KR20200016055A - Intelligent drowsiness driving prevention device - Google Patents

Abstract

The present invention relates to an intelligent drowsy driving prevention device, comprising: a main body installed in a vehicle, a speaker installed in the main body, a driving state of the vehicle, a health state of the driver, or an internal environment of the vehicle to detect The driver determining unit determining whether the user is a drowsy preliminary state in which drowsiness may occur, and a voice message including a predetermined question to prevent the driver's drowsy driving when the driver is determined to be a drowsy preliminary state through the driver determination unit. And a control module for providing the voice message to the speaker so that the voice signal is output through the speaker.
The intelligent drowsiness driving prevention device according to the present invention determines whether the driver is a drowsy preliminary state in which drowsiness may occur, and when the driver is a drowsy preliminary stage, artificially provides a question to the driver so that it is safer and effectively prevents drowsy driving. There is an advantage to this.

Description

Intelligent drowsiness driving prevention device

The present invention relates to an intelligent drowsiness driving prevention device, and more particularly, to an intelligent drowsiness driving prevention device capable of asking a driver a conversation in order to prevent the driver of a vehicle from drowsy driving.

In traffic accidents, drowsy driving accounts for 10-20% of all traffic accidents and 20-30% of highways. Generally, the driver takes a rest after stopping the car to prevent drowsy driving. However, if the driver was unable to rest in time, most of the time, he was drowsy and continued to drive the car. That is, when the driver drows instantly, there is a problem that drowsy driving leads to a traffic accident because the driver's vision is not secured. In addition, since the driver himself cannot determine the degree of fatigue, the intensity of the stimulus to be applied to the body according to the degree of fatigue could not be measured.

 Therefore, if the driver is drowsy while driving, the methods of avoiding drowsy driving by opening the car's window to take outside air or taking medicine to wake up could not be performed even if the driver does not recognize the drowsy driving state by himself. . As a result, the drowsy driving state was inevitably maintained, which causes a problem not only to the drowsy driver but also to the safety of other drivers and pedestrians.

Therefore, when the driver is detected as a drowsy state by detecting the driver's state, an intelligent drowsy driving prevention device has been developed that can prevent the driver's drowsy driving by forcibly stopping the vehicle or warning by vibration and noise. However, the conventional drowsy driving prevention device is provided with an extreme stimulus such as loud noise immediately to the driver, so that the driver may be surprised to drive the vehicle abnormally, and the warning is generated because the driver already provides drowsy driving. Accidents can also be caused by drowsy driving before.

Korean Patent Publication No. 10-2018-0081295: Drowsy driving warning system and warning method

The present invention has been made to improve the above problems, the driver determines whether the drowsy preliminary state that can cause drowsiness, if the driver is a drowsy preliminary stage, intelligently provide a question to prevent the driver's drowsy driving An object of the present invention is to provide an intelligent drowsy driving prevention device.

Intelligent drowsiness driving prevention device according to the present invention for achieving the above object is to detect the main body installed in the interior of the vehicle, the speaker installed in the main body, the driving state of the vehicle, the driver's health state or the internal environment of the vehicle A driver determination unit determining whether the driver is a drowsy preliminary state in which drowsiness may occur, and a predetermined question for preventing the driver's drowsy driving when the driver is determined to be drowsy preliminary state through the driver determination unit. And a control module for providing the voice message to the speaker so that the voice message is output through the speaker.

On the other hand, the intelligent drowsy driving prevention device according to the present invention recognizes the microphone installed in the main body and the voice received through the microphone to receive the driver's voice, the voice output from the speaker from the recognized voice Further comprising a response extracting unit for extracting the driver's answer to the message, the control module analyzes the driver's answer extracted from the answer extracting unit to determine whether the driver's drowsiness, the driver's drowsiness If it is determined to output a warning signal through the speaker.

After the voice message is output through the speaker, the control module may be a wrong answer to a question in which the driver's answer is not extracted or the driver's answer is included in the voice message for a preset reference time. In this case, the driver may be determined to be sleepy.

The driver determination unit is mounted on the driver of the vehicle and measures the heart rate of the driver and the heart rate of the driver based on the heart rate information of the driver provided by the heart rate measurement sensor, when the driver's heart rate is less than the predetermined heart rate, the driver It is provided with a state analysis unit for determining the drowsiness preliminary state.

The driver determining unit is installed on the main body to measure the carbon dioxide concentration in the vehicle and the carbon dioxide concentration in the vehicle based on the measurement information provided by the gas sensor when the concentration above the predetermined reference concentration, the driver said It may be provided with a state analysis unit for determining a sleepiness preliminary state.

The driver determining unit analyzes the driving pattern of the driver based on the vehicle connection module connected to the vehicle and collecting driving information of the vehicle, and the driving information of the vehicle provided by the vehicle connection module, and analyzing the analyzed driving pattern. The driver may further include a state analyzer that determines whether the driver is in the drowsy preliminary state.

The state analysis unit analyzes the driving pattern for the deceleration of the vehicle based on the driving information of the vehicle provided from the vehicle connection module, but operates for the deceleration of the vehicle for a predetermined analysis time from the time point at which the vehicle starts. A pattern is set as a reference pattern, and after the analysis time, the driver is determined to be drowsy preliminary state when the analyzed driving pattern for the acceleration / deceleration of the vehicle that exceeds the reference pattern exceeds a preset limit value. It is desirable to.

The control module sequentially provides a plurality of voice messages including questions having different difficulty levels at predetermined time intervals from a determination time at which the driver is determined to be drowsy preliminary state through the driver determination unit. After the time point, the voice messages are provided to the speaker so that the difficulty of the question increases as time passes.

On the other hand, the intelligent drowsiness driving prevention device according to the present invention is further provided with a display unit installed in the main body to emit light in various colors, the control module is based on the concentration of carbon dioxide in the vehicle based on the measurement information provided by the gas sensor Accordingly, the display unit is controlled to emit light of mutually different colors.

The intelligent drowsiness driving prevention device according to the present invention determines whether the driver is a drowsy preliminary state in which drowsiness may occur, and when the driver is in the preliminary stage of drowsiness, artificially provides a question so that it is safer and effectively prevents drowsy driving There is an advantage to this.

1 is a perspective view of an intelligent drowsy driving prevention device according to the present invention,
FIG. 2 is a block diagram of the intelligent drowsy driving prevention device of FIG. 1.

Hereinafter, an intelligent drowsy driving prevention device according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings. As the inventive concept allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to a specific disclosure form, it should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. In describing the drawings, similar reference numerals are used for similar elements. In the accompanying drawings, the dimensions of the structures are shown in an enlarged scale than actual for clarity of the invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "comprise" or "have" are intended to indicate that there is a feature, number, step, action, component, part, or combination thereof described on the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in the commonly used dictionaries should be construed as having meanings consistent with the meanings in the context of the related art, and shall not be construed in ideal or excessively formal meanings unless expressly defined in this application. Do not.

1 and 2 illustrate an intelligent drowsy driving prevention device 100 according to the present invention.

Referring to the drawings, the intelligent drowsiness driving prevention device 100 is the main body 110 is installed in the interior of the vehicle, the speaker 120 is installed in the main body 110, the driving state of the vehicle, the health of the driver A driver determination unit 130 that detects a state or an internal environment of the vehicle and determines whether the driver is a drowsy preliminary state in which drowsiness may occur, and is installed in the main body 110 to receive the driver's voice. Answer extraction unit 150 that recognizes the microphone 140, the voice input through the microphone 140, and extracts the driver's answer to the voice message output from the speaker 120 from the recognized voice And when the driver is determined to be drowsy preliminary state through the driver determination unit 130, a voice message including a predetermined question for preventing the drowsy driving of the driver is output through the speaker 120. The lock is provided with a control module 160 to provide voice messages to the speaker 120.

The main body 110 is formed in a cylindrical shape having a predetermined radius and is sized to be inserted into a cup holder of the vehicle. The upper end of the main body 110 is provided with a speaker 120 for receiving and outputting a voice message from the control module 160. The speaker 120 is conventionally applied to the output means for outputting sound information in general, a detailed description thereof will be omitted.

On the other hand, the main body 110 is provided with a display unit 111 on the outer peripheral surface. Although not shown in the drawing, the display 111 includes a plurality of LEDs that emit light in various colors. The display unit 111 operates under the control of the control module 160.

In addition, the main body 110 further includes a communication module 112 to enable data communication with the portable terminal 15 carried by the driver. The communication module 112 communicates with the mobile terminal 15 using any one of a Bluetooth-based beacon type, a LoRa (Long Range) type, and a Zigbee type. The portable terminal 15 is a terminal capable of call and data communication, and includes a communication unit performing call and data communication, a camera for photographing the outside of the portable terminal 15, and an angular velocity and acceleration of the portable terminal 15. In order to measure, a smart phone including an inertial sensor module embedded in the portable terminals 15 and 120 and a GPS receiver module for receiving a GPS signal from a satellite are applied. The communication module 112 transmits the measurement data detected by the driver determination unit 130 and the driver's answer information extracted by the answer extracting unit 150 to the mobile terminal 15, and the mobile terminal 15 transmits the communication module ( 112 transmits the measurement data and the response information provided through the management server (not shown). The management server stores the measurement data and answer information provided from the portable terminal 15, and utilizes the measurement data and answer information as analysis data.

The microphone 140 is installed on the lower outer circumferential surface of the main body 110 to receive the driver's voice. The microphone 140 is a microphone 140 is applied to collect the voice of the occupant, and when the uttered voice of the occupant is input, the microphone 140 converts it into an electrical voice signal and extracts the answer unit 150. To provide.

The driver determination unit 130 is mounted on the driver of the vehicle to measure the heart rate of the heart rate of the driver 131, and the gas sensor 132 installed in the main body 110 to measure the carbon dioxide concentration inside the vehicle And a vehicle connection module 133 connected to the vehicle to collect driving information of the vehicle, and a driver based on information provided from the heart rate measurement sensor 131, the gas sensor 132, and the vehicle connection module 133. It is provided with a state analysis unit 134 for determining whether or not the sleepiness preliminary state.

The heart rate measuring sensor 131 is a band type and is worn on a driver's body, such as a wrist, and is a wearable device capable of measuring the driver's heart rate. The heart rate measurement sensor 131 is a wearable device that is generally used to measure the heart rate of the wearer, and thus a detailed description thereof will be omitted. The heart rate measuring sensor 131 provides the measured heart rate information of the driver to the state analyzer 134.

The gas sensor 132 is fixed to the outer circumferential surface of the main body 110 to measure the carbon dioxide concentration inside the vehicle. The gas sensor 132 also provides the driver's measured heart rate information to the state analyzer 134.

The vehicle connection module 133 is connected to an on-board diagnostics (OBD) connector in the vehicle, and is transmitted from sensors disposed in each element constituting the vehicle such as an engine device, a brake device, a suspension device, and a transmission device through the OBD connector. Collect vehicle information. At this time, the vehicle connection module 133 calculates information on the deceleration speed of the vehicle based on the collected information, and provides the calculated information to the state analyzer 134 as driving information of the vehicle.

The state analyzer 134 is provided in the main body 110 and determines the driver's state based on the measurement information provided from the heart rate measurement sensor 131. That is, the state analyzer 134 determines the driver as the drowsy preliminary state when the heart rate of the driver is less than or equal to a preset heart rate based on the heart rate information of the driver provided by the heart rate measurement sensor 131. To the control module 160.

On the other hand, the state analysis unit 134 based on the information provided from the vehicle connection module 133, the heart rate of the driver through the heart rate information provided by the heart rate measurement sensor 131 for a predetermined unit time from the time when the operation of the vehicle starts The average may be calculated, and the calculated heart rate average may be set as the reference heart rate. Next, when the heart rate provided by the heart rate measurement sensor 131 is less than a value obtained by subtracting a preset error range value from the reference heart rate, the state analyzer 134 determines the driver as the drowsiness preliminary state after the unit time. You may.

In addition, the state analyzer 134 may determine the state of the driver through the information provided from the gas sensor 132. The state analyzer 134 determines the driver as the drowsy preliminary state when the carbon dioxide concentration in the vehicle is greater than or equal to a predetermined reference concentration based on the measurement information provided by the gas sensor 132. At this time, the reference concentration is preferably 2000ppm that can cause drowsiness to the driver.

In addition, the state analysis unit 134 analyzes the driving pattern of the driver based on the driving information of the vehicle provided by the vehicle connection module 133 and uses the analyzed driving pattern to determine whether the driver is the drowsy preliminary state. You can determine whether or not. That is, the state analysis unit 134 analyzes the driving pattern for the acceleration and deceleration of the vehicle based on the driving information of the vehicle provided by the vehicle connection module 133, and a preset analysis time from the time when the driving of the vehicle starts. While setting the driving pattern for the deceleration of the vehicle as a reference pattern, and after the analysis time, if the analyzed driving pattern for the deceleration of the vehicle differs from the reference pattern by a predetermined limit value, The driver is determined to be in the drowsy preliminary state.

At this time, the state analysis unit 134 measures the deceleration of the vehicle and the acceleration of the vehicle during braking during the analysis time from the time point at which the driving of the vehicle is started, based on the information provided from the vehicle connection module 133. An average of the accelerations is calculated, and the calculated average values of the decelerations and accelerations are set as reference patterns. Next, after the analysis time, if the difference between the deceleration of the vehicle during braking and the acceleration of the vehicle during acceleration exceeds a threshold value, the state analyzer 134 returns the driver to the drowsy preliminary state. You can also determine.

As described above, the driver determination unit 130 determines the driver's state based on the driving state of the vehicle, the driver's health state, or the internal environment of the vehicle, thereby determining the driver's state more accurately.

The answer extractor 150 is provided in the main body 110 to extract the driver's answer from the voice signal provided from the microphone 140. Although not illustrated in the drawing, the answer extractor 150 may answer the question included in the voice message in the voice recognition unit recognizing the voice signal received through the microphone 140 and the voice recognized through the voice recognition unit. Answer recognition unit for extracting.

The voice recognition unit may recognize a user's voice by applying a speech recognition algorithm or a speech recognition engine to the voice signal input from the microphone 140.

At this time, the speech signal may be converted into a more useful form for speech recognition. The speech recognition unit converts the input speech signal from an analog signal to a digital signal, and detects the start and end points of the speech and includes the same in the speech signal. Detected real voice interval. This is called end point detection (EPD).

In the detected section, features such as Cepstrum, Linear Predictive Coefficient (LPC), Mel Frequency Cepstral Coefficient (MFCC), or Filter Bank Energy A vector extraction technique may be applied to extract a feature vector of speech data (VD).

The recognition result can be obtained by comparing the extracted feature vector with the trained reference pattern. To this end, an acoustic model for modeling and comparing signal characteristics of speech and a language model for modeling linguistic order relations such as words or syllables corresponding to a recognized vocabulary may be used.

The acoustic model may be further divided into a direct comparison method for setting a recognition object as a feature vector model and comparing it with a feature vector of a speech signal and a statistical method for statistically processing the feature vector of the recognition object.

The direct comparison method is a method of setting a unit of a word, a phoneme, or the like to be recognized as a feature vector model and comparing how similar the input speech is. As a representative example, a vector quantization method is used. According to the vector quantization method, a feature vector of an input speech signal is mapped with a codebook, which is a reference model, and encoded as a representative value to compare the code values.

The statistical model method is a method of constructing a unit for a recognition object into a state sequence and using a relationship between state columns. The status column may consist of a plurality of nodes. Methods using the relationship between the state columns again include Dynamic Time Warping (DTW), Hidden Markov Model (HMM), and neural networks.

Dynamic time warping is a method of compensating for differences in the time axis when considering the dynamic characteristics of speech whose length varies over time even when the same person pronounces the same. Assuming a Markov process with probability and observed probability of nodes (output symbols) in each state, we estimate state transition probability and observed probability of the node from the training data, and calculate the probability that the input voice will occur in the estimated model. Is a recognition technology.

On the other hand, a language model that models linguistic ordinal relationships such as words or syllables may apply acoustic relations between units constituting language to units obtained in speech recognition, thereby reducing acoustic ambiguity and reducing recognition errors. The language model has a model based on a statistical language model and a finite state automata (FSA). The statistical language model uses a chain probability of words such as Unigram, Bigram, and Trigram.

Meanwhile, the speech recognition unit is not limited thereto and may be any recognition means for recognizing the speech signal provided through the microphone 140.

The answer recognition unit extracts an answer to a question included in the voice message from the voice recognized by the voice recognition unit and transmits the extracted answer information to the control module 160.

Here, the answer recognition unit is provided with a database (not shown) that stores the answers to the questions of the voice messages. At this time, the answer stored in the database includes the correct answer and the wrong answer to the question. The answer recognition unit detects an answer stored in the database among the voices recognized by the voice recognition unit, and transmits the detected answer information to the control module 160.

When the driver is determined to be drowsy preliminary state through the driver determining unit 130, the control module 160 outputs a voice message including a predetermined question to prevent the drowsy driving of the driver through the speaker 120. The voice message is provided to the speaker 120 as much as possible. In this case, the control module 160 includes a question providing unit 161 in which a plurality of voice messages are stored. In this case, the question provider 161 may store a plurality of voice messages, or may receive voice messages from the management server by communicating with the management server.

In this case, the question providing unit 161 stores a plurality of voice messages including questions having different difficulty levels. Here, the question included in the voice message includes arithmetic problems, current affairs problems, questions about the driver's personal information. The question provider 161 classifies each voice message according to the difficulty of the question included. For example, a voice message including a question about a simple arithmetic problem such as '1 + 1' is set to difficulty 1 and classified together with voice messages corresponding to difficulty 1. In addition, a voice message including a question about a relatively complex arithmetic problem such as "15x21" is set to a difficulty level higher than difficulty level 1, and classified together with voice messages corresponding to the difficulty level.

In this case, the control module 160 sequentially receives a plurality of voice messages including questions having different difficulty levels at predetermined time intervals from the determination point at which the driver is determined to be drowsy preliminary state through the driver determination unit 130. Provided to the speaker 120. In this case, the control module 160 may provide the voice messages to the speaker 120 so that the difficulty of the question increases as time passes after the determination point.

As described above, when the driver is in the preliminary stage of drowsiness, the control module 160 intelligently provides a question that the driver can answer instead of an extreme stimulus such as noise, so that the driver can safely and effectively prevent drowsy driving. have.

On the other hand, the control module 160 analyzes the driver's answer extracted from the answer extraction unit 150 to determine whether or not the drowsiness of the driver, and if the driver is determined to be drowsy state through the speaker 120 Output warning signal. Here, the control module 160 includes an answer check unit 162 for determining whether the driver's answer provided by the answer recognition unit is the correct answer. The answer confirmation unit 162 stores information on correct and incorrect answers to questions of voice messages stored in the question provider 161. When the driver's answer is provided from the answer recognition unit, the control module 160 determines whether the driver's answer is the correct answer by comparing the information with respect to the correct and incorrect answers stored in the question providing unit 161.

In this case, after the voice message is output through the speaker 120, the control module 160 may not extract the driver's answer from the answer extractor 150 or the voice of the driver's answer for the preset reference time. If the answer to the question contained in the message is incorrect, the driver is determined to be drowsy. On the other hand, the control module 160 outputs a warning signal through the speaker 120 only when the driver's answer is not extracted or the number of times that the driver's answer is incorrect is more than a preset reference number in consideration of a driver's answer mistake. It may be. In this case, 3 may be applied to the reference frequency.

On the other hand, the control module 160 controls the display unit 111 to emit light in different colors based on the concentration of carbon dioxide in the vehicle based on the measurement information provided from the gas sensor 132. Since the display unit 111 changes the emission color according to the carbon dioxide concentration in the vehicle, the driver can more easily grasp the environment inside the vehicle.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the invention. Thus, the present invention should not be limited to the embodiments set forth herein but should be construed in the broadest scope consistent with the principles and novel features set forth herein.

100: intelligent drowsiness driving prevention device
110: main body
111: display unit
112: communication module
120: speaker
130: driver determination unit
131; Heart rate sensor
132; Gas sensor
133: vehicle connection module
134: status analysis unit
140: microphone
150: Answer Extractor
160: control module
161: question provider
162: answer confirmation

Claims (9)

A body installed inside the vehicle;
A speaker installed in the main body;
A driver determination unit which senses whether the driver is a drowsy preliminary state in which drowsiness may occur by sensing the driving state of the vehicle, the health state of the driver or the internal environment of the vehicle;
A control module configured to provide the voice message to the speaker such that a voice message including a predetermined question for preventing the drowsy driving of the driver is output through the speaker when the driver is determined to be drowsy preliminary state through the driver determination unit; With,
Intelligent drowsiness driving prevention device.
The method of claim 1,
A microphone installed in the main body to receive the driver's voice; And
And a response extracting unit for recognizing a voice input through the microphone and extracting the driver's answer to the voice message output from the speaker from the recognized voice.
The control module analyzes the driver's answer extracted from the answer extracting unit to determine whether the driver is drowsy, and outputs a warning signal through the speaker when the driver is determined to be drowsy.
Intelligent drowsiness driving prevention device.
The method of claim 2,
After the voice message is output through the speaker, the control module may be a wrong answer to a question in which the driver's answer is not extracted or the driver's answer is included in the voice message for a preset reference time. If the driver is determined to be drowsy,
Intelligent drowsiness driving prevention device.
The method according to claim 1 or 2,
The driver determination unit
A heart rate measurement sensor mounted on a driver of the vehicle and measuring a heart rate of the driver; And
And a state analyzer for determining the driver as the drowsy preliminary state when the heart rate of the driver is less than or equal to a preset heart rate based on the heart rate information of the driver provided by the heart rate measuring sensor.
Intelligent drowsiness driving prevention device.
The method according to claim 1 or 2,
The driver determination unit
A gas sensor installed in the main body to measure a concentration of carbon dioxide in the vehicle; And
And a state analyzer for determining the driver as the drowsy preliminary state when the carbon dioxide concentration inside the vehicle is equal to or greater than a predetermined reference concentration based on the measurement information provided by the gas sensor.
Intelligent drowsiness driving prevention device.
The method according to claim 1 or 2,
The driver determination unit
A vehicle connection module connected to the vehicle to collect driving information of the vehicle; And
And a state analyzer to analyze the driving pattern of the driver based on the driving information of the vehicle provided by the vehicle connection module and determine whether the driver is the drowsy preliminary state by using the analyzed driving pattern.
Intelligent drowsiness driving prevention device.
The method of claim 6,
The state analysis unit
Analyze the driving pattern for the deceleration of the vehicle based on the driving information of the vehicle provided by the vehicle connection module, the reference pattern based on the driving pattern for the deceleration of the vehicle for a predetermined analysis time from the start of the operation of the vehicle Set to, and after the analysis time, if the driving pattern for the acceleration and deceleration of the analyzed vehicle is different from the reference pattern exceeds a predetermined threshold value, to determine the driver as the drowsiness preliminary state,
Intelligent drowsiness driving prevention device.
The method according to claim 1 or 2,
The control module sequentially provides a plurality of voice messages including questions having different difficulty levels at predetermined time intervals from a determination time at which the driver is determined to be drowsy preliminary state through the driver determination unit. After the time point, the voice messages are provided to the speaker so that the difficulty of the question increases as time passes.
Intelligent drowsiness driving prevention device.
The method of claim 5,
And a display unit installed at the main body to emit light in various colors.
The control module controls the display unit to emit light in different colors based on the concentration of carbon dioxide in the vehicle based on the measurement information provided by the gas sensor.
Intelligent drowsiness driving prevention device.

Images