Emotion Recognition-Based Service Providing Device for a Vehicle and Control Method Thereof

Abstract

The present invention provides an emotion recognition-based service providing apparatus for a vehicle and a control method thereof. A method for providing an emotion recognition-based vehicle service includes the following steps: monitoring an occupant and a driving situation; when an emotion of the occupant is recognized during the monitoring, comparing at least one of a first emotion and a first driving situation with at least one of a second emotion and a second driving situation, wherein the first emotion is a type of the currently generated emotion, the first driving situation is a driving situation corresponding to a first time which is a time point when the emotion is recognized, the second emotion is a type of the emotion recognized previously compared with the emotion, and the second driving situation is a driving situation corresponding to a second time which is a time point when the previously generated emotion is recognized; and based on a result of the comparison, performing a determination step: determining the currently generated emotion as one of an instantaneous emotion, a continuous emotion, and a repeated emotion.

Description

Technical Field

[0001] The present invention relates to a method for controlling vehicle functions based on the emotion recognition of a driver in a vehicle, and more particularly to a method for providing emotion recognition-based services for a vehicle, and a control method for a device that determines whether to provide a service according to the emotion pattern of the driver. Background Art

[0002] In recent years, active research has been conducted on technologies for determining the emotional state of a user in a vehicle. In addition, technologies for guiding the positive emotions of a user in a vehicle based on the determined emotional state of the user have also been actively studied.

[0003] However, traditional emotion recognition-based services only determine whether the emotional state of a user in a vehicle is positive or negative, and provide feedback for adjusting the output of components in the vehicle only based on whether the determined emotional state is negative or positive.

[0004] However, after an emotion appears during driving, the driver's emotion may quickly return to a neutral emotion, the emotion may continue to change, and a specific emotion may occur repeatedly and frequently. Therefore, in terms of service provision for a vehicle, if a service is provided when an emotion is detected even if the current emotion corresponds to a transient emotion, there is a problem that the driver's emotion has already returned to a neutral emotion when the service is provided, and thus the demand for the service is low. Summary of the Invention

[0005] An object of the present invention is to provide an emotion recognition-based service for a vehicle and a control method thereof, so as to determine whether to provide a service by further considering the emotion pattern and the emotion type.

[0006] In particular, the present invention provides an emotion recognition-based service for a vehicle and a control method thereof, so as to effectively determine the emotion that actually requires service provision according to the emotion pattern.

[0007] Other advantages, objects, and features of the present invention will be partially described below, and for those of ordinary skill in the art, other advantages, objects, and features of the present invention will become partially obvious after examining the following content, or other advantages, objects, and features of the present invention can be learned from the practice of the present invention. The objects and other advantages of the present invention can be achieved and obtained by the structures specifically pointed out in the written description, claims, and drawings.

[0008] To achieve these objects and other advantages, and in accordance with the purpose of the present invention, as embodied and broadly described herein, a method for providing a vehicle service based on emotion recognition is disclosed. The method includes the following steps: monitoring the occupant and driving conditions; when an emotion of the occupant is recognized during the monitoring, comparing at least one of the first emotion and the first driving condition with at least one of the second emotion and the second driving condition, wherein the first emotion is the type of the currently generated emotion, the first driving condition is the driving condition corresponding to the first time as the time point when the emotion is recognized, the second emotion is the type of the previously recognized emotion compared with the emotion, and the second driving condition is the driving condition corresponding to the second time as the time point when the previously generated emotion is recognized; and based on the result of the comparison, determining the currently generated emotion as one of an instantaneous emotion, a continuous emotion, and a repeated emotion.

[0009] In another aspect of the present invention, a device for providing a vehicle service based on emotion recognition is provided. The device includes: an emotion recognizer configured to determine the emotion of the occupant; a driving condition determiner configured to monitor the driving condition; and an emotion form determiner configured to: when the emotion recognizer recognizes the emotion of the occupant, compare at least one of the first emotion and the first driving condition with at least one of the second emotion and the second driving condition, and based on the result of the comparison, determine the currently generated emotion as one of an instantaneous emotion, a continuous emotion, and a repeated emotion, wherein the first emotion is the type of the currently generated emotion, the first driving condition is the driving condition corresponding to the first time as the time point when the emotion is recognized, the second emotion is the type of the previously recognized emotion compared with the emotion, and the second driving condition is the driving condition corresponding to the second time as the time point when the previously generated emotion is recognized. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings for a further understanding of the present invention are incorporated in and form a part of this application. Embodiments of the present invention are shown in the drawings and, together with the detailed description, are used to explain the principles of the present invention. In the drawings:

[0011] Figure 1 is a diagram showing an example of a device for providing a vehicle service based on emotion recognition according to an embodiment of the present invention;

[0012] Figure 2 is a flowchart showing an example of a program for providing a service based on emotion recognition according to an embodiment of the present invention;

[0013] Figure 3 is a diagram for explaining criteria for determining an emotion form according to an embodiment of the present invention;

[0014] Figure 4A diagram showing an example of determining an emotional form according to an embodiment of the present invention;

[0015] Figures 5A to 5C An experimental example showing the determination of an emotional form according to an embodiment of the present invention;

[0016] Figure 6 A diagram for explaining criteria for determining an emotional form according to another embodiment of the present invention; and

[0017] Figure 7 A flowchart showing an example of a program for providing a service based on emotion recognition according to another embodiment of the present invention. Detailed Description of Specific Embodiments

[0018] Exemplary embodiments of the present invention are described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention can be implemented in various different forms and is not limited to these embodiments. To clearly describe the present invention, parts irrelevant to the description are omitted from the drawings, and the same reference numerals denote the same elements throughout the specification.

[0019] In addition, unless there is a contrary disclosure, when a component "includes" a certain component, it means that the component may also include other components without necessarily excluding other components. The same reference numerals are used to denote the same components throughout the drawings and the specification.

[0020] In order to provide a service more effectively in response to the emotions of vehicle occupants (e.g., drivers) at more important times, embodiments of the present invention can provide a service when identifying emotions in a specific way by further considering the emotional form as well as the emotional type.

[0021] Emotional forms applicable to embodiments of the present invention may include instantaneous emotions, continuous emotions, and recurrent emotions.

[0022] Continuous emotions refer to a situation where multiple emotions appear simultaneously or continuously during the duration of a driving situation event. Examples of continuously appearing various emotions may include: a situation where a driver expresses emotions such as laughing, sadness, and regret simultaneously or continuously while talking. In this case, the actual driver emotions can be analyzed as emotional changes per unit time and treated as one emotion occurring during the event, rather than processing the emotions multiple times. Additionally, in the case of providing a related service by immediately identifying continuous emotions after the emotions occur, the service is provided in the middle of the emotional change, which may cause discomfort to the user. Therefore, for continuous emotions, it is necessary to provide the emotional analysis result at the end of the emotion and execute the related service.

[0023] Repeated emotions refer to the situation where the same emotion reappears within a relatively short time interval. Examples of repeated emotions can include: after a driver feels bored or sleepy due to continuous cruising (driving at a constant speed), the driver repeatedly feels bored or sleepy regardless of the driving situation; and after a driver is surprised because the vehicle in front suddenly stops while driving, the driver becomes sensitive to the movement of other vehicles regardless of the driving situation. From the research in the field of artificial emotion modeling, the following phenomena can be observed: emotions that have occurred once are repeatedly expressed even after the cause of the emotion no longer exists, and in driving situations, the psychological phenomenon of existing research results can be seen: the memory of past stimuli is the source of stimulating new emotions.

[0024] In addition, transient emotions refer to individual emotions that do not correspond to repeated emotions or the emotions that constitute continuous emotions.

[0025] Hereinafter, a service providing device based on emotion recognition according to an embodiment of the present invention and its control method will be described. In the following description, the target of emotion recognition is assumed to be the driver among vehicle occupants, but this is for the convenience of description. In fact, it goes without saying that for those of ordinary skill in the art, it is obvious that, without exceeding the scope not conflicting with the following description, regardless of the role of driving the vehicle, emotion-based services are provided to any occupant who is the target of emotion recognition.

[0026] Figure 1 FIG. is an example of a device for providing a vehicle service based on emotion recognition according to an embodiment of the present invention.

[0027] Referring to Figure 1 , a device for providing a vehicle service based on emotion recognition may include: an emotion recognizer 110 for recognizing the driver's emotion; a service provision determiner 120 for determining an emotion form based on the driver's emotion recognized by the emotion recognizer 110, the driving situation, and the previous determination history, and determining whether to provide a service according to the emotion form; and an output unit 130 for providing a service in the vehicle according to the determination of the service provision determiner 120.

[0028] First, the emotion recognizer 110 may include: an information acquirer 111, a pre-processor 112, a feature extractor 113, an emotion classifier 114, and a basic emotion determiner 115.

[0029] The information acquirer 111 may include a camera for acquiring an image including at least the driver's face. According to the emotion recognition method, the information acquirer 111 may further include: a microphone for receiving the driver's voice or a biosensor (e.g., a heart rate sensor) and a camera.

[0030] The preprocessor 112 can perform correction and noise removal on the information obtained by the information acquirer 111. For example, the preprocessor 112 can perform image quality correction and noise removal on the raw data of the image obtained by the camera through preprocessing.

[0031] The feature extractor 113 can extract features of feature points as a basis for determining emotions, movements, etc. from the preprocessed image.

[0032] Technologies for emotion feature extraction can broadly include three methods. One method is the holistic method of extracting features by modeling or expressing the intensity of pixel values in the image of the entire face. Another method is the geometric method of extracting features by searching for the geometric arrangement and position of features in the face. Additionally, an active appearance model (AAM) formed by combining the holistic method and the geometric method can also be applied. One or more of these feature extraction methods can be implemented by the feature extractor 113.

[0033] However, these feature extraction methods are merely exemplary, and the present invention is not limited thereto. Therefore, the feature extraction method can be any method as long as it is a method for extracting features for determining emotions.

[0034] The emotion classifier 114 can classify the expression in a given image into an emotional state based on the classification of the pattern of the extracted features.

[0035] The emotion classifier 114 can use the following various methods to classify emotions, including: Bayesian network using predefined conditional probabilities, K-nearest neighbor algorithm, artificial neural network, etc.

[0036] The basic emotion determiner 115 can finally determine the classified emotional state as a basic emotion of a preset type. Here, the basic emotions can include six emotions classified based on facial expressions proposed by P. Ekman: pain, anger, happiness, disgust, sadness, and surprise. However, this is also merely exemplary, and the types and quantities of basic emotions can be set in different ways. For example, the basic emotions according to this embodiment not only include the six basic emotions of P. Ekman, but can also include drowsiness, contempt, boredom, etc.

[0037] The service provision determiner 120 can include a driving condition determiner 121, an emotion form determiner 122, and a memory 123.

[0038] The driving condition determiner 121 can determine the driving condition based on road or traffic conditions. For example, driving in a congested section, cruising, sudden stops, or driving on a curved section, as well as the driver's vehicle operation. The driving condition determiner 121 can also determine the driver's situation that is not related to traffic conditions or vehicle operation (e.g., making a call or talking to a passenger). To this end, the driving condition determiner 121 can obtain the information required to determine the driving condition from various vehicle sensors (speed sensor or acceleration sensor), a navigation system for providing road information and traffic volume information, a head unit, etc.

[0039] When the emotion recognizer 110 recognizes a basic emotion, the emotion form determiner 122 can consider at least one of the driving condition at the corresponding time point, the previous emotion, the time point when the previous emotion was recognized, or the driving condition when the previous emotion was recognized, to determine whether the currently recognized emotion corresponds to an instantaneous emotion, a continuous emotion, or a recurring emotion. The emotion form determiner 122 can determine whether to provide a service corresponding to the emotion or representative emotion included in the recognized emotion form based on the emotion form.

[0040] Whenever the emotion recognizer 110 recognizes an emotion, the memory 123 can store the type and form of the recognized emotion, as well as the driving condition when the emotion was recognized.

[0041] When it is determined by the service provision determiner 120 to provide a service corresponding to the recognized emotion, the output unit 130 can provide the corresponding form of service through a display 131 for providing the service through visual output, a speaker 132 for providing the service through auditory output, a vibration output unit 133 for providing the service through vibration output, etc.

[0042] For example, when providing a service corresponding to boredom, the output unit 130 can output music with a fast tempo through the speaker 132. In another example, when providing a service corresponding to surprise, the output unit 130 can provide an image for guiding deep breathing through the display 131. Needless to say, the form of providing the service is merely exemplary, and any service can be provided as long as the service corresponds to the recognized emotion of the driver.

[0043] Hereinafter, the process of providing a service according to an embodiment will be described based on the above configuration of the device.

[0044] Figure 2 is a flowchart showing an example of a program for providing an emotion recognition-based service according to an embodiment of the present invention.

[0045] Refer to Figure 2First, the driver and driving condition can be monitored (S210). For example, an image containing the driver's face can be captured, the driver's emotion is determined based on the image captured by the emotion recognizer 110, and the driving condition determiner 121 can monitor the driving condition.

[0046] When the emotion recognizer 110 determines that an emotion occurs while monitoring the driving condition (Yes in S220 ), the emotion form determiner 122 may search the memory 123 and determine whether the current emotion occurs within a preset time T after the previous emotion occurs ( S230 ).

[0047] When the previous emotion occurs after the preset time T ("No" in S230), the emotion form determiner 122 can determine the form of the current emotion as an instantaneous emotion (S260), and can store information on the time and type (i.e., the type of basic emotion) of the occurrence of the current emotion and the driving conditions at the corresponding time point in the memory 123 (S290).

[0048] On the contrary, when the previous emotion occurs within the preset time T (“Yes” in S230 ), the emotion form determiner 122 may determine whether the driving condition when the current emotion occurs is the same as the driving condition when the previous emotion occurs ( S240 ).

[0049] As a result of the determination, when the current emotion appears in the same driving condition within a preset time from the occurrence of the previous emotion, the emotion form determiner 122 can determine that: the previous emotion and the current emotion are included in the continuous emotion, and the representative emotion of the continuous emotion can be determined (S270). For example, the emotion form determiner 122 can generate a representative emotion type by combining information about the previous emotion with information about the new emotion. The most frequently occurring emotion among the multiple emotions included in the continuous emotion can be determined as the representative emotion, and in the case where the emotions have the same frequency, the positive emotion can be determined as the representative emotion, or the representative emotion can be determined according to the preset priority of the preset representative emotions, but the present invention is not limited to this. For example, the candidate representative emotions can be determined mainly based on the frequency of occurrence of the emotions, the representative emotions can be determined by pre-applying the emotion sizes of each candidate representative emotion to determine the average size of the emotion, and weights can also be applied to different emotions in various driving conditions.

[0050] When it is determined that the current emotion is a continuous emotion, the emotion form determiner 122 may store the time point at which the representative emotion appears, the type of the representative emotion, and information on the driving condition at this time in the memory 123 ( S290 ).

[0051] When the current emotion appears within a preset time from the occurrence of the previous emotion but the driving conditions are different, the emotion form determiner 122 determines whether the previous emotion and the current emotion are emotions of the same type (S250).

[0052] When it is determined that the previous emotion and the current emotion are emotions of the same type (Yes in S250), the emotion form determiner 122 may determine the current emotion as a repeated emotion and provide a service corresponding to the type of the current emotion through the output unit 130 (S280). Needless to say, in the case of a repeated emotion, information about the time point when the current emotion appears, the type of the current emotion, and the driving conditions at the corresponding time point may be stored in the memory 123 (S290).

[0053] Conversely, when the current emotion appears within a predetermined time after the occurrence of the previous emotion, or when both the driving conditions and the type of the current emotion are different from those of the previous emotion (No in S250), the current emotion may be processed as an instantaneous emotion (S260), and the relevant information is stored in the memory 123 (S290).

[0054] Hereinafter, with reference to Figures 3 to 5C The method of determining the emotion form will be described in more detail.

[0055] Figure 3 FIG. is a diagram illustrating criteria for determining an emotion form according to an embodiment of the present invention. In Figure 3 the horizontal axis represents the time elapsed after the vehicle starts driving, and the vertical axis represents the magnitude of the emotion.

[0056] Referring to Figure 3 In part 1, an example is shown in which the driver becomes sensitive to the driving conditions and repeatedly feels surprised after being surprised by a sudden vehicle stop. The initially occurring surprised emotion 310 is processed as a temporarily occurring emotion, but the surprised emotion 320 that reappears within the preset threshold time T is the same emotion that occurs under different driving conditions from the surprised emotion 310. Therefore, the surprise 310 and the surprise 320 can be processed as repeated emotions, and the vehicle can provide a service corresponding to the emotion and perform vehicle control when the emotion is repeatedly recognized.

[0057] The drawing shows an example in which various emotions continuously appear within the threshold time T in the case of a conversation between the driver and the occupant. In this case, all the emotion changes in the driving condition where the driver and the occupant continue to talk can be integrated and processed as one emotion change. In part 2, the frequency of the happy emotion appearing is the highest, so the emotion change can be processed as a single occurrence of happiness (happiness as the representative emotion).

[0058] The surprised emotion 330 also appears in part 2, but it appears after the threshold time T compared to the last-appearing surprised emotion 320. Therefore, even if the driving conditions are different from each other, the surprise 330 can be not treated as a repeated emotion.

[0059] Figure 4 It is a diagram showing an example of determining an emotion form according to an embodiment of the present invention.

[0060] Similar to Figure 3 In Figure 4 the vertical axis represents the magnitude of the emotion and the horizontal axis represents the time elapsed after the vehicle starts driving. However, compared with Figure 3 in Figure 4 the driving conditions and the emotion form are also shown below the curve graph.

[0061] Referring to Figure 4 even if irritation and surprise corresponding to instantaneous emotions are recognized during driving, vehicle control and service provision may not be performed.

[0062] Conversely, in the curve graph, when boredom (which is a representative emotion of continuous emotions) is recognized and boredom is recognized again within the threshold time T, it can be treated as a repeated emotion and a service can be provided. In this case, since the driver feels bored once in traffic congestion and then the driver repeatedly feels bored during the cruise after the traffic congestion, the service provided can be to recommend and play music to overcome boredom, but the present invention is not limited thereto.

[0063] Figures 5A to 5C It shows an experimental example of determining an emotion form according to an embodiment of the present invention.

[0064] First, referring to Figure 5A traffic congestion occurs and the driver experiences an irritated emotion (irritation 1), and then repeated irritated emotions (irritation 2) are detected even when there is no traffic congestion. When irritation 1 and irritation 2 occur within the threshold time, the irritation can be treated as a repeated emotion and a service corresponding to the irritation can be provided.

[0065] Referring to Figure 5B when the driver feels sleepy (sleepiness 1) in a cruising situation and then repeated sleepiness (sleepiness 2) is detected even when there is no cruising within the threshold time, the sleepiness can be treated as a repeated emotion and a service corresponding to the sleepiness (such as operations of opening the window, air conditioner or multimedia playback) can be provided.

[0066] Referring to Figure 5CWhen the driver and the passenger continue to talk, continuous emotional changes are detected. In this case, the representative emotion of the continuous emotion can be extracted, and the continuous emotion can be processed as one representative emotion.

[0067] According to another embodiment of the present invention, the threshold time for the time interval between the previous emotion and the current emotion for processing continuous emotions and the threshold time for the time interval between the previous emotion and the current emotion for processing repeated emotions can be set differently, which will be described with reference to Figure 6 and Figure 7 hereinafter.

[0068] Figure 6 FIG. is a diagram for explaining the criteria for determining the form of emotion according to another embodiment of the present invention.

[0069] Referring to Figure 6 , the first threshold time T1 (the time difference between the previous emotion and the current emotion for processing continuous emotions) can be set to be different from the second threshold time T2 (the time difference between the previous emotion and the current emotion for processing repeated emotions).

[0070] Here, the first threshold time can be set shorter than the second threshold time. This is because continuous emotions usually occur within a short time, but repeated emotions occur at longer time intervals compared to continuous emotions. In this way, when T1 and T2 are set differently, as Figure 7 shown, the program for providing services based on emotion recognition described above with reference to Figure 2 can be modified.

[0071] Figure 7 FIG. is a flowchart showing an example of a program for providing services based on emotion recognition according to another embodiment of the present invention.

[0072] Figure 7 Different from Figure 2 , the operation step S230 of Figure 2 is divided into operation steps S230A and S230B in Figure 7 . Except for this difference, Figure 7 is similar to Figure 2 , so the description will be based on this difference.

[0073] Referring to Figure 7 , when an emotion appears during the monitoring of the driver and the driving condition (S210) (yes in S220), it can be determined whether the current emotion appears within T1 after the previous emotion appears (S230A). When the current emotion appears within T1 (yes in S230A), as Figure 2 shown, it is determined whether the driving condition when the current emotion appears is the same as the driving condition of the previous emotion (S240).

[0074] Conversely, when the current emotion appears after the previous emotion has passed T1 (being "no" in S230A), the emotion form determiner 122 determines whether the current emotion appears within T2 of the occurrence of the previous emotion (S230B).

[0075] When the current emotion appears within T2 (being "yes" in S230B), the emotion form determiner 122 determines whether the current emotion is the same as the previous emotion (S250), and when T2 has passed (being "no" in S230B), the emotion form determiner 122 can process the current emotion as a transient emotion (S260).

[0076] The remaining process is similar to Figure 2 the process, and thus, for the sake of clarity, the repeated description will be omitted.

[0077] The device for providing a vehicle service based on emotion recognition related to at least one embodiment of the present invention configured as above can determine whether to provide a service by further considering the emotion form.

[0078] Specifically, according to the present invention, continuous emotions and repeated emotions can be distinguished based on the emotion form, and corresponding services can be provided.

[0079] Those skilled in the art should understand that the effects that the present invention can achieve are not limited to those specifically described above, and other advantages of the present invention will be more clearly understood from the detailed description.

[0080] The present invention described above may also be implemented as computer-readable code stored on a computer-readable recording medium (e.g., a non-transitory computer-readable recording medium). For example, a method or operation performed by a single component (e.g., the emotion recognizer 110 or its sub-components, and the service provision determiner 120 or its sub-components) may be implemented as computer-readable code stored in a memory, which is implemented as a computer-readable recording medium (e.g., a non-transitory computer-readable recording medium). A computer-readable recording medium is any data storage device that can store data that can subsequently be read by a computer. Examples of computer-readable recording media include hard disk drives (HDDs), solid state drives (SSDs), silicon disk drives (SDDs), read-only memories (ROMs), random access memories (RAMs), CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like. The emotion recognizer 110 and the service provision determiner 120 may each or together be implemented as a computer, a processor, or a microprocessor. Alternatively, the pre-processor 112, the feature extractor 113, the emotion classifier 114, and the basic emotion determiner 115, the driving condition determiner 121, and the emotion form determiner 122 may each or together be implemented as a computer, a processor, or a microprocessor. When a computer, a processor, or a microprocessor reads and executes the computer-readable code stored on the computer-readable recording medium, the computer, the processor, or the microprocessor may be configured to perform the operations / methods described above.

[0081] It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit and scope of the invention. Accordingly, the present invention is intended to cover modifications and variations of the present invention provided they fall within the scope of the appended claims and their equivalents.

Claims

1. A method for providing vehicle services based on emotion recognition, the method comprising the following steps: Monitoring the occupant and driving conditions; When an emotion of the occupant is recognized during the monitoring, comparing at least one of the first emotion and the first driving condition with at least one of the second emotion and the second driving condition, wherein the first emotion is the type of the currently generated emotion, the first driving condition is the driving condition corresponding to the first time which is the time point when the emotion is recognized, the second emotion is the type of the previously recognized emotion compared with the emotion, and the second driving condition is the driving condition corresponding to the second time which is the time point when the previously generated emotion is recognized; And Based on the result of the comparison, performing a determination step: determining the currently generated emotion as one of an instantaneous emotion, a continuous emotion, and a repeated emotion.

2. The method according to claim 1 further comprises the following steps: When the currently generated emotion is determined to be a repeated emotion, providing a service corresponding to the first emotion.

3. The method according to claim 1 further comprises the following steps: When the currently generated emotion is determined to be a continuous emotion, determining a representative emotion among multiple emotions including at least the first emotion and the second emotion, and configuring the continuous emotion.

4. The method according to claim 1, wherein The determination step includes: determining whether the first time is within a threshold time starting from the second time.

5. The method according to claim 4, wherein, The determination step further includes: when the first time appears after the threshold time has elapsed from the second time, determining the currently generated emotion as an instantaneous emotion.

6. The method according to claim 4, wherein The determination step further includes: when the first time is within the threshold time starting from the second time, comparing the first driving condition with the second driving condition.

7. The method according to claim 6, wherein The determination step further includes: when the first driving condition is the same as the second driving condition, determining the currently generated emotion as a continuous emotion.

8. The method according to claim 6, wherein, The determination step further includes: when the first driving condition is different from the second driving condition, comparing the first emotion with the second emotion.

9. The method according to claim 8, wherein, The determination step further includes: when the first emotion is the same as the second emotion, determining the currently generated emotion as a repeated emotion.

10. The method according to claim 8, wherein The determination step further includes: when the first emotion is different from the second emotion, determining the currently generated emotion as an instantaneous emotion.

11. The method according to claim 1, wherein The determination step further includes: determining whether the first time is within a preset first threshold time starting from the second time.

12. The method according to claim 11, wherein, The determination step further includes: when the first time appears after the preset first threshold time has elapsed from the second time, determining whether the first time is within a second threshold time starting from the second time, and the second threshold time is greater than the preset first threshold time.

13. The method according to claim 12, wherein, The determination step further includes: when the first time appears after the second threshold time has elapsed from the second time, determining the currently generated emotion as an instantaneous emotion.

14. The method according to claim 12, wherein, The determination step further includes: when the first time is within the second threshold time starting from the second time, comparing the first emotion with the second emotion.

15. The method according to claim 14, wherein, The determination step further includes: When the first emotion is the same as the second emotion, determine the currently generated emotion as a repeated emotion; and When the first emotion is different from the second emotion, determine the currently generated emotion as an instantaneous emotion.

16. The method according to claim 11, wherein, The determining step further includes: comparing the first driving condition with the second driving condition when the first time is within the first threshold time starting from the second time.

17. The method according to claim 16, wherein, The determining step further includes: When the first driving condition is the same as the second driving condition, determine the currently generated emotion as a continuous emotion; and When the first driving condition is different from the second driving condition, compare the first emotion with the second emotion, and determine the currently generated emotion as a repeated emotion or an instantaneous emotion according to whether the first emotion is the same as the second emotion.

18. A non-transitory computer-readable recording medium having recorded thereon a program for executing the method according to claim 1.

19. An apparatus for providing a vehicle service based on emotion recognition, the apparatus including: An emotion recognizer configured to determine the emotion of an occupant; A driving condition determiner configured to monitor a driving condition; And An emotion form determiner configured to: when the emotion recognizer recognizes the emotion of an occupant, compare at least one of a first emotion and a first driving condition with at least one of a second emotion and a second driving condition, and determine the currently generated emotion as one of an instantaneous emotion, a continuous emotion, and a repeated emotion according to the result of the comparison, wherein the first emotion is the type of the currently generated emotion, the first driving condition is the driving condition corresponding to a first time which is the time point of recognizing the emotion, the second emotion is the type of the emotion recognized previously compared with the emotion, and the second driving condition is the driving condition corresponding to a second time which is the time point of recognizing the previously generated emotion.

Images