One-key help and vehicle networking two-in-one function terminal

Abstract

The application discloses a one-key help-seeking and vehicle networking two-in-one function terminal and relates to the technical field of vehicle networking help-seeking, which comprises a vehicle networking module, a driving behavior analysis module, a driving safety analysis module and an accident automatic help-seeking module; the vehicle networking module is used for collecting vehicle data and uploading the vehicle data to a vehicle monitoring platform; the driving behavior analysis module is used for analyzing the driving behavior of a driver and constructing a normal driving judgment model; the driving safety analysis module is used for analyzing vehicle data and judging whether the driving state of the vehicle is normal; and the accident automatic help-seeking module is used for sending a help-seeking signal to the vehicle monitoring platform and sending an accident location when the driving state of the vehicle is abnormal; the application is used for solving the problem that the existing vehicle networking help-seeking technology is too traditional in judging the start of help-seeking, has the possibility of being unable to help, and cannot ensure the safety of the driver.

Description

TECHNICAL FIELD

[0001] The application relates to a one-key emergency call and vehicle networking two-in-one function terminal. BACKGROUND

[0002] The vehicle networking emergency call technology is an intelligent emergency rescue system based on vehicle networking, which automatically or manually triggers a rescue signal and transmits key data to a rescue platform in real time to realize rapid and accurate rescue by embedding sensors, communication modules and positioning devices in vehicles.

[0003] The existing vehicle networking emergency call technology is usually enabled after a collision occurs and can only be triggered by a severe collision. Such a method cannot ensure that the vehicle can complete the emergency call every time. If the emergency call device or the power supply system of the emergency call device is damaged by the impact, the vehicle cannot actually complete the emergency call. This is very unfavorable for rescue work after a traffic accident. Therefore, the collision needs to be predicted and the emergency call needs to be completed before the collision occurs. In this way, the emergency call can be completed every time an accident occurs. For example, in the Chinese patent with the application publication number: CN118283187A, an emergency rescue system and method for a vehicle, an electronic device and a storage medium are disclosed. The scheme is to send an emergency call signal after the vehicle body deforms, that is, the emergency call can only be performed after the collision. This method has a probability of failing to complete the emergency call. Therefore, it is not suitable for emergency rescue of vehicles. The existing vehicle networking emergency call technology also has the problem of too traditional judgment of enabling the emergency call, which may not be able to call for help, resulting in the problem of inability to ensure the safety of the driver. SUMMARY

[0004] The application aims to at least solve one of the technical problems in the prior art. Vehicle data is uploaded to a vehicle monitoring platform, then the acceleration influence graph is analyzed and constructed by historical normal data analysis, the normal driving judgment model is analyzed and constructed by the acceleration influence graph, the vehicle data is input into the normal driving judgment model and a judgment signal is output, the vehicle data is specifically analyzed according to the judgment signal, and whether the vehicle is about to have an accident is judged according to the analysis result. Finally, an emergency call signal is sent to the vehicle monitoring platform and the accident location is sent when the driving state of the vehicle is abnormal, so as to solve the problem that the existing vehicle networking emergency call technology has too traditional judgment of enabling the emergency call, which may not be able to call for help, resulting in the problem of inability to ensure the safety of the driver.

[0005] To achieve the above-mentioned purpose, the application provides a one-key emergency call and vehicle networking two-in-one function terminal, which comprises a vehicle networking module, a driving behavior analysis module, a driving safety analysis module and an automatic accident emergency call module. The vehicle networking module, the driving behavior analysis module and the automatic accident emergency call module are respectively connected with the driving safety analysis module.

[0006] The vehicle networking module is configured to collect vehicle data and upload the vehicle data to a vehicle monitoring platform.

[0007] The driving behavior analysis module is configured to analyze driving behaviors of a driver based on historical vehicle data and construct a normal driving judgment model.

[0008] The driving safety analysis module is configured to analyze vehicle data based on the normal driving judgment model and determine whether a driving state of the vehicle is normal.

[0009] The accident automatic help-seeking module is configured to send a help-seeking signal to the vehicle monitoring platform and send an accident location when the driving state of the vehicle is abnormal.

[0010] Further, the vehicle data includes a driving speed, a driving acceleration, an accelerator pedal stroke, a brake pedal stroke, and position information.

[0011] Further, the driving behavior analysis module includes a normal driving analysis unit and a normal driving judgment model construction unit.

[0012] The normal driving analysis unit is configured to analyze an acceleration influence graph based on historical normal data.

[0013] The normal driving judgment model construction unit is configured to analyze the acceleration influence graph and construct a normal driving judgment model.

[0014] Further, the normal driving analysis unit is configured with a normal driving analysis strategy, and the normal driving analysis strategy includes:

[0015] The vehicle data of the vehicle in a normal driving process recorded in the vehicle monitoring platform is obtained and integrated as historical normal data.

[0016] The accelerator pedal stroke and the brake pedal stroke are marked as AT and BT, respectively, the AT-BT is calculated, and the calculation result is named as a comprehensive pedal stroke.

[0017] The driving acceleration is set as a dependent variable and marked as DV, and the driving speed and the comprehensive pedal stroke are set as independent variables, wherein the driving speed and the comprehensive pedal stroke are a first independent variable and a second independent variable in sequence and are represented by IV1 and IV2, respectively.

[0018] A two-dimensional coordinate system is established with the driving speed as an X-axis and the driving acceleration as a Y-axis, named as an acceleration influence graph, DV is recorded in the acceleration influence graph according to IV1, and a coordinate point obtained is named as an acceleration influence point.

[0019] Further, the normal driving judgment model construction unit is configured with a normal driving judgment model construction strategy, and the normal driving judgment model construction strategy includes:

[0020] Obtain IV2, mark the maximum and minimum values of IV2 as MaxV2 and MinV2 respectively, divide the interval [MinV2, MaxV2] into 256 sub-intervals, name them as pedal intervals, number the pedal intervals in ascending order, and obtain the interval gray scale G n , where n is a non-zero natural number and n is the order of I;

[0021] For each I n , assign an interval gray scale G n ; n Set G n to n-1 according to the I n in which IV2 is located; n ;

[0022] In the case of equal X-axis, the acceleration influence points with the same G n are summarized as the same stroke group, all values of X and all values of G n are analyzed to obtain different stroke groups, the average value of DV corresponding to the acceleration influence points in each stroke group is calculated, named as grouped acceleration, the difference between the grouped acceleration and the DV corresponding to the acceleration influence points in the stroke group is calculated, named as acceleration span, the maximum value of the acceleration span is obtained, named as maximum allowed error;

[0023] The grouped acceleration is entered into the acceleration influence diagram according to the value of the X-axis corresponding to the stroke group, and the acceleration grouping points are obtained, the interval gray scale of the acceleration grouping points is consistent with that of the acceleration influence points, and the original acceleration influence points are removed at the same time;

[0024] The normal driving judgment model is constructed, and the acceleration influence diagram is input into the normal driving judgment model.

[0025] Further, the driving safety analysis module comprises a judgment distinguishing unit, a data analysis unit and an abnormality judgment unit;

[0026] The judgment distinguishing unit is used for inputting vehicle data into the normal driving judgment model and outputting a judgment signal;

[0027] The data analysis unit is used for specifically analyzing the vehicle data according to the judgment signal;

[0028] The abnormality judgment unit is used for judging whether the vehicle is about to have an accident according to the analysis result.

[0029] Further, the judgment distinguishing unit is configured with a judgment distinguishing strategy, and the judgment distinguishing strategy comprises:

[0030] The vehicle data of the vehicle is acquired in real time through the Internet of Vehicles, and the driving speed, the driving acceleration, the accelerator pedal stroke and the brake pedal stroke are respectively named as real-time speed, real-time acceleration, real-time accelerator stroke and real-time brake stroke;

[0031] The real-time accelerator stroke minus the real-time brake stroke is calculated to obtain a real-time comprehensive pedal stroke, which is named as real-time pedal stroke;

[0032] The real-time speed and the real-time acceleration are input into the acceleration influence diagram to obtain a coordinate point real-time judgment point, and the interval gray corresponding to the real-time pedal stroke is inquired to obtain a real-time gray, and the real-time judgment point is filled with the real-time gray;

[0033] It is judged whether there is an acceleration grouping point G n equal to the real-time gray in the acceleration influence diagram when X is equal to the real-time speed, and if there is, a first judgment signal is output, and if there is not, a second judgment signal is output.

[0034] Further, the data analysis unit is configured with a data analysis strategy, and the data analysis strategy comprises:

[0035] If the first judgment signal is output, the acceleration grouping point G n equal to the real-time gray in the acceleration influence diagram when X is equal to the real-time speed is marked as RW, and an abnormality judgment strategy is executed at the same time;

[0036] If the second judgment signal is output, the first acceleration grouping point above the real-time gray and the first acceleration grouping point below the real-time gray when X is equal to the real-time speed are obtained, and are respectively named as the first grouping point and the second grouping point, the interval grays of the first grouping point and the second grouping point are respectively marked as GF1 and GF2, and the difference value of the DV corresponding to the first grouping point and the second grouping point is calculated and marked as LC;

[0037] Suppose there is an acceleration grouping point G n equal to the real-time gray, which is named as the assumption point, the real-time gray is marked as K, the difference value of the DV corresponding to the assumption point and the DV corresponding to the second grouping point is assumed as LG, and there is a relationship , which is transformed to , LG is solved, and the sum of LG and the DV of GF2 is marked as RW, and an abnormality judgment strategy is executed.

[0038] Further, the abnormality judgment unit is configured with an abnormality judgment strategy, and the abnormality judgment strategy comprises:

[0039] The real-time speed is marked as VF, |VF-RW| is calculated, and the calculation result is named as real-time error;

[0040] If the real-time error is greater than the maximum allowable error, an abnormal driving signal is output, otherwise a normal driving signal is output.

[0041] Further, the accident automatic help-seeking module is configured with an accident automatic help-seeking strategy, and the accident automatic help-seeking strategy comprises:

[0042] If the abnormal driving signal is output, a help-seeking signal is sent to the vehicle monitoring platform and the accident location is sent.

[0043] The accident location is the position information in the vehicle data when the abnormal driving signal is output.

[0044] The application has the advantages that: by collecting vehicle data and uploading to the vehicle monitoring platform, then analyzing the acceleration influence graph through historical normal data, and then analyzing and constructing a normal driving judgment model through the acceleration influence graph, the driving acceleration is affected by the driving speed, the throttle pedal stroke and the brake pedal stroke in the driving process, the acceleration influence graph in the normal driving judgment model reflects the relationship between the driving speed, the throttle pedal stroke, the brake pedal stroke and the driving acceleration in the normal driving process, and in a traffic accident, the driver usually discovers the danger in advance and makes irregular operation, for example, rapid deceleration when driving at high speed, and at the same time, the driving acceleration of the vehicle will also be abnormal when the vehicle is hit, so whether the vehicle is abnormal can be judged through the relationship between the driving acceleration and each data, and the accuracy and effectiveness of the vehicle networking help-seeking are improved.

[0045] The application inputs the vehicle data into the normal driving judgment model and outputs a judgment signal, analyzes the vehicle data according to the judgment signal, judges whether the vehicle is about to have an accident according to the analysis result, and finally sends a help-seeking signal to the vehicle monitoring platform and sends the accident location when the driving state of the vehicle is abnormal, and the advantages are that: the historical normal data do not necessarily include all situations, and there is a certain degree of data loss, so the existing data is used to predict the data loss, that is, the processing process when the second judgment signal is output, and finally whether the vehicle data is normal is judged, and the accuracy and comprehensiveness of the vehicle networking help-seeking are improved. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 It is a principle block diagram of the system of the application

[0047] Figure 2 It is a schematic diagram of the acceleration influence graph of the application

[0048] Figure 3 It is a simplified schematic diagram of the application Figure 2

[0049] Figure 4 ​A schematic diagram of an acceleration impact point of the present application;

[0050] Figure 5 A schematic diagram of a real-time judgment point of the present application. DETAILED DESCRIPTION

[0051] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0052] Embodiment 1, please refer to Figure 1 As shown, the application provides a one-key distress call and Internet of Vehicles two-in-one function terminal, which comprises an Internet of Vehicles module, a driving behavior analysis module, a driving safety analysis module and an accident automatic distress call module; the Internet of Vehicles module, the driving behavior analysis module and the accident automatic distress call module are respectively in data connection with the driving safety analysis module;

[0053] The Internet of Vehicles module is used for collecting vehicle data and uploading the vehicle data to a vehicle monitoring platform; the vehicle data comprises driving speed, driving acceleration, accelerator pedal stroke, brake pedal stroke and position information;

[0054] In actual application, the vehicle monitoring platform already exists universally, especially in new energy vehicles, the vehicle monitoring platform constantly monitors various data indexes of the vehicle, and the embodiment will not be described in detail.

[0055] The driving behavior analysis module is used for analyzing the driving behavior of the driver through historical vehicle data, and constructing a normal driving judgment model; the driving behavior analysis module comprises a normal driving analysis unit and a normal driving judgment model construction unit.

[0056] The normal driving analysis unit is used for analyzing an acceleration impact graph through historical normal data;

[0057] The normal driving analysis unit is configured with a normal driving analysis strategy, and the normal driving analysis strategy comprises:

[0058] The vehicle data of the vehicle in the normal driving process recorded in the vehicle monitoring platform is obtained and integrated as historical normal data;

[0059] The accelerator pedal stroke and the brake pedal stroke are respectively marked as AT and BT, AT-BT is calculated, and the calculation result is named as comprehensive pedal stroke;

[0060] The driving acceleration is set as a dependent variable and marked as DV, the driving speed and the comprehensive pedal stroke are set as independent variables, wherein the driving speed and the comprehensive pedal stroke are a first independent variable and a second independent variable in sequence, and are respectively represented by IV1 and IV2;

[0061] Please see Figures 2 to 3 As shown, a two-dimensional coordinate system is established with the vehicle speed as the X-axis and the vehicle acceleration as the Y-axis, named the acceleration influence diagram. The DV is entered into the acceleration influence diagram according to IV1, and the obtained coordinate points are named acceleration influence points.

[0062] In practical applications, the brake and accelerator pedals are usually not pressed simultaneously. The accelerator represents acceleration, and the brake represents deceleration; both have values ​​ranging from 0 to 1. Therefore, when calculating the combined pedal travel, if it is less than zero, it means the driver has pressed the brake pedal, and vice versa. The combined pedal travel can simultaneously represent the accelerator and brake pedal travel, reducing the complexity of the analysis. The resulting acceleration influence diagram is shown below. Figure 2 As shown, due to the large amount of data, it is not convenient to provide a detailed explanation in this embodiment. Therefore, [the following is omitted]. Figure 2 After simplification, we get Figure 3 , Figure 3 Only some of the acceleration-affected points are shown in the diagram to provide a detailed explanation of the subsequent analysis process;

[0063] The normal driving judgment model construction unit is used to analyze and construct a normal driving judgment model through acceleration influence diagram analysis.

[0064] The normal driving judgment model construction unit is configured with a normal driving judgment model construction strategy, which includes:

[0065] Obtain IV2, and label its maximum and minimum values ​​as MaxV2 and MinV2, respectively. Divide the interval [MinV2, MaxV2] into 256 sub-intervals, named the pedal intervals, and number them in ascending order, using the symbol I. n It represents that, where n is a non-zero natural number and n is the index of I;

[0066] Please see Figure 4 As shown, for each I n Assign a grayscale value to the interval, labeled G. n , will G n Set to n-1, based on the position of IV2 in I n To fill the grayscale range G of the acceleration-affected points n ;

[0067] In practical applications, MaxV2 and MinV2 are 1 and -1 respectively. Dividing the system into 256 sub-intervals is to match 256 grayscale values ​​from 0 to 255, so that the second independent variable can be represented by these grayscale values. This results in 256 pedal intervals, each with a span of 0.0078125. The pedal interval [-1, -0.9921875] is I1, and G1 is 0. This means that when the second independent variable is within [-1, -0.9921875], the grayscale value of the acceleration influence point is filled with 0. Filling each acceleration influence point yields the filled acceleration influence points as shown below. Figure 4 As shown;

[0068] When the X-axis is equal, they will have the same G. n The acceleration influence points are summarized into groups of the same stroke, for all values ​​of X and G. n Analyze all possible values ​​to obtain different travel groups. Calculate the average value of the DV corresponding to the acceleration influence point in each travel group, and name it the group acceleration. Calculate the difference between the group acceleration and the DV corresponding to the acceleration influence point in the travel group, and name it the acceleration span. Obtain the maximum value of the acceleration span, and name it the maximum permissible error.

[0069] The acceleration groups are entered into the acceleration influence map according to the X-axis values ​​corresponding to the travel groups to obtain the acceleration group points. The gray levels of the acceleration group points and the acceleration influence points are kept consistent, while the original acceleration influence points are removed.

[0070] Construct a normal driving judgment model and input the acceleration influence map into the normal driving judgment model;

[0071] In practical applications, in Figure 4 In the positive Y-axis direction at point X=35, the grayscale values ​​of the two acceleration-affected points below are both 145. Therefore, they are grouped into the same travel group, and the DV corresponding to these two acceleration-affected points are 2.27 m / s². 2 and 2.52m / s 2 The calculated acceleration of the group is 2.395 m / s². 2 And the acceleration span is 2.52 m / s². 2 -2.395m / s 2 =0.125m / s 2 The acceleration span of all travel groups was calculated, and the maximum permissible error was found to be 0.125. All acceleration group points were entered into the acceleration influence diagram, and the original acceleration influence points were removed. In the acceleration influence diagram at this point, in each value of the X-axis, the G of each acceleration group point was... nDifferent, so you can find different vehicle data corresponding to the reference data, for example, when the driving speed is 35km / h, and the comprehensive pedal stroke is 0.1328125, the acceleration grouping point is (35, 2.395), instead of using the original multiple different acceleration influence points as reference data.

[0072] The driving safety analysis module is used for analyzing vehicle data based on the normal driving judgment model to judge whether the driving state of the vehicle is normal; the driving safety analysis module includes a judgment distinguishing unit, a data analysis unit and an abnormality judgment unit;

[0073] The judgment distinguishing unit is used for inputting vehicle data into the normal driving judgment model and outputting a judgment signal;

[0074] The judgment distinguishing unit is configured with a judgment distinguishing strategy, and the judgment distinguishing strategy includes:

[0075] The vehicle data of the vehicle is obtained in real time through the Internet of vehicles, and the driving speed, driving acceleration, accelerator pedal stroke and brake pedal stroke are respectively named as real-time speed, real-time acceleration, real-time accelerator stroke and real-time brake stroke;

[0076] The real-time accelerator stroke minus the real-time brake stroke is calculated to obtain the real-time comprehensive pedal stroke, which is named as real-time pedal stroke;

[0077] Please refer to Figure 5 The real-time speed and real-time acceleration are input into the acceleration influence diagram to obtain the coordinate point real-time judgment point, the interval gray corresponding to the real-time pedal stroke is queried, which is named as real-time gray, and the real-time judgment point is filled with the real-time gray;

[0078] Determine whether there is an acceleration grouping point G n Equal to real-time gray in the acceleration influence diagram when X is equal to real-time speed, if it exists, output the first judgment signal, if it does not exist, output the second judgment signal;

[0079] In practical application, the real-time speed, real-time acceleration, real-time accelerator stroke and real-time brake stroke are respectively 100km / h, 0.4588m / s 2 , 0.1328125 and 0, the real-time pedal stroke is calculated to be 0.1328125, and the coordinate point real-time judgment point is obtained after inputting the acceleration influence diagram, as Figure 5 The hexagon in it is the real-time judgment point, because the real-time pedal stroke is 0.1328125, the corresponding real-time gray is 145, and there is no acceleration influence point G n =145 in the acceleration influence point at X=100km / h, so the second judgment signal is output;

[0080] The data analysis unit is configured to analyze the vehicle data according to the judgment signal;

[0081] The data analysis unit is configured with a data analysis strategy, which includes:

[0082] If the first judgment signal is output, the acceleration impact graph G n The DV corresponding to the acceleration grouping point equal to the real-time gray scale is marked as RW, and an abnormality judgment strategy is executed at the same time;

[0083] If the second judgment signal is output, the first acceleration grouping point above the real-time gray scale and the first acceleration grouping point below the real-time gray scale when X is equal to the real-time vehicle speed are obtained, which are named as the first grouping point and the second grouping point respectively, and the interval gray scales of the first grouping point and the second grouping point are marked as GF1 and GF2 respectively. The difference between the DVs corresponding to the first grouping point and the second grouping point is calculated and marked as LC;

[0084] Suppose there is G n equal to the real-time gray scale, which is named as the assumption point, the real-time gray scale is marked as K, and the difference between the DV corresponding to the assumption point and the DV corresponding to the second grouping point is assumed as LG, there is a relationship , transformation is obtained , LG is solved, and the sum of LG and the DV of GF2 is marked as RW, and an abnormality judgment strategy is executed;

[0085] In actual application, the second judgment signal is output, and the acceleration grouping point above Figure 5 is the first grouping point, and the acceleration grouping point below Figure 5 is the second grouping point, GF1 and GF2 are obtained as 194 and 135 respectively, LC is 0.5513, the calculation result is rounded to four decimal places, the real-time gray scale K is 145, and in the case of the same driving speed, the accelerator pedal stroke is proportional to the driving acceleration and basically meets the linear relationship. Therefore, in the case of equal X axis, the distribution of interval gray scales meets the characteristics of uniform distribution, the ratio of the distances between the assumption point and the first grouping point and the second grouping point is the same as the ratio of their interval gray scales, that is, there is a relationship , wherein LC=0.5513, K=145, GF2=135, GF1=194, LG=0.0934 is finally calculated, and the calculation result is rounded to four decimal places, and the sum of RW is 0.5139;

[0086] The abnormality judgment unit is configured to judge whether the vehicle is about to have an accident according to the analysis result;

[0087] The abnormality judgment unit is configured with an abnormality judgment strategy, which includes:

[0088] The real-time acceleration is marked as VF, |VF-RW| is calculated, and the calculation result is named as real-time error;

[0089] It is judged whether the real-time error is greater than the maximum allowable error, if yes, a driving abnormal signal is output, otherwise a driving normal signal is output;

[0090] In practical application, VF is 0.4588 m / s 2 , the real-time error is 0.0551 calculated, which is less than the maximum allowable error, thus a driving normal signal is output.

[0091] The accident automatic help module is used for sending a help signal to the vehicle monitoring platform and sending an accident location when the driving state of the vehicle is abnormal;

[0092] The accident automatic help module is configured with an accident automatic help strategy, and the accident automatic help strategy comprises:

[0093] If the driving abnormal signal is output, a help signal is sent to the vehicle monitoring platform and the accident location is sent;

[0094] The accident location is the position information in the vehicle data when the driving abnormal signal is output;

[0095] In practical application, the embodiment focuses on one-key help after a severe collision of the vehicle, and a collision at low speed usually does not cause serious injury to the driver, thus one-key help is usually not needed, and in the normal driving process, the driving acceleration of the vehicle is related to the driving speed and the comprehensive pedal stroke, and when analyzing, the acceleration influence point corresponding to the real-time gray scale under the condition of the real-time speed is found, which is the judgment basis of this analysis, if the acceleration deviates too much, it is considered that the vehicle is hit, causing the vehicle acceleration to be abnormal, and at the same time, the comprehensive pedal stroke suitable for different driving speeds is also different, for example, when driving at high speed, the brake is usually not deep, thus this part of data does not exist, and the embodiment will supplement the non-existing data, but only the part with reference basis above and below is supplemented, that is, there is an acceleration influence point with an interval gray scale greater than the interval gray scale to be supplemented and an interval gray scale less than the interval gray scale to be supplemented, and when driving at high speed, the data of deep brake only exists an acceleration influence point with an interval gray scale greater than the interval gray scale to be supplemented, thus it cannot be supplemented, and when it cannot be supplemented, a driving abnormal signal is output by default.

[0096] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (or computer- readable storage media) having computer-usable program code embodied in the medium. The medium can be any available storage media that can be accessed by a computer. By way of example, and not limitation, such computer-usable storage media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other storage medium(s) that can be used to carry or store desired computer program code in the form of instructions or data structures and that can be accessed by a computer. Also, the present application can be embodied in a computer program product that can be traded as goods or merchandise, through the possession of a storage medium in which the computer program instructions are stored, such as a memory device, such as a compact disc (CD), a DVD, a Blu-ray disc, a flash drive or the like, which can be read by a computer. Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks

[0097] In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. The embodiments described above are merely exemplary, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

Claims

1. A terminal with one-key SOS and vehicle networking functions, characterized in that, The application relates to a vehicle monitoring system, which comprises a vehicle networking module, a driving behavior analysis module, a driving safety analysis module and an accident automatic help-seeking module; the vehicle networking module, the driving behavior analysis module and the accident automatic help-seeking module are respectively connected with the driving safety analysis module in data mode; The vehicle networking module is used for collecting vehicle data and uploading the vehicle data to a vehicle monitoring platform; The driving behavior analysis module is used for analyzing the driving behavior of a driver through historical vehicle data and constructing a normal driving judgment model; The driving safety analysis module is used for analyzing vehicle data based on the normal driving judgment model and judging whether the driving state of the vehicle is normal; The accident automatic help-seeking module is used for sending a help-seeking signal to the vehicle monitoring platform and sending an accident location when the driving state of the vehicle is abnormal; The driving behavior analysis module comprises a normal driving analysis unit and a normal driving judgment model construction unit; The normal driving analysis unit is used for analyzing an acceleration influence graph through historical normal data; The normal driving judgment model construction unit is used for analyzing and constructing a normal driving judgment model through the acceleration influence graph; The normal driving analysis unit is provided with a normal driving analysis strategy, and the normal driving analysis strategy comprises the following steps: Vehicle data of a vehicle in a normal driving process recorded in a vehicle monitoring platform is obtained and integrated as historical normal data; A throttle pedal stroke and a brake pedal stroke are respectively marked as AT and BT, AT-BT is calculated, and the calculation result is named as a comprehensive pedal stroke; A driving acceleration is set as a dependent variable and marked as DV, a driving speed and the comprehensive pedal stroke are set as independent variables, the driving speed and the comprehensive pedal stroke are sequentially a first independent variable and a second independent variable, and are respectively represented by IV1 and IV2; A two-dimensional coordinate system is established with the driving speed as an X axis and the driving acceleration as a Y axis, is named as an acceleration influence graph, DV is recorded in the acceleration influence graph according to IV1, and a coordinate point obtained is named as an acceleration influence point; The normal driving judgment model construction unit is provided with a normal driving judgment model construction strategy, and the normal driving judgment model construction strategy comprises the following steps: Obtain IV2, mark the maximum and minimum values of IV2 as MaxV2 and MinV2 respectively, divide the interval [MinV2, MaxV2] into 256 subintervals, named as pedal intervals, and number the pedal intervals in ascending order, and the symbol I n represents, wherein n is a non-zero natural number and n is the serial number of I; For each I n Intervals gray scale is given, marked as G n , G n Is set to n-1, according to the I n For acceleration impact point filling interval gray scale G n ; In the case of equal X axis, the acceleration impact points with the same G n are summarized into the same trip group, all values of X and all values of G n are analyzed to obtain different trip groups, the average value of the DV corresponding to the acceleration impact points in each trip group is calculated, named as the grouped acceleration, the difference between the grouped acceleration and the DV corresponding to the acceleration impact points in the trip group is calculated, named as the acceleration span, the maximum value of the acceleration span is obtained, named as the maximum allowable error; Grouped accelerations are recorded in the acceleration influence graph according to the value of the X axis corresponding to the stroke, acceleration grouping points are obtained, the interval gray scale of the acceleration grouping points and the acceleration influence points is kept consistent, and the original acceleration influence points are removed; A normal driving judgment model is constructed, and the acceleration influence graph is recorded in the normal driving judgment model. 2.The one-key SOS and vehicle networking two-in-one functional terminal according to claim 1, characterized in that, The vehicle data comprises a driving speed, a driving acceleration, a throttle pedal stroke, a brake pedal stroke and position information. 3.The one-key SOS and vehicle networking two-in-one functional terminal according to claim 2, characterized in that, The driving safety analysis module comprises a judgment distinguishing unit, a data analysis unit and an abnormality judgment unit; The judgment distinguishing unit is used for recording vehicle data in the normal driving judgment model and outputting a judgment signal; The data analysis unit is used for specifically analyzing vehicle data according to the judgment signal; The abnormality judgment unit is used for judging whether a vehicle is about to have an accident according to an analysis result. 4.The one-key SOS and vehicle networking two-in-one functional terminal according to claim 3, characterized in that, The judgment distinguishing unit is provided with a judgment distinguishing strategy, and the judgment distinguishing strategy comprises the following steps: Vehicle data of the vehicle is acquired in real time through the vehicle networking, and the driving speed, the driving acceleration, the accelerator pedal stroke and the brake pedal stroke are respectively named as real-time speed, real-time acceleration, real-time accelerator stroke and real-time brake stroke; The real-time accelerator stroke minus the real-time brake stroke is calculated to obtain a real-time comprehensive pedal stroke, which is named as real-time pedal stroke; The real-time speed and the real-time acceleration are input into the acceleration influence diagram to obtain a coordinate point real-time judgment point, and the interval gray corresponding to the real-time pedal stroke is inquired to obtain a real-time gray, and the real-time judgment point is filled as the real-time gray; determining whether G exists in the acceleration influence graph when X is equal to the real-time vehicle speed n the acceleration grouping point equal to the real-time gray scale, if G exists, outputting the first determination signal, if G does not exist, outputting the second determination signal. 5.The one-key SOS and vehicle networking two-in-one functional terminal according to claim 4, characterized in that, The data analysis unit is configured with a data analysis strategy, and the data analysis strategy comprises: If the first determination signal is output, the G in the acceleration influence graph when X is equal to the real-time vehicle speed n The DV corresponding to the acceleration grouping point equal to the real-time gray scale is marked as RW, and an abnormal determination strategy is executed simultaneously. If the second judgment signal is output, the first acceleration grouping point above the real-time gray and the first acceleration grouping point below the real-time gray are obtained when X is equal to the real-time speed, and are respectively named as the first grouping point and the second grouping point, the interval gray of the first grouping point and the second grouping point is respectively marked as GF1 and GF2, and the difference value of the DV corresponding to the first grouping point and the second grouping point is calculated and marked as LC; Assume G n Equal to the acceleration grouping point of real-time gray, named as assumption point, mark the real-time gray as K, assume the difference between the DV corresponding to the assumption point and the DV corresponding to the second grouping point as LG, there is a relationship , transformation gets , solve LG, add LG and the DV of GF2, mark the sum as RW, and execute the abnormal judgment strategy. 6.The one-key SOS and vehicle networking two-in-one functional terminal according to claim 5, characterized in that, The abnormality judgment unit is configured with an abnormality judgment strategy, and the abnormality judgment strategy comprises: The real-time speed is marked as VF, and |VF-RW| is calculated, and the calculation result is named as real-time error; It is judged whether the real-time error is greater than the maximum allowable error, if yes, the driving abnormality signal is output, otherwise the driving normal signal is output. 7.The one-key SOS and vehicle networking two-in-one functional terminal according to claim 6, characterized in that, The accident automatic help-seeking module is configured with an accident automatic help-seeking strategy, and the accident automatic help-seeking strategy comprises: If the driving abnormality signal is output, a help-seeking signal is sent to the vehicle monitoring platform and the accident location is sent; The accident location is the position information in the vehicle data when the driving abnormality signal is output.

Images