design and management of the power module is crucial to the stability and reliability of the wristband, because it directly affects the service life and performance of the wristband.

[0156] The CPU 406 is mainly responsible for controlling and coordinating the various functional modules and tasks of the smart bracelet. The CPU is usually the core component of the smart bracelet, responsible for processing various data and instructions, coordinating the collection and processing of sensor data, controlling the display content of the display module, managing the data transmission of the communication module, and performing various health monitoring and human-computer interaction functions. The performance and efficiency of the CPU directly affect the speed and functional performance of the bracelet, and is a key component of the smart bracelet.

[0157] The smart bracelet is provided with multiple modules, and in the process, multiple modules are used to detect vital sign data, and combined with response strategies, the strategy is executed.

[0158] Furthermore, in some embodiments, the smart bracelet further comprises the following steps:

[0159] Step 501: After obtaining the dangerous driving level, set an interval time for secondary confirmation according to the dangerous driving level;

[0160] Specifically, different interval times are set according to different levels of dangerous driving. For example, severe dangerous driving is 3 seconds, moderately dangerous driving is 15 seconds, and slightly dangerous driving is 30 seconds.

[0161] The beneficial effect of this step is that, through secondary confirmation, the acquired vital sign data is more accurate and will not cause misjudgment.

[0162] Step 502: If the second confirmation is the original result, the current diagnosis result is prompted by voice, and the first response strategy is fed back based on the current diagnosis result; if the dangerous driving level confirmed by the second confirmation changes, the vital sign data is immediately re-tested to further determine the dangerous driving level.

[0163] Specifically, when it is confirmed as the current level, the response strategy for the current level is implemented. If the secondary detection level is different, it is necessary to re-detect and determine the danger level.

[0164] This step also includes manually touching and confirming the target task at a high risk driving level. If no manual confirmation is received from the target driver, the first response strategy is urgently initiated.

[0165] In some embodiments, a dangerous driving level exit method is also included, specifically including:

[0166] If the current vital sign data tends to be normal, the dangerous driving level will be further re-judged based on the detected vital sign data.

[0167] Embodiment 5:

[0168] This embodiment provides a computer-readable storage medium. The present invention proposes a computer-readable storage medium, in which at least one execution instruction is stored. When the executable instruction is run on the vehicle-mounted system takeover device of embodiment 3 and / or embodiment 4, the device implements the vehicle-mounted system takeover method of any one of embodiments 1 and / or embodiment 2.

[0169] Obtain the target user's physical sign data through the physical sign detection module and input it into the physical sign judgment model;

[0170] According to the physical sign judgment model, the dangerous driving level and the first response strategy of the current target person are obtained based on the physical sign data;

[0171] Obtaining feedback information from the target user, obtaining a second response strategy based on the feedback information, setting a current reliability based on the vital sign data, and determining whether the current reliability is greater than a preset reliability threshold;

[0172] If yes, choose the second coping strategy, otherwise choose the first coping strategy;

[0173] The current reliability is obtained by inputting the vital sign data into a preset fuzzy inference model for calculation.

[0174] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system or other device. In addition, the embodiments of the present invention are not directed to any particular programming language.

[0175] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. Similarly, in order to simplify the present invention and help understand one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself is a separate embodiment of the present invention.

[0176] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

[0177] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A vehicle system takeover method, characterized in that: include: Obtaining the first physical sign data of the target user and inputting it into the physical sign judgment model; The physical sign judgment model determines the dangerous driving level and the first coping strategy of the target user according to the first physical sign data; receiving feedback information from the target user, and determining a second response strategy according to the feedback information; After determining the second coping strategy, obtaining second vital sign data of the target user to determine current reliability; It is determined whether the current reliability is greater than a preset reliability threshold, and if so, the second response strategy is selected, otherwise, the first response strategy is selected.

2. The vehicle system takeover method according to claim 1, characterized in that: After determining the second coping strategy, obtaining the second vital sign data of the target user to determine the current reliability; comprising: defining a fuzzy set, fuzzifying the second vital sign data of the target user to obtain first fuzzy data, and inputting the data into the fuzzy set; defining a membership function, inputting the first fuzzy data into the membership function to obtain the membership; A fuzzy rule is defined, and the current reliability is obtained by a weighted average method according to the fuzzy rule and the membership degree.

3. The vehicle system takeover method according to claim 2, characterized in that: The step of defining a fuzzy set, fuzzifying the second vital sign data of the target user to obtain first fuzzy data, and inputting the data into the fuzzy set comprises: The value range of the second vital sign data is set to mild, moderate, and severe, and the detected second vital sign data is fuzzily defined as any one of mild, moderate, and severe fuzzy data according to the value range; and the fuzzy data is input into the fuzzy set.

4. The vehicle system takeover method according to claim 3, characterized in that: Defining a membership function, inputting the first fuzzy data into the membership function, and obtaining the membership; comprising: The membership function of each feature element is determined by triangular fuzzy numbers or Gaussian fuzzy numbers, and then the membership is calculated.

5. The vehicle system takeover method according to claim 3, characterized in that: The defining of fuzzy rules and obtaining the current reliability by weighted average method according to the fuzzy rules and the membership degree include: When the fuzzy data is mild, the current reliability is high; when the fuzzy data is moderate, the current reliability is medium; when the fuzzy data is severe, the current reliability is low; After each fuzzy rule is generated, the fuzzy rule weight level is set so that when multiple fuzzy rules simultaneously point to the same current reliability and calculate the overall current reliability, the overall current reliability is calculated by a weighted average algorithm according to the weight level.

6. The vehicle system takeover method according to claim 1, characterized in that: The physical sign judgment model determines the dangerous driving level and the first coping strategy of the target user according to the first physical sign data, including: According to the physical sign data, the overall judgment is made into a slight dangerous driving level, a moderate dangerous driving level, or a high dangerous driving level, and the first response strategy corresponding to the dangerous driving level is queried; The first response strategy includes a slightly dangerous driving level strategy, a moderately dangerous driving level strategy, and a highly dangerous driving level strategy.

7. The vehicle-mounted system takeover method according to claim 1, characterized in that: The receiving feedback information from the target user and determining a second response strategy according to the feedback information includes: Determine a second response strategy based on the feedback information of the target person on the first response strategy; The feedback information includes the target person's confirmation of the coping strategy, rejection of the coping strategy, and additional coping strategies proposed by the target person.

8. A vehicle-mounted system takeover device, characterized in that: include: A physical sign data acquisition module is used to obtain the physical sign data of the target person and input it into the physical sign judgment model; A dangerous driving judgment module, used for a physical sign judgment model to determine the dangerous driving level and a first coping strategy of the target user according to the first physical sign data; A strategy implementation module, configured to receive feedback information from the target user and determine a second response strategy according to the feedback information; The reliability calculation module is used to obtain the second vital sign data of the target user after determining the second coping strategy to determine the current reliability.

9. The vehicle-mounted system takeover device according to claim 8, characterized in that: The vital sign data acquisition module includes any one or more of a smart bracelet, a camera, a thermal sensor, and an infrared sensor.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one execution instruction. When the executable instruction is executed on the vehicle-mounted system takeover device as described in claims 8-9, the device executes the vehicle-mounted system takeover method as described in any one of claims 1-7.

Images