CN114179811B - Data processing method, equipment, medium and product for acquiring driving state - Google Patents
Data processing method, equipment, medium and product for acquiring driving state Download PDFInfo
- Publication number
- CN114179811B CN114179811B CN202210144164.6A CN202210144164A CN114179811B CN 114179811 B CN114179811 B CN 114179811B CN 202210144164 A CN202210144164 A CN 202210144164A CN 114179811 B CN114179811 B CN 114179811B
- Authority
- CN
- China
- Prior art keywords
- driving state
- vehicle
- target
- data
- driving
- 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.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W2040/0872—Driver physiology
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/221—Physiology, e.g. weight, heartbeat, health or special needs
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/20—Ambient conditions, e.g. wind or rain
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a data processing method, equipment, a medium and a product for acquiring a driving state, wherein the method comprises the following steps: acquiring vehicle state data, traffic state data, weather state data, physiological state data and the like of a target vehicle ID, determining the current state of a driver according to state data of multiple dimensions, and automatically iterating an initial driving state model through a target training set to acquire a target driving state model; the automatic iteration of the initial driving state model can be realized, the initial driving state model is more deviated to the target vehicle, the initial driving state model is optimized, the accuracy of judging the driving state of the target vehicle is improved, the reasonable arrangement of the requirement of the current driving task on attention is realized, the driver is reminded of distributing the attention, the task complexity and the attention insufficiency are avoided, the potential safety hazard is caused, or the task complexity insufficiency is avoided, the concentration is higher, and the driving fatigue is caused.
Description
Technical Field
The invention relates to the technical field of driver attention, in particular to a data processing method, equipment, medium and product for acquiring a driving state.
Background
With the development of economy, automobiles become indispensable tools in human life, and a DMS (driver Monitor system) system is used in most automobiles, and generally, a vision monitoring scheme is used in the DMS system, which may include measuring eye movement of a driver, measuring a gaze direction of the driver, measuring an eye closure amount of the driver, measuring a blink movement of the driver, measuring a head position of the driver, measuring a head direction of the driver, measuring a facial feature of the driver's movement, and measuring a facial temperature pattern of the driver, to determine a concentration of the driver on attention, and consider the concentration of the driver from a single method, which may not effectively reflect an influence of a driving task, for example, the driver frequently observes a road surface, may be reported as distraction by the vision monitoring system, thereby causing false positives.
Currently, the concentration of the driver's attention can be determined by detecting the change of the concentration of the driver's attention by physiological state data, such as heart rate, heart rate variability, respiration, skin resistance, brain electricity, and pupils, but the influence of the complexity of the driving task on the concentration of the attention is not considered as the determination factor of the driving state, which causes the following problems:
1) the driver's inattention leads to accidents;
2) the unreasonable attention distribution of the driver caused by the excessively complicated operation can not process complicated driving tasks, thereby causing accidents;
in the low-level autopilot phase (below L4), the driving task may be handed to the autopilot function, but the driver is still required to remain attentive to take over the driving task at any time to cope with situations that the autopilot function cannot handle.
Disclosure of Invention
In order to solve the problems in the prior art, the technical scheme is as follows:
a data processing method of acquiring a driving state, the method comprising the steps of:
s100, acquiring an initial priority list Q = { Q of driving tasks1，Q2，……，Qm}，Qi={Qi1，Qi2，……，Qis}，QirThe sample data set of the r-th sample vehicle ID corresponding to the i-th initial priority is defined, i =1 … … m, m is the number of initial priorities, r =1 … … s, and s is the number of sample vehicle IDs;
s200, mixing all QiTaking the corresponding sample data set as an initial training set H0And is formed by0Inputting the driving state data into a preset driving state model for training to obtain an initial driving state model, wherein the initial driving state modelThe driving state function of the initial driving state model is F0（）；
S300, acquiring the target vehicle ID and a data set H = { H) corresponding to the target vehicle ID1，H2，……，Hn}，HjThe method comprises the steps of referring to a key data set corresponding to the jth time point, wherein j =1 … … n, and n is the number of time points in a preset time period;
s400, according to HjObtaining HjCorresponding target training set UjTo construct U = { U = { U =1，U2，……，Un}；
S500 according to U and F0() And acquiring a target driving state model corresponding to the target vehicle ID, wherein a driving state function corresponding to the target driving state model is Fn（）；
S600, acquiring a current data set corresponding to the target vehicle ID as a target prediction set H 'corresponding to the target vehicle ID, inputting the H' into a target driving state model, and acquiring a target probability value K 'corresponding to the target vehicle ID, wherein the K' meets the following conditions:
K'=Fn（H'）；
s700, comparing the K' with a preset threshold value, and determining the current driving state of the target vehicle ID.
The invention also protects a non-transitory computer readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, and the at least one instruction or the at least one program is loaded by a processor and executed to realize the data processing method for acquiring the driving state.
The invention also protects an electronic device comprising a processor and the non-transitory computer-readable storage medium described above.
The invention also protects a computer program product comprising a computer program executed by a processor for implementing the above-mentioned data processing method for acquiring a driving state.
The data processing method, equipment, medium and product for acquiring the driving state have the following technical effects:
according to the method, vehicle state data, traffic state data, weather state data, physiological state data and the like of the ID of the target vehicle are obtained, the current state of the driver is determined according to the state data of multiple dimensions, the accuracy of determining the current state of the driver is improved, and meanwhile, the initial driving state model is automatically iterated through a target training set to obtain the target driving state model; the automatic iteration of the initial driving state model can be realized, the initial driving state model is more deviated to the target vehicle, the initial driving state model is optimized, the accuracy of judging the driving state of the target vehicle is improved, the reasonable arrangement of the requirement of the current driving task on attention is realized, the driver is reminded of distributing the attention, the task complexity and the attention insufficiency are avoided, the potential safety hazard is caused, or the task complexity insufficiency is avoided, the concentration is higher, and the driving fatigue is caused.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a data processing method for acquiring a driving state according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the information so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
As shown in fig. 1, an embodiment of the present invention provides a data processing method for acquiring a driving state, the method including the steps of:
s100, acquiring an initial priority list Q = { Q of driving tasks1，Q2，……，Qm}，Qi={Qi1，Qi2，……，Qis}，QirThe sample data set refers to the sample data set of the r-th sample vehicle ID corresponding to the i-th initial priority, i =1 … … m, m is the number of initial priorities, r =1 … … s, and s is the number of sample vehicle IDs.
Specifically, the initial priority of the driving task refers to a complexity level for reflecting the driving task of the vehicle.
Specifically, the step S100 further includes the steps of:
s101, acquiring P = { P = { (P)1，P2，……，Pm}，Pi={Pi1，Pi2，……，Pizi}，PigIs the g-th first data list corresponding to the ith initial priority, g =1 … … zi，ziThe initial state dimension number of the vehicle corresponding to the ith initial priority is referred to, wherein each first data list comprises: all state feature vectors in a single initial state dimension.
Further, the initial state dimensions include: vehicle state, traffic state, weather state, driving operation state and other dimensions.
Further, the vehicle state dimension includes: one or more combined dimensional characteristics of vehicle speed, vehicle driving distance, vehicle driving time and vehicle gear.
Further, the traffic status dimension includes: one or more combined dimension characteristics of the distance between the vehicles, the route priority of the vehicles and the road condition priority of the vehicles.
Preferably, the route priority of the vehicle refers to a degree of repeated driving of the driving route of the vehicle, that is, a degree of familiarity of the driving route of the vehicle, and those skilled in the art know that the route priority of the vehicle is obtained by any method in the prior art, and will not be described herein again.
Preferably, the road condition priority of the vehicle refers to a road condition congestion degree reflecting a driving route of the vehicle, and a person skilled in the art knows that the road condition priority of the vehicle is obtained by any method in the prior art, which is not described herein again.
Further, the weather status dimension includes: temperature, humidity, illumination intensity, priority of abnormal weather.
Preferably, each first data list is set in a controlled preset experimental environment; wherein, each first data list is set for an automatic driving environment or an active driving environment according to a controlled preset experimental environment, and further, each first data list is set for an automatic driving environment according to an automatic driving level (L1-L5 level), which can be understood as: the automatic driving environment and the active driving environment have different set data due to different attention concentrations of required drivers, and further have different automatic driving grades and different set data due to different attention concentrations of the required drivers.
S103, adding PiInputting into a first target model, and obtaining PiCorresponding initial priority Ki(ii) a Those skilled in the art will appreciate that any method known in the art for obtaining an initial priority for a driving task, such as logistic regression, linear regression, etcAnd will not be described herein.
S105, acquiring PiCorresponding sample vehicle ID List Di={Di1，Di2，……，Dis}，DirIs the r-th sample vehicle ID.
In particular, the sample vehicle ID characterizes a unique identification of a sample vehicle identity, wherein the sample vehicle is known to a person skilled in the art to be a pre-provisioned vehicle.
S107, obtaining DirCorresponding second data list and based on the data according to DirConstructing Q as corresponding second data list and Piir(ii) a Can be understood as QirComprising DirCorresponding second data list and Pi。
Specifically, the second data list refers to a driver physiological state data list corresponding to any sample vehicle ID, where the physiological state corresponding to the driver physiological state data list includes: physiological state data collected by the in-vehicle sensor and physiological state data collected by the non-in-vehicle sensor.
Further, physiological state data collected by in-vehicle sensors, such as sensors deployed on the steering wheel, e.g., a pyroelectric sensor, a skin sensor, a pulse sensor, an accelerometer, a gyroscope, etc., are collected.
Further, the physiological state data collected by the non-in-vehicle sensor, for example, the data collected by a wearable intelligent device equipped with sensors such as a pulse sensor, a skin electric sensor, a temperature sensor, an accelerometer, a gyroscope bottom, or the data collected by an electrocardiogram plaster, or the data collected by a heart rate belt, wherein the wearable intelligent device is, for example, a smart bracelet, a smart watch, a smart arm belt, etc.
S200, mixing all QiTaking the corresponding sample data set as an initial training set H0And is formed by0Inputting the driving state function into a preset driving state model for training to obtain an initial driving state model, wherein the driving state function of the initial driving state model is F0（）。
Specifically, the preset model is a model for determining the driving state through the relationship between the complexity of the driving task and the attention of the driver, and can be understood as follows: the complexity of the driving task affects the concentration of the driver's attention required.
Preferably, F0() Any artificial intelligence algorithm, such as a neural network algorithm, a machine learning algorithm, etc., will not be described herein.
S300, acquiring the target vehicle ID and a data set H = { H ] corresponding to the target vehicle ID1，H2，……，Hn}，HjThe method is characterized in that a key data set corresponding to the jth time point is referred to, j =1 … … n, and n is the number of time points in a preset time period.
Specifically, the preset time period refers to a time period before the current time point, wherein a value of the preset time period is determined according to actual requirements, for example, the preset time period is 7 days, and a single time point in the terminal is 1 day.
Specifically, the method further comprises the following steps before the step S300:
s1, obtaining DirCorresponding second data list and according to DirCorresponding second data list, obtain DirCorresponding sample attention Air(ii) a The sample attention refers to the attention of the driver in the sample vehicle corresponding to the sample vehicle ID, and those skilled in the art know that the attention of the driver is determined by the physiological state data list of the driver.
S2, when AirNot less than a preset attention threshold A0Then, obtain PiCorresponding all dimension features and constructing a dimension feature list.
Specifically, P is acquirediCorresponding driver operation state data list, determining A according to the driver operation state data list0Wherein the driver operating state dimension comprises: the method comprises the following steps of (1) one or more combined dimensional characteristics in all data in a preset specified time period before an accident occurs, wherein the data comprise steering wheel rotating frequency, steering wheel rotating angle, braking times, braking reflecting time, lane offset and the like; wherein, the preset designated time period position is 5 s.
Preferably, the driver operating state dimension includes: the system comprises the steering wheel rotating frequency, the steering wheel rotating angle, the braking times, the braking response time, the lane offset and all data in a preset specified time period before an accident occurs.
S3, obtaining B = { B1，B2… …, By }, wherein BxRefers to the x-th dimension feature list, x =1 … … y, and y is the number of dimension feature lists.
S3, traversing B and acquiring a target dimension feature list B0Wherein B is0The following conditions are met:
B0=B1∩B2∩……∩By。
in particular, the key data list is according to B0Corresponding to all the characteristics, the data acquisition device acquires the relevant data of the target vehicle corresponding to the target vehicle ID in real time, and those skilled in the art know the method for acquiring the vehicle data through the existing acquisition device, which is not described herein again.
In a specific practical application, it can be determined by the above method that: preferably, the vehicle state dimension comprises: the dimension characteristics of the vehicle speed, the vehicle running distance, the vehicle running duration and the vehicle gear; preferably, the traffic status dimension comprises: the dimension characteristics of the distance between vehicles, the route priority of the vehicles and the road condition priority of the vehicles; preferably, the weather status dimension comprises: dimensional characteristics of temperature, humidity, illumination intensity and priority of abnormal weather; the characteristics suitable for obtaining the priority of the driving task can be screened out from the multiple dimensional characteristics, and the accuracy of determining the driving state is improved.
S400 according to HjObtaining HjCorresponding target training set UjTo construct U = { U =1，U2，……，Un}。
Specifically, UjThe following conditions are met:
Preferably, UjThe following conditions are met:
S500 according to U and F0() Acquiring a target driving state model corresponding to the target vehicle ID, wherein the driving state function corresponding to the target driving state model is Fn（）。
Specifically, the step S500 further includes the steps of:
s501, traversing U and combining UjIs input to Uj-1In the corresponding key driving state model, obtaining UjCorresponding key driving state model, wherein UjThe driving state function of the corresponding key driving state model is Fj() (ii) a It can be understood that: automatically iterating the initial driving state model through a target training set to obtain a target driving state model; the automatic iteration of the initial driving state model can be realized, so that the initial driving state model is more inclined to the target vehicle, the initial driving state model is optimized, and the accuracy of judging the driving state of the target vehicle is improved.
S503, when j = n, adding UjAnd taking the corresponding key driving state model as a target driving state model.
Further, in step S501, when j =1, U0The corresponding key driving state model is the initial driving state model.
S600, acquiring a current data set corresponding to the target vehicle ID as a target prediction set H 'corresponding to the target vehicle ID, inputting the H' into a target driving state model, and acquiring a target probability value K 'corresponding to the target vehicle ID, wherein the K' meets the following conditions:
K'=Fn（H'）。
specifically, the current data set corresponding to the target vehicle ID has the same dimensional characteristics as the key data of the target vehicle ID.
S700, comparing the K' with a preset threshold value, and determining the current driving state of the target vehicle ID.
Specifically, the step S700 further includes the steps of:
s701, when K' is equal to a preset first threshold value, determining that the current driving state of the target vehicle ID is a normal driving state; it can be understood that: when the current driving state of the target vehicle ID is the normal driving state, no auxiliary measures need to be taken for the target vehicle.
Specifically, the preset first threshold is 0 or 1, and preferably, the preset first threshold is 0.
S703, when K' is equal to a preset second threshold value, determining that the current driving state of the target vehicle ID is an abnormal driving state; it can be understood that: when the current driving state of the target vehicle ID is an abnormal driving state, auxiliary measures are required to be taken for the target vehicle, wherein the auxiliary measures comprise measures of closing partial functions of a central control system, sending prompt information and the like, for example, music and navigation are closed in the central control system, or a prompt tone is sent as the prompt information and the like; the driving environment is complex, the attention investment requirement is high, vehicle interaction information is automatically simplified, unnecessary content presentation and notification are reduced, and driver interference is avoided.
Specifically, the preset second threshold is 1 or 0, and the preset second threshold is not equal to the preset first threshold, preferably, the preset second threshold is 1.
The method comprises the steps of obtaining vehicle state data, traffic state data, weather state data, physiological state data and the like of a target vehicle ID, determining the current state of a driver according to state data of multiple dimensions, improving the accuracy of determining the current state of the driver, and automatically iterating an initial driving state model through a target training set to obtain a target driving state model; the automatic iteration of the initial driving state model can be realized, so that the initial driving state model is more biased to the target vehicle, the initial driving state model is optimized, the accuracy of judging the driving state of the target vehicle is improved, the attention requirement of the current driving task is reasonably arranged, the driver is reminded of distributing the attention, the potential safety hazard caused by the fact that the task is complicated and the attention is insufficient is avoided, or the driving fatigue caused by the fact that the task is complicated and the attention is insufficient when the concentration is high is avoided;
meanwhile, compared with the situation that single condition judgment is adopted for the concentration of the attention of the driver in the prior art, the method and the device have the advantages that the requirement of the complexity of the driving task on the concentration of the attention of the driver is dynamically changed, the model can calculate the attention input requirement and the actual concentration of the attention of the driver in real time, and determine whether the current state of the driver is a normal state or not, so that appropriate measures can be taken conveniently.
In a specific embodiment, QirComprising DirCorresponding second data list, PiA third data list corresponding to Dir, wherein the third data list is a data list of the attention state of the driver in the target monitoring area; the driver can be kept at a minimum level of alertness, and excessive attention on non-driving tasks is avoided.
Further, the target monitoring area refers to a monitoring area constructed based on an observation range of a driver and a vehicle type corresponding to the sample vehicle ID in the driving direction, and a method for determining the monitoring area according to the observation range of the driver and the vehicle type is known by those skilled in the art, and is not described herein again.
Further, the data list of the driver attentiveness state includes: a ratio between a first driver attention, a second driver attention, the first driver attention and the second driver attention, wherein the first driver attention refers to driver attention within the target monitored area and the second driver attention refers to driver attention within the non-target monitored area.
Further, the non-target monitoring area refers to other monitoring areas except the target monitoring area in the vehicle driving monitoring area corresponding to the sample vehicle ID, for example, a control area of a vehicle-mounted computer, an observation area required by a driver to observe a rearview mirror, and the like.
Embodiments of the present invention also provide a non-transitory computer-readable storage medium, which may be disposed in an electronic device to store at least one instruction or at least one program for implementing a method of the method embodiments, where the at least one instruction or the at least one program is loaded and executed by the processor to implement a data processing method for acquiring a driving status provided by the above embodiments.
Embodiments of the present invention also provide an electronic device comprising a processor and the non-transitory computer-readable storage medium described above.
The computer apparatus of the embodiments of the present invention exists in many forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. This type of device comprises: audio, video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.
(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.
(5) And other electronic devices with data interaction functions.
Embodiments of the present invention also provide a computer program product including a computer program executed by a processor to implement the data processing method of acquiring a driving state described above.
Although some specific embodiments of the present invention have been described in detail by way of illustration, it should be understood by those skilled in the art that the above illustration is only for the purpose of illustration and is not intended to limit the scope of the invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (7)
1. A data processing method for acquiring a driving state, the method comprising the steps of:
s100, acquiring an initial priority list Q = { Q of driving tasks1，Q2，……，Qi，……，Qm}，Qi={Qi1，Qi2，……，Qir，……，Qis}，QirThe method is a sample data set of an r-th sample vehicle ID corresponding to an i-th initial priority, i =1 … … m, m is the number of initial priorities, r =1 … … S, S is the number of sample vehicle IDs, and the method further includes the following steps in step S100:
s101, acquiring P = { P = { (P)1，P2，……，Pi，……，Pm}，
，PigIs the g-th first data list corresponding to the ith initial priority, g =1 … … zi，ziThe initial state dimension number of the vehicle corresponding to the ith initial priority is referred to, wherein each first data list comprises: single initial state dimensionAll state feature vectors in degrees, the initial state dimensions comprising: vehicle status, traffic status, weather status, and driving operation status;
s103, adding PiInputting into a first target model, and obtaining PiCorresponding initial priority Ki；
S105, acquiring PiCorresponding sample vehicle ID List Di={Di1，Di2，……，Dir，……，Dis}，DirIs the r-th sample vehicle ID;
s107, obtaining DirCorresponding second data list and based on the data according to DirCorresponding second data list and PiConstructed as QirThe second data list refers to a driver physiological state data list corresponding to any sample vehicle ID, where the physiological state corresponding to the driver physiological state data list includes: physiological state data collected by the in-vehicle sensor and physiological state data collected by the non-in-vehicle sensor;
s200, mixing all QiTaking the corresponding sample data set as an initial training set H0And is formed by0Inputting the driving state function into a preset driving state model for training to obtain an initial driving state model, wherein the driving state function of the initial driving state model is F0（）；
S300, acquiring the target vehicle ID and a data set H = { H) corresponding to the target vehicle ID1，H2，……，Hj，……，Hn}，HjThe method comprises the steps of referring to a key data set corresponding to the jth time point, wherein j =1 … … n, and n is the number of time points in a preset time period;
s400, according to HjObtaining HjCorresponding target training set UjTo construct U = { U =1，U2，……，Uj，……，UnIn which UjThe following conditions are met:
s500 according to U and F0() Acquiring a target driving state model corresponding to the target vehicle ID, wherein the driving state function corresponding to the target driving state model is Fn() Wherein, the step of S500 further comprises the following steps:
s501, traversing U and combining UjIs input to Uj-1In the corresponding key driving state model, obtaining UjCorresponding key driving state model, wherein UjThe driving state function of the corresponding key driving state model is Fj（）；
S503, when j = n, adding UjThe corresponding key driving state model is used as a target driving state model;
s600, acquiring a current data set corresponding to the target vehicle ID as a target prediction set H 'corresponding to the target vehicle ID, inputting the H' into a target driving state model, and acquiring a target probability value K 'corresponding to the target vehicle ID, wherein the K' meets the following conditions:
K'=Fn（H'）；
s700, comparing the K' with a preset threshold value, and determining the current driving state of the target vehicle ID, wherein the step S700 further comprises the following steps:
s701, when K' is equal to a preset first threshold value, determining that the current driving state of the target vehicle ID is a normal driving state;
and S703, when the K' is equal to a preset second threshold value, determining that the current driving state of the target vehicle ID is an abnormal driving state.
2. Data processing method for obtaining driving conditions, according to claim 1, characterized in that F0() Is any artificial intelligence algorithm.
3. The data processing method for acquiring driving state of claim 1, wherein U isjThe following conditions are met:
4. the data processing method for acquiring driving state according to claim 1, wherein in step S501, when j =1, U is set to be equal to or greater than 10The corresponding key driving state model is the initial driving state model.
5. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, and the at least one instruction or the at least one program is loaded by a processor and executed to implement a data processing method for obtaining driving status according to any one of claims 1 to 4.
6. An electronic device comprising a processor and the non-transitory computer readable storage medium of claim 5.
7. A computer program product comprising a computer program, characterized in that the computer program is executed by a processor to implement a data processing method of acquiring a driving status according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210144164.6A CN114179811B (en) | 2022-02-17 | 2022-02-17 | Data processing method, equipment, medium and product for acquiring driving state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210144164.6A CN114179811B (en) | 2022-02-17 | 2022-02-17 | Data processing method, equipment, medium and product for acquiring driving state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114179811A CN114179811A (en) | 2022-03-15 |
| CN114179811B true CN114179811B (en) | 2022-06-10 |
Family
ID=80546106
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210144164.6A Active CN114179811B (en) | 2022-02-17 | 2022-02-17 | Data processing method, equipment, medium and product for acquiring driving state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114179811B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008103119A1 (en) * | 2007-02-19 | 2008-08-28 | Scania Cv Ab (Publ) | Method, device and computer program product for estimating the tiredness of a motor vehicles driver and a motor vehicle including such a device |
| CN101746269A (en) * | 2010-01-08 | 2010-06-23 | 东南大学 | Fatigue driving fusion detection method based on soft computing |
| EP2311707A1 (en) * | 2009-10-16 | 2011-04-20 | Audi AG | Method for operating a driver assistance system in a motor vehicle and motor vehicle |
| JP2011081570A (en) * | 2009-10-06 | 2011-04-21 | Toyota Motor Corp | Driver condition estimating device and driver condition estimating method |
| CN105809152A (en) * | 2016-04-06 | 2016-07-27 | 清华大学 | Monitoring method for cognitive distraction of driver on basis of multi-source information fusion |
| CN107194346A (en) * | 2017-05-19 | 2017-09-22 | 福建师范大学 | A kind of fatigue drive of car Forecasting Methodology |
| CN108146344A (en) * | 2018-01-05 | 2018-06-12 | 吉林大学 | A kind of driver fatigue monitor system based on Multi-source Information Fusion |
| US10081366B1 (en) * | 2015-05-04 | 2018-09-25 | Carnegie Mellon University | Sensor-based assessment of attention interruptibility |
| CN109147279A (en) * | 2018-10-19 | 2019-01-04 | 燕山大学 | A kind of driver tired driving monitoring and pre-alarming method and system based on car networking |
| CN209063895U (en) * | 2018-12-03 | 2019-07-05 | 安阳师范学院 | Tired driver combined of multi-sensor information drives early warning and pro-active intervention system |
| CN110236576A (en) * | 2019-07-18 | 2019-09-17 | 内蒙古师范大学 | A kind of driver's acquiring brain waves and analysis system based on data fusion |
| KR102096617B1 (en) * | 2018-12-12 | 2020-04-02 | 충남대학교산학협력단 | Driver drowsiness detection system using image and ppg data based on multimodal deep learning |
| WO2020086015A1 (en) * | 2018-10-22 | 2020-04-30 | Innomel Muhendislik Sanayi Ve Ticaret Limited Sirketi | A system that perceives, reports fatigue and distraction of the driver and processes big data and a method of its implementation |
| CN111433103A (en) * | 2017-12-18 | 2020-07-17 | 智加科技公司 | Method and system for adaptive motion planning in autonomous vehicles based on occupant reaction to vehicle motion |
| CN113743471A (en) * | 2021-08-05 | 2021-12-03 | 暨南大学 | Driving evaluation method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170267251A1 (en) * | 2016-03-15 | 2017-09-21 | Palo Alto Research Center Incorporated | System And Method For Providing Context-Specific Vehicular Driver Interactions |
| EP3795441A1 (en) * | 2019-09-17 | 2021-03-24 | Aptiv Technologies Limited | Method and device for determining an estimate of the capability of a vehicle driver to take over control of a vehicle |
-
2022
- 2022-02-17 CN CN202210144164.6A patent/CN114179811B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008103119A1 (en) * | 2007-02-19 | 2008-08-28 | Scania Cv Ab (Publ) | Method, device and computer program product for estimating the tiredness of a motor vehicles driver and a motor vehicle including such a device |
| JP2011081570A (en) * | 2009-10-06 | 2011-04-21 | Toyota Motor Corp | Driver condition estimating device and driver condition estimating method |
| EP2311707A1 (en) * | 2009-10-16 | 2011-04-20 | Audi AG | Method for operating a driver assistance system in a motor vehicle and motor vehicle |
| CN101746269A (en) * | 2010-01-08 | 2010-06-23 | 东南大学 | Fatigue driving fusion detection method based on soft computing |
| US10081366B1 (en) * | 2015-05-04 | 2018-09-25 | Carnegie Mellon University | Sensor-based assessment of attention interruptibility |
| CN105809152A (en) * | 2016-04-06 | 2016-07-27 | 清华大学 | Monitoring method for cognitive distraction of driver on basis of multi-source information fusion |
| CN107194346A (en) * | 2017-05-19 | 2017-09-22 | 福建师范大学 | A kind of fatigue drive of car Forecasting Methodology |
| CN111433103A (en) * | 2017-12-18 | 2020-07-17 | 智加科技公司 | Method and system for adaptive motion planning in autonomous vehicles based on occupant reaction to vehicle motion |
| CN108146344A (en) * | 2018-01-05 | 2018-06-12 | 吉林大学 | A kind of driver fatigue monitor system based on Multi-source Information Fusion |
| CN109147279A (en) * | 2018-10-19 | 2019-01-04 | 燕山大学 | A kind of driver tired driving monitoring and pre-alarming method and system based on car networking |
| WO2020086015A1 (en) * | 2018-10-22 | 2020-04-30 | Innomel Muhendislik Sanayi Ve Ticaret Limited Sirketi | A system that perceives, reports fatigue and distraction of the driver and processes big data and a method of its implementation |
| CN209063895U (en) * | 2018-12-03 | 2019-07-05 | 安阳师范学院 | Tired driver combined of multi-sensor information drives early warning and pro-active intervention system |
| KR102096617B1 (en) * | 2018-12-12 | 2020-04-02 | 충남대학교산학협력단 | Driver drowsiness detection system using image and ppg data based on multimodal deep learning |
| CN110236576A (en) * | 2019-07-18 | 2019-09-17 | 内蒙古师范大学 | A kind of driver's acquiring brain waves and analysis system based on data fusion |
| CN113743471A (en) * | 2021-08-05 | 2021-12-03 | 暨南大学 | Driving evaluation method and system |
Non-Patent Citations (3)
| Title |
|---|
| 基于多源信息融合的疲劳检测系统研究;张博;《中国优秀硕士学位论文全文数据库工程科技II辑》;20190615(第06期);全文 * |
| 基于脉搏波特征融合的驾驶疲劳检测方法;李鑫等;《中国公路学报》;20200615(第06期);全文 * |
| 浅谈汽车驾驶员疲劳监测技术的研究进展;吴春莹;《机电一体化》;20070720(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114179811A (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7092116B2 (en) | Information processing equipment, information processing methods, and programs | |
| US20220164026A1 (en) | Methods and systems for using artificial intelligence to evaluate, correct, and monitor user attentiveness | |
| Abou Elassad et al. | The application of machine learning techniques for driving behavior analysis: A conceptual framework and a systematic literature review | |
| JP7288911B2 (en) | Information processing device, mobile device, method, and program | |
| US10467488B2 (en) | Method to analyze attention margin and to prevent inattentive and unsafe driving | |
| Xu et al. | Human-factors-in-driving-loop: Driver identification and verification via a deep learning approach using psychological behavioral data | |
| Chan et al. | A comprehensive review of driver behavior analysis utilizing smartphones | |
| JP6972629B2 (en) | Information processing equipment, information processing methods, and programs | |
| DE102017114049B4 (en) | SYSTEMS FOR SELECTING AND IMPLEMENTING ROUTES FOR AUTONOMOUS VEHICLES | |
| JP7324716B2 (en) | Information processing device, mobile device, method, and program | |
| US11814054B2 (en) | Exhaustive driving analytical systems and modelers | |
| US7394393B2 (en) | Adaptive driver workload estimator | |
| JP2022552860A (en) | Passenger Condition Adjustment System for Passenger Cars Based on Predictive and Anticipatory Control | |
| US20200247422A1 (en) | Inattentive driving suppression system | |
| EP4042322A1 (en) | Methods and systems for using artificial intelligence to evaluate, correct, and monitor user attentiveness | |
| Yang et al. | Real-time driver cognitive workload recognition: Attention-enabled learning with multimodal information fusion | |
| CN112455461B (en) | Human-vehicle interaction method for automatically driving vehicle and automatically driving system | |
| CN108898795B (en) | Pedestrian state real-time analysis method and system based on mobile device | |
| CN114179811B (en) | Data processing method, equipment, medium and product for acquiring driving state | |
| KR20220089772A (en) | Drive ability evaluated method for evaluating driving ability of driver and, human factor evaluation system for performing the method | |
| CN109249931A (en) | Control method and device for vehicle drive | |
| JP7390329B2 (en) | Recognition index setting device | |
| Priyadharshini et al. | A comprehensive review of various data collection approaches, features, and algorithms used for the classification of driving style | |
| Murphey et al. | Driver workload in an autonomous vehicle | |
| Ansari et al. | Factors influencing driver behavior and advances in monitoring methods |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |