CN113901979A - A driving trend prediction method and system - Google Patents
A driving trend prediction method and systemDownload PDFInfo
- Publication number
- CN113901979A CN113901979ACN202110973800.1ACN202110973800ACN113901979ACN 113901979 ACN113901979 ACN 113901979ACN 202110973800 ACN202110973800 ACN 202110973800ACN 113901979 ACN113901979 ACN 113901979A
- Authority
- CN
- China
- Prior art keywords
- driving
- driver
- driving behavior
- time
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Technical Field
The invention relates to the technical field of safe driving,
in particular, the invention relates to a driving tendency prediction method and system.
Background
With the development of social economy, vehicles are becoming more popular, and under the condition that the vehicle density is gradually increased, the frequency of car accidents is also becoming higher, especially under the circumstances of turning, crossroads or rainy days, improper operation is easy to occur, the probability of car accidents is higher than that under normal circumstances, the car accidents are scratched slightly to cause loss, and the car accidents are dangerous for drivers or pedestrians.
In addition to unexpected improper operation of the driver, subjective improper operation of the driver, that is, when the driver smokes, plays a mobile phone, drives fatigued or drives after drinking, is an increase in the rate of improper operation caused by the personal behavior of the driver, so that during the driving process of the driver, the cooperation between the assistant driving of the vehicle and the state of the driver is important in the safety of the vehicle operation, many vehicles have assistant driving at present, and the driver is involved in controlling the vehicle in time when the driver operates improperly, so as to prevent the occurrence of traffic accidents or reduce the traffic accident loss, for example, chinese patent invention CN112750324A discloses a driving assistance method, a driving assistance device, a vehicle and a server, wherein the driving assistance method comprises the following steps: transmitting state information of the vehicle and a driving assistance request to a server; and receiving the driving assistance information generated by the server responding to the driving assistance request and performing intersection lane matching calculation according to the state information of the vehicle and the intersection traffic environment information so as to complete the driving assistance operation. Therefore, the server responds to the driving assistance request, intersection lane matching calculation is carried out according to the state information of the vehicle and the intersection traffic environment information to generate driving assistance information, and the driving assistance information is directly sent to the vehicle by the server, so that the direct communication between the information acquisition unit and the vehicle-mounted unit in the prior art is avoided, the communication capacity requirements on the vehicle-mounted unit and the information acquisition unit in the prior art are reduced, the calculation capacity requirements on the vehicle-mounted unit are reduced, and the implementation cost of driving assistance is reduced.
However, the vehicle driving assistance method described above still has the following drawbacks: when a driver normally drives, auxiliary driving is carried out without intervention; when the driver is abnormally driven due to subjective behaviors of the driver, the auxiliary driving intervention judgment accuracy is not enough, namely, the accuracy of the judgment on the driving state of the driver is not enough, the auxiliary driving of the vehicle and the matching between the states of the driver cannot be completed, and the safety guarantee degree of the vehicle is low.
Therefore, in order to solve the above problems, it is necessary to design a reasonable driving tendency prediction method or system.
Disclosure of Invention
The invention aims to provide a driving tendency prediction method which is simple and reasonable, effectively obtains the driving habits of a driver from the normal driving data of the driver, assists in driving when the driving habits of the driver cannot be maintained so as to improve the safety, has high accuracy in judging the habits of the driver, effectively predicts the state and driving tendency of the driver and effectively reduces the risk of safety accidents by analyzing the relationship among the frame behavior characteristics of the driver.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
a driving tendency prediction method comprising the steps of:
s1: acquiring driving data of a driver in a first preset time before driving prediction;
s2: inputting the acquired driving data into the trained feature classification model to obtain a feature distribution rule of each driving behavior, and obtaining a plurality of driving behavior feature association rules of the driver as driving habit parameters;
s3: during driving prediction, acquiring real-time driving behavior data of a driver, and acquiring each driving behavior characteristic in real time;
s4: judging whether another driving behavior feature associated with the driving behavior feature appears within a second preset time after the one driving behavior feature, if so, returning to the step S3; otherwise, recording the current abnormal state and the current time;
s5: judging whether the occurrence frequency of the abnormal state in the third preset time is greater than a preset value, if so, entering an intelligent intervention state and sending a prompt alarm; otherwise, no operation is performed. .
Preferably, when step S2 is executed, the driving behavior characteristics are drawn and superimposed in a square-wave graph, the X-axis of the square-wave graph is time, and the law of the intersection of the square-wave graphs is analyzed to obtain the association law of the multiple behavior characteristics of the driver.
Preferably, in the present invention, the driving data is vehicle control data for normal driving by the driver himself/herself when step S1 is executed.
Preferably, when step S2 is executed, the output of the feature classification model is the driving behavior feature and the appearance time thereof.
As a preferable aspect of the present invention, the driving behavior characteristics include rapid acceleration, rapid deceleration, sharp turn, preceding vehicle distance, lane departure, and steering wheel angle when step S2 is executed.
Preferably, when step S4 is executed, if another driving behavior feature associated with the driving behavior feature occurs within a second predetermined time after the one driving behavior feature, the driving behavior feature is recorded as a normal habit state, and the process returns to step S3; otherwise, the habit is abnormal and the record is made.
Preferably, when step S5 is executed, if the number of occurrences of abnormal state is greater than a preset value or the frequency of occurrences of abnormal state is higher than another preset value within a third preset time, the intelligent intervention state is entered and a prompt alarm is sent.
Preferably, in step S5, in the intelligent intervention state, the vehicle-mounted terminal obtains the distance between the vehicle ahead and the vehicle ahead through the camera, the millimeter wave, the laser radar, the ultrasonic radar, and the G-sensor, and obtains the lane line to rotate the steering wheel and the collision detection to avoid.
It is another object of the present invention to provide a driving tendency prediction system, comprising:
the driving prediction device comprises a preliminary data acquisition module, a data processing module and a data processing module, wherein the preliminary data acquisition module is used for acquiring driving data of a driver in first preset time before driving prediction;
the characteristic classification model is used for inputting the driving data acquired by the characteristic classification model and outputting a characteristic distribution rule of each driving behavior;
the habit parameter obtaining module is used for analyzing each driving behavior feature distribution rule output by the feature classification model to obtain a plurality of driving behavior feature association rules of the driver;
the real-time data acquisition module is used for acquiring real-time driving behavior data of a driver and acquiring each driving behavior characteristic in real time during driving prediction;
the first judging module is used for judging whether another driving behavior characteristic related to the driving behavior characteristic appears in second preset time after the driving behavior characteristic obtained by the real-time data obtaining module;
the recording module is used for recording the current abnormal state and the current time when the first judging module judges that the current abnormal state and the current time are not recorded;
the second judgment module is used for judging whether the occurrence frequency of the abnormal state recorded by the recording module in third preset time is greater than a preset value;
an intervention module; and the intelligent intervention control module is used for starting the vehicle to enter an intelligent intervention state and sending a prompt alarm when the second judgment module judges that the vehicle is in the intelligent intervention state.
Preferably, the system further comprises: and the analysis auxiliary module is used for drawing and superposing a plurality of driving behavior characteristics in a square wave diagram when the habit parameter acquisition module works, wherein the X axis of the square wave diagram is time, and the rule of the intersection of a plurality of square waves is analyzed to obtain the association rule of the multi-behavior characteristics of the driver.
The driving trend prediction method and the system have the beneficial effects that: the method is simple and reasonable, the driving habits of the driver are effectively obtained from the normal driving data of the driver, the auxiliary driving is carried out when the driving habits of the driver cannot be kept so as to improve the safety, the relevance analysis among the posture behavior characteristics of the driver is realized, the judgment accuracy of the habits of the driver is high, the state and the driving trend of the driver are effectively predicted, and the safety accident risk is effectively reduced.
Drawings
FIG. 1 is a schematic flow chart of a driving tendency prediction method according to the present invention;
fig. 2 is a schematic flow chart of a driving tendency prediction system according to the present invention.
Detailed Description
The following are specific examples of the present invention and further describe the technical solutions of the present invention, but the present invention is not limited to these examples.
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the modules and structures set forth in these embodiments does not limit the scope of the invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and systems known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
The first embodiment is as follows: as shown in fig. 1, which is only one embodiment of the present invention, a driving tendency prediction method includes the steps of:
s1: acquiring driving data of a driver in a first preset time before driving prediction;
of course, when step S1 is executed, the driving data is vehicle control data in which the driver himself or herself normally drives.
The driver can select one or more sections of vehicle driving data during normal driving (no drinking, no fatigue driving and no driving bad study) as the reference data of the driver.
S2: inputting the acquired driving data into the trained feature classification model to obtain a feature distribution rule of each driving behavior, and obtaining a plurality of driving behavior feature association rules of the driver as driving habit parameters;
when step S2 is executed, the output of the feature classification model is the driving behavior feature and the occurrence time thereof.
Here, the driving behavior characteristics include sharp acceleration, sharp deceleration, sharp turn, preceding vehicle distance, lane departure, and steering wheel angle.
It should be noted that, when step S2 is executed, multiple driving behavior features are drawn and superimposed in one square wave diagram, where the X axis of the square wave diagram is time, and the rule at the intersection of multiple square waves is analyzed to obtain the association rule of multiple behavior features of the driver.
For example: in the square wave diagram, the characteristic value is 1 when the acceleration is rapid, the characteristic value is 0 when the acceleration is not rapid, and the line of the rapid acceleration square wave diagram is marked with red; during rapid deceleration, the characteristic value is 1, when rapid deceleration does not exist, the characteristic value is 0, and the rapid deceleration square wave icon is orange; when the automobile turns sharply, the characteristic value is 1, when the automobile does not turn sharply, the characteristic value is 0, and the sharp-turning square wave icon is blue; the characteristic value is 1 when the lane deviates, the characteristic value is 0 when the lane does not deviate, and the lane deviation square wave icon is black; the characteristic value is 1 when the steering wheel angle is larger than a certain value (such as 30 degrees), the characteristic value is 0 when the steering wheel angle does not reach the certain value (such as 30 degrees), and the square wave diagram of the steering wheel angle is green.
Because everyone has unique driving habits, for example, when the vehicle brakes suddenly, the gravity center of the body can be changed due to the force of the right foot, the steering wheel can be rotated, for example, the steering wheel deflects to the right by 8 degrees, and lane departure can be caused after the sudden braking lasts for 1 second; for example, when the driver turns, the steering wheel angle is larger than a certain value (for example, 30 °), the driver can habitually step on the brake, which are personal driving habits, and the personal habits of the driver are obtained through the association and the association frequency of two square-wave graph curves with different colors in time.
S3: during driving prediction, acquiring real-time driving behavior data of a driver, and acquiring each driving behavior characteristic in real time;
here, it is not necessary to find the rule of each driving behavior feature, but only to list each rule.
S4: judging whether another driving behavior feature associated with the driving behavior feature appears within a second preset time after the one driving behavior feature, if so, returning to the step S3; otherwise, recording the current abnormal state and the current time;
when step S4 is executed, if another driving behavior feature associated with the driving behavior feature occurs within a second predetermined time after the one driving behavior feature, the driving behavior feature is recorded as a normal habit state, and the step returns to step S3; otherwise, the habit is abnormal and the record is made.
Generally, when a driver is driving a car (without the possibility of driving another person), the driving habit is deviated, and if the driver is not drunk driving or tired driving, the driver must deal with something other than driving the car, such as smoking, making a call, and the like, and the driver can be interpreted as abnormal driving.
S5: judging whether the occurrence frequency of the abnormal state in the third preset time is greater than a preset value, if so, entering an intelligent intervention state and sending a prompt alarm; otherwise, no operation is performed. .
Then, when step S5 is executed, if the number of occurrences of abnormal state is greater than a preset value or the frequency of occurrences of abnormal state is higher than another preset value within a third preset time, the intelligent intervention state is entered and a prompt alarm is sent.
That is, within 5 minutes, if the abnormal driving state occurs many times, it can be determined that the driving safety of the driver is not guaranteed, and the third predetermined time is set to prevent accidental abnormal driving caused when the driver adjusts the navigation window or the like, but during this time, the accidental abnormal driving is intentionally eliminated, and then the driver is intervened and warned to normally drive.
In addition, when step S5 is executed, in the intelligent intervention state, the vehicle-mounted terminal acquires the distance of the leading vehicle through the camera, the millimeter wave, the laser radar, the ultrasonic radar and the G-sensor to brake, acquire the lane line to rotate the steering wheel and detect the collision to avoid.
It should be noted that if the method of the present invention is connected to a traffic police center via a network, the method can also shoot the image of the driver while the driver intervenes and send the image to the traffic police center, so as to give an alarm and facilitate the determination of responsibility after an accident.
As mentioned above, if it is necessary to exclude other people from driving the vehicle, the driving data of family and friends of the driver may be preset and stored (step S1), and when driving, the real-time driver image is obtained, and the driver is determined to be who, and the driving habit of the driver is called from the database, and the monitoring and driving prediction are performed.
The driving trend prediction method is simple and reasonable, effectively obtains the driving habits of the driver from the normal driving data of the driver, assists in driving when the driving habits of the driver cannot be maintained so as to improve the safety, enables the driving habits to be judged with high accuracy through correlation analysis among the frame behavior characteristics of the driver, effectively predicts the state and the driving trend of the driver, and effectively reduces the risk of safety accidents.
In a second embodiment, as shown in fig. 2, the present invention further provides a prediction system of a driving tendency prediction method in all the above embodiments, the system includes:
the driving prediction device comprises a preliminary data acquisition module, a data processing module and a data processing module, wherein the preliminary data acquisition module is used for acquiring driving data of a driver in first preset time before driving prediction;
the characteristic classification model is used for inputting the driving data acquired by the characteristic classification model and outputting a characteristic distribution rule of each driving behavior;
the habit parameter obtaining module is used for analyzing each driving behavior feature distribution rule output by the feature classification model to obtain a plurality of driving behavior feature association rules of the driver;
the real-time data acquisition module is used for acquiring real-time driving behavior data of a driver and acquiring each driving behavior characteristic in real time during driving prediction;
the first judging module is used for judging whether another driving behavior characteristic related to the driving behavior characteristic appears in second preset time after the driving behavior characteristic obtained by the real-time data obtaining module;
the recording module is used for recording the current abnormal state and the current time when the first judging module judges that the current abnormal state and the current time are not recorded;
the second judgment module is used for judging whether the occurrence frequency of the abnormal state recorded by the recording module in third preset time is greater than a preset value;
an intervention module; and the intelligent intervention control module is used for starting the vehicle to enter an intelligent intervention state and sending a prompt alarm when the second judgment module judges that the vehicle is in the intelligent intervention state.
Moreover, the system further comprises: and the analysis auxiliary module is used for drawing and superposing a plurality of driving behavior characteristics in a square wave diagram when the habit parameter acquisition module works, wherein the X axis of the square wave diagram is time, and the rule of the intersection of a plurality of square waves is analyzed to obtain the association rule of the multi-behavior characteristics of the driver.
The driving trend prediction method and the system are simple and reasonable, the driving habits of the driver are effectively obtained from the normal driving data of the driver, the auxiliary driving is carried out when the driving habits of the driver cannot be maintained so as to improve the safety, the relevance analysis among the frame behavior characteristics of the driver ensures that the habit judgment accuracy of the driver is high, the state and the driving trend of the driver are effectively predicted, and the safety accident risk is effectively reduced.
The present invention is not limited to the above-described specific embodiments, and various modifications and variations are possible. Any modifications, equivalents, improvements and the like made to the above embodiments in accordance with the technical spirit of the present invention should be included in the scope of the present invention.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973800.1ACN113901979A (en) | 2021-08-24 | 2021-08-24 | A driving trend prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973800.1ACN113901979A (en) | 2021-08-24 | 2021-08-24 | A driving trend prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113901979Atrue CN113901979A (en) | 2022-01-07 |
Family
ID=79188194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110973800.1APendingCN113901979A (en) | 2021-08-24 | 2021-08-24 | A driving trend prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113901979A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115499776A (en)* | 2022-09-14 | 2022-12-20 | 智能网联汽车(山东)协同创新研究院有限公司 | Internet of things automobile state remote control system |
| CN116091250A (en)* | 2023-02-09 | 2023-05-09 | 中国人民健康保险股份有限公司深圳分公司 | Insurance wind control management method and system |
| WO2023230740A1 (en)* | 2022-05-28 | 2023-12-07 | 华为技术有限公司 | Abnormal driving behavior identification method and device and vehicle |
| CN118115290A (en)* | 2024-01-24 | 2024-05-31 | 河南中平云能新能源科技有限公司 | Insurance method, medium and equipment based on new energy vehicle configuration parameters |
| CN118810798A (en)* | 2024-07-10 | 2024-10-22 | 湖北中交航胜科技有限公司 | Vehicle driving abnormal behavior safety intervention system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105679020A (en)* | 2016-01-29 | 2016-06-15 | 深圳市美好幸福生活安全系统有限公司 | Driving behavior analysis device and method |
| CN107697070A (en)* | 2017-09-05 | 2018-02-16 | 百度在线网络技术（北京）有限公司 | Driving behavior Forecasting Methodology and device, unmanned vehicle |
| CN108944799A (en)* | 2017-05-18 | 2018-12-07 | 腾讯科技（深圳）有限公司 | Vehicle drive abnormal behavior treating method and apparatus |
| CN109591824A (en)* | 2018-11-22 | 2019-04-09 | 上海为森车载传感技术有限公司 | A kind of safety assistant driving method |
| CN111191545A (en)* | 2019-12-20 | 2020-05-22 | 郑州嘉晨电器有限公司 | Real-time monitoring and analyzing system and method for driver behavior |
- 2021
- 2021-08-24CNCN202110973800.1Apatent/CN113901979A/enactivePending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105679020A (en)* | 2016-01-29 | 2016-06-15 | 深圳市美好幸福生活安全系统有限公司 | Driving behavior analysis device and method |
| CN108944799A (en)* | 2017-05-18 | 2018-12-07 | 腾讯科技（深圳）有限公司 | Vehicle drive abnormal behavior treating method and apparatus |
| CN107697070A (en)* | 2017-09-05 | 2018-02-16 | 百度在线网络技术（北京）有限公司 | Driving behavior Forecasting Methodology and device, unmanned vehicle |
| CN109591824A (en)* | 2018-11-22 | 2019-04-09 | 上海为森车载传感技术有限公司 | A kind of safety assistant driving method |
| CN111191545A (en)* | 2019-12-20 | 2020-05-22 | 郑州嘉晨电器有限公司 | Real-time monitoring and analyzing system and method for driver behavior |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023230740A1 (en)* | 2022-05-28 | 2023-12-07 | 华为技术有限公司 | Abnormal driving behavior identification method and device and vehicle |
| CN115499776A (en)* | 2022-09-14 | 2022-12-20 | 智能网联汽车(山东)协同创新研究院有限公司 | Internet of things automobile state remote control system |
| CN115499776B (en)* | 2022-09-14 | 2024-01-12 | 深圳市智安智能科技有限公司 | Internet of things automobile state remote control system |
| CN116091250A (en)* | 2023-02-09 | 2023-05-09 | 中国人民健康保险股份有限公司深圳分公司 | Insurance wind control management method and system |
| CN116091250B (en)* | 2023-02-09 | 2023-12-15 | 中国人民健康保险股份有限公司深圳分公司 | Insurance wind control management method and system |
| CN118115290A (en)* | 2024-01-24 | 2024-05-31 | 河南中平云能新能源科技有限公司 | Insurance method, medium and equipment based on new energy vehicle configuration parameters |
| CN118810798A (en)* | 2024-07-10 | 2024-10-22 | 湖北中交航胜科技有限公司 | Vehicle driving abnormal behavior safety intervention system and method |
| CN118810798B (en)* | 2024-07-10 | 2025-01-28 | 湖北中交航胜科技有限公司 | Vehicle driving abnormal behavior safety intervention system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113901979A (en) | A driving trend prediction method and system | |
| US10229461B2 (en) | Continuous identity monitoring for classifying driving data for driving performance analysis | |
| US10183679B2 (en) | Apparatus, system and method for personalized settings for driver assistance systems | |
| US10150478B2 (en) | System and method for providing a notification of an automated restart of vehicle movement | |
| US9840254B2 (en) | Method and system for adaptive detection and application of horn for an autonomous vehicle | |
| US10189482B2 (en) | Apparatus, system and method for personalized settings for driver assistance systems | |
| CN114132332B (en) | System and method for evaluating driver performance using crowdsourced data | |
| CN106128099B (en) | Driver's recognition methods and device | |
| CN112699721B (en) | Context-sensitive adjustments to off-road glance times | |
| JP7640224B2 (en) | Proximity-based vehicle tagging | |
| CN109740433B (en) | Vehicle avoiding method and vehicle-mounted terminal | |
| WO2018058266A1 (en) | Mobile terminal-based notification method and system | |
| WO2018058275A1 (en) | Smart driving method and system employing mobile terminal | |
| CN116572984A (en) | Dangerous driving management and control method and system based on multi-feature fusion | |
| US20240025432A1 (en) | Driver assistance system for vehicle | |
| CN116767237A (en) | Fraud detection for hands-on automated driving | |
| JP2025500379A (en) | An awareness checker for enhancing collaborative driving supervision. | |
| US20200312050A1 (en) | Control device, server, safety system, and control method of control device | |
| WO2018058267A1 (en) | Car adjustment method and system | |
| US20240119762A1 (en) | Information processing device, vehicle, information processing system, information processing method, and non-temporary storage medium | |
| CN113753058A (en) | Method and device for preventing drunk driving of automobile and automobile | |
| CN118323187A (en) | Multimodal driving state detection method, device, electronic device and storage medium | |
| WO2018058265A1 (en) | Car control method and system | |
| CN118046915A (en) | Traffic vehicle system and method providing feedback based on occupant behavior and emotion | |
| CN115240393A (en) | A collision warning method, device and vehicle based on driver's driving experience |
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 |