System and method supporting voice operation using fatigue measurements of nuclear power plant operators

Abstract

The present invention relates to a system supporting voice operation using fatigue measurements of nuclear power plant operators, and the system carries out the following: a stress index calculation step of calculating a stress index by comparing received biometric information with prestored biometric information of a normal state; a determination step of determining the operator's state as one of normal, observational, and dangerous on the basis of whether the calculated stress index exceeds a preset threshold value; a haptic function driving unit activation step of activating a chatbot operating unit and a haptic function driving unit if the determined state indicates that the observational state has been entered; and a success determination step of determining whether the stress index has been successfully reduced after the haptic function driving unit activation step. According to an embodiment, dynamic responses to fatigue of the operators can start at the observational state, thereby preventing entry into the dangerous state.

Description

Voice driving support system and method using fatigue measurement of nuclear power plant operators

[0001] The present invention relates to a voice driving support system and method using fatigue measurement of a nuclear power plant operator, and more particularly, to a voice driving support system and method using fatigue measurement of a nuclear power plant operator, which can prevent entry into a dangerous state by actively responding to fatigue of the operator from a state of careful observation.

[0002] Typically, the operators working in the nuclear power plant control room are experts with advanced knowledge and experience.

[0003] For the safe operation of nuclear power plants, not only the knowledge and experience of operators, but also their health and psychological stability are important factors to be managed.

[0004] Nuclear power plant operators work in three shifts in turn through multiple teams organized into groups. Due to the nature of shift work, operators who work night shifts in particular are highly likely to have irregular biological rhythms and have a higher stress index than nuclear power plant workers who do not work shifts.

[0005] To ensure the safe operation of nuclear power plants, drug and psychological tests are conducted annually to check the health and psychological state of operators. However, there is still a lack of measures to periodically monitor the psychological health of operators.

[0006] Accordingly, it is necessary to develop a technology that can measure the stress of main control room operators in real time and manage their stress so that they can relieve their workload or work stress based on the measured stress.

[0007] In addition, it is necessary to develop technology that can prevent entry into dangerous situations by actively responding to driver fatigue from the state of careful observation.

[0008]

[0009] The technical task of the present invention is to improve the conventional problems, and to provide a voice operation support system and method using fatigue measurement of nuclear power plant operators, which can prevent entry into a dangerous state by actively responding to operator fatigue from a state of careful observation.

[0010] In addition, the technical task to be achieved by the present invention is to provide a voice operation support system and method using fatigue measurement of nuclear power plant operators, which is capable of improving work productivity by preventing human errors of operators, in order to improve conventional problems.

[0011] In addition, the technical task to be achieved by the present invention is to improve the conventional problem, and to provide a voice driving support system and method using fatigue measurement of a nuclear power plant operator, in which when the fatigue of the operator enters a state of attention observation, the control unit automatically operates a voice chatbot function and stimulates the operator's concentration.

[0012] In addition, the technical task to be achieved by the present invention is to improve the conventional problem, and to provide a voice driving support system and method using fatigue measurement of nuclear power plant operators, which can improve the reduced concentration by activating a haptic function driving unit so that the operator automatically receives feedback on the performance of work and commands.

[0013]

[0014] The voice driving support system using fatigue measurement of nuclear power plant operator according to the characteristics of the present invention to solve these problems is as follows.

[0015] A business database that stores the procedure and instruction information necessary for drivers to understand the job they are currently performing;

[0016] A biosignal detection device having a heart rate measurement sensor, a skin electrical resistance measurement sensor, and a haptic function driving unit;

[0017] Including a server that communicates with the above biosignal detection device,

[0018] The above server,

[0019] A stress index calculation unit that calculates a stress index by comparing biometric information received from a biometric signal detection device with previously stored normal biometric information;

[0020] A judgment unit that derives the driver's status information as one of a normal state, a caution observation state, and a dangerous state depending on whether the stress index calculated above exceeds a preset threshold value;

[0021] Chatbot storage that stores past chatbot operation history, text preprocessing results, and response generation history;

[0022] A chatbot operation unit that checks the current task in progress by referring to the above-mentioned task DB and chatbot storage unit and informs the driver of the task to be performed in the future through voice;

[0023] If the derived state information is judged to be an entry into a state of attention observation, the chatbot operation unit and the haptic function driving unit are activated, and if the derived state information is a dangerous state, a control unit is included to generate alarm notification information.

[0024] The above chatbot storage unit is,

[0025] When an operation start command is received from the above control unit, a job status judgment module that inputs data from the job DB and chatbot storage unit for text preprocessing and past work history confirmation and judges the current job progress status;

[0026] A response generation module that generates an appropriate response in the form of a dialogue script for the job that the driver must perform in the future based on the results processed by the above job status judgment module, and accumulates and records the generated response in the chatbot storage;

[0027] It includes a TTS module that converts the text-type response generated by the above response generation module into voice and outputs it.

[0028] Preferably, the judgment unit may determine that the vehicle is in a normal state if the standard deviation is less than or equal to a preset first threshold based on the average of the driver's biometric information, and may determine that the vehicle is in a state of caution if the standard deviation exceeds the first threshold more than or equal to a preset number of times and is less than or equal to a preset second threshold, and may determine that the vehicle is in a dangerous state if the standard deviation exceeds the second threshold.

[0029] Preferably, the control unit can transmit the generated alarm notification information to either a display device or a speaker.

[0030] A voice driving support method using fatigue measurement of a nuclear power plant operator according to the characteristics of the present invention to solve these problems is as follows.

[0031] A data receiving step for receiving bio-information from a bio-signal detection device;

[0032] A stress index calculation step for calculating a stress index by comparing the received biometric information with previously stored normal biometric information;

[0033] A derivation step for deriving the driver's status information into one of a normal state, a caution observation state, and a dangerous state depending on whether the stress index calculated above exceeds a preset threshold value;

[0034] If the above derived state information is judged to be an entry into an attention observation state, a haptic function driving unit activation step for activating the chatbot operation unit and the haptic function driving unit;

[0035] A success determination step for determining whether the stress index reduction was successful after the above haptic function driving unit activation step;

[0036] If the above stress index reduction is not successful and the derived status information is in a dangerous state, a control step for generating alarm notification information is included.

[0037] If the above stress index reduction is successful, it is characterized in that the process is repeated from the data receiving step.

[0038]

[0039] According to one embodiment, a voice operation support system and method using fatigue measurement of nuclear power plant operators can be provided, which is expected to improve work productivity by stimulating the operator's concentration through voice chatbot function and haptic kick function technology from the state of attention observation, enabling active response before entering the test state, preventing careless human errors due to work proficiency, and utilizing it to familiarize new employees with the work.

[0040] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of a nuclear power plant operator can be provided, which can prevent entry into a dangerous state by actively responding to the operator's fatigue from a state of careful observation.

[0041] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of nuclear power plant operators can be provided, which can improve work productivity by preventing human errors of operators.

[0042] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of a nuclear power plant operator can be provided, in which, when the fatigue of the operator enters a state of attention observation, the control unit automatically operates a voice chatbot function to stimulate the operator's concentration.

[0043] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of a nuclear power plant operator can be provided, which can increase reduced concentration by activating a haptic function driving unit so that the operator can automatically receive feedback on his / her own work performance and commands.

[0044] Figure 1 is a configuration diagram of a voice driving support system that uses fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0045] Figure 2 is a detailed configuration diagram of the chatbot operation unit of Figure 1.

[0046] Figure 3 is a graph showing stress levels in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0047] Figure 4 is a graph showing the normal distribution of stress levels in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0048] FIG. 5 is an exemplary diagram comparing normal and dangerous states according to stress index distribution in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0049] Figure 6 is a graph showing the alarm generation stage in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0050] Figure 7 is a flowchart illustrating a voice driving support method using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0051] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present invention. The present invention may be implemented in various different forms and is not limited to the embodiments described herein.

[0052] Additionally, throughout the specification, whenever a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0053] Figure 1 is a configuration diagram of a voice driving support system that uses fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0054] Referring to FIG. 1, a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention,

[0055] A work DB (500) that stores procedure and instruction information necessary for the driver to understand the job he is currently performing;

[0056] A biosignal detection device (100) having a heart rate measurement sensor (110), a skin electrical resistance measurement sensor (130), and a haptic function driving unit (150);

[0057] Includes a server (300) that communicates with the above biosignal detection device (100),

[0058] The above server (300)

[0059] A stress index calculation unit (310) that calculates a stress index by comparing bio-information received from a bio-signal detection device with previously stored normal state bio-information;

[0060] A judgment unit (330) that derives the driver's status information as one of a normal state, a caution observation state, and a dangerous state depending on whether the stress index calculated above exceeds a preset threshold value;

[0061] A chatbot storage unit (390) that stores past chatbot operation history, text preprocessing results, and response generation history;

[0062] A chatbot operation unit (370) that checks the current task in progress by referring to the above-mentioned task DB (500) and chatbot storage unit (390) and informs the driver of the task to be performed in the future by voice;

[0063] If the derived status information is judged to be an entry into a state of attention observation, the chatbot operation unit (370) and the haptic function driving unit (150) are activated, and if the derived status information is a dangerous state, a control unit (350) is included to generate alarm notification information.

[0064] The haptic function driving unit (150) can set the type and number of vibrations so as to be able to distinguish between cases where it is performed appropriately according to the instructions of the chatbot operating unit (370) and cases where it is performed contrary to the instructions.

[0065] As an example of the invention implementation, if properly performed, it will only perform two times (0.1 seconds each) with weak vibration, and if performed differently from the instructions, it will perform one time (lasting for 3 seconds) with strong vibration.

[0066] In addition, the control unit (350) notifies the management department (or health department) personnel of the risk state by sending an alarm through the management department speaker (820) as an additional function. In addition, the management department (or health department) DB (830) stores and continuously manages stress measurement values ​​according to the command of the control unit (350) and utilizes them for health and psychological counseling of the relevant driver.

[0067] The above biosignal detection device (100) can be equipped on either a mouse or a wrist-worn smart band.

[0068] The stress index calculation unit (310) calculates a stress index by comparing the bio-information received from the bio-signal detection device (100) with the bio-information in a previously stored normal state. Here, the bio-signal may be heart rate data measured from a heart rate measurement sensor (110) and skin resistance data measured from a skin electrical resistance measurement sensor (130).

[0069] The judgment unit (330) derives the driver's status information as one of a normal state, a caution observation state, and a dangerous state depending on whether the calculated stress index exceeds a preset threshold value. Here, the judgment unit (330) determines the driver's status as a normal state if the standard deviation is less than or equal to a preset first threshold value based on the average of the driver's bio-information, and determines the driver's status as a caution observation state if the standard deviation exceeds the first threshold value a preset number of times or more and is less than or equal to a preset second threshold value, and determines the driver's status as a dangerous state if the standard deviation exceeds the second threshold value.

[0070] The control unit (350) generates alarm notification information if the derived status information indicates a dangerous state. Here, the control unit (350) can generate login authentication key information if the driver's status information is either a normal state or a caution observation state. In addition, the control unit (350) can transmit the generated alarm notification information to either the display device (400) or the speaker (700).

[0071] The chatbot storage unit (390) stores past chatbot operation history, text preprocessing results, and response generation history.

[0072] The chatbot operation unit (370) refers to the above-mentioned work DB (500) and chatbot storage unit (390) to check the current work in progress and inform the driver of the work to be done in the future through voice.

[0073] If the derived status information is determined to be an entry into a state of caution, the control unit (350) activates the chatbot operation unit and the haptic function driving unit (150), and if the derived status information is a dangerous state, it generates alarm notification information.

[0074] The display device (400) can receive alarm notification information from the control unit (350) and display an alarm notification message. At this time, the speaker (700) can generate sound and noise to notify nearby drivers of the alarm notification.

[0075] In addition, the control unit (350) can transmit the generated alarm notification information to a smart band dedicated to the nuclear power plant operator, and the smart band can receive the generated alarm notification information and perform either an alarm notification generation function or a vibration generation function. Here, the server (300) can further include a chatbot storage unit (390) that stores the operator's biometric information and status information by period, and the chatbot storage unit (390) can calculate and store an average of the operator's biometric information. In addition, the chatbot storage unit (390) can generate a graph based on the operator's biometric information by period and status information by period.

[0076] When drivers are working normally, their bio-signals can be measured using a driver-specific mouse or driver-specific smart band, which is comprised of a heart rate measurement sensor (110) and an electrical skin resistance measurement sensor (130). In this case, when logging into the internal system through a driver-use terminal, the user can be set to wear a bio-signal detection device (100) equipped on the driver-specific mouse or driver-specific smart band and have the bio-signals measured before final logging in.

[0077] Figure 2 is a detailed configuration diagram of the chatbot operation unit of Figure 1.

[0078] Referring to Figure 2, the chatbot operation unit (370)

[0079] When an operation start command is received from the above control unit (350), a job status judgment module (371) that inputs data from the job DB (500) and the chatbot storage unit (390) for text preprocessing and past work history confirmation and judges the current job progress status;

[0080] A response generation module (373) that generates an appropriate response in the form of a dialogue script for the job that the driver must perform in the future based on the result processed in the above job status judgment module (371) and accumulates and records the generated response in the chatbot storage unit (390);

[0081] It includes a TTS module (375) that converts the text-type response generated in the above response generation module (373) into voice and outputs it.

[0082] When a command to start operation is received from the control unit (350), the current task progress judgment module (371) receives and processes data from the task DB (500) and the chatbot storage unit (390) for text preprocessing and past task history confirmation.

[0083] The response generation module (373) generates an appropriate response in the form of a dialogue script for the driver's future tasks based on the processed results. The generated response is accumulated and recorded in the chatbot storage unit (390). The TTS module (375) converts the text-based response into voice and outputs it.

[0084] Figure 3 is a graph showing stress levels in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0085] Figure 4 is a graph showing the normal distribution of stress levels in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0086] Referring to FIG. 3 or FIG. 4, the server (300) receives a bio-signal from a driver-only mouse or smart band equipped with a bio-signal detection device (heart rate measurement sensor (110) and skin electrical resistance measurement sensor (130)), extracts the driver's bio-information (heart rate, skin tension), compares it with the driver's bio-information in a normal state, calculates a stress index, and visually provides the stress index through a display device (400).

[0087] If the driver's stress level exceeds a preset value, an alarm notification can be generated through the speaker (700) built into the display device (400) and the built-in speaker (700) of the driver's dedicated smart band.

[0088] The chatbot storage unit (390) can store the results of the data processing processor. The driver's status information for each scheduled period is stored in the storage device, and this can be used to calculate the average value for a specific point in time or period.

[0089] As shown in Fig. 3, the stress level according to one embodiment, for example, in the case of driver A among 10 drivers, the statistical distribution of the stress level of a typical driver will show the mean (μ) and standard deviation (σ), and if this is normalized, it can be represented as Fig. 4.

[0090] As shown in Fig. 4, among the preset values, +3σ can be set as UCL (Upper Control Limit), and -3σ can be set as LCL (Lower Control Limit). Here, the first threshold value can be +2σ, and the second threshold value can be +3σ.

[0091] FIG. 5 is an exemplary diagram comparing normal and dangerous states according to stress index distribution in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0092] Figure 6 is a graph showing the alarm generation stage in a voice driving support system using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0093] Referring to Figure 5 or Figure 6, the distribution of the driver's stress index can be divided into a normal state and a dangerous state. At this time, if the stress index is measured within +2σ around the mean, it corresponds to the first section and driver A can be indicated as being in a normal state. However, if the measured value exceeds +2σ three times in a row, it corresponds to the second section and can be indicated as a caution observation stage.

[0094] If the measured value exceeds the UCL, it means that the third section has been entered, and an alarm may be generated when the third section is entered.

[0095] The alarm notification can be generated through the display device (400) and the smart band worn by the operator. That is, when the nuclear power plant operator uses a mouse, the heart rate data can be measured from the heart rate measurement sensor (110) of the biosignal detection device (100) equipped in the mouse, and the skin resistance data can be measured from the skin electrical resistance measurement sensor (130), and the measured data can be transmitted to the server (300). The data transmitted to the server (300) can be compared with the previously stored normal state bioinformation to calculate a stress index, and the operator's status information can be derived from the calculated stress index.

[0096] When the derived driver status information is derived as a dangerous state, alarm notification information can be generated and transmitted to either a display device (400) or a speaker (700). At this time, the display device (400) may be a display device (400) connected to a server (300) by wire, or may be a display device (400) equipped in a smart band that performs wireless communication.

[0097] In addition, the speaker (700) can be built into the display device (400) and can be built into the smart band. The server (300) can further include a communication unit, and the communication unit can perform data communication with the smart band using a communication channel preset for performing wireless communication with the smart band. Here, the server (300) can be a computer, and can include a memory storing computer-readable commands and a processor implemented to execute the commands stored in the memory. The processor can perform the functions of a stress index calculation unit (310), a determination unit (330), and a control unit (350).

[0098] Figure 7 is a flowchart illustrating a voice driving support method using fatigue measurement of a nuclear power plant operator according to an embodiment of the present invention.

[0099] Referring to FIG. 7, the data receiving step (S100) receives bio-information from a bio-signal detection device (100).

[0100] The stress index calculation step (S300) calculates a stress index by comparing the received biometric information with previously stored normal biometric information.

[0101] The derivation step (S500) derives the driver's status information as one of normal status, caution observation status, and dangerous status depending on whether the calculated stress index exceeds a preset threshold value.

[0102] The haptic function driving unit activation step (S600) activates the chatbot operating unit and the haptic function driving unit when the derived state information is determined to be in an attention observation state. Here, in the attention observation state, the chatbot operating unit and the haptic function driving unit are operated so that the driver actively manages the stress index, and when the index value decreases and returns to a normal state, it becomes a successful case (Y). In addition, when it is determined to be in an attention observation state, the control unit (350) automatically activates the chatbot operating unit (370) and the haptic function driving unit (150), and when the chatbot operating unit (370) receives a command signal from the control unit (350), it confirms the task currently in progress and informs the driver of the task to be performed in the future through voice.

[0103] The success determination step (S610) determines whether the stress index reduction was successful after the haptic function driving unit activation step.

[0104] Meanwhile, if the stress index reduction is successful, it is characterized in that the process is repeated from the data receiving step.

[0105] In the control step (S700), if the stress index reduction is not successful and the derived status information is in a dangerous state, the control unit (350) generates alarm notification information. Here, if the index value increases and enters a dangerous state (N), an alarm notification is generated to take other measures. In addition, the control unit (350) stores the relevant information and the measures taken in the management department DB (830). That is, the management department (or health department) DB (830) stores and continuously manages the stress measurement value according to the command of the control unit (350) and utilizes it for health and psychological counseling of the driver.

[0106] According to one embodiment, it is expected that work productivity will be improved by activating the driver's concentration through the voice chatbot function and the haptic kick function technology from the attention observation state, enabling active response before entering the test state, preventing careless human errors due to work proficiency, and utilizing it to familiarize new employees with their work.

[0107] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of a nuclear power plant operator can be provided, which can prevent entry into a dangerous state by actively responding to the operator's fatigue from a state of careful observation.

[0108] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of nuclear power plant operators can be provided, which can improve work productivity by preventing human errors of operators.

[0109] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of a nuclear power plant operator can be provided, in which, when the fatigue of the operator enters a state of attention observation, the control unit automatically operates a voice chatbot function to stimulate the operator's concentration.

[0110] In addition, according to one embodiment, a voice driving support system and method using fatigue measurement of a nuclear power plant operator can be provided, which can increase reduced concentration by activating a haptic function driving unit so that the operator can automatically receive feedback on his / her own work performance and commands.

[0111] Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims also fall within the scope of the present invention.

Claims

1. A business DB that stores information on procedures and instructions necessary for drivers to understand the tasks they are currently performing; A biosignal detection device having a heart rate measurement sensor, a skin electrical resistance measurement sensor, and a haptic function driving unit; Including a server communicating with the above biosignal detection device, The above server, A stress index calculation unit that calculates a stress index by comparing bio-information received from a bio-signal detection device with previously stored normal bio-information; A judgment unit that derives the driver's status information as one of a normal state, a state of caution observation, and a state of danger depending on whether the stress index calculated above exceeds a preset threshold value; Chatbot storage that stores past chatbot operation history, text preprocessing results, and response generation history; A chatbot operation unit that checks the current task in progress by referring to the above-mentioned task DB and chatbot storage unit and informs the driver of the task to be performed in the future through voice; A voice driving support system using fatigue measurement of a nuclear power plant operator, comprising a control unit that activates the chatbot operation unit and the haptic function operation unit when the derived status information is determined to be in a state of caution, and generates alarm notification information when the derived status information is in a dangerous state.

2. In paragraph 1, The above chatbot storage unit is, When an operation start command is received from the above control unit, a job status judgment module that inputs data from the job DB and chatbot storage unit for text preprocessing and past work history confirmation and judges the progress status of the currently performed job; A response generation module that generates an appropriate response in the form of a dialogue script for the job that the driver must perform in the future based on the results processed by the above job status judgment module, and accumulates and records the generated response in the chatbot storage; A voice driving support system using fatigue measurement of nuclear power plant operators, including a TTS module that converts a text-based response generated from the above response generation module into voice and outputs it.

3. In paragraph 2, The above judgment unit determines that the operation is in a normal state if the standard deviation is lower than or equal to a preset first threshold based on the average of the operator's bio-information, determines that the operation is in a state of caution and observation if the standard deviation exceeds the first threshold value a preset number of times and is lower than or equal to a preset second threshold value, and determines that the operation is in a dangerous state if the standard deviation exceeds the second threshold value. This is a voice driving support system using fatigue measurement of an operator of a nuclear power plant.

4. In paragraph 3, The above control unit is a voice driving support system that uses fatigue measurement of nuclear power plant operators to transmit generated alarm notification information to either a display device or a speaker.

5. Data receiving step for receiving biometric information from a biometric signal detection device; A stress index calculation step for calculating a stress index by comparing the received biometric information with previously stored normal biometric information; A derivation step for deriving the driver's status information into one of a normal state, a state of caution observation, and a state of danger depending on whether the calculated stress index exceeds a preset threshold value; If the above derived state information is determined to be an entry into an attention observation state, a haptic function driving unit activation step for activating the chatbot operating unit and the haptic function driving unit; A success determination step for determining whether the stress index reduction is successful after the above haptic function driving unit activation step; A method for supporting voice driving using fatigue measurement of a nuclear power plant operator, including a control step of generating alarm notification information if the above stress index reduction is not successful and the above derived status information is in a dangerous state.

6. In paragraph 5, A method for supporting voice driving using fatigue measurement of a nuclear power plant operator, characterized in that the process is repeated from the data receiving step if the above stress index reduction is successful.

Images