JP2019076596A - Information processing device, information processing system and program - Google Patents

Abstract

To readily use a trend on personality at each point.SOLUTION: An information processing device includes correction means for correcting a trend on personality that is preliminarily estimated for an object person based on the current biological information of the object person.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus, an information processing system, and a program.

  Knowing the individual's personality traits makes it easier to predict each individual's responses and behavior.

JP, 2013-109656, A

  In order to improve the accuracy of prediction, it is desirable to obtain information necessary for estimation whenever there is an opportunity for use. On the other hand, frequent acquisition of information necessary for estimation places a burden on the subject. In addition, it may not be possible to secure the time required to acquire and diagnose information.

  An object of the present invention is to make it easy to utilize the tendency of the character at each time point.

The invention described in claim 1 is an information processing apparatus including a correction unit that corrects a tendency on a character estimated in advance for a subject based on current biometric information of the subject.
The invention according to claim 2 is the information processing apparatus according to claim 1, wherein the current biological information is information at a point in time when the tendency on the character is used.
The invention according to claim 3 is the information processing apparatus according to claim 2, wherein the biological information is sequentially obtained.
In the invention according to claim 4, the correction means corrects the tendency of the character on the basis of one or both of the physical condition and the mental condition of the subject estimated from the biological information. It is an information processor of a statement.
The invention according to claim 5 is the information processing apparatus according to claim 4, wherein the correction means makes correction so as to strengthen or weaken the tendency on the character according to the physical condition.
The invention according to claim 6 is the information processing apparatus according to claim 4, wherein the correction means corrects or weakens the tendency to strengthen or weaken the personality depending on the state of the mind. It is.
The invention according to claim 7 is that, when the state of mind is an excited state, the correction means strengthens some tendency in the character and weakens other some tendency. It is an information processor given in a.
The invention described in claim 8 is the information processing apparatus according to claim 1, wherein the tendency in personality is estimated based on a feature appearing in the handwriting of the subject.
The invention according to claim 9 is the information processing apparatus according to claim 8, wherein the estimation based on the features appearing in the handwriting is performed using artificial intelligence.
The invention according to claim 10 is the information processing apparatus according to claim 1, wherein the correction means is configured using artificial intelligence.
The invention according to claim 11 is the information processing apparatus according to claim 1, wherein the speaker is selected based on the corrected tendency on the character and the physical condition or mental state of the subject.
The invention according to claim 12 is an information processing system including a correction unit that corrects a tendency on a character estimated in advance for a subject based on current biometric information of the subject.
The invention according to claim 13 is a program that causes a computer to function as a correction unit that corrects a tendency of a character estimated in advance for a subject based on current biometric information of the subject.

According to the first aspect of the present invention, it is possible to easily utilize the tendency in personality at each time point.
According to the second aspect of the present invention, it is possible to easily utilize the tendency in character at each time point.
According to the third aspect of the present invention, it is possible to easily utilize the tendency in character at each time point.
According to the fourth aspect of the present invention, it is possible to easily utilize the tendency in character at each time point.
According to the fifth aspect of the present invention, it is possible to easily utilize the tendency in character at each time point.
According to the sixth aspect of the present invention, it is possible to easily utilize the tendency in character at each time point.
According to the seventh aspect of the present invention, it is possible to easily utilize the tendency in character at each time point.
According to the eighth aspect of the present invention, it is possible to easily utilize the tendency in character at each time point.
According to the invention as set forth in claim 9, it is possible to easily utilize the tendency in character at each time point.
According to the invention as set forth in claim 10, it is possible to easily utilize the tendency in character at each time point.
According to the invention of claim 11, it is possible to easily utilize the tendency of the character at each time point.
According to the invention as set forth in claim 12, it is possible to easily utilize the tendency in character at each time point.
According to the invention as set forth in claim 13, it is possible to easily utilize the tendency in character at each time point.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the structural example of the conversation assistance system which concerns on embodiment. It is a figure which shows the structural example of a character tendency diagnostic part. It is a figure which shows a part of classification | category which paid its attention to the characteristic of 1 character 1 character. It is a figure which shows the remainder of the classification which paid its attention to the 1 character 1 character feature. It is a figure which shows the classification which paid its attention to the feature on chapter law. It is a figure which shows the structural example of a character tendency correction | amendment part. It is a figure which shows the example of the correspondence of biometric information and the state of mind and body. It is a figure which shows the structural example of a correction table. It is a figure which shows the structural example of the conversation assistance part used by this Embodiment. It is a figure which shows the example of the table which a speaker selection part refers to for selection of a speaker.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

<System-wide configuration>
FIG. 1 is a diagram showing a configuration example of a conversation support system 1 according to the embodiment.
The conversation support system 1 shown in FIG. 1 uses the character estimation device 2 for estimating the tendency on the character of each of a plurality of natural persons (hereinafter referred to as "the target person") and the information on the tendency on the character. A conversation support device 3 for supporting a conversation and a cloud network 4 for connecting the character estimation device 2 and the conversation support device 3 are provided.
The conversation support system 1 is an example of an information processing system.
In the example of FIG. 1, although the character estimation apparatus 2 and the speech assistance apparatus 3 are represented as another apparatus, you may be comprised as one apparatus.
The whole or a part of the character estimation device 2 and the conversation support device 3 in the present embodiment is configured as a computer, and realizes various functions through the execution of a program.

<Configuration of Character Estimator>
The character estimation device 2 has a character tendency diagnosis unit 10 that diagnoses the tendency of the character on the individual, and a character tendency database 20 that stores the result of the diagnosis in association with the individual.
The character estimation device 2 here functions as a server of the conversation support system 1.
The personality tendency diagnostic unit 10 diagnoses or estimates the personality tendency of the individual who is the subject, for example, through execution of a diagnostic program. The personality tendency diagnostic unit 10 in the present embodiment diagnoses personality traits of the individual based on the handwriting of the individual. The result of the diagnosis by the personality tendency diagnostic unit 10 is stored in the personality tendency database 20.
The personality tendency database 20 is configured by, for example, a hard disk drive, and is connected to the cloud network 4. The personality tendency stored in the personality tendency database 20 is referred to by the conversation support device 3.

FIG. 2 is a diagram showing a configuration example of the personality tendency diagnosis unit 10. As shown in FIG.
The personality tendency diagnostic unit 10 in the present embodiment takes an image capturing unit 11 that captures an image of a document D in which a target person writes a character by handwriting, and a handwriting type classification unit 12 that classifies the type of handwriting appearing in the character from the image. And a handwriting feature database 13 in which the relationship between the classification of handwriting types and the tendency of personality corresponding to each classification is associated, and the tendency of personality to estimate and output the tendency of personality of the subject from the classified result And an output unit 14.
In the document D, characters are described by kanji, hiragana, katakana, alpha bed and the like.

The image capturing unit 11 includes, for example, an imaging camera, a scanner, and a touch sensor with a pen pressure detection function. The image capturing unit 11 acquires information such as, for example, the shape of a character, the stroke order, the writing pressure, and the writing pressure. The information obtained depends on the device used. In the present embodiment, only the shape of characters is used.
The handwriting type classification unit 12 is configured by a computer, and classifies features appearing in characters into any of several predetermined handwriting types. This function is realized through the execution of a program. An example of the program is an artificial intelligence program. A deep learning program or a machine learning program may be used.
The handwriting type features are stored in the handwriting feature database 13.

An example of classification of handwriting types stored in the handwriting feature database 13 is shown in FIGS. 3-1 to 3-3.
FIGS. 3-1 is a figure which shows a part of classification | category which paid its attention to the 1 character 1 character feature. 3-2 is a figure which shows the remainder of the classification which paid its attention to the 1 character 1 character feature. FIG. 3-3 is a diagram illustrating classification based on chapter features.
The chapter method is the writing of characters as a set, and is classified, for example, according to how and where a character as a set is written at a specified position.

In the case of the present embodiment, 70 handwriting classifications are prepared in the handwriting feature database 13.
This handwriting type corresponds to items 1 to 70 in the “Illustration of 72 items of the handwriting feature manual” issued on March 27, 2001 by the Japanese Association of Writing Diagnosticians.
In the example of FIGS. 3-1 to 3-3, there are 50 classifications as one-character / one-character features (FIGS. 3-1 and 3-2) and 20 classifications as chapter-wise features (FIG. 3-3). It is shown.
For example, among the features of each character, the features of the touch-sensitive part are "touch-and-close type" in which the picture and the picture are properly attached and there is a place where writing is done without sticking between the picture and the picture. “Type”, “contact-type ambiguity type” where drawing and drawing are attached and separated, and “top opening and closing type” where drawing and drawing are open at the top and closed at the bottom, Between the drawing and the drawing, the upper opening and the lower opening also open, the upper cutting and the lower cutting open, and the blade cutting type that intersects to cut other drawing lines. It is classified into "abnormal touch-on type" to cut.
In the example of the figure, a column 13B of 70 classifications, a column 13C for explaining the features corresponding to each classification, and a column 13D for explaining the characteristics of the tendency of the personality associated with each classification are provided.

As shown in the column 13D, although a plurality of tendencies are assigned to one classification, in the present embodiment, one representative tendency is selected from them from the viewpoint of processing, and a broad classification of the personality tendency is made. Is used as the column 13E.
For example, the character tendency of a person who is recognized as "touch-and-close type" includes not only seriousness but also multi-facetedness such as determination and difficulty in deciding things, but in the present embodiment, "Science" is used as a representative trend.
In this embodiment, any of 70 categories of “seriousness”, “compromise”, “indecisive”, “aggressive”, “confused”, “creative” tendencies. Assign
The tendency described in the column 13E is an initial value, and may change to a different tendency when different evaluations are made by learning such as artificial intelligence (AI), deep learning, machine learning, and the like.

Here, the handwriting type classification unit 12 recognizes each character described on the document D by image processing for the document D acquired from the image acquiring unit 11 as pre-processing.
After recognition of the character, the handwriting type classification unit 12 determines a part of the characters having a large difference between the recognized characters and the shape of the corresponding standard (basic) character (that is, the characteristic of the handwriting is large). The classification is determined by performing a comparison with the classification features.
The handwriting type classification unit 12 may give all of the determined classifications to the personality tendency output unit 14 or the frequency of appearance among a plurality of classifications or a plurality of classifications that appear with a frequency equal to or higher than a predetermined threshold. May selectively provide the personality tendency output unit 14 with more classifications than other classifications.

The personality tendency output unit 14 reads the personality tendency corresponding to the determined classification from the handwriting feature database 13 and outputs it.
In this example, it is assumed that, for example, those who are classified as "touch-open type" have a tendency of being serious, innocent, hard to accept, etc. The relationship between the individual classifications stored in the handwriting feature database 13 and the tendency of personality changes by learning of the artificial intelligence program.
When a plurality of classifications are detected for the handwriting of the same person, the personality tendency output unit 14 in the present embodiment outputs each tendency on the character corresponding to these classifications as the tendency of the subject person.
However, one character may be output for one subject in accordance with a predetermined rule. For example, among the six typical trends ("serious", "with compromise", "indecisive", "aggressive", "confused", "creative") appear with a frequency greater than a predetermined threshold Among the plurality of tendencies and the plurality of tendencies determined, the frequency of appearance may be output as the tendency on the character as compared with other classifications.

  In the case of the present embodiment, the personality tendency (characteristic tendency data) of each individual is determined through the execution of a program (including an artificial intelligence program etc.) and recorded in the personality tendency database 20, The diagnosis of the personality tendency itself may be performed by an expert who is a natural person. In this case, the result of the diagnosis by the expert is recorded in the personality tendency database 20.

<Configuration of Conversation Support Device>
It returns to the explanation of FIG.
The conversation support device 3 uses the biological information sensor 30 for measuring in real time various physiological or anatomical information (hereinafter referred to as “biological information”) emitted from the body of the object person, and the object person using the biological information. A character tendency correction unit 40 for correcting a character tendency (character tendency data) of a character, and a conversation support unit 50 for supporting a conversation based on the character tendency after correction and the state of mind and body estimated from biological information have.

The conversation support device 3 here is an example of an information processing device.
The conversation support device 3 functions as a terminal device on the conversation support system 1. The conversation support device 3 adopts, for example, a form such as a computer, a smartphone, a conversation robot, or a server.
In the case of the present embodiment, the biological information sensor 30 is configured by a plurality of types of sensors built in a device worn by a participant. The biological information sensor 30 may be a sensor or a sensor group that measures biological information in a non-contact manner.

Specifically, it comprises a body temperature sensor 31 for measuring a body temperature, a pulse sensor 32 for measuring a pulse, and an electroencephalogram sensor 33 for measuring an electroencephalogram.
In addition, these sensors are an example and it is not necessary to use all the sensors. Further, as sensors (not shown), a part of the line-of-sight sensor for detecting the line of sight, the voice sensor for detecting characteristics appearing in the voice, the posture sensor for detecting posture, the motion sensor for detecting motion, and the blood pressure sensor for measuring blood pressure Or you may use all.
Each sensor measures biological information at least before the start of conversation, and sequentially measures biological information at a predetermined timing or cycle even after the start of conversation. This is because biological information may change to such an extent that it affects the state of mind and body also during conversation.

The personality tendency correction unit 40 functions as an information processing apparatus that corrects the personality tendency estimated in advance for the participants of the conference according to the current state of mind and body, for example, through execution of a correction program.
In the present embodiment, the term "prior" is used in the sense of a point in time before the point of utilizing the tendency in personality. However, the correction by the character tendency correction unit 40 is a change between the state of mind and body at the time when the tendency on the character is estimated by the character estimation device 2 and the state of mind and body at the time of using the information on the tendency of the character. The effect of the correction in the present embodiment can be expected by utilizing it in the case where it is foreseen.

The personality tendency correction unit 40 is an example of correction means in the claims, and is also an example of an information processing apparatus.
FIG. 4 is a view showing a configuration example of the personality tendency correction unit 40. As shown in FIG.
The personality tendency correction unit 40 estimates the state of mind and body, which estimates the state of mind and body based on the biological information (body temperature, pulse, brain wave), and the subject person estimated in advance based on the estimated state of mind and body. And a correction unit 42 for correcting the tendency of the character.

The physical and mental state estimation unit 41 calculates, for example, the difference value between the measurement value and the average value for body temperature, and based on whether the calculated difference value is larger than a threshold (for example, ± 1 ° C.), presence or absence of abnormality Determine If the difference value exceeds the threshold, it is determined that the physical condition is abnormal (not healthy).
Since the average value of the body temperature differs depending on the race, age, gender, measurement site, etc., an average value according to the subject or the measurement site is adopted. Desirably, the average temperature of the subject individual is obtained in advance and used.
In the case of Japanese, the average value of the body temperature of more than 3,000 healthy men and women around 10 to 50 is 36.89 ° C. ± 0.34 ° C. (measured under armpit).

For example, with regard to the pulse, the physical and mental state estimation unit 41 determines the presence or absence of an abnormality based on whether or not the measured value is within the normal range. When the measured value exceeds the normal range, it is called tachycardia, and when the measured value is lower than the normal range, it is called bradycardia. A combination of tachycardia and bradycardia is called an arrhythmia. If it is determined to be an arrhythmia, it is determined that the physical condition is abnormal (not healthy).
Since the normal range of the pulse differs depending on the race, age, etc., the normal range according to the subject is adopted.
The pulse is also biological information in which individual differences tend to appear. Therefore, it is not necessary to use the general range. Preferably, the resting pulse range obtained for the subject individual is used.
In the case of Japanese, the normal range of children and elementary school students is 70 to 110 times / minute, the normal range of junior high school students, high school students, college students and adults is 60 to 100 times / minute, and the normal range of elderly people is 60 to 80 Times per minute.
In this embodiment, a state in which the pulse is faster than a predetermined threshold within the normal range or a state in which the pulse is faster than the normal range is determined as tension or stressed state, and the pulse is greater than the predetermined threshold even in the normal range. Determines the slow state as the calm (relaxed) state. The threshold value for determination within the normal range shall be given in advance.

For example, with regard to an electroencephalogram, the mind / body state estimation unit 41 determines whether the measurement waveform is a γ wave, a β wave, an α wave, a θ wave, or a δ wave.
The γ wave is a waveform having a frequency of 30 Hz or more, and is said to appear in a strong anxiety or excited state.
The beta wave is a waveform having a frequency of 30 to 14 hertz, and is said to appear under tension or under stress.
The alpha wave is a waveform having a frequency of 13 to 8 Hz, and is said to appear in a calm (relaxed) state or in a state in which the eyes are closed.
The θ wave is a waveform having a frequency of 7 to 4 Hz, and is said to appear during deep relaxation or sleep.
The δ wave is a waveform having a frequency of 3.5 Hz or less, and is said to appear at the time of deep sleep and coma.
The mind-body state estimation unit 41 estimates the present mind-body state of the participant using the determination table 41A shown in FIG.
The function of the mind-body state estimation unit 41 is realized through the execution of a program. Examples of programs include artificial intelligence programs, deep learning programs, and machine learning programs.

FIG. 5 is a diagram showing an example of the correspondence between the biological information and the state of mind and body.
In the determination table 41A, the relationship between the biological information 410 (body temperature, pulse, brain waves) and the state of mind and body (physical condition 411, concentration 412, relaxation / rest 413, sleepiness 414, anxiety 415, excitement 416, tension / stress 417). An example is recorded.
Among them, the physical abnormality 411 is a form of physical condition, and concentration 412, relaxation / rest 413, sleepiness 414, anxiety 415, excitement 416, and tension / stress 417 are forms of psychological state.

The determination table 41A indicates that, for example, it is determined that the physical condition 411 is abnormal if any of the body temperature and the pulse is abnormal.
The determination table 41A indicates that it is determined to be relaxation / rest 413 when the pulse is slow in the normal range or when an α wave appears in the brain wave.
The determination table 41A indicates that it is determined as tension / stress 417 when the pulse speed is high in the normal range or when the β wave appears in the electroencephalogram. In addition, when the pulse exceeds the normal range, it is determined as tension / stress 417.
The determination table 41A indicates that, for example, concentration α 412 is determined when an α wave appears in the brain wave.
The determination table 41A indicates that it is determined that the sleepiness 414 is felt when δ waves or θ waves appear in the brain waves.
The determination table 41A indicates that it is determined that anxiousness 415 or excitement 416 is felt when γ waves appear in the brain waves.

It returns to the explanation of FIG.
The correction unit 42 refers to the correction table 42A (see FIG. 6) based on the estimated physical and mental state, and corrects the tendency (character tendency data) on the character estimated in advance.
FIG. 6 is a diagram showing a configuration example of the correction table 42A. The correction table 42A shows the relationship among the six representative (large class) personality tendency changes (here, correction) depending on the state of mind and body.
In FIG. 6, the weakening of the tendency is indicated by a minus sign (-), the strengthening of the tendency is indicated by a plus sign (+), and the absence of any action is indicated by a blank.

Here, the major classification 420 of the character tendency to be corrected is “serious”, “compromise”, “indecisive”, “aggressive”, “confused”, “creative”.
For example, when physical condition abnormality (physical condition abnormality 421) is estimated from biological information, when the state of sleepiness 424, anxiety 425, excitement 426, tension / stress 427 is estimated, the tendency with "serious" is weakened Corrected in the direction.
For example, when the state of concentration 422 and the state of relaxation / rest 423 are estimated from biological information, correction is made so as to intensify the tendency to "score".

In addition, the state of mind and body does not act uniformly on all trends. That is, it does not uniformly strengthen or weaken all trends.
For example, in the case of concentration 422 and relaxation / rest 423, it acts to intensify the tendency of “compromise”, “active” and “creative”, but to the tendency of “decision” and “confusion”. There is no effect of
Similarly, in the case of anxiety 425, it acts to weaken the five tendencies except “creative” but does not affect “creative”.
In the case of tension and stress 427, it acts to weaken the tendency of “seriousness,” “indecisiveness,” and “creative”, but to “compromise,” “aggressive,” and “confusion”. There is no impact.
In the case of the excitement 426, the operation is different from the other states. That is, in the case of excitement 426, while acting in the direction of weakening the tendency of “seriousness”, “with compromise” and “confusion”, it acts in the direction of strengthening the tendency of “active” and “creative” . However, in the case of excitement 426, it does not act on the tendency of "indecision".

Here, how to use “strong” and “weak” which are correction information varies depending on the structure of data processing.
For example, when the tendency on the character can be expressed in multiple stages, it is used to change the stage of the tendency (character tendency data) estimated in advance.
Further, depending on the contents of the process executed in the subsequent stage (for example, the conversation support unit 50 (see FIG. 1)), the correction information is output as attached information of the tendency of the character estimated in advance.
In the present embodiment, information on the tendency of personality on which attached information is added is referred to as personality trend data after correction.
In any case, by correcting the tendency on the character that was estimated at a time different from the time of use according to the physical and mental state at the time of use, it is possible to support conversations that accurately reflect the tendency on the character at the time of use Becomes possible.

In FIG. 6, priorities are set between the physical and mental states. This priority is used to determine how to make corrections when multiple states are estimated as physical and mental states.
In the case of the present embodiment, in order from the highest priority, the physical condition is 421, sleepiness 424, excitement 426, concentration 422, relaxation / rest 423, tension / stress 427.
For this reason, in the case where two physical and physical states, physical condition and excitement, are estimated for a person with "positive" tendency in personality, correction with priority given to physical condition 421 is executed. That is, correction that weakens the tendency of "positive" is performed, and correction that does not strengthen is performed. The same is true for "creative".
In addition, when two mental and physical states of relaxation and drowsiness are estimated for a person whose personality tendency is "active", a drowsiness-first correction is performed. That is, correction that weakens the tendency of "positive" is performed, and correction that does not strengthen is performed.
The function of the correction unit 42 here is realized through the execution of a program. Examples of programs include artificial intelligence programs, deep learning programs, and machine learning programs.

It returns to the explanation of FIG.
The conversation support unit 50 executes processing for supporting a conversation based on the information on the corrected personality tendency and the state of mind and body.
FIG. 7 is a diagram showing a configuration example of the conversation support unit 50 used in the present embodiment.
The conversation support unit 50 shown in FIG. 7 has a speaker selection unit 51 that selects a speaker who is mainly asked to speak in a conversation.
Here, the speaker selection unit 51 executes a function of selecting a speaker who is urged to speak using information such as the state of mind and body, the purpose of conversation, and the current topic, as well as the tendency of the character after correction.
The purpose of the conversation and current topics include, for example, derivation of conclusions (including solution derivation), sharing of information, idea creation, problem finding, situationalization, topic convergence, conversational activation, etc. . These goals are given in advance by a person (e.g. a presenter, one of the subjects) or in the middle of a conversation.
Given information on the purpose of the conversation and the current topic, it is possible to select a desirable target person for the purpose of the conversation and the current topic.

FIG. 8 is a diagram showing an example of a table 51A which the speaker selection unit 51 refers to for selection of a speaker.
In the table 51A, the state of the speaker's mental state where a speech is desired for realization of the phase break 511, the conclusion derivation 512, the idea out 513, the convergence 514, and the activation 515 which are examples of the purpose of conversation and the current topic. An example of 510 is described.
In the case of the table 51A shown in FIG. 8, with regard to the phase break 511, the idea extraction 513, and the activation 515, the speech of a person whose mental state is "concentration" is urged. In addition, with regard to conclusion derivation 512 and convergence 514, the utterance of a person whose mental state is "relax" is prompted.

The speaker selection unit 51 (see FIG. 7) selects a speaker based on the table 51A, the correction table 42A (see FIG. 6), the tendency of the character after correction, and the state of mind and body.
More specifically, the speaker selection unit 51 first refers to the table 51A according to the given topic to obtain information on the state of the psychology prompting to speak, and then the speakers of a plurality of persons to be selected Choose a person who is in a mental state that encourages them to speak.
Furthermore, in the case of this embodiment, the speaker selection unit 51 refers to the correction table 42A, and prioritizes a person having a tendency in personality to be intensified by the state of a specific mental state and selects it as a speaker to urge speech. Do.

For example, when the criterion for selecting a speaker is the conclusion derivation 512, the speaker selection unit 51 focuses on the person who is in a relaxed state from the table 51A, and the character tendency is further intensified by the relaxed state. Choose a speaker who has a tendency ("serious", "compromise", "aggressive", "creative").
When there are a plurality of corresponding persons, a speaker is selected in accordance with predetermined conditions. The selection here may be, for example, all of the corresponding persons or a selection of some persons. In addition, when there is no person who satisfies the tendency of personality, the person in the state of relaxation may be given priority.
Information of the selected speaker may be output through a speaker or the like, or may be provided as information for support to the presenter or a person who controls the progress of the conversation.
The function of the speaker selection unit 51 is realized through the execution of a program. Examples of programs include artificial intelligence programs, deep learning programs, and machine learning programs.

<Effect of the embodiment>
By using the conversation support system 1 according to the present embodiment, it is possible to correct the tendency of the character who has been estimated in advance for the target person participating in the conversation according to the current state of mind and body. For example, even if a serious person is in a poor physical condition, the original seriousness and aggressiveness may be weakened. In addition, in the state of concentration, it is expected to expect more positive reactions and actions.

As described above, by utilizing the character tendency after correction, information that accurately reflects the character tendency at the time of use can be used for various processes, not at the time of prior estimation.
In the present embodiment, it is used for speaker selection as an example of various processing operations.
By selecting the speaker based on the personality tendency corrected according to the physical and mental state at the time of execution of the conversation, the conversation performed between the participants of the conversation can be enhanced.
Further, by providing the information of the selection by the conversation support unit 50 to the target person, it is possible to give an awareness for enhancing the quality of the conversation.
By prompting the target person's speech according to the purpose of the conversation and the current topic, it is expected to improve the quality of the conversation.

<Other Embodiments>
As mentioned above, although embodiment of this invention was described, the technical scope of this invention is not limited to the range as described in embodiment mentioned above. It is also apparent from the scope of the claims that the embodiments described above with various changes or improvements are included in the technical scope of the present invention.

For example, in the above-mentioned embodiment, although the character tendency after correction is used for supporting conversations with a plurality of people, the application using the character tendency after correction is not limited to this. For example, it may be used to predict the reaction or behavior of the subject. Moreover, you may use for the selection of how to talk according to an object person, and the selection of a topic.
Although the case where the tendency in personality is weakened by the physical condition was explained in the explanation of the above-mentioned embodiment, when it is judged that the physical condition is good (for example, in the case of satisfying the predetermined temperature and pulse conditions) The personality tendency may be strengthened.

DESCRIPTION OF SYMBOLS 1 ... Conversation support system, 2 ... Character estimation apparatus, 3 ... Conversation support apparatus, 4 ... Cloud network, 10 ... Personality tendency diagnostic part, 11 ... Image taking part, 12 ... Writing type classification part, 13 ... Writing feature database, 14 ... personality tendency output unit, 20 ... personality tendency database, 30 ... living body information sensor, 31 ... body temperature sensor, 32 ... pulse sensor, 33 ... brain wave sensor, 40 ... personality tendency correction unit, 41 ... mind-body condition estimation unit, 42 ... correction unit, 50 ... conversation support unit, 51 ... speaker selection unit

Claims (13)

An information processing apparatus, comprising: a correction unit configured to correct a tendency of a character estimated in advance for a subject based on current biometric information of the subject.   The information processing apparatus according to claim 1, wherein the current biological information is information at a time point of utilizing the tendency on the character.   The information processing apparatus according to claim 2, wherein the biological information is sequentially acquired.   The information processing apparatus according to claim 1, wherein the correction unit corrects the tendency of the character based on one or both of the physical condition and the mental state of the subject estimated from the biological information.   5. The information processing apparatus according to claim 4, wherein said correction means corrects to strengthen or weaken said personality tendency according to said physical condition.   5. The information processing apparatus according to claim 4, wherein the correction means corrects or weakens the tendency of the character to strengthen or weaken depending on the state of the mind.   7. The information processing apparatus according to claim 6, wherein said correction means strengthens a part of the tendency in the character and weakens another part of the tendency when the state of the mind is excited.   The information processing apparatus according to claim 1, wherein the tendency on the character is estimated based on a feature appearing in the handwriting of the subject.   The information processing apparatus according to claim 8, wherein the estimation based on the features appearing in the handwriting is performed using artificial intelligence.   The information processing apparatus according to claim 1, wherein the correction unit is configured using artificial intelligence.   The information processing apparatus according to claim 1, wherein a speaker is selected based on the corrected tendency of the character and the condition or physical condition of the subject. An information processing system, comprising: a correction unit configured to correct a tendency of a character estimated in advance for a subject based on current biometric information of the subject. Computer,
A program that functions as a correction unit that corrects a tendency in personality estimated in advance for a subject based on the current biological information of the subject.

Images