JP2018153570A - Sentiment estimation device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a sentiment estimation device for reflecting information on an outside of a vehicle and information of a drive scene which are recognized by a driver of the vehicle for improving estimation accuracy of a sentiment.SOLUTION: A sentiment estimation device 10 comprises: a model data storage part 26; an on-vehicle camera 12; an image feature amount calculation part 22; and a sentiment estimation part 27. The model data storage part 26 stores a sentiment estimation model or model data in which at least a feature amount vector of the image with information of a sentiment. The on-vehicle camera 12 acquires the picked up image. The image feature amount calculation part 22 calculates an image feature amount vector from the picked up image acquired by the on-vehicle camera 12. The sentiment estimation part 27 uses the sentiment estimation model or the model data stored in the model data storage part 26, for estimating information of the sentiment associated with the image feature amount vector calculated by the image feature amount calculation part 22.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a feeling estimation apparatus.

  2. Description of the Related Art Conventionally, a playback apparatus that estimates an occupant's image based on various information related to vehicle driving, occupant's biological information, and input items by the occupant, and selects a reproduction candidate according to the occupant's image from a plurality of content data. It is known (see, for example, Patent Document 1). In this playback device, various types of information related to driving the vehicle include, for example, date / time information, weather information, location information, occupant configuration, destination, boarding purpose, driving status, traffic status, content data playback frequency, and content data. Such as palatability.

JP 2007-108134 A

  By the way, according to the reproducing apparatus according to the above-described prior art, the occupant of the vehicle can only estimate the occupant's image based on the information related to the driving of the vehicle and the biological information detected by various sensors mounted on the vehicle. The estimation according to the information outside the vehicle to be perceived and the information of the driving scene cannot be performed. This causes a problem that it is difficult to improve the estimation accuracy of the occupant's image.

  The present invention has been made in view of the above circumstances, and it is possible to improve the estimation accuracy of the emotion by reflecting the information outside the vehicle and the information of the driving scene perceived by the driver of the vehicle in the emotion estimation. An object is to provide an estimation device.

In order to solve the above problems and achieve the object, the present invention employs the following aspects.
(1) A emotion estimation apparatus according to an aspect of the present invention includes a data storage unit (for example, the model data storage unit 26 in the embodiment) that stores data that associates a feature vector of an image and emotion information, and an image An image acquisition unit (for example, the vehicle exterior camera 12 in the embodiment) and an image feature amount calculation unit (for example, an image feature in the embodiment) that calculates a feature amount vector from the image acquired by the image acquisition unit. A quantity calculation unit 22) and a heart estimation unit (e.g., estimation of emotion information related to the feature quantity vector calculated by the image feature quantity calculation unit using the data stored in the data storage unit) The emotion estimation unit 27) in the embodiment.

(2) In the emotion estimation apparatus according to (1), the image acquisition unit may be mounted on a moving body and acquire an image ahead of the moving body in the traveling direction.

(3) In the emotion estimation apparatus according to the above (1) or (2), an input device (for example, the steering switch 11 in the embodiment) that detects an input operation related to information on the emotion of the operator, and the input device The emotion data generation unit (for example, the emotion data generation unit 21 in the embodiment) that generates the operator's emotion data according to the detected input operation, and the emotion data generated by the emotion data generation unit An estimation model that associates the feature quantity vector calculated by the image feature quantity calculation unit and stores data related to the estimation model in the data storage unit (for example, estimation in the embodiment) A model creation unit 25).

(4) The emotion estimation apparatus according to (3) includes a biological information acquisition unit (for example, the biological sensor 15 and the biological index calculation unit 24 in the embodiment) that acquires biological information of the operator, and the estimation The model creation unit may associate the biological information acquired by the biological information acquisition unit with each of the emotional data and the feature quantity vector in the estimated model.

  According to the emotion estimation apparatus according to the aspect described in (1) above, since the feature vector of the image is associated with the emotion of the person who visually recognizes the actual scene corresponding to the image, the biological information is used. In addition, the estimation accuracy of the emotion can be improved.

  Furthermore, in the case of (2), the estimation accuracy of the feeling can be improved by reflecting the external information perceived by the occupant of the moving body in the feeling estimation.

  Furthermore, in the case of (3) above, since the emotional data, which is the objective variable, is generated according to the input operation by the operator himself, the estimation model can be created with high accuracy.

  Furthermore, in the case of (4) above, the estimation accuracy can be improved by using biological information that is highly directly related to the emotional information.

It is a block diagram of the functional structure of the emotion estimation apparatus which concerns on embodiment of this invention. It is a perspective view which expands and shows the steering switch of the emotion estimation apparatus which concerns on embodiment of this invention. It is a figure which shows an example of the map data which shows the information of the emotion of the emotion estimation apparatus which concerns on embodiment of this invention. It is a flowchart which shows operation | movement of the emotion estimation apparatus which concerns on embodiment of this invention. It is a figure which shows the example of the time-dependent change of the actual value of the emotion value of the emotion estimation apparatus which concerns on embodiment of this invention, and an estimated value. It is a block diagram of a functional structure of the heart condition estimation apparatus which concerns on the modification of embodiment of this invention. It is a figure which shows typically the relationship between the explanatory variable and objective variable of the emotion estimation apparatus which concerns on the modification of embodiment of this invention.

  Hereinafter, a heart estimator according to an embodiment of the present invention will be described with reference to the accompanying drawings.

The emotion estimation apparatus 10 according to the present embodiment is mounted on a moving body such as the vehicle 1 and estimates the emotion of a passenger of the moving body. The occupant's feelings include, for example, emotions such as psychology, feelings, mood, comfort, and discomfort, and physical states such as sleepiness and non-sleepiness (wakefulness).
As shown in FIG. 1, the vehicle 1 includes, for example, a steering switch 11, a camera 12 outside the vehicle, a current position sensor 13, a vehicle sensor 14, a biosensor 15, an in-vehicle device 16, and a processing unit 17. I have.
The emotion estimation device 10 according to the embodiment includes, for example, a steering switch 11, a camera 12 outside the vehicle, a current position sensor 13, a vehicle sensor 14, a biosensor 15, and an in-vehicle device 16.

  The steering switch 11 is arranged on the steering wheel 18 as shown in FIG. The steering switch 11 is an input device that is disposed at a position that can be operated by a driver's finger that holds the steering wheel 18 in order to drive the vehicle 1. The steering switch 11 detects an operator's contact and operation. The steering switch 11 includes, for example, a cross key 19 as a mechanical switch that receives an operation with an operator's finger. The cross key 19 includes a first key 19a, a second key 19b, a third key 19c, and a fourth key 19d. The cross key 19 receives a tilting operation with the finger of the operator, and outputs an operation signal from each key 19a, ..., 19d in accordance with the tilting operation.

  In the steering switch 11, the first key 19 a and the second key 19 b of the cross key 19 accept an input operation related to information about the level of arousal level among the emotions of the operator, for example. The first key 19a outputs an operation signal indicating that the degree of wakefulness is high, and the second key 19b outputs an operation signal indicating that the degree of wakefulness is low. The third key 19c and the fourth key 19d of the cross key 19 accept, for example, an input operation relating to pleasant and uncomfortable information of the operator's feelings. The third key 19c outputs an operation signal indicating unpleasantness, and the fourth key 19d outputs an operation signal indicating comforting.

  The vehicle exterior camera 12 is a digital camera including a solid-state imaging device such as a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS). For example, the vehicle exterior camera 12 captures an image of a front area in the traveling direction of the vehicle 1 and outputs captured image data.

  The current position sensor 13 receives a positioning signal transmitted from an artificial satellite or the like in a navigation satellite system (for example, GNSS: Global Navigation Satellite System) including a positioning system such as GPS (Global Positioning System). Is used to detect the current position. The current position sensor 13 outputs a signal of a detected value of the current position.

  The vehicle sensor 14 is a variety of sensors mounted on the vehicle 1 and outputs detection value signals of various vehicle state quantities. The vehicle sensor 14 is, for example, a vehicle speed sensor, an engine rotation sensor, an acceleration sensor, a yaw rate sensor, an accelerator sensor, a throttle opening sensor, a brake pressure sensor, a steering sensor, or the like. The vehicle speed sensor detects the speed (vehicle speed) of the vehicle 1. The engine rotation sensor detects the engine speed. The acceleration sensor detects the acceleration of the vehicle 1, for example, longitudinal acceleration and lateral acceleration. The yaw rate sensor detects an angular velocity around the vertical axis of the vehicle 1. The accelerator sensor detects the amount of displacement (accelerator opening) of the accelerator pedal. The throttle opening sensor detects the opening of the throttle valve. The brake pressure sensor detects the hydraulic pressure (brake pressure) of the master cylinder, the brake caliper, or the wheel cylinder. The steering sensor detects the steering angle or steering torque of the steering wheel.

  The biosensor 15 is a sensor that detects each of, for example, an electroencephalogram (EEG), an electrocardiogram (ECG), a skin conductance level (SCL), a skin conductance response (SCR), and a skin electrical reflex (GSR). The biosensor 15 outputs detection values of various biometric data.

  The in-vehicle device 16 is various devices mounted on the vehicle 1. The in-vehicle device 16 is, for example, a driving force output device, a brake device, a steering device, a video and audio device, a navigation device, a display device, and a control device that controls various devices.

  The driving force output device outputs a driving force (torque) for driving the vehicle 1 to driving wheels. The driving force output device includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, and the like, and an ECU (Electronic Control Unit) that controls them. The ECU controls the driving force according to information input from the control device of the vehicle 1 or information input from the driving operator.

  The brake device includes, for example, a brake caliper or wheel cylinder, an electric motor that generates hydraulic pressure in the brake caliper or wheel cylinder, and a brake ECU. The brake ECU controls the electric motor in accordance with information input from the control device of the vehicle 1 or information input from the driving operator, and outputs brake torque corresponding to the braking operation to each wheel. The brake device includes, for example, a mechanism that transmits hydraulic pressure generated by operation of a brake pedal of a driving operator to a cylinder via a master cylinder in addition to hydraulic pressure generated by an electric motor. Note that the brake device is not limited to the configuration described above, and may control the actuator according to information input from the control device to transmit the hydraulic pressure of the master cylinder to the brake caliper or the wheel cylinder.

  The steering device includes, for example, a steering ECU and an electric motor. For example, the electric motor changes the direction of the steered wheels by applying a force to a rack and pinion mechanism. The steering ECU drives the electric motor and changes the direction of the steered wheels according to information input from the control device or information input from the driving operator.

  The processing unit 17 is a software function unit that functions when a predetermined program is executed by a processor such as a CPU (Central Processing Unit). The software function unit is an ECU including a processor such as a CPU, a ROM (Read Only Memory) that stores a program, a RAM (Random Access Memory) that temporarily stores data, and an electronic circuit such as a timer. Note that at least a part of the processing unit 17 may be an integrated circuit such as an LSI (Large Scale Integration).

  The processing unit 17 includes, for example, a feeling data generation unit 21, an image feature amount calculation unit 22, a vehicle information feature amount calculation unit 23, a biological index calculation unit 24, an estimated model creation unit 25, and a model data storage unit 26. And a feeling estimation unit 27 and a vehicle characteristic correction unit 28.

  The emotional data generation unit 21 generates operator's emotional data according to an operation signal output from the cross key 19 of the steering switch 11, and inputs the operator's emotional data as an objective variable to the estimated model generation unit 25. . The emotion data generation unit 21 uses the map data indicating the emotion information, such as the Russell's circular emotion map shown in FIG. 3, for example, to calculate the operator's emotion according to the operation signal output from the cross key 19. get. The map data indicating the emotion information is map data that associates the accumulation of operation signals output from the cross key 19 in time series with the emotion information. For example, in the circular emotion map of Russell shown in FIG. 3, the level of arousal associated with the first key 19a and the second key 19b and the pleasure associated with the third key 19c and the fourth key 19d are displayed. And uncomfortable information is set on two coordinate axes of a two-dimensional orthogonal coordinate system. In the two-dimensional Cartesian coordinate system of Russell's ring emotion map, a plurality of types of emotional regions are set that differ depending on the combination of the level of arousal level and information on pleasantness and discomfort. The emotional data generation unit 21 displaces the coordinate position in the two-dimensional orthogonal coordinate system of Russell's annular emotion map in accordance with the accumulation of operation signals output from the cross key 19, and is associated with the region including the coordinate position. Get emotional information. The emotional data generation unit 21 uses the emotional information acquired from the map data as the emotional data of the operator. Note that the operation signal output from the cross key 19 is, for example, an operator's intuitive recognition of the level of arousal level at the current time point or pleasant and uncomfortable information as compared to a past time point at an appropriate time interval. It shows a change.

  The image feature quantity calculation unit 22 calculates an image feature quantity vector from the captured image data output from the outside camera 12, and inputs the image feature quantity vector as an explanatory variable to the estimation model creation unit 25. The image feature quantity calculation unit 22 calculates an image feature quantity vector by machine learning such as a convolutional neural network (CNN). The image feature amount calculation unit 22 may reduce data and time necessary for learning by using, for example, an existing learned CNN model.

  The vehicle information feature amount calculation unit 23 calculates vehicle information feature amounts using signals of detected values of various vehicle state amounts output from the current position sensor 13 and the vehicle sensor 14, and uses the vehicle information feature amounts as explanatory variables. Input to the estimation model creation unit 25. The vehicle information feature amount calculation unit 23 uses, for example, the detection value itself output from the vehicle sensor 14 or secondary information obtained by a predetermined calculation using the detection value output from the vehicle sensor 14. Information feature amount. The vehicle information feature amount calculation unit 23 calculates the steering angular velocity using, for example, the detected value of the steering angle of the steering wheel output from the steering sensor of the vehicle sensor 14.

  The biometric index calculation unit 24 calculates a biometric index using detection value signals of various types of biometric data output from the biometric sensor 15, and inputs the biometric index as an explanatory variable to the estimation model creation unit 25. The biological index calculation unit 24 uses, for example, the detection value itself output from the biological sensor 15 or secondary information obtained by a predetermined calculation using the detection value output from the biological sensor 15 as a biological index. To do. The biometric index calculation unit 24 uses, for example, a detection value of an electroencephalogram (EEG) output from the biosensor 15 to calculate the amplitude of a specific frequency band (for example, α wave band, β wave band, and θ wave band). calculate. The biological index calculation unit 24 calculates an R wave interval (RRI) using, for example, an electrocardiogram (ECG) detection value output from the biological sensor 15.

The estimation model creation unit 25 creates a heart estimation model when execution of the estimation model generation mode is instructed. The estimation model creation unit 25 uses the emotional data of the operator output from the emotional data generation unit 21 as an objective variable. The estimated model creating unit 25 includes an image feature amount vector output from the image feature amount calculating unit 22, a vehicle information feature amount output from the vehicle information feature amount calculating unit 23, and a biometric index output from the biometric index calculating unit 24. Is an explanatory variable. The estimation model creation unit 25 creates a mind estimation model so that the emotional data of the operator as the objective variable is uniquely determined from at least one of the image feature quantity vector, the vehicle information feature quantity, and the biological index as the explanatory variables. To do.
The estimation model creation unit 25, for example, uses a sparse estimation method based on a Lasso (Least absolute shrinkage and selection operator) regularization method in a multiple regression model that receives an image feature vector and outputs an operator's emotional data. By using, the emotion estimation model is created.
For example, the estimation model creation unit 25 creates the emotion estimation model by using a stepwise method in a multiple regression model that receives the vehicle information feature amount and the biometric index and outputs the emotion data of the operator. .
For example, the estimation model creation unit 25 may set a plurality of groups based on similarity regarding information such as an operator's physiological reaction and driving characteristics, and create a heart estimation model for each of the plurality of groups.

  The model data storage unit 26 stores model data obtained by combining the emotion estimation model created by the estimation model creation unit 25 or an appropriate input value and the estimated emotion value estimated by the emotion estimation model with respect to the input value. Remember.

When the execution of the estimated model generation mode is not instructed, the emotion estimation unit 27 uses the emotion estimation model or model data stored in the model data storage unit 26 to generate an image feature vector, vehicle information feature, And emotional information related to at least one of the biological indices. The emotion estimation unit 27 acquires an estimated value of emotion related to at least one of the image feature vector, the vehicle information feature, and the biometric index by estimation using a emotion estimation model or search of model data.
When a plurality of emotion estimation models or model data are stored in the model data storage unit 26 for each group, the emotion estimation unit 27 receives an appropriate emotion estimation model or model data according to a selection instruction from the operator. You may choose.

  The vehicle characteristic correction unit 28 corrects the vehicle characteristic according to the estimated emotion value acquired by the emotion estimation unit 27. The vehicle characteristics are information characterizing the operating state of the in-vehicle device 16, for example.

  The emotion estimation apparatus 10 according to the present embodiment has the above-described configuration. Next, the operation of the emotion estimation apparatus 10 will be described with reference to FIG.

First, in step S01, the image feature amount calculation unit 22 acquires data of a captured image captured by the vehicle exterior camera 12.
Next, in step S02, the image feature amount calculation unit 22 calculates an image feature amount vector from the captured image data.
Next, in step S <b> 03, the vehicle information feature amount calculation unit 23 acquires the detected value of the current position detected by the current position sensor 13.
Next, in step S <b> 04, the vehicle information feature amount calculation unit 23 acquires detection values of various vehicle state amounts detected by the vehicle sensor 14.
Next, in step S05, the vehicle information feature amount calculation unit 23 calculates the vehicle information feature amount based on the detected values of the current position and various vehicle state amounts.

Next, in step S06, the estimated model creation unit 25 determines whether execution of the estimated model generation mode is instructed.
If the determination result is “NO”, the estimated model creation unit 25 advances the process to step S13.
On the other hand, if the determination result is “YES”, the estimated model creation unit 25 advances the process to step S07.
Next, in step S <b> 07, the biological index calculation unit 24 acquires detection values of various biological data detected by the biological sensor 15.
Next, in step S08, the biometric index calculation unit 24 calculates a biometric index based on detection values of various types of biometric data.
Next, in step S <b> 09, the emotional data generation unit 21 acquires an operation signal output from the cross key 19 of the steering switch 11.
Next, in step S10, the emotional data generation unit 21 generates the emotional data of the operator according to the operation signal.

Next, in step S <b> 11, the estimated model creation unit 25 uniquely determines the operator's emotional data as an objective variable depending on at least one of an image feature vector, a vehicle information feature, and a biological index that are explanatory variables. In this way, the emotion estimation model is created.
Next, in step S12, the model data storage unit 26, the emotion estimation model created by the estimation model creation unit 25, or an appropriate input value, and the estimated emotion value estimated by the emotion estimation model with respect to this input value. Model data in combination with. Then, the process proceeds to the end.

In step S <b> 13, the biological index calculation unit 24 determines whether detection values of various biological data detected by the biological sensor 15 have been acquired.
When the determination result is “NO”, the biological index calculation unit 24 advances the process to step S15.
On the other hand, if the determination result is “YES”, the biological index calculation unit 24 advances the process to step S14.
Next, in step S14, the biometric index calculation unit 24 calculates a biometric index from detection values of various types of biometric data.
Next, in step S15, the emotion estimation unit 27 acquires an estimated emotion value related to at least one of the image feature quantity vector, the vehicle information feature quantity, and the biometric index by estimation using the emotion estimation model or search of model data. To do.
Next, in step S <b> 16, the vehicle characteristic correction unit 28 corrects the vehicle characteristic according to the estimated emotion value acquired by the emotion estimation unit 27. Then, the process proceeds to the end.

Hereinafter, an embodiment will be described in which a feeling estimation model is created by using predetermined vehicle information feature values and biometric data obtained during actual driving of the vehicle 1 and a feeling estimation value (estimated value) is estimated. .
In this embodiment, predetermined vehicle information feature values and biometric data used as explanatory variables include RRI, GSR, vehicle speed, engine speed, accelerator opening, brake pressure, steering angle, steering angular velocity, lateral acceleration, front and rear Acceleration, yaw rate, EEG theta band amplitude, EEG alpha band amplitude, and EEG beta band amplitude. In the embodiment, the average value over 1 minute of each data acquired at a predetermined time interval (for example, 1 second) is set to 1 trial (trial) data, and the total number of trials is set to 126, thereby 126 minutes. The data of 126 trials (trials) were acquired. . In the embodiment, in each of arbitrary N-th trials (1 ≦ N ≦ 126) from the first trial to the 126th trial, the emotion is estimated by the emotion estimation model while using the Leave one out method (one extraction method). Estimates were estimated. FIG. 5 is a diagram in which 126 estimated emotion values and 126 actual measured values (actual measured values) corresponding to the input operation of the operator synchronized with the acquisition of each data are drawn according to the driving time. .
According to FIG. 5, it is recognized that the estimated emotion value and the actually measured emotion value are in good agreement, and the estimated accuracy of the estimated emotion value is high.

As described above, according to the emotion estimation apparatus 10 according to the present embodiment, the captured image in front of the traveling direction of the vehicle 1 is associated with the emotion of the occupant who visually recognizes the actual scene corresponding to the captured image. It is possible to improve the estimation accuracy of emotion without using biological information. By reflecting information outside the vehicle 1 and information on the driving scene perceived by the occupant of the vehicle 1 in the emotion estimation, the estimation accuracy of the emotion can be improved.
Furthermore, since the emotional data, which is the objective variable, is generated according to the input operation of the operator himself using the steering switch 11, the emotion estimation model can be created with high accuracy.
Furthermore, the estimation accuracy of the emotion estimation model can be improved by using various types of biological data that are highly directly related to the emotion information.

Hereinafter, modifications of the above-described embodiment will be described.
In the embodiment described above, when the creation of the emotion estimation model has been completed, the emotion data generation unit 21, the biological index calculation unit 24, and the estimation model creation unit 25 are omitted as in the modification shown in FIG. May be.
In this modification, the emotion estimation unit 27 may acquire an estimated value of emotion related to an image feature quantity vector or a vehicle information feature quantity by using the emotion estimation model or model data stored in the model data storage unit 26. .
According to this modification, even if the biometric index is omitted as shown in FIG. 7 as the creation of the emotion estimation model is completed, the emotion estimation related to the image feature quantity vector or the vehicle information feature quantity is performed. The value can be estimated with high accuracy.

  In the above-described embodiment or modification, the emotion estimation model or model data created by the estimation model creation unit 25 may be stored in a server device provided outside the vehicle 1. In this case, the emotion estimation device 10 may include a communication device that communicates with the server device, and may acquire the emotion estimation value using a emotion estimation model or model data acquired from the server device.

  In the above-described embodiment, the emotion estimation apparatus 10 may include another input device instead of the steering switch 11. Other input devices may be, for example, a switch, a touch panel, a keyboard, and a voice input device.

  The embodiments of the present invention are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalents thereof.

DESCRIPTION OF SYMBOLS 1 ... Vehicle (moving body), 10 ... Heart condition estimation apparatus, 11 ... Steering switch (input device), 12 ... Outside camera (image acquisition part), 13 ... Current position sensor, 14 ... Vehicle sensor, 15 ... Biosensor (biological body) (Information acquisition unit), 16 ... vehicle-mounted device, 17 ... processing unit, 19 ... cross key, 19a ... first key, 19b ... second key, 19c ... third key, 19d ... fourth key, 21 ... heart emotion data generation unit , 22 ... image feature value calculation unit, 23 ... vehicle information feature value calculation unit, 24 ... biometric index calculation unit (biological information acquisition unit), 25 ... estimated model creation unit, 26 ... model data storage unit (data storage unit), 27 ... emotion estimation unit, 28 ... vehicle characteristic correction unit

Claims (4)

A data storage unit for storing data associating the feature vector of the image and the emotion information;
An image acquisition unit for acquiring images;
An image feature amount calculation unit that calculates a feature amount vector from the image acquired by the image acquisition unit;
Using the data stored in the data storage unit, a emotion estimation unit that estimates emotion information related to the feature vector calculated by the image feature calculation unit;
Comprising
The emotion estimation apparatus characterized by the above. The image acquisition unit is mounted on a moving body and acquires an image ahead of the moving body in the traveling direction.
The emotion estimation apparatus according to claim 1. An input device for detecting an input operation related to information on the emotion of the operator;
A mind data generation unit that generates mind data of the operator in response to the input operation detected by the input device;
An estimation model that associates the emotional data generated by the emotional data generation unit with the feature amount vector calculated by the image feature amount calculation unit is created, and data relating to the estimation model is stored in the data storage unit An estimation model creation unit;
Comprising
The emotion estimation apparatus according to claim 1 or 2, characterized in that A biological information acquisition unit that acquires the operator's biological information;
The estimated model creation unit associates the biological information acquired by the biological information acquisition unit with each of the emotional data and the feature quantity vector in the estimated model.
The emotion estimation apparatus according to claim 3.

Images