KR100914309B1 - Intelligent Agent System And Method Of Generating Emotion Of Intelligent Agent - Google Patents

Abstract

The present invention relates to an intelligent agent system and a method for generating emotion of an intelligent agent. The present invention includes the steps of sensing the external or internal stimulus of the intelligent agent system; Converting the sensed stimulus into an emotional stimulus associated with the emotion; Generating an emotion of the intelligent agent based on the emotion stimulus; Obtaining environmental information about an internal environment and an external environment of the system; Adjusting the intensity of the generated emotion in consideration of the obtained environmental information; And an emotion generating method of the intelligent agent comprising the step of outputting the emotion whose intensity is adjusted, and an intelligent agent system capable of implementing the same.

Intelligent agent, emotion, personality, environment

Description

Intelligent Agent System and Method of Generating Emotion Of Intelligent Agent

The present invention relates to an intelligent agent such as an intelligent character that can communicate with a user and a robot that can express emotions. The present invention recognizes an environment in which an intelligent agent and an intelligent agent system are located and reflects it in the emotion generation of an intelligent agent. The present invention relates to an intelligent agent system and an intelligent agent emotion generating method capable of improving the reliability of the emotion generation and the expression of the emotion.

According to the conventional method of generating and expressing an emotion of an intelligent agent, an emotion is generated and expressed mainly based on a physical stimulus input from an external sensor or a periodic biorhythm modeled inside the intelligent agent. For example, an intelligent agent recognizes the emotions expressed by humans interacting with them and appropriately expresses them accordingly, or is appropriate for physical sensor signal values such as contact with specific areas or external voice signals. Represents an emotional response.

The intelligent agent is a mechanism that models life. It can include the motives and biological rhythm changes that are the characteristics of life, and the change of these factors can also be used for expressing emotions of intelligent agents.

When an intelligent agent is rewarded from the outside, it can rejoice, avoid or dislike disliked things, and change its emotional expression according to changes in biological signals such as hunger or curiosity inside the intelligent agent.

1 is a diagram illustrating a emotion generation and expression process of an intelligent agent according to the prior art. That is, according to the related art, after generating a emotion based on the recognized stimulus, the emotion of the intelligent agent is generated and expressed by a simple mechanism of expressing the generated emotion.

As described above, according to the method of generating and expressing emotions only for a specific stimulus or internal state change, it takes a structure that simply responds to a given input value, and considers the physical and social environment information of the intelligent agent. There is a problem that can not be. As a result, the intelligent agent modeling the real life causes the reliability of the emotional expression to be output.

The present invention solves the above problems and has been proposed in accordance with recent trends and requests, and can amplify or suppress the generated emotion in consideration of the external environment encountered by the intelligent agent and the internal environment of the system to which the intelligent agent belongs. The purpose of the present invention is to provide an intelligent agent system and a method for generating emotions of intelligent agents.

Another object of the present invention is to provide an intelligent agent system and an intelligent agent's emotion generating method capable of generating and expressing an emotion close to a real life by reflecting the nature of the intelligent agent on both an input stimulus and an output emotion.

Still another object of the present invention is to provide an intelligent agent system and an intelligent agent's emotion generating method capable of generating and managing an emotional of an intelligent agent when a plurality of stimuli are simultaneously input.

As an aspect of the present invention for achieving the above object, the intelligent agent emotion generating method according to the present invention, in the system having the intelligent agent emotion generating function of the emotion generating method of the intelligent agent, the system Detecting at least two external or internal stimuli simultaneously; Converting the sensed stimulus into the emotional stimulus by referring to a database that matches the emotional stimulus associated with the emotion with respect to the external or internal stimulus; Generating emotions of the intelligent agent in consideration of personality of the intelligent agent set by the user or pre-formed by learning and relationship information between a plurality of emotions based on the converted emotional stimulus; Obtaining environmental information about an internal environment and an external environment of the system; Adjusting the intensity of the generated emotion in consideration of the personality of the intelligent agent and the obtained environmental information; And outputting the emotion whose intensity is adjusted.

delete

As another aspect of the present invention for achieving the above object, the intelligent agent system according to the present invention, the stimulus detector for detecting at least two external or internal stimulus of the intelligent agent system at the same time; A storage unit for storing the personality of the intelligent agent set by the user or pre-formed by learning; An emotional stimulation converter for converting the stimulus transmitted from the stimulus detector into an emotional stimulus related to the emotion by referring to the database; An emotion generation unit generating emotions of the intelligent agent in consideration of the personality of the intelligent agent and relationship information between a plurality of emotions based on the emotional stimulus transmitted from the emotional stimulation converter; An environment information acquisition unit for obtaining environment information about an internal environment and an external environment of the system; And an intensity adjusting unit adjusting the intensity of the emotion generated by the emotion generating unit in consideration of both the personality of the intelligent agent and the environment information.

According to the intelligent agent system and the emotion generating method of the intelligent agent according to the present invention, the following effects are obtained.

First, since the generated emotion can be amplified or suppressed in consideration of the external environment in which the intelligent agent is located and the internal environment of the system to which the intelligent agent belongs, more complicated and reliable emotion expression is possible than in the prior art.

Second, by reflecting the nature of the intelligent agent for both the input stimulus and the output emotion, it is possible to generate and express emotions close to real life.

Third, since the emotion of the intelligent agent can be generated and managed when a plurality of stimuli are input at the same time, it is possible to implement a real life-like mechanism that expresses complex emotions by simultaneously processing multiple stimuli.

The above objects, features and advantages of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Like numbers refer to like elements throughout. In addition, when it is determined that the detailed description of the known function or configuration related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted.

2 is a block diagram of an intelligent agent system having an emotion generating function of an intelligent agent according to an embodiment of the present invention. 3 is a block diagram of an emotion management module of an intelligent agent according to an embodiment of the present invention. 2 and 3, an intelligent agent system having an emotion generating function of the intelligent agent according to an embodiment of the present invention will be described in detail.

Intelligent agent system according to an embodiment of the present invention, the intelligent agent module 100, including the emotion management module 103 and intelligent agent management module 105, storage unit 110, input unit 120, display unit ( 130, the audio processor 140, the vibration unit 150, and the controller 160 may be included.

The emotion management module 103 is a module that processes data related to emotion of the intelligent agent, such as generation, management, and expression of the emotion of the intelligent agent. The emotion management module 103 may include a stimulus detector 11, an environment information acquirer 13, an emotion stimulus converter 15, an emotion generator 17, and an intensity adjuster 19. Detailed features of the emotion management module 103 will be described later.

The intelligent agent management module 105 manages everything necessary for the intelligent agent to maintain life inside the intelligent agent system as an artificial life in addition to the emotion of the intelligent agent.

The storage unit 110 stores a predetermined program for controlling the overall operation of the intelligent agent system, and the data inputted and outputted when the overall operation of the intelligent agent system is performed by the controller 160 is processed. Store various data.

In particular, the storage unit 110 stores a database in which emotional stimuli related to emotion are matched with respect to external and internal stimuli of the intelligent agent system. In other words, the database contains information about what emotion a particular stimulus causes to the intelligent agent. The emotional stimulus refers to a stimulus associated with emotion as a stimulus for inducing emotion.

The intelligent agent module 100 may recognize a stimulus that generates an emotion as a specific object, action, or event. The object, action or event may be classified as an emotional stimulus that may cause a specific emotion depending on the kind and the occurrence background. For example, physical sensors such as visual, tactile, auditory, olfactory, temperature, humidity, and light and stimuli transmitted from the intelligent agent system or the internal state of the intelligent agent are combined again to construct and classify objects, behaviors, and events. This, in turn, depends on which of the six basic emotions contributes to the generation of emotions, which can cause joy, sadness, hate, anger, fear, It can be categorized into six basic emotion-stimulating stimuli, including surprise-inducing stimuli. The database has information thus matching the emotional stimulus that causes the emotion with respect to the specific stimulus. However, it is noted that the six basic emotions are merely examples, and various emotions of the six basic emotions or more may be applied to the present invention.

In addition, the storage unit 110 may store the personality of the intelligent agent. The personality of the intelligent agent may be set by a user or formed by learning. For example, the intelligent agent management module 105 may include a learning algorithm regarding the nature of the intelligent agent. The intelligent agent management module 105 may learn the characteristics of the intelligent agent with respect to various events occurring over time using the learning algorithm.

The input unit 120 is a device for receiving various information or commands from a user, and may be implemented as a keypad or a touch input device having various numeric keys, direction keys, and the like. As an example of the touch input device, the touch screen may simultaneously perform an input function and a display function.

The display unit 130 is a display device for displaying the state or various information of the intelligent agent system by a control signal output from the control unit 160.

The audio processor 140 processes audio to input and output audio through a microphone MIC and a speaker SPK. The audio processor 140 outputs various processing and control operations of the intelligent agent system as audio through a speaker SPK, or processes audio to input various information or commands as audio through a microphone MIC.

The vibration unit 150 is a vibration device including a vibration motor and a vibration element for generating a vibration of the intelligent agent system according to the control signal of the control unit 160. The vibration element generates vibration by the vibration motor. Since the detailed configuration and operation of the vibration device is a known technique, a detailed description thereof will be omitted.

The controller 160 controls the components and controls the overall operation of the intelligent agent system according to an embodiment of the present invention.

As described above, the emotion management module 103 may include a stimulus detector 11, an environment information acquirer 13, an emotion stimulus converter 15, an emotion generator 17, and an intensity adjuster 19. It may include.

The stimulus detector 11 detects stimuli of the outside and the inside of the intelligent agent system.

The external stimulus includes changes in environmental factors that occur outside of the intelligent agent system. The stimulus detector 11 may include a visual sensor, an olfactory sensor, a tactile sensor, a distance sensor, and various sensing sensors capable of sensing various environmental elements such as temperature, humidity, and light in order to detect the external stimulus. have. The stimulus detector 11 does not necessarily include the detection sensors. The intelligent agent system may include the detection sensors, and the stimulus detection unit 11 may receive a value detected by the detection sensors from the detection sensors.

The internal stimulus includes elements related to the status of the intelligent agent system, such as the location of the intelligent agent system, the moving speed, the part status, the battery level, and the like. The internal stimulus may also include information such as emotional state, hunger, boredom, interest, and novelty as an internal state value that the intelligent agent should always maintain as an artificial life. Information about the internal stimulus may be received from the intelligent agent management module 105.

 The stimulus detector 11 may simultaneously detect two or more external stimuli or internal stimuli. For example, the stimulus detector 11 may simultaneously detect two external stimuli-for example, a change in temperature and a light-and an internal stimulus-for example, the battery level is outside the set value. Can be.

The environment information acquisition unit 13 obtains environment information regarding an internal environment and an external environment of the intelligent agent system. An example of the internal environment is the remaining battery capacity or part status of the intelligent agent system. For example of the external environment, there is a place where the intelligent agent system is located. The environmental information acquisition unit 13, like the stimulus detection unit 11, includes a visual sensor, an olfactory sensor, a tactile sensor, a distance sensor, and various detection sensors capable of detecting various environmental elements such as temperature, humidity, and lighting. It may include. In addition, the intelligent agent system may include the detection sensors, and the environment information acquisition unit 13 may receive a value sensed by the detection sensors from the detection sensors. The environment information may be input from the user through the input unit 120. In this case, the environmental information acquisition unit 13 receives environmental information through the input unit 120. For example, the user may input through the input unit 120 that the place where the intelligent agent system is currently located is a “room” or a “playground”.

The emotional stimulus converter 15 converts the stimulus transmitted from the stimulus detector 11 into an emotional stimulus related to the emotion with reference to the database stored in the storage 110. The emotion stimulus converter 15 may transmit the emotion stimulus converted with reference to the database to the emotion generator 17 by reflecting the characteristics of the intelligent agent.

The emotion generator 17 generates an emotion of the intelligent agent based on the emotion stimulus transmitted from the emotion stimulus converter 15. The emotion generating unit 17 may generate the emotion of the intelligent agent in consideration of the nature of the intelligent agent and relationship information between a plurality of emotions.

The strength adjusting unit 19 adjusts the strength of the emotion of the intelligent agent generated by the emotion generating unit 17 in consideration of at least one of the personality of the intelligent agent and the environment information.

The intensity adjuster 19 may adjust the intensities of the plurality of sensed stimuli when there are a plurality of stimuli sensed by the stimulus detector 11. In particular, there may be emotions that are set to not be output at the same time among the plurality of detected emotions. For example, assume that the first stimulus and the second stimulus are simultaneously sensed by the stimulus detector 11. In this case, when the emotion caused by the first stimulus is "joy" and the emotion induced by the second stimulus is "sorrow," "joy" and "sorrow" may be set to emotions that cannot be simultaneously expressed. . The intensity adjusting unit 19 may persist only the emotion with the highest intensity among the emotions that cannot be output at the same time, and extinguish the remaining emotions. For example, assume that "joy", which is an emotion caused by the first stimulus, has a value of 2.0, and "sorrow," which is an emotion caused by the second stimulus, has a value of 0.7. Since the intensity adjusting unit 19 cannot output "joy" and "sadness" at the same time, it is possible to output "joy" at an intensity of 1.3 corresponding to the difference between the intensity of "joy" and the intensity of "sadness". . At this time, the feeling of sadness is not output.

4 is a conceptual diagram illustrating a method for generating emotion of an intelligent agent according to an embodiment of the present invention. 5 is a flowchart of a method for generating emotion of an intelligent agent according to an embodiment of the present invention. 4 and 5, the emotion generating method of the intelligent agent according to an embodiment of the present invention will be described in detail. The terms mentioned below are the same as the terms mentioned in the above description of the intelligent agent system.

According to the present invention, unlike the prior art described with reference to FIG. 1, as shown in FIG. 4, the emotion of the intelligent agent may be expressed by reflecting the personality of the intelligent agent and the environment information.

First, an external or internal stimulus of the intelligent agent system is detected [S500].

The detected stimulus is converted into an emotional stimulus related to the emotion [S510]. The step S510 may be performed by referring to the database stored in the storage unit 110. As described above, the database includes information that matches the emotional stimulus with respect to the external or internal stimulus.

In step S510, the personality of the intelligent agent may be reflected on the emotional stimulus converted with reference to the database. The reason for reflecting the personality of the intelligent agent with respect to the emotional stimulus is that the degree of responding to the stimulus or the degree of accepting the stimulus may vary depending on the personality of the intelligent agent.

The emotion of the intelligent agent is generated based on the emotional stimulus [S520]. The step S520 may be performed in consideration of the nature of the intelligent agent. Here, the nature of the intelligent agent is considered to reflect this, even if the same stimulus, the degree of accepting the stimulus is different depending on the nature of the intelligent agent.

In addition, environment information regarding an internal environment and an external environment of the intelligent agent system is acquired [S530]. The environment information may be input from a user or obtained by automatic detection of the intelligent agent system.

The strength of the emotion generated in step S520 is adjusted in consideration of the obtained environment information and the personality of the intelligent agent [S540]. For example, when the intelligent agent or the external environment of the intelligent agent system corresponds to a "room" requiring quietness, the intensity of the generated emotion may be weakly adjusted. Also, for example, when the external environment corresponds to a noisy "playground", the intensity of the generated emotion may be strongly amplified.

Considering the nature of the intelligent agent in the step S540, even if the same feeling is to reflect this because the type and degree of expressing the emotion is different depending on the nature of the intelligent agent.

In operation S540, the emotion of which the intensity is adjusted is expressed (S550). At step S540, the emotion may be expressed in various ways. For example, the emotion information may be displayed on the display unit 130 provided in the intelligent agent system, and the audio intensity may be output through the audio processor 140 and the speaker, or the vibration unit ( 150 may generate vibration.

6 is a flowchart of a method for generating emotion of an intelligent agent according to another embodiment of the present invention. Referring to Figure 6, it will be described in detail the emotion generation method of the intelligent agent according to an embodiment of the present invention. The emotion generating method of FIG. 6 corresponds to a case in which two or more external or internal stimuli are simultaneously detected. The terms mentioned below are the same as the terms mentioned in the above description of the intelligent agent system.

First, a plurality of external or internal stimuli of the intelligent agent system are detected [S600]. Two or more stimuli are detected by the stimulus detector 11. For example, the stimulus detector 11 simultaneously detects "change in external temperature" and "hunger of an intelligent agent." "Change in external temperature" corresponds to an external stimulus, and "hunger of an intelligent agent" corresponds to an internal stimulus.

On the other hand, the external stimulus received by the intelligent agent, such as the five senses of the human, can be defined as five stimulus S for the visual, auditory, tactile, temperature, olfactory and can be expressed by Equation 1 below.

Here, S _VS is visual, S _AS is auditory, S _TS is tactile, S _HS is temperature, and S _OS is olfactory.

In operation S610, the detected stimulus is converted into an emotional stimulus related to the emotion. The step S610 corresponds to the step S510. That is, step S610 may be performed by referring to the database stored in the storage unit 110. As described above, the database includes information that matches the emotional stimulus with respect to the external or internal stimulus. In step S610, as in step S510, the personality of the intelligent agent may be reflected on the emotional stimulus converted with reference to the database.

Equation 2 below is an example of expressing the emotional stimulus.

Where U _Happy is an emotional stimulus that induces joy, U _Sad is an emotional stimulus that induces sadness, U _Disgust is an emotional stimulus that causes disgust, U _Anger is an emotional stimulus that causes anger, and U _Fear is a fear-induced emotion The stimulus, U _Surprise , represents an emotional stimulus, each causing a surprise. The categorization of emotions as “joy, sadness, disgust, anger, fear, surprise” is based on six basic emotion classifications according to P.Ekman's facial expressions.

For example, as shown in FIG. 6, by the step S610, an emotional stimulus u = {2.0, 1.0, 0, 0, 0, 0} is generated. In other words, by a plurality of stimuli, emotional stimuli that cause "joy" and "sorrow" are generated with sizes of "2.0" and "1.0", respectively.

The emotion of the intelligent agent is generated based on the emotional stimulus [S620]. The step S620 may be performed in consideration of the personality of the intelligent agent and relationship information between a plurality of emotions.

The relationship information between the plurality of emotions may include information that mutually opposing emotions suppress generation of each other, and that the generated emotions gradually disappear as time passes when the emotions are generated at some point and no further stimulation is detected. It may include information about things.

Equation 3 below shows an example of a relation for generating emotion in step S620.

Here, x denotes the emotion of the intelligent agent, u denotes the emotional stimulus, A denotes relationship information between the plurality of emotions, B denotes the personality of the intelligent agent, and a denotes a parameter for determining the speed of generating the emotion. . x, u, A and B can be represented by a vector or a matrix.

FIG. 7 is a diagram illustrating an example in which emotion x and emotion stimulus u are expressed as vectors, and FIG. 8 is a diagram illustrating an example in which relationship information A between a plurality of emotions is expressed in a matrix. In FIG. 8, since the feelings of "happy" and the feelings of "sad" cannot be expressed at the same time, "joy" and "sorrow" are generated from each other by the area indicated by reference numeral 30. Will be suppressed. In addition, in FIG. 8, since the emotion of "Anger" and the feeling of "Fear" are emotions that cannot be expressed at the same time, "anger" and "fear" are generated by the area indicated by reference numeral 40. Will be suppressed.

For example, as shown in FIG. 6, by step S620, emotion x = {1.85, 0.78, 0, 0, 0, 0} is generated. That is, "joy" and "sorrow" are generated, having sizes of "1.85" and "0.78", respectively.

In addition, environment information regarding an internal environment and an external environment of the intelligent agent system is acquired [S630]. The environment information may be input from a user or obtained by automatic detection of the intelligent agent system.

The strength of the emotion generated in step S620 is adjusted in consideration of the obtained environment information and the personality of the intelligent agent [S640]. The step S640 corresponds to step S540 of FIG. 5.

Equation 4 below shows an example of a relationship for adjusting the intensity of emotion.

Here, y represents the emotion whose intensity is adjusted, C represents the environment information, and D represents the personality of the intelligent agent. As described above, the personality B used in Equation 3 reflects the degree of accepting the stimulus according to the personality, and the personality D used in Equation 4 reflects the degree of expressing the emotion according to the personality. It is to. 9 is a diagram illustrating an example in which the emotion y whose intensity is adjusted is represented by a vector.

Equation 5 below is an example of a relational expression for expressing environmental information C.

Here, β represents an environmental index determined according to the obtained environmental information, and I represents an identity matrix.

Table 1 below shows an example of the environmental index β.

External and internal environment β (Environmental Index) If not considered 0 Suppress emotions 0 <β <1 Amplify emotions 1 <β

For example, the environmental index β has a value less than 1 when the intensity of emotion is to be reduced, such as "meeting room", and a value greater than 1 when it is necessary to increase the intensity of emotion, such as "playground". Will have Since the environmental index β shown in Table 1 is merely an example, it is not necessarily limited thereto.

For example, as shown in FIG. 6, the emotion index β = 1.2 is obtained by step S630 and the intensity y is adjusted by step S640. Y = {2.22, 0.936, 0, 0, 0 , 0} is generated. This is the result of multiplying the obtained β = 1.2 by x, which is the result of the step S620.

As a result of performing step S640, it is determined whether there are emotions that cannot be expressed at the same time [S650].

As a result of the determination of step S650, if there are no emotions that cannot be expressed at the same time, the emotion of which the intensity is adjusted is expressed in step S640 [S670]. The step S670 corresponds to the step S550 of FIG. 5.

As a result of the determination in step S650, if there are emotions that cannot be expressed at the same time, only one of the emotions that cannot be expressed at the same time is selected and the other emotions are extinguished (S660), and then the emotions are expressed [S670]. Here, among the emotions that cannot be expressed simultaneously, the emotion with the highest intensity may be selected and persisted. The remaining less intense emotions disappear.

In the example shown in FIG. 6, as a result of performing step S640, emotions of “joy” and “sorrow” exist. Since "joy" and "sorrow" cannot be expressed at the same time, only one emotion is selected by the step S660 and the other emotion must be extinguished. As a result of performing step S640, "joy" has an intensity of 2.22, and "sorrow" has an intensity of 0.936. In step S660, 1.284 corresponding to a difference between 2.22 and 0.936 may be set to an intensity of “joy”. Thus, the final emotion expressed at step S670 is "joy" with an intensity of 1.284.

The emotion generating method of the intelligent agent according to the present invention described above may be provided by recording in a computer-readable recording medium as a program for executing in a computer.

The emotion generation method of the intelligent agent according to the present invention can be executed through software. When implemented in software, the constituent means of the present invention are code segments that perform the necessary work. The program or code segments may be stored on a processor readable medium or transmitted by a computer data signal coupled with a carrier on a transmission medium or network.

Computer-readable recording media include all kinds of recording devices that store data that can be read by a computer system. Examples of computer-readable recording devices include ROM, RAM, CD-ROM, DVD ± ROM, DVD-RAM, magnetic tape, floppy disks, hard disks, optical data storage devices, and the like. The computer readable recording medium can also be distributed over network coupled computer devices so that the computer readable code is stored and executed in a distributed fashion.

The present invention described above is capable of various substitutions, modifications, and changes without departing from the spirit of the present invention for those skilled in the art to which the present invention pertains. It is not limited by the drawings.

1 is a diagram illustrating a emotion generation and expression process of an intelligent agent according to the prior art.

2 is a block diagram of an intelligent agent system having an emotion generating function of an intelligent agent according to an embodiment of the present invention.

3 is a block diagram of an emotion management module of an intelligent agent according to an embodiment of the present invention.

4 is a conceptual diagram illustrating a method for generating emotion of an intelligent agent according to an embodiment of the present invention.

5 is a flowchart of a method for generating emotion of an intelligent agent according to an embodiment of the present invention.

6 is a flowchart of a method for generating emotion of an intelligent agent according to another embodiment of the present invention.

7 is a diagram illustrating an example of expressing an emotion x and an emotion stimulus u as a vector.

8 is a diagram illustrating an example of expressing relationship information A between a plurality of emotions in a matrix.

9 is a diagram illustrating an example in which the emotion y whose intensity is adjusted is represented by a vector.

<Explanation of symbols for the main parts of the drawings>

100: intelligent agent module 103: emotion management module

11: stimulus detector 13: environmental information acquisition unit

15: emotion stimulation converter 17: emotion generator

19: strength adjuster 105: intelligent agent management module

110: storage unit 120: input unit

130: display unit 140: audio processing unit

150: vibration unit 160: control unit

Claims (20)

delete delete delete delete In a system having an intelligent agent's emotion generating function, two or more stimuli externally or internally detected in the system are simultaneously detected, and the detected stimulus is referred to by referring to a database that matches an emotional stimulus related to emotion with respect to the external or internal stimulus. Converting to the emotional stimulus, and generating the emotion of the intelligent agent based on the converted emotional stimulus, Emotional generation method of the intelligent agent, Equation 1: considering the relationship between the personality (personality) and a plurality of emotions of the intelligent agent is set by the user or pre-formed by learning;

By generating the emotion (x) of the intelligent agent, The emotion generation method of the intelligent agent, Acquiring environmental information (C) of the internal environment and external environment of the system by input from a user or automatic detection by the system; Generating an emotion (y) is adjusted by adjusting the strength by y = CDx;: Equation (2) that the intensity of the generated feeling (x), of the above-obtained environmental information and the character of the intelligent agent And Outputting the emotion y with the intensity adjusted; The environmental information (C) is determined by Equation 3: C = β I , In Equation 1, u denotes the emotion stimulus, A denotes relationship information between the plurality of emotions, B denotes a personality of the intelligent agent, and a denotes a parameter for determining a rate of generating the emotion, respectively. In Equation 2, C represents the environment information, D represents the nature of the intelligent agent, and In Equation 3, β is an environment index determined according to the obtained environmental information, and I represents an identity matrix, respectively. The method of claim 5, wherein If there are emotions that are set to not be output at the same time among the two or more detected emotions before performing the outputting of the emotions, only the emotion with the highest intensity among the emotions that cannot be output at the same time lasts and the remaining emotions are maintained. They've gone through the emotional adjustment phase The emotion generating method of the intelligent agent further comprising. The method of claim 6, wherein the persisting emotion in the emotion adjustment step is: And a strength corresponding to a difference between the strength of the remaining emotion and the strength of the remaining emotions before performing the emotion adjustment step. delete delete delete A computer-readable recording medium having recorded thereon a computer program capable of executing the method of any one of claims 5 to 7. delete delete delete delete delete delete delete delete An intelligent agent system having an emotion generating function of an intelligent agent, comprising: a stimulus detector configured to simultaneously detect at least two external or internal stimuli of the intelligent agent system, and a database matching the emotional stimuli related to the emotion with respect to the external or internal stimulus And a storage unit configured to store a memory, an emotional stimulus converter configured to convert the detected stimulus into the emotional stimulus, and an emotion generator configured to generate an emotion of the intelligent agent based on the converted emotional stimulus. In the intelligent agent system, The storage unit further stores the personality of the intelligent agent set by the user or pre-formed by learning, Equation 1: considering the relationship between the personality and the plurality of emotions of the intelligent agent, the emotion generating unit;

To generate the emotion ( x ) of the intelligent agent, The intelligent agent system, An environment information acquisition unit for obtaining environment information (C) of the internal environment and the external environment of the system by an input from a user or automatic detection by the system; And The intensity of the generated feeling (x), the obtained setting information, and Equation (2) considering the character of the intelligent agent: the intensity adjusting unit for generating an adjusted by y = CDx the strength adjustment emotional (y) Including more, The environmental information (C) is determined by Equation 3: C = β I , In Equation 1, u denotes the emotion stimulus, A denotes relationship information between the plurality of emotions, B denotes a personality of the intelligent agent, and a denotes a parameter for determining a rate of generating the emotion, respectively. In Equation 2, C represents the environment information, D represents the nature of the intelligent agent, and In Equation 3, β is an environmental index determined according to the obtained environmental information, and I represents an identity matrix, respectively.

Images