CN117437765A - Accident alarm method and system based on big data driving records - Google Patents
Accident alarm method and system based on big data driving records Download PDFInfo
- Publication number
- CN117437765A CN117437765A CN202311760828.2A CN202311760828A CN117437765A CN 117437765 A CN117437765 A CN 117437765A CN 202311760828 A CN202311760828 A CN 202311760828A CN 117437765 A CN117437765 A CN 117437765A
- Authority
- CN
- China
- Prior art keywords
- accident
- vehicle
- image
- fault
- big data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 239000000463 material Substances 0.000 claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 46
- 230000008439 repair process Effects 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 30
- 210000003127 knee Anatomy 0.000 claims description 22
- 210000003205 muscle Anatomy 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000009795 derivation Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000005587 bubbling Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000000110 cooling liquid Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0816—Indicating performance data, e.g. occurrence of a malfunction
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
Abstract
The invention relates to the technical field of automobiles, and provides an accident alarming method and system based on big data driving records, which are used for analyzing weight detection faults corresponding to a driving recorder; calculating an image gradient value corresponding to the shake image, and analyzing an anti-shake function fault corresponding to the automobile data recorder; setting fault prompt information corresponding to the automobile data recorder, and repairing the automobile data recorder to obtain a repaired automobile data recorder; evaluating a sitting posture safety level corresponding to a vehicle driver of the starting vehicle; and (3) carrying out accident monitoring on the starting vehicle, recording accident video and accident time when the starting vehicle has an accident, detecting the material flow coefficient of the starting vehicle in real time, analyzing the corresponding accident level of the starting vehicle, and setting an alarm scheme of the starting vehicle. The invention aims to improve the analysis accuracy of accident alarm.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to an accident alarming method and system based on big data driving records.
Background
With the increase of global vehicles and the acceleration of urban processes, the number of casualties caused by traffic accidents in the world is millions, and huge economic and manpower losses are brought to society, so that how to timely discover and prevent the traffic accidents becomes a urgent problem to be solved.
The existing traffic accident alarm system mainly relies on manual patrol and a monitoring camera to carry out accident identification, but the problems of low identification accuracy, low reaction speed and the like exist in the mode, the timely early warning and alarm requirements on traffic accidents cannot be met, further the analysis accuracy of accident alarm is reduced, and therefore an accident alarm system capable of improving the analysis accuracy of accident alarm is needed.
Disclosure of Invention
The invention provides an accident alarming method and system based on big data driving records, and mainly aims to improve the analysis accuracy of accident alarming.
In order to achieve the above purpose, the accident alarming method based on big data driving records provided by the invention comprises the following steps:
acquiring a starting vehicle of an accident to be analyzed, starting a vehicle data recorder of the starting vehicle, acquiring a vehicle weight value of the starting vehicle by using the vehicle data recorder, and analyzing a weight detection fault corresponding to the vehicle data recorder according to the vehicle weight value and a preset big data platform;
performing jitter processing on the automobile data recorder, capturing a jitter image of the automobile data recorder in the jitter processing process, calculating an image gradient value corresponding to the jitter image, and analyzing an anti-jitter function fault corresponding to the automobile data recorder according to the image gradient value, the jitter image and the big data platform;
Setting fault prompt information corresponding to the automobile data recorder according to the weight detection fault and the anti-shake function fault, and repairing the automobile data recorder according to the fault prompt information to obtain a repaired automobile data recorder;
evaluating the sitting posture safety level corresponding to the vehicle driver of the started vehicle by combining the big data platform, and adjusting the sitting posture of the vehicle driver according to the sitting posture safety level to obtain a safe sitting posture;
when the sitting posture of the vehicle driver is the safe sitting posture, accident monitoring is carried out on the starting vehicle, when an accident occurs on the starting vehicle, accident video and accident time are recorded by using the repair vehicle recorder, the material flow coefficient of the starting vehicle is detected in real time, the accident level corresponding to the starting vehicle is analyzed according to the material flow coefficient, the accident time and the big data platform, and an alarm scheme of the starting vehicle is set according to the accident level and the accident video.
Optionally, the analyzing the weight detection fault corresponding to the automobile data recorder according to the vehicle weight value and a preset big data platform includes:
Identifying a timestamp corresponding to the vehicle weight value;
according to the time stamp, sorting the vehicle weight values to obtain sorting weight values;
calculating the weight ratio between adjacent weight values in the sorting weight values;
inquiring a preset threshold value corresponding to the starting vehicle from the big data platform;
and analyzing the weight detection fault corresponding to the automobile data recorder according to the weight ratio and the preset threshold.
Optionally, the calculating an image gradient value corresponding to the jittered image includes:
performing image noise reduction processing on the jittered image to obtain a noise-reduced jittered image;
performing gray level conversion processing on the noise-reduced jittered image to obtain a gray level jittered image;
calculating a pixel gradient value corresponding to each pixel point in the gray scale dithering image;
and calculating an image gradient value corresponding to the jittering image according to the pixel gradient value.
Optionally, the calculating a pixel gradient value corresponding to each pixel point in the gray scale dithering image includes:
calculating a pixel gradient value corresponding to each pixel point in the gray scale dithering image through the following formula:
；
wherein A represents a pixel gradient value corresponding to each pixel point in the gray scale dithering image, and B j Representing the gray value of the j-th pixel point in the gray dither image, B j+1 Represents the gray value, B (B) j -B j +1) represents a forward difference quotient of gray values of jth and jth+1th pixel points in the gray dither image, d (B) j） Representing the value of the jth pixel point in the standard face image after derivation, B (B) j -B j +1) represents a backward difference quotient of gray values of j-th and j+1th pixel points in the gray dither image.
Optionally, the analyzing, according to the image gradient value, the shake image, and the big data platform, the anti-shake function fault corresponding to the automobile data recorder includes:
according to the image gradient value, turning over pixel points in the jittering image to obtain a turned over jittering image;
calculating a pixel variance value corresponding to the overturning shaking image, and inquiring a fuzzy judgment section corresponding to the automobile data recorder from the big data platform;
according to the pixel variance value and the fuzzy judgment section, performing fuzzy judgment on the overturning shaking image to obtain a judgment result;
and analyzing the anti-shake function fault corresponding to the automobile data recorder according to the judging result.
Optionally, the calculating a pixel variance value corresponding to the flipped dither image includes:
Calculating a pixel variance value corresponding to the flipped dither image according to the following formula:
wherein G represents a pixel variance value corresponding to the flip dither image, M represents an image width corresponding to the flip dither image, N represents an image height corresponding to the flip dither image, H (x, y) represents a brightness value corresponding to a pixel point with a coordinate point (x, y) in the flip dither image,representing the pixel average of the flipped dither image.
Optionally, the setting the fault prompt information corresponding to the automobile data recorder according to the weight detection fault and the anti-shake function fault includes:
respectively analyzing the fault types corresponding to the weight detection fault and the anti-shake function fault to obtain a first fault type and a second fault type;
inquiring fault codes corresponding to the first fault type and the second fault type to obtain a first fault code and a second fault code;
configuring the repair information of the first fault code and the second fault code to obtain first repair information and second repair information;
and generating fault prompt information corresponding to the automobile data recorder by combining the first fault code, the second fault code, the first repair information and the second repair information.
Optionally, the evaluating, in combination with the big data platform, a sitting posture security level corresponding to a vehicle driver of the starting vehicle includes:
calculating a frontal muscle distance value between a vehicle driver and a steering wheel in the starting vehicle, and calculating a knee distance value between the vehicle driver and a driver seat knee barrier in the starting vehicle;
dispatching sign information corresponding to the vehicle driver;
according to the sign information, inquiring a standard frontal muscle distance value and a standard knee distance value corresponding to the automobile data recorder by utilizing the big data platform;
and evaluating the sitting posture safety level corresponding to the vehicle driver by combining the standard frontalis distance value, the standard knee distance value, the frontalis distance value and the knee distance value.
Optionally, the analyzing the accident level corresponding to the starting vehicle according to the material flow coefficient, the accident time and the big data platform includes:
classifying the material flow coefficient according to the accident time to obtain a flow coefficient before an accident and an accident flow coefficient;
calculating an average flow coefficient corresponding to each substance in the pre-accident flow coefficients;
Calculating the coefficient ratio of the average flow coefficient to the accident flow coefficient;
inquiring a flow threshold corresponding to the accident level from the big data platform;
and analyzing the accident level corresponding to the starting vehicle according to the coefficient ratio and the flow threshold.
An accident alarm system based on big data driving records, which is characterized in that the system comprises:
the weight detection fault analysis module is used for acquiring a starting vehicle of an accident to be analyzed, starting a vehicle recorder of the starting vehicle, acquiring a vehicle weight value of the starting vehicle by using the vehicle recorder, and analyzing a weight detection fault corresponding to the vehicle recorder according to the vehicle weight value and a preset big data platform;
the anti-shake function fault analysis module is used for carrying out shake processing on the automobile data recorder, capturing shake images of the automobile data recorder in the shake processing process, calculating image gradient values corresponding to the shake images, and analyzing anti-shake function faults corresponding to the automobile data recorder according to the image gradient values, the shake images and the big data platform;
the fault repairing module is used for detecting faults and the anti-shake function faults according to the weight, setting fault prompt information corresponding to the automobile data recorder, and repairing the automobile data recorder according to the fault prompt information to obtain a repaired automobile data recorder;
The sitting posture adjustment module is used for evaluating the sitting posture safety level corresponding to the vehicle driver of the starting vehicle by combining the big data platform, and adjusting the sitting posture of the vehicle driver according to the sitting posture safety level to obtain a safe sitting posture;
the alarm processing module is used for carrying out accident monitoring on the starting vehicle when the sitting posture of the vehicle driver is the safe sitting posture, recording accident video and accident time by using the repair vehicle recorder when the starting vehicle is in an accident, detecting the material flow coefficient of the starting vehicle in real time, analyzing the accident level corresponding to the starting vehicle according to the material flow coefficient, the accident time and the big data platform, and setting an alarm scheme of the starting vehicle according to the accident level and the accident video.
According to the weight value of the vehicle, the weight detection fault corresponding to the vehicle recorder is judged, whether the vehicle recorder has the fault or not can be analyzed according to the weight detection fault so as to facilitate the subsequent repair treatment of the vehicle recorder, the pixel change rate of the shaking image can be known through calculating the image gradient value corresponding to the shaking image so as to facilitate the analysis of the subsequent shaking prevention function fault. Therefore, the accident alarming method and the accident alarming method based on the big data driving records can improve the analysis accuracy of accident alarming.
Drawings
Fig. 1 is a schematic flow chart of an accident alarming method based on big data driving records according to an embodiment of the present invention;
fig. 2 is a functional block diagram of an accident alarm system based on big data driving records according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides an accident alarming method based on big data driving records. In the embodiment of the present application, the execution body of the accident alarming method based on big data driving records includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided in the embodiment of the present application. In other words, the accident alarming method based on the big data driving record can be executed by software or hardware installed in the terminal equipment or the server equipment, and the software can be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of an accident alarming method based on big data driving records according to an embodiment of the present invention is shown. In this embodiment, the accident alarming method based on big data driving records includes steps S1 to S5.
S1, acquiring a starting vehicle of an accident to be analyzed, starting a vehicle data recorder of the starting vehicle, acquiring a vehicle weight value of the starting vehicle by using the vehicle data recorder, and analyzing a weight detection fault corresponding to the vehicle data recorder according to the vehicle weight value and a preset big data platform.
According to the method, whether the vehicle event data recorder has a fault or not can be analyzed according to the weight detection fault, so that the vehicle event data recorder can be repaired conveniently, wherein the starting vehicle is a vehicle needing accident alarm analysis, the vehicle event data recorder is a camera device installed in the starting vehicle and is used for recording images and sounds in the driving process of the vehicle, the vehicle weight value represents the weight corresponding to the starting vehicle, the weight detection fault represents the problem of the weight detection function of the vehicle event data recorder, optionally, the vehicle event data recorder can be started through a vehicle-mounted computer system in the starting vehicle, the vehicle weight value of the starting vehicle can be collected through a weight sensor in the vehicle event data recorder, and a large data platform is a platform constructed by utilizing a large data technology and comprises a large number of standard parameter values related to the vehicle.
As an embodiment of the present invention, the analyzing the weight detection fault corresponding to the vehicle recorder according to the vehicle weight value and a preset big data platform includes: and identifying a time stamp corresponding to the vehicle weight value, sorting the vehicle weight values according to the time stamp to obtain sorted weight values, calculating a weight ratio between adjacent weight values in the sorted weight values, inquiring a preset threshold value corresponding to the starting vehicle from the large data platform, and analyzing a weight detection fault corresponding to the vehicle recorder according to the weight ratio and the preset threshold value.
The time stamp is a collection time point of the vehicle weight value, the sorting weight value is a weight value obtained after the vehicle weight values are sorted according to the sequence of the time stamp, the weight ratio is a value obtained by dividing a previous vehicle weight value by a next vehicle weight value, and the preset threshold is a judgment standard value corresponding to the vehicle importance value.
Optionally, the timestamp corresponding to the vehicle weight value may be implemented by an identification tool, the identification tool is compiled by a scripting language, the sorting processing of the vehicle weight value may be implemented by a sorting algorithm, for example, an bubbling sorting algorithm, the querying of the preset threshold corresponding to the starting vehicle may be implemented by a find function, and the analyzing whether the weight sensor of the vehicle recorder has a fault includes the specific steps of: and multiplying the weight ratio by 100% to obtain a first percentage, and if the first percentage is greater than 80% when the preset threshold is 80%, detecting that the weight of the automobile data recorder has faults.
S2, performing jitter processing on the automobile data recorder, capturing a jitter image of the automobile data recorder in the jitter processing process, calculating an image gradient value corresponding to the jitter image, and analyzing an anti-jitter function fault corresponding to the automobile data recorder according to the image gradient value, the jitter image and the big data platform.
According to the invention, the pixel change rate of the jittering image can be known by calculating the image gradient value corresponding to the jittering image, so that the analysis of the follow-up anti-jittering function fault is facilitated, wherein the jittering image is an image shot by the automobile recorder in the process of jittering treatment, and optionally, the jittering treatment of the automobile recorder can be realized by a jittering sensor, and the capturing of the jittering image of the automobile recorder in the process of jittering treatment can be realized by a Haar cascade algorithm.
As one embodiment of the present invention, the calculating the image gradient value corresponding to the dithered image includes: and performing image noise reduction processing on the jittered image to obtain a noise-reduced jittered image, performing gray level conversion processing on the noise-reduced jittered image to obtain a gray level jittered image, calculating a pixel gradient value corresponding to each pixel point in the gray level jittered image, and calculating an image gradient value corresponding to the jittered image according to the pixel gradient value.
The noise-reducing jittering image is an image obtained by removing noise interference in the jittering image, the gray scale jittering image is an image expressed by single color of the noise-reducing jittering image, and the pixel gradient value represents the gray scale change degree of each pixel point and adjacent pixel points in the gray scale jittering image.
Optionally, the image noise reduction processing on the jittered image may be implemented by a low-pass filter, and the step of performing the gray conversion processing on the noise reduced jittered image includes: and calculating the gray pixel value of each pixel point by weighted average of the pixel values of RGB channels of each pixel point in the noise reduction jittering image, expressing the image by using the gray pixel value to obtain a gray jittering image, calculating the average gradient value of the pixel gradient value, and taking the average gradient value as the image gradient value of the jittering image.
Optionally, as an optional embodiment of the present invention, the calculating a pixel gradient value corresponding to each pixel point in the gray scale dithering image includes:
calculating a pixel gradient value corresponding to each pixel point in the gray scale dithering image through the following formula:
wherein A represents a pixel gradient value corresponding to each pixel point in the gray scale dithering image, and B j Representing the gray value of the j-th pixel point in the gray dither image, B j+1 Represents the gray value, B (B) j +B j + 1 ) A forward difference quotient, d (B), representing the gray value of the j-th and j+1-th pixel points in the gray dither image j ) Representing the value of the jth pixel point in the standard face image after derivation, B (B) j +B j + 1 ) And the backward difference quotient of the gray values of the j-th pixel point and the j+1-th pixel point in the gray dither image is represented.
According to the image gradient value, the anti-shake function fault corresponding to the automobile data recorder is analyzed, whether the automobile data recorder has shooting faults or not can be judged, and further the accuracy of subsequent accident analysis is improved, wherein the anti-shake function fault is an image which cannot be effectively stabilized by the automobile data recorder under the shaking condition, so that the quality of the image is reduced.
As an embodiment of the present invention, the analyzing the anti-shake function fault corresponding to the vehicle recorder according to the image gradient value, the shake image and the big data platform includes: and according to the image gradient value, performing overturn processing on pixel points in the jitter image to obtain an overturn jitter image, calculating a pixel variance value corresponding to the overturn jitter image, inquiring a fuzzy judgment section corresponding to the automobile data recorder from the big data platform, and according to the pixel variance value and the fuzzy judgment section, performing fuzzy judgment on the overturn jitter image to obtain a judgment result, and according to the judgment result, analyzing an anti-jitter function fault corresponding to the automobile data recorder.
The overturn shaking image is an image obtained by horizontally overturning pixel points in the shaking image according to the image gradient values, the pixel variance value is a variance of pixel gray values in the overturn shaking image, and the fuzzy judgment section is a range of the automobile data recorder for judging whether the image is a fuzzy image or not.
Optionally, the overturning processing of the pixel points in the jittering image may be implemented by exchanging the pixel points of the left half part and the pixel points of the right half part of the image along the vertical central axis, calculating the pixel variance value corresponding to the overturning jittering image may be implemented by a variance calculator, and querying the fuzzy determination section corresponding to the automobile data recorder may be implemented by the find function, where the step of performing fuzzy determination on the jittering image includes: the fuzzy judgment section is (a, d), the pixel variance value is c, if c is larger than d, the overturn shaking image is a cleaning image, if c is between a and d, the overturn shaking image is a low-fuzzy image, if c is smaller than a, the overturn shaking image is a high-fuzzy image, and if the judgment result is a low-fuzzy image and a high-fuzzy image, the anti-shaking function of the automobile data recorder is faulty.
Optionally, as an optional embodiment of the present invention, the calculating a pixel variance value corresponding to the flipped dither image includes:
calculating a pixel variance value corresponding to the flipped dither image according to the following formula:
wherein G represents a pixel variance value corresponding to the flip dither image, M represents an image width corresponding to the flip dither image, N represents an image height corresponding to the flip dither image, H (x, y) represents a brightness value corresponding to a pixel point with a coordinate point (x, y) in the flip dither image,representing the pixel average of the flipped dither image.
S3, setting fault prompt information corresponding to the automobile data recorder according to the weight detection fault and the anti-shake function fault, and repairing the automobile data recorder according to the fault prompt information to obtain a repaired automobile data recorder.
According to the weight detection fault and the anti-shake function fault, the fault prompt information corresponding to the automobile data recorder is set so as to facilitate the follow-up repair treatment of the automobile data recorder in time, and the accuracy of follow-up accident monitoring is improved, wherein the fault prompt information is fault prompt repair information corresponding to the automobile data recorder, and optionally, the repair treatment of the automobile data recorder can be realized through manual repair.
As an embodiment of the present invention, the setting the fault indication information corresponding to the automobile data recorder according to the weight detection fault and the anti-shake function fault includes: analyzing the weight detection fault and the fault type corresponding to the anti-shake function fault respectively to obtain a first fault type and a second fault type, inquiring fault codes corresponding to the first fault type and the second fault type to obtain a first fault code and a second fault code, configuring repair information of the first fault code and the second fault code to obtain first repair information and second repair information, and generating fault prompt information corresponding to the automobile data recorder by combining the first fault code, the second fault code, the first repair information and the second repair information.
The first fault type and the second fault type are fault types corresponding to the weight detection fault and the anti-shake function fault, the first fault code and the second fault code are program codes corresponding to the first fault type and the second fault type, and the first repair information and the second repair information are repair operation flows corresponding to the first fault code and the second fault code, respectively.
Optionally, the analysis of the fault types corresponding to the weight detection fault and the anti-shake function fault may be implemented through a fault simulation method, the fault codes corresponding to the first fault type and the second fault type may be obtained by querying a production manual of the automobile data recorder, a first repair operation scheme and a second repair operation scheme may be obtained by querying a repair operation scheme of the first fault code and the second fault code in a preset fault code database, the first repair operation scheme and the second repair operation scheme are used as the first repair information and the second repair information, and the preset fault code database is a database containing names, descriptions, influences, possible reasons, solutions, repair steps and other contents of all fault codes.
S4, evaluating the sitting posture safety level corresponding to the vehicle driver of the starting vehicle by combining the big data platform, and adjusting the sitting posture of the vehicle driver according to the sitting posture safety level to obtain the safe sitting posture.
According to the invention, by evaluating the sitting posture safety level corresponding to the vehicle driver starting the vehicle, the sitting posture danger degree of the vehicle driver can be known, so that the subsequent sitting posture adjustment processing is facilitated, the sitting posture of the vehicle driver is adjusted to be a safe sitting posture, and the interference of the subsequent sitting posture on accident analysis is reduced, wherein the safe sitting posture is the corresponding safe posture of the vehicle driver during driving.
As one embodiment of the present invention, the evaluating, in conjunction with the big data platform, a sitting posture security level corresponding to a vehicle driver of the starting vehicle includes: calculating a frontalis distance value between a vehicle driver and a steering wheel in the starting vehicle, calculating a knee distance value between the vehicle driver and a knee baffle of a driving position in the starting vehicle, scheduling sign information corresponding to the vehicle driver, inquiring a standard frontalis distance value and a standard knee distance value corresponding to the vehicle recorder by using the big data platform according to the sign information, and evaluating a sitting posture safety level corresponding to the vehicle driver by combining the standard frontalis distance value, the standard knee distance value, the frontalis distance value and the knee distance value.
The frontal muscle distance value represents the distance between the frontal muscle position of the vehicle driver and the steering wheel, the knee distance value represents the distance between the knee of the vehicle driver and a knee baffle of a driving position in the starting vehicle, the sign information is information such as height and weight corresponding to the vehicle driver, and the standard frontal muscle distance value and the standard knee distance value are respectively corresponding to the sitting position of the vehicle driver being a safe sitting position.
Optionally, calculating a distance value between the frontal muscle position of the vehicle driver and the infrared sensor of the steering wheel, taking the distance value as the frontal muscle distance value, wherein the knee distance value is the same as the calculation principle of the frontal muscle distance value, and not described in detail herein, scheduling the sign information corresponding to the vehicle driver can be achieved through a priority scheduling algorithm, comparing the standard frontal muscle distance value with the frontal muscle distance value, if the frontal muscle distance value is smaller than 82% of the standard frontal muscle distance value, the sitting posture of the vehicle driver is unsafe, if the frontal muscle distance value is smaller than 62% of the standard frontal muscle distance value, the sitting posture of the vehicle driver is unsafe, dividing the knee distance value by the standard knee distance value, and obtaining a distance ratio, and if the distance ratio is smaller than 0.93, the sitting posture of the vehicle driver is unsafe.
According to the sitting posture safety level, the sitting posture of the vehicle driver is adjusted, so that the sitting posture safety of the vehicle driver is improved, the subsequent accident analysis is not interfered, and the sitting posture of the vehicle driver is optionally adjusted to adjust the angle of a driving seat back and the height of a seat.
S5, when the sitting posture of the vehicle driver is the safe sitting posture, accident monitoring is conducted on the starting vehicle, when the starting vehicle is in an accident, accident time is recorded by using the repair vehicle recorder, the material flow coefficient of the starting vehicle is detected, the corresponding accident level of the starting vehicle is analyzed according to the material flow coefficient, the accident time and the big data platform, and an alarm scheme of the starting vehicle is set according to the accident level and the accident video.
It should be understood that when the sitting posture of the vehicle driver is the safe sitting posture, no accident is indicated, the accident is monitored by the starting vehicle, accident analysis is not disturbed due to the safety of the sitting posture, the flow coefficient of the substance in the starting vehicle is detected according to the accident time, so that the flow degree of the substance in the starting vehicle can be known, and the analysis accuracy of the accident level is improved.
As one embodiment of the present invention, the analyzing the accident level corresponding to the starting vehicle according to the material flow coefficient, the accident time and the big data platform includes: and classifying the material flow coefficients according to the accident time to obtain a pre-accident flow coefficient and an accident flow coefficient, calculating an average flow coefficient corresponding to each material in the pre-accident flow coefficient, calculating a coefficient ratio of the average flow coefficient to the accident flow coefficient, inquiring a flow threshold value corresponding to an accident level from the big data platform, and analyzing the accident level corresponding to the starting vehicle according to the coefficient ratio and the flow threshold value.
The average flow coefficient is an average value of flow coefficients of corresponding substances in the flow coefficients before an accident, such as a water tank or a cooling liquid, and the flow threshold is a standard value for evaluating an accident level according to the flow coefficients, and specifically comprises the following steps: small accident flow threshold: 133%, middle event flow threshold: 152%, large accident flow threshold: 174%, extra large accident flow threshold: 193%.
Optionally, the classifying treatment of the material flow coefficient may be implemented by a decision tree function, calculating an average flow coefficient corresponding to each material in the pre-accident flow coefficient may be implemented by an average function, analyzing that the coefficient ratio belongs to a range in the flow threshold, and further analyzing an accident level corresponding to the starting vehicle, where if the coefficient ratio is greater than 133% and less than 152%, the accident level is indicated as a minor accident, and if the accident level is indicated as a minor accident.
According to the accident level and the accident video, the alarm scheme of starting the vehicle is set so as to help the vehicle driver to carry out pre-alarm processing, and related accident data is sent so as to improve the analysis accuracy of accident alarm, wherein the accident video is accident video data recorded by the automobile recorder, optionally, the accident feature in the accident video can be analyzed, the accident feature can be sent to a 119 alarm center, the accident level and the accident feature are combined, the alarm scheme of starting the vehicle is set, such as the occurrence of open fire feature of the vehicle, the accident feature can be sent to the 119 alarm center so as to facilitate the alarm center to arrange corresponding alarm equipment, and therefore the efficiency of alarm processing is improved.
According to the weight value of the vehicle, the weight detection fault corresponding to the vehicle recorder is judged, whether the vehicle recorder has the fault or not can be analyzed according to the weight detection fault so as to facilitate the subsequent repair treatment of the vehicle recorder, the pixel change rate of the shaking image can be known through calculating the image gradient value corresponding to the shaking image so as to facilitate the analysis of the subsequent shaking prevention function fault. Therefore, the accident alarm system based on the big data driving records provided by the embodiment of the invention can improve the analysis accuracy of accident alarm.
Fig. 2 is a functional block diagram of an accident alarm system based on big data driving records according to an embodiment of the present invention.
The accident alarm system 100 based on big data driving records can be installed in electronic equipment. In implementation, the system may be one or more service devices, may be installed on a cloud (e.g., a server of a live service operator, a server cluster, etc.), or may be developed as a website as an application. According to the implemented functions, the accident alarm system 100 based on the big data driving records comprises a weight detection fault analysis module 101, an anti-shake function fault analysis module 102, a fault repair module 103, a sitting posture adjustment module 104 and an alarm processing module 105.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the weight detection fault analysis module 101 is configured to obtain a starting vehicle of an accident to be analyzed, start a vehicle recorder of the starting vehicle, collect a vehicle weight value of the starting vehicle by using the vehicle recorder, and analyze a weight detection fault corresponding to the vehicle recorder according to the vehicle weight value and a preset big data platform;
The anti-shake function fault analysis module 102 is configured to perform shake processing on the vehicle recorder, capture a shake image of the vehicle recorder during the shake processing, calculate an image gradient value corresponding to the shake image, and analyze an anti-shake function fault corresponding to the vehicle recorder according to the image gradient value, the shake image and the big data platform;
the fault repairing module 103 is configured to detect a fault and the anti-shake function fault according to the weight, set fault prompt information corresponding to the automobile data recorder, and repair the automobile data recorder according to the fault prompt information to obtain a repaired automobile data recorder;
the sitting posture adjustment module 104 is configured to evaluate a sitting posture security level corresponding to a vehicle driver of the starting vehicle in combination with the big data platform, and adjust the sitting posture of the vehicle driver according to the sitting posture security level to obtain a safe sitting posture;
the alarm processing module 105 is configured to monitor an accident of the starting vehicle when the sitting posture of the driver of the vehicle is the safe sitting posture, record an accident video and an accident time by using the repair vehicle recorder when the starting vehicle has an accident, detect a material flow coefficient of the starting vehicle in real time, analyze an accident level corresponding to the starting vehicle according to the material flow coefficient, the accident time and the big data platform, and set an alarm scheme of the starting vehicle according to the accident level and the accident video.
In detail, each module in the accident alarm system 100 based on big data driving records in the embodiment of the present application adopts the same technical means as the accident alarm method based on big data driving records in fig. 1, and can generate the same technical effects, which is not repeated here.
In several embodiments provided by the present invention, it should be understood that the methods and systems provided may be implemented in other ways. For example, the above-described method embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is a theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and extend artificial intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Multiple units or systems as set forth in the system claims may also be implemented by means of one unit or system in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. An accident alarming method based on big data driving records is characterized by comprising the following steps:
acquiring a starting vehicle of an accident to be analyzed, starting a vehicle data recorder of the starting vehicle, acquiring a vehicle weight value of the starting vehicle by using the vehicle data recorder, and analyzing a weight detection fault corresponding to the vehicle data recorder according to the vehicle weight value and a preset big data platform;
performing jitter processing on the automobile data recorder, capturing a jitter image of the automobile data recorder in the jitter processing process, calculating an image gradient value corresponding to the jitter image, and analyzing an anti-jitter function fault corresponding to the automobile data recorder according to the image gradient value, the jitter image and the big data platform;
Setting fault prompt information corresponding to the automobile data recorder according to the weight detection fault and the anti-shake function fault, and repairing the automobile data recorder according to the fault prompt information to obtain a repaired automobile data recorder;
evaluating the sitting posture safety level corresponding to the vehicle driver of the started vehicle by combining the big data platform, and adjusting the sitting posture of the vehicle driver according to the sitting posture safety level to obtain a safe sitting posture;
when the sitting posture of the vehicle driver is the safe sitting posture, accident monitoring is carried out on the starting vehicle, when an accident occurs on the starting vehicle, accident video and accident time are recorded by using the repair vehicle recorder, the material flow coefficient of the starting vehicle is detected in real time, the accident level corresponding to the starting vehicle is analyzed according to the material flow coefficient, the accident time and the big data platform, and an alarm scheme of the starting vehicle is set according to the accident level and the accident video.
2. The accident alarming method based on big data driving records of claim 1, wherein the analyzing the weight detection fault corresponding to the driving recorder according to the vehicle weight value and a preset big data platform comprises:
Identifying a timestamp corresponding to the vehicle weight value;
according to the time stamp, sorting the vehicle weight values to obtain sorting weight values;
calculating the weight ratio between adjacent weight values in the sorting weight values;
inquiring a preset threshold value corresponding to the starting vehicle from the big data platform;
and analyzing the weight detection fault corresponding to the automobile data recorder according to the weight ratio and the preset threshold.
3. The accident alarming method based on big data driving records as set forth in claim 1, wherein the calculating the image gradient value corresponding to the jittered image includes:
performing image noise reduction processing on the jittered image to obtain a noise-reduced jittered image;
performing gray level conversion processing on the noise-reduced jittered image to obtain a gray level jittered image;
calculating a pixel gradient value corresponding to each pixel point in the gray scale dithering image;
and calculating an image gradient value corresponding to the jittering image according to the pixel gradient value.
4. The accident alarming method based on big data driving records as set forth in claim 3, wherein the calculating the pixel gradient value corresponding to each pixel point in the gray scale dithering image includes:
Calculating a pixel gradient value corresponding to each pixel point in the gray scale dithering image through the following formula:
；
wherein A represents a pixel gradient value corresponding to each pixel point in the gray scale dithering image, and B j Representing the gray value of the j-th pixel point in the gray dither image, B j+1 Represents the gray value, B (B) j -B j +1) represents a forward difference quotient of gray values of jth and jth+1th pixel points in the gray dither image, d (B) j） Representing the value of the jth pixel point in the standard face image after derivation, B (B) j -B j +1) represents a backward difference quotient of gray values of j-th and j+1th pixel points in the gray dither image.
5. The accident alarming method based on big data driving records of claim 1, wherein the analyzing the anti-shake function fault corresponding to the driving recorder according to the image gradient value, the shake image and the big data platform comprises:
according to the image gradient value, turning over pixel points in the jittering image to obtain a turned over jittering image;
calculating a pixel variance value corresponding to the overturning shaking image, and inquiring a fuzzy judgment section corresponding to the automobile data recorder from the big data platform;
According to the pixel variance value and the fuzzy judgment section, performing fuzzy judgment on the overturning shaking image to obtain a judgment result;
and analyzing the anti-shake function fault corresponding to the automobile data recorder according to the judging result.
6. The accident alarming method based on big data driving records as set forth in claim 5, wherein the calculating the pixel variance value corresponding to the flipped jittered image includes:
calculating a pixel variance value corresponding to the flipped dither image according to the following formula:
；
wherein G represents a pixel variance value corresponding to the flip dither image, M represents an image width corresponding to the flip dither image, N represents an image height corresponding to the flip dither image, H (x, y) represents a brightness value corresponding to a pixel point with a coordinate point (x, y) in the flip dither image,representing the pixel average of the flipped dither image.
7. The accident alarming method based on big data driving records of claim 1, wherein the setting the fault prompt information corresponding to the driving recorder according to the weight detection fault and the anti-shake function fault comprises:
respectively analyzing the fault types corresponding to the weight detection fault and the anti-shake function fault to obtain a first fault type and a second fault type;
Inquiring fault codes corresponding to the first fault type and the second fault type to obtain a first fault code and a second fault code;
configuring the repair information of the first fault code and the second fault code to obtain first repair information and second repair information;
and generating fault prompt information corresponding to the automobile data recorder by combining the first fault code, the second fault code, the first repair information and the second repair information.
8. The accident alarming method based on big data driving records according to claim 1, wherein the step of evaluating the sitting posture security level corresponding to the vehicle driver of the starting vehicle in combination with the big data platform comprises the steps of:
calculating a frontal muscle distance value between a vehicle driver and a steering wheel in the starting vehicle, and calculating a knee distance value between the vehicle driver and a driver seat knee barrier in the starting vehicle;
dispatching sign information corresponding to the vehicle driver;
according to the sign information, inquiring a standard frontal muscle distance value and a standard knee distance value corresponding to the automobile data recorder by utilizing the big data platform;
and evaluating the sitting posture safety level corresponding to the vehicle driver by combining the standard frontalis distance value, the standard knee distance value, the frontalis distance value and the knee distance value.
9. The accident alarming method based on big data driving records as set forth in claim 1, wherein the analyzing the accident level corresponding to the starting vehicle according to the material flow coefficient, the accident time and the big data platform includes:
classifying the material flow coefficient according to the accident time to obtain a flow coefficient before an accident and an accident flow coefficient;
calculating an average flow coefficient corresponding to each substance in the pre-accident flow coefficients;
calculating the coefficient ratio of the average flow coefficient to the accident flow coefficient;
inquiring a flow threshold corresponding to the accident level from the big data platform;
and analyzing the accident level corresponding to the starting vehicle according to the coefficient ratio and the flow threshold.
10. An accident alarm system based on big data driving records, which is characterized in that the system comprises:
the weight detection fault analysis module is used for acquiring a starting vehicle of an accident to be analyzed, starting a vehicle recorder of the starting vehicle, acquiring a vehicle weight value of the starting vehicle by using the vehicle recorder, and analyzing a weight detection fault corresponding to the vehicle recorder according to the vehicle weight value and a preset big data platform;
The anti-shake function fault analysis module is used for carrying out shake processing on the automobile data recorder, capturing shake images of the automobile data recorder in the shake processing process, calculating image gradient values corresponding to the shake images, and analyzing anti-shake function faults corresponding to the automobile data recorder according to the image gradient values, the shake images and the big data platform;
the fault repairing module is used for detecting faults and the anti-shake function faults according to the weight, setting fault prompt information corresponding to the automobile data recorder, and repairing the automobile data recorder according to the fault prompt information to obtain a repaired automobile data recorder;
the sitting posture adjustment module is used for evaluating the sitting posture safety level corresponding to the vehicle driver of the starting vehicle by combining the big data platform, and adjusting the sitting posture of the vehicle driver according to the sitting posture safety level to obtain a safe sitting posture;
the alarm processing module is used for carrying out accident monitoring on the starting vehicle when the sitting posture of the vehicle driver is the safe sitting posture, recording accident video and accident time by using the repair vehicle recorder when the starting vehicle is in an accident, detecting the material flow coefficient of the starting vehicle in real time, analyzing the accident level corresponding to the starting vehicle according to the material flow coefficient, the accident time and the big data platform, and setting an alarm scheme of the starting vehicle according to the accident level and the accident video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311760828.2A CN117437765B (en) | 2023-12-20 | 2023-12-20 | Accident alarm method and system based on big data driving records |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311760828.2A CN117437765B (en) | 2023-12-20 | 2023-12-20 | Accident alarm method and system based on big data driving records |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117437765A true CN117437765A (en) | 2024-01-23 |
| CN117437765B CN117437765B (en) | 2024-03-15 |
Family
ID=89552090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311760828.2A Active CN117437765B (en) | 2023-12-20 | 2023-12-20 | Accident alarm method and system based on big data driving records |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117437765B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3839221A1 (en) * | 1988-08-01 | 1990-02-08 | Morche Dirk W Dipl Ing | Travel data memory |
| US20140046546A1 (en) * | 2011-04-20 | 2014-02-13 | Peter Kollegger | Vehicle with a safety system involving prediction of driver tiredness |
| CN107067718A (en) * | 2016-12-29 | 2017-08-18 | 盯盯拍（深圳）技术股份有限公司 | Traffic accident responsibility appraisal procedure, traffic accident responsibility apparatus for evaluating and traffic accident responsibility assessment system |
| CN112885036A (en) * | 2021-01-26 | 2021-06-01 | 昆山小眼探索信息科技有限公司 | Method and device for assisting driver in safe driving |
| US20210362748A1 (en) * | 2019-03-08 | 2021-11-25 | Lg Electronics Inc. | System and method for providing customized recommendation service used for autonomous vehicle |
| CN115472001A (en) * | 2022-07-25 | 2022-12-13 | 深圳市城市交通规划设计研究中心股份有限公司 | Simulation evaluation method for human-vehicle traffic evacuation in stadium, electronic device and storage medium |
| CN116740840A (en) * | 2023-04-03 | 2023-09-12 | 深圳益国电子科技有限公司 | Video early warning system for automobile data recorder |
-
2023
- 2023-12-20 CN CN202311760828.2A patent/CN117437765B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3839221A1 (en) * | 1988-08-01 | 1990-02-08 | Morche Dirk W Dipl Ing | Travel data memory |
| US20140046546A1 (en) * | 2011-04-20 | 2014-02-13 | Peter Kollegger | Vehicle with a safety system involving prediction of driver tiredness |
| CN107067718A (en) * | 2016-12-29 | 2017-08-18 | 盯盯拍（深圳）技术股份有限公司 | Traffic accident responsibility appraisal procedure, traffic accident responsibility apparatus for evaluating and traffic accident responsibility assessment system |
| US20210362748A1 (en) * | 2019-03-08 | 2021-11-25 | Lg Electronics Inc. | System and method for providing customized recommendation service used for autonomous vehicle |
| CN112885036A (en) * | 2021-01-26 | 2021-06-01 | 昆山小眼探索信息科技有限公司 | Method and device for assisting driver in safe driving |
| CN115472001A (en) * | 2022-07-25 | 2022-12-13 | 深圳市城市交通规划设计研究中心股份有限公司 | Simulation evaluation method for human-vehicle traffic evacuation in stadium, electronic device and storage medium |
| CN116740840A (en) * | 2023-04-03 | 2023-09-12 | 深圳益国电子科技有限公司 | Video early warning system for automobile data recorder |
Non-Patent Citations (1)
| Title |
|---|
| 庞昌乐;: "汽车行驶记录仪在交通事故再现分析中的应用", 拖拉机与农用运输车, no. 01, 15 February 2008 (2008-02-15), pages 54 - 55 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117437765B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111325872B (en) | Driver driving abnormity detection method based on computer vision | |
| CN107967323B (en) | Method and system for analyzing abnormal traveling vehicles based on big data | |
| CN110866427A (en) | Vehicle behavior detection method and device | |
| CN111629181B (en) | Fire-fighting life passage monitoring system and method | |
| CN111661059B (en) | Method and system for monitoring distracted driving and electronic equipment | |
| CN112073480B (en) | Method and device for monitoring consumption of muck vehicle through neural network algorithm self-organizing mapping | |
| CN111275962A (en) | Vehicle track data aggregation effect prediction method and device | |
| Ki et al. | A traffic accident detection model using metadata registry | |
| CN111563468A (en) | Driver abnormal behavior detection method based on attention of neural network | |
| CN117437765B (en) | Accident alarm method and system based on big data driving records | |
| CN113055651A (en) | Artificial intelligence type vehicle security system and computer readable storage medium | |
| CN116913099A (en) | Intelligent traffic real-time monitoring system | |
| CN109344705B (en) | Pedestrian behavior detection method and system | |
| CN110909641A (en) | Method, device and system for detecting overload of motorcycle | |
| CN116030592A (en) | Abnormal event early warning system and method based on multi-point association analysis | |
| CN115376037A (en) | Station key area safety state monitoring method based on video | |
| CN113986893A (en) | Active early warning system and method based on generator car risk identification | |
| CN116091989A (en) | Violation auditing method, device and storage medium | |
| CN115017014B (en) | Highway electromechanical monitoring system and method | |
| CN111222587A (en) | Method and system for predicting dangerous driving behavior of people with loss of evidence based on feature fusion | |
| CN117012035A (en) | Fake-licensed car identification method, system and medium based on big data | |
| CN118043248A (en) | Driving risk analysis method and system for driver, electronic equipment and storage medium | |
| CN115376312A (en) | Road monitoring method and system based on radar and video fusion | |
| CN114330596A (en) | Equipment state feedback method and system based on neural network image classification algorithm | |
| CN116704402A (en) | Method for detecting vehicle rule-breaking event |
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 |