JP2021012660A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To achieve discriminating output of information according to a temporary change of characteristics.SOLUTION: An information processing device comprises a determination unit and a control unit. The determination unit determines whether first characteristics, which are characteristics of a user during a first period and estimated on the basis of first user information, which is user information of the user acquired during the first period, have changed. The control unit controls information distributed to the user according to the post-change characteristics which have changed from the first characteristics when the determination unit determines that the first characteristics have changed.SELECTED DRAWING: Figure 5

Description

Embodiments of the present invention relate to information processing devices, information processing methods and information processing programs.

Conventionally, a technique of changing the response of an agent according to the personality of a user has been known. For example, Patent Document 1 discloses a technique of determining a user's personality from a response result of a user input by a microphone and changing the personality of an agent according to the user's personality.

JP-A-2010-224622

However, with the above-mentioned conventional technique, it is not always possible to separate information according to a temporary change in personality. For example, since a person's personality contributes to the formation of that person's humanity, it can be interpreted as a uniform one that does not change in the long term. On the other hand, a person's personality may change temporarily depending on the surrounding situation, such as while talking or driving. For example, a person who is usually cheerful and open may temporarily change to a mentally unstable personality when he or she remembers an unpleasant event in a conversation.

In the above-mentioned prior art, the personality of the user is discriminated from the answer result of the user input by the microphone, and the discriminated personality is defined as the fixed personality of this user. For example, whether or not this personality has changed temporarily. Etc. are not discriminated. For this reason, the above-mentioned conventional technique cannot realize the distribution of information according to a temporary change in personality.

The present application has been made in view of the above, and an object of the present application is to provide an information processing device, an information processing method, and an information processing program capable of realizing information processing according to a temporary change in personality. And.

The information processing apparatus according to the present application is the personality of the user estimated based on the first user information which is the user information of the user acquired in the first period, and is the personality of the user in the first period. A determination unit that determines whether or not a change has occurred in the first personality, and if it is determined that a change has occurred in the first personality, the changed personality changed from the first personality. Correspondingly, it is characterized by having a control unit that controls information provided to the user.

According to one aspect of the embodiment, it is possible to realize the distribution of information according to a temporary change in personality.

FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 2 is a diagram showing an example (1) of the determination process according to the embodiment. FIG. 3 is a diagram showing an example (2) of the determination process according to the embodiment. FIG. 4 is a diagram showing a configuration example of the information processing system according to the embodiment. FIG. 5 is a diagram showing a configuration example of the information processing device according to the embodiment. FIG. 6 is a flowchart showing an information processing procedure for information processing according to the embodiment. FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, an information processing apparatus, an information processing method, and a mode for carrying out an information processing program (hereinafter, referred to as “the embodiment”) according to the present application will be described with reference to the drawings. Note that this embodiment does not limit the information processing apparatus, information processing method, and information processing program according to the present application. Further, in the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. An example of information processing]
An example of information processing according to the embodiment will be described with reference to FIG. Further, when an example of information processing according to the embodiment will be described in more detail, FIGS. 2 and 3 will be used as appropriate. FIG. 1 is a diagram showing an example of information processing according to an embodiment. The information processing according to the embodiment is performed by the information processing device 100 shown in FIG. Before explaining an example of information processing according to the embodiment with reference to FIG. 1, first, an outline of information processing according to the embodiment will be shown.

First, the information processing system according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As shown in FIG. 4, the information processing system 1 according to the embodiment includes a terminal device 10, an external device 30, and an information processing device 100. The terminal device 10, the external device 30, and the information processing device 100 are connected by wire or wirelessly via a network N so as to be communicable. The information processing system 1 shown in FIG. 4 may include a plurality of terminal devices 10, a plurality of external devices 30, and a plurality of information processing devices 100.

The terminal device 10 is an information processing device used by the user. The terminal device 10 is, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The terminal device 10 executes various information processing according to the user's actions on the Internet. For example, the terminal device 10 enables a user to browse by displaying various contents on a display screen. Further, for example, the terminal device 10 realizes a purchasing behavior by a user by displaying various product information on a display screen. Of course, user behavior on the Internet is not limited to browsing behavior and purchasing behavior. For example, actions on the Internet include input actions of sentences posted to a predetermined SNS site.

The dialogue agent system 20 is a dialogue robot that realizes a dialogue with a user. The dialogue agent system 20 may be a stationary terminal device, or may be realized as an application, for example, in the terminal device 10. Further, the dialogue agent system 20 may be realized as a car navigation system that guides directions while interacting with the user. In the present embodiment, it is assumed that the terminal device is installed indoors as a stationary terminal device. Further, in the following, the dialogue agent system 20 may be abbreviated as "dialogue system 20".

Further, for example, it is assumed that the information processing device 100 acquires utterance information indicating the utterance of the user as an utterance history for each user via the dialogue system 20. The information processing device 100 may acquire the utterance information directly from the dialogue system 20, or may access and acquire the utterance information if the utterance information is stored in the predetermined server device. ..

The external device 30 is a server device that provides various services. For example, there are as many external devices 30 as there are services, but in the present embodiment, it is assumed that one external device 30 provides various services for the sake of simplicity. For example, the external device 30 provides a portal site in which article contents such as news articles are displayed in a list. Further, the external device 30 provides various services such as a shopping service, an auction service, a search service, an information sharing service, and a video distribution service. In addition, advertising content is displayed on the pages corresponding to these services as appropriate. Further, it is assumed that the business operator that manages the external device 30 and the information processing device 100 described later is the same. Therefore, the above-mentioned various services can be rephrased as services operated by such a business operator.

Here, the premise for performing information processing according to the embodiment will be described. For example, since a person's personality contributes to the formation of that person's humanity, it can be interpreted as a uniform one that does not change in the long term. On the other hand, a person's personality may change temporarily depending on the surrounding situation, such as while talking or driving. For example, a person who is usually cheerful and open may temporarily change to a mentally unstable personality when he or she remembers an unpleasant event in a conversation. In such a case, the user may be more offended if a response message that seems to encourage this unpleasant event is output or if the content related to this unpleasant event is delivered.

On the other hand, if the personality changes temporarily, it is considered that the user's satisfaction will be high if the change can be dealt with. For example, if the personality is changed to a mentally unstable personality and a response message in a manner of returning to the original open personality is output, the user's satisfaction is high. In addition, if the character has changed to a mentally unstable personality, for example, if content related to a healing spot or a calm place is delivered, such content can become useful content for the user in the future.

I will also touch on the "personality" of the user. The "personality" referred to in the present embodiment is different from the mere attribute information of the user such as preference. In other words, personality is the basis for forming the human nature of the user, and is the tendency of motivation and behavior based on the innate tendency. Therefore, in the long run, the personality can be understood as uniform.

Based on the above premise, the information processing apparatus 100 according to the embodiment performs the following information processing. Specifically, the information processing device 100 is the personality of the user estimated based on the first user information, which is the user information of the user acquired in the first period, and is the personality of the user in the first period. It is determined whether or not a change has occurred in the first personality. Then, when it is determined that the first personality has changed, the information processing device 100 controls the information provided to the user according to the changed personality changed from the first personality.

For example, the information processing apparatus 100 has a second user information, which is user information of a user acquired in a second period, which is a period shorter than the first period and corresponds to the current passage of time, and a second user information. Based on the change in information with the first personality, it is determined whether or not the first personality has changed. More specifically, the information processing apparatus 100 has, as the second period, the second user information acquired in the second period in which the start point and the end point of the period change so as to follow the passage of time, and the first Based on the change in information with the personality of, it is determined whether or not the first personality has changed. For example, in the information processing device 100, each time the second period changes with the passage of time, the information between the second user information acquired in the second period after the change and the first character Based on the change in, it is determined whether or not a change has occurred in the first personality.

Then, when it is determined that the first personality has changed, the information processing device 100 controls the response regarding the response of the dialogue system 20 to the user's utterance input according to the changed personality. In addition, the information processing apparatus 100 controls the content distribution when it is determined that the first character has changed.

The first period does not mean a short period such as a few seconds or a few minutes, but a grouped period (long term) of at least one week, for example. As will be described later, the information processing apparatus 100 estimates the first personality, which is the personality of the user in the first period, by using the user information (first user information) during the first period. .. As described above, the first personality estimated by the information processing apparatus 100 using the first user information for a long period of time is the personality that is the basis for forming the human nature of the user, and is a long-term personality. It shows a uniform personality that does not change when viewed in. On the other hand, the second period is shorter than the first period, and refers to a short period of several seconds or minutes, for example. Basically, the user lives in the state of the first personality, but when viewed in the short period of the second period, the user temporarily changes from the first personality to the second personality. The information processing apparatus 100 detects this change. Further, in the following embodiment, the first period is assumed to be a predetermined one month in the past.

From here, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of information processing according to an embodiment. In FIG. 1, an example of information processing according to the embodiment will be described step by step. Further, the storage unit included in the information processing apparatus 100 will be described as appropriate.

First, the information processing device 100 performs an estimation process for estimating the personality of the sample user (step S11). The sample user is a user whose information is used to generate the model and correct answer data described later. Further, in the following, the sample user may be referred to as "S user".

For example, the information processing device 100 diagnoses the personality of each S user (diagnoses which personality characteristic each S user has) by a predetermined personality diagnosis method, and stores the diagnosis result in the diagnosis result storage unit 121. For example, the information processing device 100 calculates a score for each of five personality traits such as openness, seriousness, extroversion, cooperation, and mental stability by using a personality diagnosis method called Big5, and the calculated score. Based on, it is possible to diagnose which personality trait each S user best fits into. For example, if the information processing apparatus 100 obtains the highest score in openness as a result of performing Big5 for user U1 among S users, user U1 obtains a diagnosis result that the personality characteristic is "open". In other words, the information processing apparatus 100 obtains a diagnosis result that the user U1 has an open personality (a highly open personality).

The information processing device 100 calculates scores of personality traits such as "severity", "kindness", "calmness", "freedom", and "obedience" by a personality diagnosis method called ecogram. Then, based on the calculated score, each S user may diagnose which personality trait is most applicable. In addition, the information processing device 100 calculates scores of personality traits such as "others'negativeness", "others'affirmation", "self-denial", and "self-affirmation" by a personality diagnosis method called OKgram. , Based on the calculated score, each S user may diagnose which personality trait is most applicable.

Further, such a personality diagnosis result may be, for example, information obtained by asking each S user some questions in advance and based on the answers to the questions. Further, such a personality diagnosis result may be estimated from the usage history of various services provided to the S user, such as a fortune-telling site or a matchmaking site. In the present embodiment, the personality diagnosis result based on Big5 will be described as an example.

The diagnosis result storage unit 121 stores the personality diagnosis result obtained by the personality diagnosis for each S user. In the example of FIG. 1, the diagnosis result storage unit 121 has items such as "personality characteristic" and "user ID". "Personality trait" indicates a candidate for the personality trait obtained from the diagnosis result in Big5. There are five items in "personality traits" such as openness, seriousness, extroversion, cooperation, and mental instability. The "user ID" indicates identification information that identifies an S user belonging to the corresponding "personality characteristic".

In the example of the diagnosis result storage unit 121 shown in FIG. 1, the user IDs “U1, U3, U5” and the like are associated with the personality characteristic “open”. Such an example shows that the information processing apparatus 100 has obtained the diagnosis result that the personality characteristic is "open" to the user U1, the user U3, and the user U5 by the Big5. That is, the users U1, U3, and U5 indicate that the diagnosis result of "open personality" has been obtained.

Next, the information processing device 100 distributes (associates) an action history indicating the behavior of each S user belonging to the personality characteristic in the first period (long-term) for each personality characteristic, and analyzes the result of the distribution. It is stored in the storage unit 122 (step S12). For example, the information processing device 100 distributes an utterance history indicating an utterance made by an S user belonging to the personality trait in the first period for each personality trait. Further, for example, the information processing apparatus 100 distributes an action history indicating various actions on the net performed by an S user belonging to the personality trait in the first period for each personality trait. This point will be described with reference to the example of the analysis result storage unit 122 shown in FIG.

The analysis result storage unit 122 further stores information on the analysis result in which the relationship between the personality trait and the action performed by the S user of the personality trait is analyzed, and the analysis process is described in detail in step S13. explain.

In the example of FIG. 1, the analysis result storage unit 122 has items such as "personality characteristic", "speech history", "behavior history", "speech tendency", and "behavioral tendency". The “speech tendency” and the “behavioral tendency” will be described in conjunction with the contents of step S13. “Personality trait” indicates a candidate for the personality trait obtained from the diagnosis result in the personality diagnosis with Big5. The "utterance history" indicates the history of utterance information indicating the utterance of the S user of each personality trait in the first period, which is a predetermined one month in the past. In the analysis result storage unit 122 shown in FIG. 1, the information processing device 100 distributes TK11, TK12, TK13, etc. to the "utterance history" corresponding to the personality characteristic "open". Such an example shows an example in which an open personality user makes an utterance indicated by TK11, TK12, TK13, or the like. In the example of FIG. 1, it is shown by a conceptual symbol such as TK11, but in reality, for example, a text indicating the utterance content is input.

The "behavior history" indicates the history of behavior information indicating the behavior of the S user of each personality trait on the Internet in the first period, which is a predetermined one month in the past. Actions on the Internet include, but are not limited to, content browsing history, search history, purchase history, and the like. Further, for example, assuming that the "action history" is the "browsing history", the "browsing history" is the history information indicating what kind of content the S user of each character characteristic has browsed, that is, the browsed article content. It is a browsing history including a URL, a character string (text) of a heading sentence and a detailed sentence of the browsed article content. In the analysis result storage unit 122 shown in FIG. 1, the information processing device 100 distributes AcDA11, AcDA32, AcDA43, and the like to the "behavior history" corresponding to the personality characteristic "open". Such an example shows an example in which a user having an open personality browses the contents represented by AcDA11, AcDA32, AcDA43, and the like.

Next, the information processing apparatus 100 analyzes the relationship between the personality trait and the behavior of the S user belonging to the personality trait (step S13). For example, the information processing apparatus 100 has a behavioral tendency of a sample user belonging to the personality trait in the first period based on the history information (utterance history, action history) for each personality trait stored in the analysis result storage unit 122. To analyze. For example, in the information processing device 100, based on the history information, what kind of words the S user of the personality trait tends to say (speaking tendency), and what kind of behavior (browsing, searching) , Purchase, etc.) Analyze whether there is a tendency (behavioral tendency). Then, the information processing apparatus 100 stores the information indicating the "speech tendency" and the information indicating the "behavioral tendency" obtained as the analysis result in the analysis result storage unit 122.

Here, the utterance tendency may be a word or expression that frequently appears in the utterance information of the S user having the corresponding personality trait, that is, a characteristic word. In order to extract such a feature word, the information processing apparatus 100 can perform an analysis process using an index called mutual information amount in step S13. For example, the information processing apparatus 100 calculates the amount of mutual information between the words included in the utterance information and the personality characteristics of the S user who input the utterance information, and the calculated mutual information amount is a predetermined value or more. Is classified as a characteristic word according to the personality trait. For example, the information processing device 100 extracts a character string such as a word or a frequently occurring expression from the utterance information, and calculates the mutual information amount between the extracted character string and the personality trait. Then, the information processing apparatus 100 classifies (selects) a predetermined number of feature words as feature words according to their personality traits in order from the one with the highest mutual information amount value.

In addition, the information processing apparatus 100 uses the analysis result (classification result) in step S13 to determine the personality traits of an unknown user whose personality traits are unknown and for which no answer for Big5 has been obtained. A model for estimation can be generated, and the generated model can also be stored in the analysis result storage unit 122 as an analysis result.

For example, the information processing device 100 shows the personality trait of the unknown user when the utterance information of the unknown user is input by learning the relationship between the personality trait and the feature word corresponding to the personality trait. A model that outputs information can be generated. For example, the information processing apparatus 100 learns a model by using a technique such as back propagation so that when a feature word is input to the model, information indicating the personality characteristic corresponding to the feature word is output. Generate a model with. The information processing apparatus 100 may learn a model for each personality trait that outputs a score indicating the probability that the input feature word and the personality trait correspond to each other.

The behavioral tendency may also be a characteristic word. Specifically, the behavioral tendency may be a word or expression that frequently appears in the content viewed by the S user having the corresponding personality trait, that is, a characteristic word. Here, too, the information processing apparatus 100 can perform analysis processing using an index called mutual information amount. For example, the information processing device 100 calculates the amount of mutual information between the words included in the browsed content and the personality characteristics of the S user who browsed the content, and the calculated mutual information amount is equal to or greater than a predetermined value. Words are classified as characteristic words according to their personality traits. For example, the information processing device 100 extracts a character string such as a word or a frequently-used expression from the browsed content, and calculates the mutual information amount between the extracted character string and the personality trait. Then, the information processing apparatus 100 classifies (selects) a predetermined number of feature words as feature words according to their personality traits in order from the one with the highest mutual information amount value.

Further, when the behavior history (for example, browsing history) of an unknown user is input by the information processing device 100 by learning the relationship between the personality characteristic and the characteristic word corresponding to the personality characteristic, the unknown is unknown. It is possible to generate a model that outputs information indicating the personality characteristics of the user.

Then, in the analysis result storage unit 122 shown in FIG. 1, the information processing device 100 inputs W11 and W32 to, for example, the "utterance history" corresponding to the personality characteristic "open". Such an example shows an example in which a user having an open personality tends to make an utterance including a word represented by W11 or W32. Further, in the analysis result storage unit 122 shown in FIG. 1, the information processing device 100 inputs FE11 and FE32 to, for example, the “behavior history” corresponding to the personality characteristic “open”. Such an example shows an example in which a user having an open personality tends to take the behavior shown by FE11 or FE32. Furthermore, such an example shows an example in which a user having an open personality tends to browse contents including words indicated by FE11 and FE32.

Further, the analysis result stored in the analysis result storage unit 122 can be said to be correct answer data used for estimating the personality trait.

Next, the information processing apparatus 100 acquires action information (an example of the first user information) indicating the action performed by the user to be processed (for example, user Ux1) in the first period (step S14). For example, the information processing apparatus 100 acquires the first utterance information, which is the utterance information indicating the utterances made by the user Ux1 in the first period. The information processing device 100 may acquire the first action information indicating the action on the Internet performed by the user Ux1 in the first period. For example, the information processing device 100 can acquire the first user information from the external device 30. Further, the user Ux1 is an unknown user whose personality trait is unknown at the present time because the personality diagnosis such as Big5 has not been performed.

Next, the information processing apparatus 100 performs an estimation process for estimating the personality characteristics of the user Ux1 based on the behavior information acquired in step S14 and the analysis result stored in the analysis result storage unit 122 (step S15). .. For example, when the information processing apparatus 100 acquires the first utterance information as the first user information, the words included in the first utterance information and the utterance tendency stored in the analysis result storage unit 122 (for example, the feature). The personality trait of the user Ux1 is estimated by matching with the word). For example, the information processing apparatus 100 extracts a character string (word, expression, etc.) included in the text indicated by the first utterance information, which is used a predetermined number of times or more during the first period. Then, in the analysis result storage unit 122, the information processing device 100 sets the personality trait that matches or is associated with the extracted character string as the utterance tendency of the user Ux1 in the first period. It is defined as the first personality, which is a personality trait. Further, the information processing device 100 inputs the first utterance information to the model generated by the analysis of the utterance history, and the output personality characteristic is the personality characteristic of the user Ux1 in the first period. It may be defined as the character of 1.

Further, for example, when the information processing apparatus 100 acquires the first action information as the first user information, the user Ux1 is matched by matching the first action information with the action tendency stored in the analysis result storage unit 122. Character characteristics can be estimated. For example, the information processing apparatus 100 extracts action information indicating an action by performing the first action information a predetermined number of times or more during the first period from the actions. Then, the information processing device 100 sets the personality trait of the user Ux1 in the first period as the personality trait to which the behavior information behavior that matches or is associated with the extracted behavior information behavior is associated with the analysis result storage unit 122. It is defined as the first personality. Further, the information processing device 100 inputs the first action information to the model generated by the analysis of the action history, and the output personality characteristic is the personality characteristic of the user Ux1 in the first period. It may be defined as the character of 1.

In the example of FIG. 1, it is assumed that the information processing apparatus 100 estimates that the user Ux1 has the personality characteristic "open".

Next, the information processing apparatus 100 executes a determination process for determining whether or not the first character (open) of the user Ux1 estimated in step S15 has changed (step S16). For example, the information processing apparatus 100 sets a second period, which is shorter than the first period and in which the start point and the end point change so as to follow the current passage of time. Then, each time the set second period changes according to the lapse of the current time, the information processing device 100 receives the second utterance information (2nd utterance information) indicating the utterance made by the user Ux1 in the second period. Second user information) is acquired. In addition, the information processing device 100 determines whether or not a change has occurred in the first personality based on the change in the information between the information regarding the second utterance information and the first personality. There are two variations of such determination processing. Therefore, first, an example of one determination process is shown with reference to FIG. FIG. 2 is a diagram showing an example of the determination process according to the embodiment.

In the example of FIG. 2, the information processing apparatus 100 determines whether or not a change has occurred in the first personality based on the change in the information between the information regarding the second utterance information and the first personality. .. For example, the information processing apparatus 100 includes features of another personality different from the first personality in the second user information as a change of information between the information related to the second speech information and the first personality. It is determined whether or not the first personality has changed depending on whether or not the degree of inclusion of the indicated feature information is greater than a predetermined value. Hereinafter, this point will be described in detail with reference to FIG.

In the example of FIG. 2, since the dialogue is performed between the user Ux1 and the dialogue system 20, the second utterance information corresponds to the utterance information indicating the utterance made by the user Ux1 in this dialogue. In addition, the user Ux1 has the first character of being "open" in the long run. In such a state, when the information processing apparatus 100 detects that the dialogue has started between the user Ux1 and the dialogue system 20, the information processing device 100 has the current time at which the dialogue has started with respect to the time axis T at the present time. A second period SP0 with a time interval of X seconds (X = an arbitrary numerical value) starting from a certain time t0 is set.

Then, the information processing apparatus 100 acquires the second utterance information in the second period SP0, and corresponds to a character different from the first character "open" in the words included in the second utterance information. If a word is included, that word and personality traits are detected. For example, the information processing device 100 extracts a character string indicating a word or expression from the text corresponding to the second utterance information. Then, the information processing apparatus 100 compares the extracted character string with the utterance tendency (characteristic word) stored in the analysis result storage unit 122, and in the extracted character string, the character characteristic other than "open" is included. If there is a character string that is a characteristic word in the personality trait, the character string and the personality trait are detected. For example, if the extracted character string contains the character string W79, which is one of the characteristic words associated with the personality characteristic "mental instability", the information processing apparatus 100 uses the character string W79 and the personality characteristic "Mental instability". Detect "mental instability".

Next, the information processing apparatus 100 counts the number of character strings W79 (number of appearances or number of uses) in the second period SP0, and whether the cumulative total of the count results exceeds a predetermined value (for example, 3 times). Judge whether or not. For example, the information processing apparatus 100 counts the number of character strings W79 included in the second utterance information in the second period SP0, and whether or not the cumulative total of the counting results exceeds a predetermined value (for example, three times). Is determined. For example, if the counting result is less than 3 times, the information processing apparatus 100 determines that there is no change in the first character "open" in the current second period SP0. On the other hand, if the cumulative total is 3 times or more, the information processing apparatus 100 determines that the change has occurred in the first character "open" in the current second period SP0. In the example of FIG. 2, it is assumed that the information processing apparatus 100 determines that there is no change in the first character "open" in the second period SP0.

Further, the information processing apparatus 100 moves the second period of the time interval X seconds according to the passage of time (so as to follow the passage of time). Therefore, for example, at the current time t1 in which a predetermined second has passed from the time t0, the information processing apparatus 100 sets a second period SP1 having a time interval of X seconds starting from the time t1. In this case, the end point of the second period SP1 is the time X seconds before the time t1. In such a state, the information processing apparatus 100 re-performs the determination process of the example described in the second period SP0. Although detailed description will be omitted because it is repeated, the information processing apparatus 100 acquires the second utterance information in the second period SP1, the character string included in the acquired second utterance information, and the analysis result storage unit. By comparing with the speech tendency (characteristic word) stored in 122, it is determined whether or not a change has occurred in the first character "open". In the example of FIG. 2, it is assumed that the information processing apparatus 100 determines that there is no change in the first character "open" in the second period SP1.

Further, the information processing apparatus 100 moves the second period of the time interval X seconds according to the passage of time (so as to follow the passage of time). Therefore, for example, at the current time t2, which is a predetermined second after the time t1, the information processing apparatus 100 sets a second period SP2 having a time interval of X seconds, starting from the time t2. In this case, the end point of the second period SP2 is the time X seconds before the time t2. In such a state, the information processing apparatus 100 re-performs the determination process of the example described in the second period SP0. That is, the information processing apparatus 100 acquires the second utterance information in the second period SP2, and the character string included in the acquired second utterance information and the utterance tendency (characteristic word) stored in the analysis result storage unit 122. ) To determine whether or not a change has occurred in the first character "open".

At this point, the information processing apparatus 100 counts the number of character strings W79 included in the second utterance information in the second period SP2, and accumulates the counting results (cumulative total from the second period SP0 to the present). ) Was 3 times or more. In such a case, the information processing apparatus 100 determines that the change has occurred in the first character "open" in the current second period SP2. Specifically, the information processing apparatus 100 determines that a change has occurred from the first personality "open" to the second personality "mental instability" which is a different personality. That is, in the information processing device 100, the number of appearances of the character string W79 (an example of the degree to which the characteristic information is included), which is one characteristic word in the personality characteristic "mental instability", is greater than three times at the current time t2. At the timing, it is determined that the first character "open" has changed.

In this way, when the information processing device 100 gradually begins to use words that are not normally used in the first personality, the information processing device 100 counts the number of words used at small time intervals according to the passage of time. Based on the counting result, it is determined that the first personality has changed at the timing when the frequency of using this word becomes high to some extent. As a result, the information processing apparatus 100 can accurately detect the timing at which the first personality changes, so that the information provided to the user can be controlled without giving the user a sense of discomfort.

Now, an example of the determination process has been described with reference to FIG. From here, another example of the determination process will be described with reference to FIG. FIG. 3 is a diagram showing an example (2) of the determination process according to the embodiment. In the example of FIG. 3, the information processing apparatus 100 determines whether or not a change has occurred in the first personality based on the change in the information between the information regarding the second utterance information and the first personality. .. For example, the information processing apparatus 100 has a second personality in the second period and a first personality in the first period as changes in the information between the information related to the second speech information and the first personality. Based on the comparison result in which the personality of the first character is compared, it is determined whether or not the first character has changed. For example, when the comparison result shows that the second personality and the first personality are different, the information processing apparatus 100 determines that the first personality has changed. Hereinafter, this point will be described in detail with reference to FIG.

Also in the example of FIG. 2, since the dialogue is performed between the user Ux1 and the dialogue system 20, the second utterance information corresponds to the utterance information indicating the utterance made by the user Ux1 in this dialogue. In addition, the user Ux1 has the first character of being "open" in the long run. In such a state, when the information processing apparatus 100 detects that the dialogue has started between the user Ux1 and the dialogue system 20, the information processing device 100 has the current time at which the dialogue has started with respect to the time axis T at the present time. A second period SP0 with a time interval of X seconds (X = an arbitrary numerical value) starting from a certain time t0 is set.

Then, the information processing apparatus 100 acquires the second utterance information in the second period SP0, and estimates the current personality characteristic of the user Ux1 based on the words included in the acquired second utterance information. For example, when the information processing device 100 includes a word corresponding to a personality different from the first personality "open" in the words included in the second utterance information, the word and the personality characteristic are combined. To detect. For example, the information processing device 100 extracts a character string indicating a word or expression from the text corresponding to the second utterance information. Then, the information processing apparatus 100 compares the extracted character string with the utterance tendency (characteristic word) stored in the analysis result storage unit 122, and finds out which character in the text corresponding to the second utterance information. Determine whether the characteristic contains the most character strings that are characteristic words. Then, the information processing device 100 estimates the current personality trait of the user Ux1 according to the determination result.

For example, the information processing apparatus 100 states that the text corresponding to the second utterance information in the second period SP0 contains the character string that is the characteristic word with the personality characteristic "open". If the determination result of is obtained, it is presumed that the personality trait of the user Ux1 at the present time is "open". The personality trait "open" estimated in this way can be said to be the second personality, which is the personality of the user Ux1 in the second period.

Then, in such a state, the information processing apparatus 100 compares the second personality with the first personality, and when the comparison result shows that the second personality and the first personality are different, , It is determined that a change has occurred in the first personality. The information processing apparatus 100 has obtained an estimation result that the second personality of the user Ux1 is "open" in the current second period SP0, and the first personality of the user Ux1 is also "open". Therefore, it is determined that there is no change in the first personality based on the comparison result between the second personality and the first personality.

Further, the information processing apparatus 100 moves the second period of the time interval X seconds according to the passage of time (so as to follow the passage of time). Therefore, for example, at the current time t1 in which a predetermined second has passed from the time t0, the information processing apparatus 100 sets a second period SP1 having a time interval of X seconds starting from the time t1. In this case, the end point of the second period SP1 is the time X seconds before the time t1. In such a state, the information processing apparatus 100 re-performs the determination process of the example described in the second period SP0. Specifically, the information processing apparatus 100 acquires the second utterance information in the second period SP1, and based on the words included in the acquired second utterance information, the user Ux1's current personality trait (first). 2) is estimated. Then, the information processing apparatus 100 compares the estimated second personality with the first personality, and when the comparison result shows that the second personality and the first personality are different, the first personality Judge that a change has occurred in personality. Assuming that the information processing device 100 obtains an estimation result of "open" as the second personality of the user Ux1 in the current second period SP1, the second personality and the first personality are the same. Based on the comparison result of, it is determined that there is no change in the first personality.

Further, the information processing apparatus 100 moves the second period of the time interval X seconds according to the passage of time (so as to follow the passage of time). Therefore, for example, at the current time t2, which is a predetermined second after the time t1, the information processing apparatus 100 sets a second period SP2 having a time interval of X seconds, starting from the time t2. In this case, the end point of the second period SP2 is the time X seconds before the time t2. In such a state, the information processing apparatus 100 re-performs the determination process of the example described in the second period SP0. Specifically, the information processing apparatus 100 acquires the second utterance information in the second period SP2, and based on the words included in the acquired second utterance information, the user Ux1's current personality trait (first). 2) is estimated. Then, the information processing apparatus 100 compares the estimated second personality with the first personality, and when the comparison result shows that the second personality and the first personality are different, the first personality Judge that a change has occurred in personality. Assuming that the information processing device 100 obtains an estimation result of "mental instability" as the second personality of the user Ux1 in the current second period SP2, the second personality and the first personality are different. Based on the comparison result with, it is determined that the first personality has changed.

Specifically, the information processing apparatus 100 determines that a change has occurred from the first personality "open" to the second personality "mental instability" which is a different personality. That is, in the information processing device 100, the first personality "open" changes at the timing of the current time t2 when words (words and expressions) that are easy for the user with the personality characteristic "mental instability" are used. Judged as

In this way, the information processing apparatus 100 estimates the second personality based on which personality trait user is most likely to use the words used in the current short-term utterance. .. Then, the information processing apparatus 100 compares the second personality with the first personality, and if both personalities are different, it is determined that the first personality has changed. As a result, the information processing apparatus 100 can accurately detect the timing at which the first personality changes, so that the information provided to the user can be controlled without giving the user a sense of discomfort.

Up to this point, the determination process in step S16 has been described with reference to FIGS. 2 and 3. From here, the information processing according to the embodiment will be described again with reference to FIG. When it is determined that the first personality has changed, the information processing device 100 controls the information provided to the user Ux1 according to the changed personality (step S17). For example, the information processing device 100 controls the response regarding the response of the dialogue system 20 to the utterance input of the user Ux1. Further, for example, the information processing apparatus 100 controls the content distribution to the user Ux1.

First, an example of response control will be described. For example, it is assumed that the information processing apparatus 100 determines that the first personality of the user Ux1 has changed. Specifically, it is determined that the information processing apparatus 100 has determined that the user Ux1 has changed from the first personality trait "open" to the second personality trait "mental instability". To do. In such a case, the information processing apparatus 100 controls the response so that the dialogue system 20 makes a response in consideration of compatibility with the changed personality. For example, the information processing apparatus 100 has a storage unit in which template information indicating contents that respond to input information (for example, input information by voice input) from a user of the personality characteristic is associated with each personality characteristic. By having the above, the response can be controlled by referring to the storage unit.

Further, in such a storage unit, fixed phrases that are considered to be compatible with each personality characteristic are stored as template information. For example, for a positive personality trait, a fixed phrase or the like in which the current situation can be shared with the user is stored. Further, for example, for a negative personality trait, a fixed phrase or the like that can calm the user is stored.

For example, it is assumed that the information processing device 100 receives a voice input of "Be careful!" From the user Ux1 in a state of being changed to the personality characteristic "mental instability" via the dialogue system 20. Further, it is assumed that the input information "Be careful" corresponding to the personality characteristic "Mental instability" is associated with a fixed phrase such as "Please calm down" in the above storage unit. Then, the information processing apparatus 100 controls the dialogue system 20 to respond with "Please calm down".

In this way, the information processing device 100 performs response control for the second user whose personality is changing, conscious of sympathy with the user. As a result, for example, when the information processing device 100 is happy and the feeling is temporarily uplifted, the information processing device 100 makes a response to the dialogue system 20 to share the joy during that time. Because it can be done, the dialogue can be made more exciting. Further, for example, when the information processing device 100 is temporarily frustrated, the information processing device 100 can make a calming response to the dialogue system 20 to realize a safe dialogue. be able to.

In addition, the information processing apparatus 100 can also change the response style or intonation so that the dialogue system 20 makes a response in consideration of compatibility with the changed personality. Here, for convenience of explanation, it is assumed that the information processing apparatus 100 determines that the user Ux1 has changed from the first personality "open" to the second personality "serious". People with a serious personality are often theoretical. Therefore, in such a case, the information processing apparatus 100 controls the dialogue system 20 to convert the fixed phrase corresponding to the input information into a fixed phrase with a polite expression and then respond with the converted fixed phrase. Further, the information processing apparatus 100 may control the dialogue system 20 so as to respond to the converted fixed phrase with a voice having a quiet tone having no conspicuous features.

Further, for convenience of explanation, it is assumed that the information processing apparatus 100 determines that the user Ux1 has changed from the first personality "open" to the second personality "diplomatic". People with a diplomatic personality tend to prefer funny and fun conversations, while not theoretical. Therefore, in such a case, the information processing apparatus 100 controls the dialogue system 20 to respond including the onomatopoeia, the onomatopoeia, or the onomatopoeia.

In this way, the information processing apparatus 100 changes the response style and intonation of the second user whose personality is changing according to the second static attack. As a result, the information processing apparatus 100 can prevent the user from feeling unpleasant due to the response, and can excite the dialogue.

Next, an example of control related to content distribution will be described. The content is advertising content or article content, but of course other content may be used. For example, it is assumed that the information processing apparatus 100 determines that the user Ux1 has changed from the personality trait "open", which is the first personality, to the personality trait "mental instability", which is the second personality. Content distribution during or after the personality of user Ux1 has changed to the second personality trait "mental instability" or after the change to the second personality trait "mental instability" The information processing apparatus 100 performs the following processing, for example.

For example, the information processing device 100 determines the content corresponding to the changed character among the content of the distribution candidate as the content to be distributed to be distributed to the user Ux1. Since it is determined that the user Ux1 has changed to the personality characteristic "mental instability", for example, the information processing device 100 determines the advertisement content or the article content regarding the healing spot or the calm place as the content to be distributed.

In addition, the information processing device 100 identifies the cause of the change in the personality trait of the user Ux1 to "mental instability" based on the second utterance information, and thereby an advertisement related to the cause. It is also possible to control the content and article content so that they are not determined as distribution targets. For example, it is assumed that the information processing device 100 identifies that the personality trait of Ux1 has changed to "mental instability" as soon as the conversation about the ceremonial occasion is made based on the second utterance information. That is, it is assumed that the information processing device 100 has identified that the personality trait of the user Ux1 has changed to "mental instability" due to the conversation about the ceremonial marriage. In such a case, the information processing device 100 controls the user Ux1 so that the advertisement content and the article content related to the ceremonial occasion are not distributed in the future.

As a result, the information processing device 100 can realize content distribution corresponding to a temporary change in the personality of the user, so that a wider range of content can be distributed, and conversely, content that the user dislikes can be distributed. It can be detected accurately and restricted from being delivered.

Further, the information processing device 100 may control the display mode of the content to be distributed to the user Ux1, which is the content determined from the content of the distribution candidate, according to the character after the change. .. For example, it is assumed that the information processing apparatus 100 determines that the user Ux1 has changed from the personality trait "open", which is the first personality, to the personality trait "mental instability", which is the second personality. In such a case, the information processing device 100 changes, for example, the expression of the sentence included in the content to be distributed to the expression corresponding to the personality characteristic "mental instability". Further, the information processing apparatus 100 changes the character style of the text included in the content to be distributed to the character style according to the personality characteristic "mental instability".

As a result, the information processing device 100 can realize a change in display correspondence corresponding to a temporary change in the personality of the user, so that the appealing power of the content can be further enhanced.

By the way, as described above, the information processing apparatus 100 estimates the long-term personality of the user based on the user information acquired in a relatively long period of time. Then, the information processing apparatus 100 determines whether or not the long-term personality has changed based on the change in the information between the user information acquired in each of the short periods that change from time to time and the long-term personality. judge. Then, when it is determined that the change has occurred, the information processing device 100 controls the information provided to the user according to the character after the change. As a result, the information processing apparatus 100 can realize the distribution of information according to the temporary change in personality. Further, as a result, the information processing apparatus 100 can increase the satisfaction of the user.

[2. Information processing device configuration]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a diagram showing a configuration example of the information processing device 100 according to the embodiment. As shown in FIG. 5, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. For example, the information processing device 100 is a server device that performs information processing described with reference to FIGS. 1 to 3.

(About communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from, for example, the terminal device 10, the dialogue system 20, and the external device 30.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 has a diagnosis result storage unit 121 and an analysis result storage unit 122. Since these storage units have already been described with reference to FIG. 1, description thereof will be omitted here.

The information processing device 100 may have a storage unit for storing various submitted contents (for example, article contents and advertisement contents).

(About control unit 130)
The control unit 130 is realized by executing various programs stored in the storage device inside the information processing device 100 using the RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. .. Further, the control unit 130 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 5, the control unit 130 includes an acquisition unit 131, an estimation unit 132, an analysis unit 133, a determination unit 134, an output control unit 135, and a distribution control unit 136, which will be described below. Realize or execute the functions and actions of information processing. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be another configuration as long as it performs information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 5, and may be another connection relationship.

(About acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires the user's action history from the external device 30. For example, the acquisition unit 131 acquires the utterance history and the action history on the net as the action history.

In addition, the acquisition unit 131 acquires information indicating the personality trait estimated by the estimation unit 132 and the analysis result by the analysis unit 133. For example, when the personality characteristic (diagnosis result) stored in the diagnosis result storage unit 121 is used for information processing, the acquisition unit 131 acquires information necessary for processing from the diagnosis result storage unit 121 and responds to it. Send to the processing unit. Further, for example, when the analysis result stored in the analysis result storage unit 122 is used for information processing, the acquisition unit 131 acquires information necessary for processing from the analysis result storage unit 122 and corresponds to the processing unit. Send to.

(About estimation unit 132)
The estimation unit 132 estimates the personality of the user. For example, for a user who has all the information necessary for diagnosing a personality trait by a predetermined personality diagnosis method (Big5, ecogram, OKgram, etc.), that is, a sample user, a predetermined personality diagnosis method is used using such information. Estimate personality traits. In addition, the estimation unit 132 stores the diagnosis result of the predetermined personality diagnosis method in the diagnosis result storage unit 121.

Further, when the user to be processed is a user whose personality characteristic is unknown and the answer for Big5 is not obtained, the estimation unit 132 is stored in the analysis result storage unit 122. Based on the analysis results, the personality characteristics of the user to be processed are estimated. For example, the estimation unit 132 estimates the personality characteristics of the user to be processed based on the first user information corresponding to the user to be processed and the analysis result stored in the analysis result storage unit 122. For example, the estimation unit 132 is the first user's personality characteristic in the first period based on the first user information corresponding to the user to be processed and the analysis result stored in the analysis result storage unit 122. Estimate the character of. For example, when the first utterance information is acquired as the first user information of the user to be processed, the estimation unit 132 uses the words included in the first utterance information and the utterances stored in the analysis result storage unit 122. The personality trait of the user to be processed is estimated by matching with a tendency (for example, a feature word).

For example, the estimation unit 132 extracts a character string (word, expression, etc.) included in the text indicated by the first utterance information that has been used a predetermined number of times or more during the first period. Then, in the analysis result storage unit 122, the estimation unit 132 sets the personality trait that matches or is associated with the extracted character string as the utterance tendency of the user in the first period. It is defined as the first personality. In addition, the estimation unit 132 inputs the first utterance information to the model generated by the analysis of the utterance history, and the output personality characteristic is the first personality characteristic of the user in the first period. It may be presumed to be the character of.

Further, when the first behavior information is acquired as the first user information of the user to be processed, the estimation unit 132 matches the first behavior information with the behavior tendency stored in the analysis result storage unit 122. It is possible to estimate the personality characteristics of the user to be processed. For example, the estimation unit 132 extracts the action information indicating the action performed a predetermined number of times or more during the first period from the actions indicated by the first action information. Then, the estimation unit 132 sets the personality trait that matches or is associated with the extracted behavior information in the analysis result storage unit 122 as the personality trait of the user in the first period. It is defined as the character of 1. In addition, the estimation unit 132 inputs the first behavior information to the model generated by the analysis of the behavior history, and the output personality trait is the first personality trait of the user in the first period. It may be presumed to be a personality. For this reason, the estimation unit 132 performs the processes of steps S11 and S15 described in FIG. 1, for example.

(About Analysis Department 133)
Next, the analysis unit 133 analyzes the relationship between the personality trait and the behavior of the S user belonging to the personality trait. For example, the analysis unit 133 determines the behavioral tendency of the sample user belonging to the personality characteristic in the first period based on the history information (utterance history, behavior history) for each personality characteristic stored in the analysis result storage unit 122. analyse. For example, the analysis unit 133 determines what kind of words the S user of the personality trait tends to say (speaking tendency) and what kind of behavior (browsing, searching, etc.) based on the history information. Analyze whether there is a tendency (behavioral tendency) to cause (purchase, etc.).

Here, the utterance tendency may be a word or expression that frequently appears in the utterance information of the S user having the corresponding personality trait, that is, a characteristic word. Then, in order to extract such a feature word, the analysis unit 133 can perform an analysis process using an index called mutual information amount. For example, the analysis unit 133 calculates the mutual information amount between the words included in the utterance information and the personality trait of the S user who input the utterance information, and the calculated mutual information amount is a word having a predetermined value or more. , Classify as characteristic words according to the personality trait. For example, the analysis unit 133 extracts a character string such as a word or a frequently occurring expression from the utterance information, and calculates the mutual information amount between the extracted character string and the personality trait. Then, the analysis unit 133 classifies (selects) a predetermined number of feature words as feature words according to their personality traits in order from the one with the highest mutual information amount value.

In addition, the analysis unit 133 uses the above analysis results (for example, feature words) to estimate the personality traits of an unknown user whose personality traits are unknown and for which no answer for Big5 has been obtained. It is also possible to generate a model for this purpose and store the generated model as an analysis result in the analysis result storage unit 122.

For example, the analysis unit 133 learns the relationship between the personality trait and the feature word corresponding to the personality trait, and when the utterance information of the unknown user is input, the information indicating the personality trait of the unknown user. You can generate a model that outputs. For example, when the analysis unit 133 inputs a feature word into the model, the analysis unit 133 learns the model by using a technique such as backpropagation so as to output information indicating the personality characteristic corresponding to the feature word. Generate a model.

The behavioral tendency may also be a characteristic word. Specifically, the behavioral tendency may be a word or expression that frequently appears in the content viewed by the S user having the corresponding personality trait, that is, a characteristic word. In this case, the analysis unit 133 calculates the mutual information amount between the words included in the browsed content and the personality characteristic of the S user who browsed the content, and the calculated mutual information amount is equal to or more than a predetermined value. Words are classified as characteristic words according to their personality traits. For example, the analysis unit 133 extracts a character string such as a word or a frequently used expression from the browsed content, and calculates the mutual information amount between the extracted character string and the personality trait. Then, the analysis unit 133 classifies (selects) a predetermined number of feature words as feature words according to their personality traits in order from the one with the highest mutual information amount value.

Further, the analysis unit 133 learns the relationship between the personality trait and the feature word corresponding to the personality trait, so that when the behavior history (for example, browsing history) of the unknown user is input, the unknown user It is possible to generate a model that outputs information indicating the personality traits of. Further, for this reason, the analysis unit 133 performs, for example, the process of step S13 described with reference to FIG.

(About judgment unit 134)
The determination unit 134 is a first user personality characteristic estimated based on the first user information, which is the user information of the user acquired in the first period, and is a user personality characteristic in the first period. Determine if there has been a change in the character of. For example, the determination unit 134 determines whether or not the first personality estimated based on the utterance information indicating the utterance of the user in the first period has changed as the first user information. Since the estimation unit 132 estimates what kind of personality trait the first personality corresponds to, the determination unit 134 receives the personality trait indicating the first personality from the estimation unit 132 as the estimation result. Then, the determination unit 134 performs the determination process using the estimation result received from the estimation unit 132.

For example, the determination unit 134 has a second user information, which is user information of the user acquired in the second period, which is a period shorter than the first period and corresponds to the current passage of time, and a first. Based on the change in information with the personality of, it is determined whether or not the first personality has changed. For example, the determination unit 134 has a second period between the second user information acquired in the second period in which the start point and the end point of the period change so as to follow the passage of time and the first character. Based on the change in the information in, it is determined whether or not the change has occurred in the first personality. More specifically, each time the second period changes with the passage of time, the determination unit 134 between the second user information acquired in the second period after the change and the first personality. Based on the change in the information of, it is determined whether or not the change has occurred in the first personality.

As described with reference to FIG. 2, in the determination unit 134, the degree to which the second user information includes characteristic information indicating a characteristic of another personality different from the first personality as a change of information is larger than a predetermined value. It is determined whether or not the first personality has changed depending on whether or not it has become. For example, the determination unit 134 determines that the first personality has changed at the timing when the degree becomes larger than the predetermined value.

Further, as described with reference to FIG. 3, the determination unit 134 has the second personality, which is the personality of the user estimated based on the second user information, and the personality of the user in the second period, and the first. It is determined whether or not a change has occurred in the first personality based on the change in information between the changes in the personality of the first character. For example, the determination unit 134 determines whether or not a change has occurred in the first personality as a change in information, based on a comparison result in which the second personality and the first personality are compared. For example, when the comparison result shows that the second personality and the first personality are different, the determination unit 134 determines that the first personality has changed.

Further, when the determination unit 134 determines that the first personality has changed, the information processing device 100 controls the information provided to the user according to the changed personality changed from the first personality. To do. For example, the following output control unit 135 and distribution control unit 136 control the information provided to the user.

(About output control unit 135)
When it is determined that the first personality has changed, the output control unit 135 controls the response of the dialogue system 20 to the user's utterance input according to the changed personality. For example, the output control unit 135 controls the response mode of the response by the dialogue system 20 according to the character after the change. For example, the output control unit 135 controls the response so that the dialogue system 20 makes a response in consideration of compatibility with the changed personality. The output control unit 135 changes the response style or intonation so that the dialogue system 20 makes a response in consideration of compatibility with the changed personality. For this reason, the output control unit 135 performs, for example, the process of step S17 described with reference to FIG.

(About distribution control unit 136)
When it is determined that the first character has changed, the distribution control unit 136 determines the content of the distribution candidate content according to the changed character as the content to be distributed to the user. .. Further, for example, the distribution control unit 136 controls the display mode of the content to be distributed to the user determined from the content of the distribution candidate according to the character after the change. For this reason, the distribution control unit 136 performs, for example, the process of step S17 described with reference to FIG.

[3. Processing procedure]
Next, the procedure of information processing according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing an information processing procedure for information processing according to the embodiment.

First, the estimation unit 132 performs a personality diagnosis of the S user (step S101). For example, the estimation unit 132 diagnoses (estimates) what kind of personality trait the S user belongs to by using a personality diagnosis method such as Big5. Further, the estimation unit 132 stores the diagnosis result in the diagnosis result storage unit 121.

Next, the analysis unit 133 distributes (associates) the behavior history indicating the behavior of the S user belonging to the personality characteristic in the first period for each personality characteristic, and stores the distributed result in the analysis result storage unit 122. (Step S102). For example, the analysis unit 133 distributes the utterance history indicating the utterances made by the S user belonging to the personality trait in the first period for each personality trait. In addition, the analysis unit 133 distributes an action history showing various actions on the net performed by the S user belonging to the personality trait in the first period for each personality trait.

Next, the analysis unit 133 analyzes the relationship between the personality trait and the behavior of the S user belonging to the personality trait (step S103). For example, the analysis unit 133 determines the behavioral tendency of the S user belonging to the personality characteristic in the first period based on the history information (utterance history, behavior history) for each personality characteristic stored in the analysis result storage unit 122. analyse. For example, the analysis unit 133 determines what kind of words the S user of the personality trait tends to say (speaking tendency) and what kind of behavior (browsing, searching, etc.) based on the history information. Analyze whether there is a tendency (behavioral tendency) to cause (purchase, etc.). As such a tendency, the analysis unit 133 can analyze the feature words, for example.

Next, the acquisition unit 131 acquires the action information (an example of the first user information) indicating the action performed by the user to be processed in the first period (step S104). For example, the acquisition unit 131 acquires the first utterance information, which is the utterance information indicating the utterance made by the user to be processed in the first period, as the action information. In addition, the acquisition unit 131 may acquire the first action information indicating the action on the Internet performed by the user to be processed in the first period as the action information.

In such a state, the estimation unit 132 determines the personality characteristic as the first personality of the user to be processed based on the behavior information acquired in step S104 and the analysis result stored in the analysis result storage unit 122. Estimate (step S105). For example, when the first utterance information is acquired as the first user information, the estimation unit 132 describes the words included in the first utterance information and the utterance tendency (for example, the feature) stored in the analysis result storage unit 122. The character characteristics of the user to be processed are estimated by matching with the word). Further, for example, when the first action information is acquired as the first user information, the estimation unit 132 processes by matching the first action information with the action tendency stored in the analysis result storage unit 122. Estimate the personality traits of the user.

Next, the determination unit 134 determines whether or not the first personality estimated in step S105 has changed (step S106). For example, the determination unit 134 sets a second period, which is shorter than the first period and in which the start point and the end point change so as to follow the current passage of time. Then, each time the set second period changes according to the lapse of the current time, the information processing device 100 is the second utterance information indicating the utterance made by the user to be processed in the second period. Acquire information (second user information). In addition, the determination unit 134 determines whether or not a change has occurred in the first personality based on the change in the information between the information regarding the second utterance information and the first personality.

Then, while the determination unit 134 determines that there is no change in the first personality (step S106; No), the determination unit 134 repeats the determination process until the first personality changes, and responds to the first personality. Continue to provide information. For example, the determination unit 134 instructs the output control unit 135 to cause the dialogue system 20 to make a response in a mode corresponding to the first character while determining that there is no change in the first character. .. Further, while the determination unit 134 determines that there is no change in the first character, the distribution control unit 136 causes the distribution control unit 136 to determine the content according to the first character, or the mode of the content to be distributed. Is changed to the mode according to the first personality.

On the other hand, when it is determined that the first character has changed (step S106; Yes), the output control unit 135 performs response control regarding the response of the dialogue system 20 in response to an instruction from the determination unit 134. (Step S107). For example, the output control unit 135 changes the response style or intonation so that the dialogue system 20 makes a response in consideration of compatibility with the changed personality. Then, the output control unit 135 controls the dialogue system 20 so as to respond with the changed response style and intonation.

Further, in step S107, the information processing apparatus 100 can also control the content distribution instead of the response control regarding the response of the dialogue system 20. For example, when it is determined that the first personality has changed (step S106; Yes), the distribution control unit 136 processes the content of the distribution candidate content according to the changed personality by the user in the processing mode. It is determined as the content to be delivered to be delivered to (step S107). Further, the distribution control unit 136 may change the display mode of the content to be distributed to be distributed to the user to be processed to a display mode according to the changed personality.

[4. Hardware configuration]
Further, the information processing apparatus 100 according to the above embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 7 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the communication network 50 and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the communication network 50.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 50.

[5. Others]
Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in any unit according to various loads and usage conditions. It can be integrated and configured.

The embodiments of the present application have been described in detail with reference to some drawings, but these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

In addition, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the reception unit can be read as a reception means or a reception circuit.

1 Information processing system 10 Terminal device 30 External device 100 Information processing device 120 Storage unit 121 Diagnosis result storage unit 122 Analysis result storage unit 130 Control unit 131 Acquisition unit 132 Estimating unit 133 Analysis unit 134 Judgment unit 135 Output control unit 136 Distribution control unit

Claims (19)

The personality of the user estimated based on the first user information which is the user information of the user acquired in the first period, and changes to the first personality which is the personality of the user in the first period. And a judgment unit that determines whether or not
When it is determined that a change has occurred in the first personality, it is characterized by having a control unit that controls information provided to the user according to the changed personality changed from the first personality. Information processing device. The determination unit is characterized in that, as the first user information, it is determined whether or not a change has occurred in the first personality estimated based on the utterance information indicating the utterance of the user in the first period. The information processing apparatus according to claim 1. The determination unit includes second user information, which is user information of the user acquired in the second period, which is a period shorter than the first period and corresponds to the current passage of time, and the second user information. The information processing apparatus according to claim 1 or 2, wherein it is determined whether or not a change has occurred in the first personality based on a change in information with and from the personality 1. The determination unit includes the second user information acquired in the second period in which the start point and the end point of the period change so as to follow the passage of time as the second period, and the first character. The information processing apparatus according to claim 3, wherein it is determined whether or not a change has occurred in the first personality based on a change in information between the two. Each time the second period changes according to the passage of time, the determination unit receives the second user information acquired in the second period after the change and the first character. The information processing apparatus according to claim 3 or 4, wherein it is determined whether or not a change has occurred in the first personality based on a change in information. The determination unit is a change between the second personality, which is the personality of the user estimated based on the second user information, and the personality of the user in the second period, and the first personality. The information processing apparatus according to any one of claims 3 to 5, wherein it is determined whether or not a change has occurred in the first personality based on a change in information between the two. The determination unit determines whether or not a change has occurred in the first personality based on a comparison result in which the second personality and the first personality are compared as a change in the information. The information processing apparatus according to claim 6. A claim, wherein the determination unit determines that a change has occurred in the first personality when the comparison result indicates that the second personality and the first personality are different. The information processing apparatus according to 7. The determination unit determines whether or not the degree to which the second user information includes characteristic information indicating a characteristic of another personality different from the first personality is greater than a predetermined value as a change in the information. The information processing apparatus according to any one of claims 3 to 8, wherein it is determined whether or not a change has occurred in the first personality accordingly. The information processing apparatus according to claim 9, wherein the determination unit determines that a change has occurred in the first personality at a timing when the degree becomes larger than a predetermined value. The determination unit uses the first user information as the first user information based on a change in information between the utterance information indicating the user's utterance in the second period and the first personality. The information processing apparatus according to any one of claims 3 to 10, wherein it is determined whether or not a change in personality has occurred. When it is determined that a change has occurred in the first personality, the control unit performs response control regarding the response of the dialogue agent system to the utterance input of the user according to the changed personality. The information processing apparatus according to any one of claims 1 to 11. The information processing device according to claim 12, wherein the control unit controls the response mode of the response by the dialogue agent system according to the character after the change. The information processing apparatus according to claim 12, wherein the control unit controls the response so that the dialogue agent system performs a response in consideration of compatibility with the changed personality. The control unit is described in any one of claims 12 to 14, wherein the dialogue agent system changes the response style or intonation so as to perform a response in consideration of compatibility with the changed personality. Information processing equipment. When it is determined that the first character has changed, the control unit determines the content of the distribution candidate content according to the changed character as the content to be distributed to the user. The information processing apparatus according to any one of claims 1 to 15, wherein the information processing apparatus is used. Any of claims 1 to 16, wherein the control unit controls a display mode of the content to be distributed to the user determined from the content of the distribution candidate according to the character after the change. The information processing device according to one. It is an information processing method executed by an information processing device.
The personality of the user estimated based on the first user information which is the user information of the user acquired in the first period, and changes to the first personality which is the personality of the user in the first period. And the judgment process to determine whether or not
When it is determined that a change has occurred in the first personality, it is characterized by including a control step of controlling information provided to the user according to the changed personality changed from the first personality. Information processing method. The personality of the user estimated based on the first user information which is the user information of the user acquired in the first period, and changes to the first personality which is the personality of the user in the first period. Judgment procedure to determine whether or not
When it is determined that a change has occurred in the first personality, the computer is made to execute a control procedure for controlling the information provided to the user according to the changed personality changed from the first personality. An information processing program characterized by this.

Images