CN117295044A - Automatic help seeking method and device for vehicle - Google Patents
Automatic help seeking method and device for vehicle Download PDFInfo
- Publication number
- CN117295044A CN117295044A CN202210689850.1A CN202210689850A CN117295044A CN 117295044 A CN117295044 A CN 117295044A CN 202210689850 A CN202210689850 A CN 202210689850A CN 117295044 A CN117295044 A CN 117295044A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- traffic accident
- driving data
- feature
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 206010039203 Road traffic accident Diseases 0.000 claims abstract description 104
- 230000006378 damage Effects 0.000 claims description 20
- 208000027418 Wounds and injury Diseases 0.000 claims description 19
- 208000014674 injury Diseases 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 12
- 238000010801 machine learning Methods 0.000 description 7
- 230000001133 acceleration Effects 0.000 description 6
- 239000000779 smoke Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000002826 coolant Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/90—Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Environmental & Geological Engineering (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides an automatic vehicle recourse method and device, which relate to the technical field of data processing and vehicle recourse, and comprise the following steps: acquiring running information of a vehicle, wherein the running information comprises various running data; extracting features of the driving information based on the feature extractor to obtain feature representations of various driving data; identifying the characteristic representation of the driving data based on a plurality of characteristic libraries to acquire a current target traffic accident scene of the vehicle; and acquiring one or more rescue platforms associated with the target traffic accident scene, and sending help seeking information to the associated rescue platforms. In the embodiment of the application, the common characteristics of historical traffic accidents can be learned, and traffic accident scenes are judged by combining multiple types of driving data, so that the accuracy of identifying the traffic accident scenes is improved, help is automatically required according to the accident scenes, rescue delay is avoided, and the safety of accident personnel is improved.
Description
Technical Field
The application relates to the technical field of data processing and vehicle recourse, in particular to an automatic vehicle recourse method and device.
Background
In the related art, after a traffic accident occurs, a rescue platform needs to be required to be subjected to rescue by manual operation, and the rescue method is not high in safety, for example, if personnel on the accident scene lose autonomous behavior capability or the accident position is remote, the rescue platform cannot be subjected to rescue in time or the position where the traffic accident occurs can be accurately described, so that rescue delay is caused, and the optimal rescue opportunity of the personnel on the accident scene is delayed. Therefore, how to accurately judge the traffic accident scene, automatically asking for help according to the accident scene, avoiding rescue delay, has become one of important research directions.
Disclosure of Invention
The present application aims to solve, at least to some extent, one of the technical problems in the related art. For this purpose, an embodiment of a first aspect of the present application provides a method for automatically asking for assistance of a vehicle, including:
acquiring running information of a vehicle, wherein the running information comprises various running data;
extracting features of the driving information based on the feature extractor to obtain feature representations of various driving data;
identifying the characteristic representation of the driving data based on a plurality of characteristic libraries to acquire a current target traffic accident scene of the vehicle;
and acquiring one or more rescue platforms associated with the target traffic accident scene, and sending help seeking information to the associated rescue platforms.
In the embodiment of the application, multiple types of driving data are acquired as driving information, traffic accident scenes can be judged according to the multiple types of driving data, characteristic representations of the driving data are identified based on multiple characteristic libraries, the current target traffic accident scene of a vehicle is acquired, common characteristics of historical traffic accidents can be learned, accuracy of identifying the traffic accident scenes is improved, one or more rescue platforms associated with the target traffic accident scene are acquired, help seeking information is sent to the associated rescue platforms, help seeking is automatically carried out according to the accident scenes, rescue delay is avoided, and accordingly safety of accident personnel is improved.
An embodiment of a second aspect of the present application provides an automatic vehicle help-seeking device, including:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring running information of a vehicle, and the running information comprises multiple types of running data;
the feature extraction module is used for carrying out feature extraction on the running information based on the feature extractor so as to obtain feature representations of various running data;
the identification module is used for identifying the characteristic representation of the driving data based on the plurality of characteristic libraries and acquiring a current target traffic accident scene of the vehicle;
the recourse module is used for acquiring one or more rescue platforms associated with the target traffic accident scene and sending recourse information to the associated rescue platforms.
An embodiment of a third aspect of the present application provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the vehicle automatic help method provided in the embodiments of the first aspect of the present application.
An embodiment of a fourth aspect of the present application proposes a computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the vehicle automatic help seeking method provided in an embodiment of the first aspect of the present application.
An embodiment of a fifth aspect of the present application proposes a computer program product comprising a computer program which, when executed by a processor, implements the vehicle automatic help method provided in the embodiment of the first aspect of the present application.
An embodiment of a sixth aspect of the present application proposes a vehicle including the vehicle automatic help-seeking device provided in the embodiment of the third aspect of the present application.
Drawings
FIG. 1 is a flow chart of a method of automatically asking for assistance in a vehicle in accordance with one embodiment of the present application;
FIG. 2 is a schematic diagram of a vehicle automatic help method according to one embodiment of the present application;
FIG. 3 is a flow chart of a method of automatically asking for assistance in a vehicle in accordance with one embodiment of the present application;
FIG. 4 is a flow chart of a method of automatically asking for assistance in a vehicle in accordance with one embodiment of the present application;
FIG. 5 is a schematic diagram of a vehicle automatic help method according to one embodiment of the present application;
FIG. 6 is a block diagram of an automatic vehicle help-seeking device according to one embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein; it will be apparent that the embodiments in the specification are only some, but not all, embodiments of the disclosure.
The following describes a vehicle automatic help seeking method and a device thereof according to an embodiment of the present application with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method for automatically asking for assistance in a vehicle according to one embodiment of the present application, as shown in FIG. 1, the method comprising the steps of:
s101, acquiring running information of the vehicle, wherein the running information comprises multiple types of running data.
In the embodiment of the application, various sensors are deployed in the vehicle, so that various running data can be acquired. Alternatively, the acceleration of the vehicle may be acquired as one type of travel data by an acceleration sensor. Alternatively, the wheel speed may be acquired as one type of running data of the vehicle by an antilock brake system (antilock brake system, ABS) sensor. Alternatively, the relative posture between the vehicle and the ground, that is, the vehicle posture, may be acquired as one type of running data of the vehicle by the vehicle posture sensor. Alternatively, smoke data in the environment in which the vehicle is currently located may be detected by a smoke sensor as one type of running data of the vehicle. Alternatively, wading data in the environment in which the vehicle is currently located may be detected by a wading sensor as one type of running data of the vehicle. Alternatively, whether or not the airbag of the vehicle is ejected may be detected by the airbag sensor, and the airbag data may be acquired as one type of running data of the vehicle.
In some implementations, optical cameras are disposed in all directions around the body of the vehicle, and video data of multiple directions of the vehicle can be collected through the optical cameras in all directions to serve as driving data of the vehicle. In some implementations, the vehicle is forward deployed with a vehicle recorder, and forward video data can be collected by the vehicle recorder as a type of driving data of the vehicle.
In some implementations, vehicle fault data may also be obtained through a fault self-checking module deployed on the vehicle as a type of travel data for the vehicle. For example, the engine coolant temperature signal system provides for a voltage of 0.08-4.8V in a normal condition, and if the fault self-checking module detects a voltage outside this range, it is diagnosed as abnormal. Alternatively, the abnormality level may be further classified into a light failure that does not cause an obstacle, a failure that causes a decline in function, a major failure, and the like. Alternatively, the vehicle fault data may be a code of the fault location. Optionally, the fault self-checking module may further obtain vehicle fault data of a fault location of the engine, the automatic transmission, and the like.
S102, carrying out feature extraction on the driving information based on the feature extractor so as to obtain feature representations of various driving data.
In some implementations, feature extraction may be performed on each type of travel data in the travel information using a feature extractor, respectively, to obtain a feature representation of each type of travel data.
Alternatively, in the embodiment of the present application, the feature extractor may be a convolutional neural network (Convolutional Neural Network, CNN), a recurrent neural network (Recurrent Neural Network, RNN), or the like.
Optionally, when the running data is text data acquired according to the sensor, the encoding layer may be used to perform feature extraction to acquire a feature representation, that is, encode the text of the running data to acquire the feature representation of the running data; alternatively, when the running data is text data acquired according to the sensor, feature extraction may be performed by using a convolution layer to acquire a feature representation, that is, a convolution operation is performed on the text of the running data to acquire the feature representation of the running data.
And S103, identifying the characteristic representation of the driving data based on the plurality of characteristic libraries to acquire a current target traffic accident scene of the vehicle.
In the embodiment of the application, a plurality of candidate traffic accident scenes can be acquired, based on the historical driving information of a plurality of traffic accidents which occur in any candidate traffic accident scene, the historical common characteristics of various driving data are extracted, one characteristic library in a plurality of characteristic libraries corresponds to the historical common characteristics contained in one candidate traffic accident scene, and further, based on the historical common characteristics of various driving data and the characteristic representation of current driving data, the confidence coefficient of each candidate scene of the current target traffic accident scene of the vehicle is acquired, and further, the target traffic accident scene is confirmed from the candidate traffic accident scenes according to the confidence coefficient. For example, the candidate traffic accident scene with the highest confidence may be confirmed as the target traffic accident scene, or the candidate traffic accident scene with the confidence greater than the preset threshold may be confirmed as the target traffic accident scene. As shown in fig. 2, alternatively, the confidence may be obtained by the following formula:
wherein E is m The confidence that the current target traffic accident scene of the vehicle is the mth candidate traffic accident scene is represented, i represents the ith class of running data of the running information, n represents the running information with n classes of running data, n is an integer greater than 1, i epsilon [1, n]Similarity (q.) represents an operation for similarity, q m Representing the common historical characteristics in the mth candidate traffic accident scene, Q i A characteristic representation representing current class i travel data. Alternatively, cosine similarity may be used to represent various types of travel dataSimilarity between the common historical features and the feature representation of the current travel data. In the embodiment of the application, there are M candidate traffic accident scenes in total.
S104, acquiring one or more rescue platforms associated with the target traffic accident scene, and sending help seeking information to the associated rescue platforms.
Alternatively, the help seeking platform may be a medical platform, a fire platform, a traffic platform, or the like.
In some implementations, the target traffic accident scenario is a person injured and the vehicle damaged, and the associated rescue platform is a medical platform and a traffic management platform, that is, the help seeking information is sent to the medical platform and the traffic management platform. In some implementations, the target traffic accident scenario is vehicle wading, and the associated rescue platform is a fire platform and a traffic management platform, that is, the rescue information is sent to the fire platform and the traffic management platform. In some implementations, the target traffic accident scenario is a fire platform, a medical platform, and a traffic management platform, i.e., the fire platform, the medical platform, and the traffic management platform are respectively sent help seeking information.
Optionally, a global positioning system (Global Positioning System, GPS) is deployed on the vehicle, so as to obtain a current position of the vehicle, and further generate recourse information based on the current position of the vehicle, a confidence level of a target traffic accident scene of the vehicle, and driving information. For example, the help seeking information may be "a white minibus turns on one's side at the location XXX, and the probability of occurrence of a traffic accident is C m Help and rescue.
In some implementations, a short message or a mail can be generated according to the rescue information and a preset template and sent to the rescue platform. In some implementations, the service telephone of the rescue platform can be automatically dialed to conduct intelligent conversation so as to report the help seeking information and conduct help seeking.
In the embodiment of the application, multiple types of driving data are acquired as driving information, common characteristics of historical traffic accidents can be learned, traffic accident scenes are judged by combining the multiple types of driving data, the current target traffic accident scene of the vehicle is identified according to the characteristic representation of the driving data, accuracy of identifying the traffic accident scene can be improved, one or more rescue platforms associated with the target traffic accident scene are acquired, help seeking information is sent to the associated rescue platforms, and automatic help seeking is carried out according to the accident scene, so that rescue delay is avoided, and safety of accident personnel is improved.
FIG. 3 is a flow chart of a method for automatically asking for assistance in a vehicle according to one embodiment of the present application, as shown in FIG. 3, the method comprising the steps of:
s301, acquiring running information of the vehicle, wherein the running information comprises multiple types of running data.
S302, carrying out feature extraction on the driving information based on the feature extractor so as to obtain feature representations of various driving data.
The description of step S301 to step S302 may be referred to the relevant content in the above embodiment, and will not be repeated here.
S303, classifying and identifying the characteristic representation of the driving data based on the plurality of characteristic libraries to obtain the classifying probability of the driving data in any characteristic library.
Optionally, in the embodiment of the present application, the machine learning model is trained by taking historical driving information of a plurality of traffic accidents that have occurred as a sample, so as to extract common features of a plurality of candidate traffic accident scenes, thereby generating a plurality of feature libraries, where one feature library in the plurality of feature libraries corresponds to one candidate traffic accident scene. Alternatively, the machine learning model may be a naive bayes model, a decision tree model, or the like.
Taking one of the feature libraries as a human injury feature library for example, in some implementations, inputting a feature representation of the driving data into a machine learning model, and the machine learning model classifies and identifies the feature representation of any type of driving data based on a first feature representation of the human injury feature library to obtain a first candidate classification probability of the first feature representation of any type of driving data; and acquiring the first classification probability of the driving data in the personnel injury feature library according to the first candidate classification probability of any type of driving data and the first weight of any type of driving data.
The embodiment of the application comprises acceleration A and wheel speed V as running data t Vehicle fault data V f Vehicle attitude P, airbag data B, video data V c For example, the smoke data S and wading data W are described, and if the candidate traffic accident scene is a person injury scene, the following formula may be adopted to obtain a first classification probability of the driving data in the person injury feature library:
C 1 ＝F 1 (A)+F 2 (V t )+F 3 (V f )+F 4 (B)+F 5 (P)+F 6 (V c )+F 7 (S)+F 8 (W)
wherein C is 1 Representing a first classification probability of driving data in a personal injury feature library, F 1 (A) Representing a first candidate class probability, F, at acceleration A for a first feature 2 (V t ) For the first characteristic to be expressed in wheel speed V t The first candidate classification probability F 3 (V f ) For the first characteristic to be represented in the vehicle fault data V f The first candidate classification probability F 4 (B) Representing a first candidate class probability, F, under the airbag data B for a first feature 5 (P) representing a first candidate classification probability under the vehicle pose P for the first feature, F 6 (V c ) For the first characteristic to be represented in video data V c The first candidate classification probability F 7 (S) representing a first candidate class probability under the smoke data S for the first feature, F 8 (W) represents a first candidate classification probability under the wading data W for the first feature.
Taking one of the feature libraries as a vehicle damaged feature library for illustration, in some implementations, inputting the feature representation of the driving data into a machine learning model, and the machine learning model classifies and identifies the feature representation of any type of driving data based on a second feature representation of the vehicle damaged feature library to obtain a second candidate classification probability of the second feature representation of any type of driving data; and acquiring the second classification probability of the driving data in the personnel injury feature library according to the second candidate classification probability of any type of driving data and the second weight of any type of driving data.
The embodiment of the application comprises acceleration A and wheel speed V as running data t Vehicle fault data V f Vehicle attitude P, airbag data B, video data V c For example, the smoke data S and wading data W are described, if the candidate traffic accident scene is a vehicle damaged scene, the following formula may be adopted to obtain the second classification probability of the driving data in the vehicle damaged feature library:
C 2 ＝F’ 1 (A)+F’ 2 (V t )+F’ 3 (V f )+F’ 4 (B)+F’ 5 (P)+F’ 6 (V c )+F’ 7 (S)+F’ 8 (W)
wherein C is 2 Representing a second classification probability, F ', of driving data in a vehicle damaged feature library' 1 (A) Representing a second candidate classification probability, F ', at acceleration A for a second feature' 2 (V t ) For the second characteristic to be expressed in wheel speed V t The probability of the second candidate class, F' 3 (V f ) For the second characteristic to be represented in the vehicle fault data V f The probability of the second candidate class, F' 4 (B) Representing a second candidate class probability, F ', for the second feature under the airbag data B' 5 (P) representing a second candidate classification probability, F ', at the vehicle pose P for the second feature' 6 (V c ) For the second characteristic to be represented in the video data V c The probability of the second candidate class, F' 7 (S) representing a second candidate class probability, F ', under the smoke data S for a second feature' 8 (W) represents a second candidate classification probability under the wading data W for the second feature.
S304, determining one or more target traffic accident scenes from the candidate traffic accident scenes according to the classification probability of any feature library and the corresponding classification threshold value.
For example, Y candidate traffic accident scenes having the largest classification probability may be identified as target traffic accident scenes, or candidate traffic accident scenes having a classification probability greater than a preset classification threshold may be identified as target traffic accident scenes. Wherein Y is a positive integer.
S305, generating a target traffic accident scene where the vehicle is currently located according to one or more target traffic accident scenes.
In some implementations, the target traffic accident scene is a damaged scene of the vehicle and a damaged scene of the person, and the target traffic accident scene in which the vehicle is currently located is generated according to the target traffic accident scene to be damaged by the person and the vehicle is damaged.
In some implementations, the target traffic accident scene is only a wounded scene of a person, and the target traffic accident scene where the vehicle is currently located is generated according to the target traffic accident scene to be wounded of the person.
In some implementations, the target traffic accident scene is only a vehicle damaged scene, and then the target traffic accident scene where the vehicle is currently located is generated according to the target traffic accident scene as the vehicle is damaged.
S306, acquiring one or more rescue platforms associated with the target traffic accident scene, and sending help seeking information to the associated rescue platforms.
The description of step S306 may be referred to the relevant content in the above embodiment, and will not be repeated here.
In the embodiment of the application, multiple types of driving data are acquired as driving information, common characteristics of historical traffic accidents can be learned, and traffic accident scenes are judged by combining the multiple types of driving data.
FIG. 4 is a flow chart of a method for automatically asking for assistance in a vehicle according to one embodiment of the present application, as shown in FIG. 4, the method comprising the steps of:
s401, vehicle collision detection data is acquired.
In the embodiment of the application, whether the vehicle collides or not can be monitored based on the vehicle collision monitoring system, so that the vehicle collision detection data can be obtained.
S402, responding to the vehicle collision data to indicate that the vehicle collides or receives an emergency help seeking instruction, and confirming that the vehicle needs to seek help.
In some implementations, if the vehicle collision data indicates that the vehicle is in a collision, that is, when the vehicle collision monitoring system is triggered, it is determined that the vehicle needs recourse.
In some implementations, an emergency assistance button is disposed in the vehicle, and after the emergency assistance button is triggered, an emergency assistance seeking instruction is sent out, and the vehicle controller receives the emergency assistance seeking instruction and confirms that the vehicle needs assistance seeking. Alternatively, the emergency assistance button may be deployed at the center console of the vehicle.
S403, acquiring the running information of the vehicle, wherein the running information comprises multiple types of running data.
And S404, carrying out feature extraction on the running information based on the feature extractor so as to acquire feature representations of various running data.
S405, identifying the characteristic representation of the driving data based on the plurality of characteristic libraries to acquire a current target traffic accident scene of the vehicle.
The description of step S403 to step S405 may be referred to the relevant content in the above embodiment, and will not be repeated here.
S406, generating recourse information based on the driving information, the current position information of the vehicle and preset vehicle attribute parameters.
Alternatively, the vehicle attribute information may include a model, license plate number, driver information (e.g., name, age, blood type), etc. of the vehicle.
Alternatively, the recourse information may be voice information or text information.
For example, the help seeking information may be "a white minibus turns over at site XXX, license plate number XXX, driver name XXX, age XXX, blood group XXX, and help is required to be assisted.
S407, the help seeking information is sent to one or more rescue platforms associated with the target traffic accident scene.
Alternatively, the help seeking platform may be a medical platform, a fire platform, a traffic platform, or the like.
In some implementations, a short message or a mail can be generated according to the rescue information and a preset template corresponding to the rescue platform and sent to the rescue platform. In some implementations, the service telephone of the rescue platform can be automatically dialed to conduct intelligent conversation so as to report the help seeking information and conduct help seeking.
In the embodiment of the application, the vehicle is confirmed to need to ask for help in response to the vehicle collision data indicating that the vehicle collides or the emergency asking for help instruction is received, so that the accuracy of asking for help can be improved, and erroneous judgment is avoided. The method comprises the steps of obtaining multiple types of driving data as driving information, learning common characteristics of historical traffic accidents, judging traffic accident scenes by combining the multiple types of driving data, identifying the current target traffic accident scene of the vehicle according to the characteristic representation of the driving data, improving the accuracy of identifying the traffic accident scene, obtaining one or more rescue platforms associated with the target traffic accident scene, sending help seeking information to the associated rescue platforms, and automatically seeking help according to the accident scene, so that the rescue delay is avoided, and the safety of accident personnel is improved.
Fig. 5 is a schematic diagram of an automatic vehicle help seeking method according to an embodiment of the present application, as shown in fig. 5, in the embodiment of the present application, after an emergency rescue button or a vehicle collision monitoring system is triggered, a vehicle controller obtains running information including multiple types of running data, performs classification recognition on the running information based on a machine learning model, obtains a first classification probability of the running data in a personnel injury feature library, and a second classification probability of the running data in a vehicle injury feature library, determines whether personnel injury occurs based on the first classification probability, and determines whether vehicle injury occurs based on the second classification probability. If the vehicle is damaged, sending help seeking information to a fire platform and/or a traffic management platform based on the current GPS position of the vehicle; if personnel injury occurs, help seeking information is sent to the medical platform based on the current GPS position of the vehicle.
Fig. 6 is a block diagram of a vehicle automatic help-seeking device according to the present application, and as shown in fig. 6, the vehicle automatic help-seeking device 600 includes:
an obtaining module 610, configured to obtain driving information of a vehicle, where the driving information includes multiple types of driving data;
the feature extraction module 620 is configured to perform feature extraction on the driving information based on the feature extractor, so as to obtain feature representations of various driving data;
the identifying module 630 is configured to identify, based on the feature libraries, a feature representation of the driving data, and obtain a current target traffic accident scene where the vehicle is located;
the recourse module 640 is configured to obtain one or more rescue platforms associated with the target traffic accident scene, and send recourse information to the associated rescue platforms.
In some implementations, one of the feature libraries corresponds to a candidate traffic accident scene, and the identification module 630 is further configured to:
classifying and identifying the characteristic representation of the driving data based on a plurality of characteristic libraries to obtain the classifying probability of the driving data in any characteristic library;
determining one or more target traffic accident scenes from the candidate traffic accident scenes according to the classification probability of any feature library and the corresponding classification threshold value;
and generating a target traffic accident scene where the vehicle is currently located according to one or more target traffic accident scenes.
In some implementations, the identification module 630 is further to:
classifying and identifying the characteristic representation of any type of driving data based on the first characteristic representation of the personnel injury characteristic library, and acquiring a first candidate classification probability of the first characteristic representation of any type of driving data;
and acquiring the first classification probability of the driving data in the personnel injury feature library according to the first candidate classification probability of any type of driving data and the first weight of any type of driving data.
In some implementations, the identification module 630 is further to:
classifying and identifying the characteristic representation of any type of driving data based on the second characteristic representation of the vehicle damaged characteristic library, and acquiring a second candidate classification probability of the second characteristic representation of any type of driving data;
and acquiring the second classification probability of the driving data in the personnel injury feature library according to the second candidate classification probability of any type of driving data and the second weight of any type of driving data.
In some implementations, the recourse module 640 is further configured to:
generating help seeking information based on the driving information, the current position information of the vehicle and preset vehicle attribute parameters;
and sending the recourse information to one or more rescue platforms associated with the target traffic accident scene.
In some implementations, the acquisition module 610 is further configured to:
acquiring vehicle collision detection data;
and responding to the vehicle collision data to indicate that the vehicle collides or receive an emergency help seeking instruction, and confirming that the vehicle needs to seek help.
In the embodiment of the application, multiple types of driving data are acquired as driving information, common characteristics of historical traffic accidents can be learned, traffic accident scenes are judged by combining the multiple types of driving data, the current target traffic accident scene of the vehicle is identified according to the characteristic representation of the driving data, accuracy of identifying the traffic accident scene can be improved, one or more rescue platforms associated with the target traffic accident scene are acquired, help seeking information is sent to the associated rescue platforms, and automatic help seeking is carried out according to the accident scene, so that rescue delay is avoided, and safety of accident personnel is improved.
In order to implement the foregoing embodiments, the embodiments of the present application further provide an electronic device 700, as shown in fig. 7, where the electronic device 700 includes: the processor 710 and a memory 720 communicatively coupled to the processor, the memory 720 storing instructions executable by the at least one processor, the instructions being executable by the at least one processor 710 to implement a vehicle automatic help method as described herein.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Based on the same application concept, the embodiment of the application further provides a computer readable storage medium, on which computer instructions are stored, wherein the computer instructions are used for making a computer execute the vehicle automatic help seeking method in the above embodiment.
Based on the same application concept, the embodiments of the present application also provide a computer program product, including a computer program, which when executed by a processor, is configured to implement the vehicle automatic recourse method in the above embodiments.
Based on the same application concept, the embodiment of the application also provides a vehicle, which comprises: the vehicle automatic help-seeking device in the above embodiment.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (10)
1. A method for automatically asking for assistance in a vehicle, comprising:
acquiring running information of a vehicle, wherein the running information comprises multiple types of running data;
extracting the characteristics of the running information based on a characteristic extractor to obtain characteristic representations of various running data;
identifying the characteristic representation of the driving data based on a plurality of characteristic libraries to acquire a target traffic accident scene where the vehicle is currently located;
and acquiring one or more rescue platforms associated with the target traffic accident scene, and sending help seeking information to the associated rescue platforms.
2. The method of claim 1, wherein one of the feature libraries corresponds to a candidate traffic accident scene, wherein the identifying the feature representation of the driving data based on the feature libraries to obtain the target traffic accident scene in which the vehicle is currently located comprises:
classifying and identifying the characteristic representation of the driving data based on the plurality of characteristic libraries to obtain the classifying probability of the driving data in any characteristic library;
determining one or more target traffic accident scenes from the candidate traffic accident scenes according to the classification probability of any feature library and the corresponding classification threshold value of the feature library;
and generating a target traffic accident scene where the vehicle is currently located according to the one or more target traffic accident scenes.
3. The method of claim 2, wherein one of the plurality of feature libraries is a person injury feature library, the method further comprising:
classifying and identifying the characteristic representation of any type of the driving data based on the first characteristic representation of the personnel injury characteristic library, and acquiring a first candidate classification probability of the first characteristic representation of any type of the driving data;
and acquiring the first classification probability of the driving data in the personnel injury feature library according to the first candidate classification probability of the driving data of any type and the first weight of the driving data of any type.
4. The method of claim 2, wherein one of the plurality of feature libraries is a vehicle damage feature library, the method further comprising:
classifying and identifying the characteristic representation of any type of driving data based on a second characteristic representation of a vehicle damaged characteristic library, and acquiring a second candidate classification probability of the second characteristic representation of any type of driving data;
and acquiring the second classification probability of the driving data in the personnel injury feature library according to the second candidate classification probability of the driving data of any type and the second weight of the driving data of any type.
5. The method according to any one of claims 1 to 4, further comprising, before the acquiring the running information of the vehicle:
acquiring vehicle collision detection data;
and responding to the vehicle collision data to indicate that the vehicle collides or receives an emergency help seeking instruction, and confirming that the vehicle needs to seek help.
6. An automatic help-seeking device for a vehicle, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring running information of a vehicle, and the running information comprises multiple types of running data;
the feature extraction module is used for carrying out feature extraction on the running information based on a feature extractor so as to obtain feature representations of various running data;
the identification module is used for identifying the characteristic representation of the driving data based on a plurality of characteristic libraries and acquiring a current target traffic accident scene of the vehicle;
the help seeking module is used for acquiring one or more rescue platforms associated with the target traffic accident scene and sending help seeking information to the associated rescue platforms.
7. The apparatus of claim 6, wherein one of the plurality of feature libraries corresponds to a candidate traffic accident scene, the identification module further configured to:
classifying and identifying the characteristic representation of the driving data based on the plurality of characteristic libraries to obtain the classifying probability of the driving data in any characteristic library;
determining one or more target traffic accident scenes from the candidate traffic accident scenes according to the classification probability of any feature library and the corresponding classification threshold value of the feature library;
and generating a target traffic accident scene where the vehicle is currently located according to the one or more target traffic accident scenes.
8. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1-5.
10. A vehicle, characterized in that the vehicle comprises: the automatic vehicle recourse apparatus as claimed in claim 6 or 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210689850.1A CN117295044A (en) | 2022-06-17 | 2022-06-17 | Automatic help seeking method and device for vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210689850.1A CN117295044A (en) | 2022-06-17 | 2022-06-17 | Automatic help seeking method and device for vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117295044A true CN117295044A (en) | 2023-12-26 |
Family
ID=89255868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210689850.1A Pending CN117295044A (en) | 2022-06-17 | 2022-06-17 | Automatic help seeking method and device for vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117295044A (en) |
-
2022
- 2022-06-17 CN CN202210689850.1A patent/CN117295044A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112389448B (en) | Abnormal driving behavior identification method based on vehicle state and driver state | |
| CN109800633B (en) | Non-motor vehicle traffic violation judgment method and device and electronic equipment | |
| JP6737906B2 (en) | Control device, system and method for determining the perceptual load of a visual and dynamic driving scene | |
| CN111191697B (en) | ADAS road test verification optimization method and device based on sensor fusion | |
| MX2014015331A (en) | Affective user interface in an autonomous vehicle. | |
| CN109270524B (en) | Unmanned-vehicle-based multi-data fusion obstacle detection device and detection method thereof | |
| CN112277936B (en) | Vehicle collision detection processing method and device, vehicle-mounted terminal and storage medium | |
| US20200175474A1 (en) | Information processing system, program, and control method | |
| US11315349B2 (en) | Method, apparatus and device for identifying passenger state in unmanned vehicle, and storage medium | |
| EP3712860A1 (en) | Storage system for vehicle | |
| El Masri et al. | Toward self-policing: Detecting drunk driving behaviors through sampling CAN bus data | |
| CN114049677B (en) | Vehicle ADAS control method and system based on driver emotion index | |
| CN112585550A (en) | Driving function monitoring based on neural network | |
| US10589741B2 (en) | Enhanced collision avoidance | |
| CN111800314B (en) | Automatic driving fault monitoring system | |
| CN111800508B (en) | Automatic driving fault monitoring method based on big data | |
| CN117295044A (en) | Automatic help seeking method and device for vehicle | |
| CN111862529A (en) | Alarm method and equipment | |
| CN114793334B (en) | Rescue calling method, device, equipment and storage medium based on Internet of vehicles | |
| DE102019126208A1 (en) | Emergency system for a vehicle | |
| CN108401234A (en) | For the method for detection data, the method for updating scene catalogue, equipment, computer program and machine readable storage medium | |
| US10562450B2 (en) | Enhanced lane negotiation | |
| CN113393643B (en) | Abnormal behavior early warning method and device, vehicle-mounted terminal and medium | |
| US11577753B2 (en) | Safety architecture for control of autonomous vehicle | |
| CN116625702A (en) | Vehicle collision detection method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |