Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device, an information processing method and an information processing program, which enable provision of dialog that makes a user feel a sense of closeness.SOLUTION: An information processing device (100) is provided, comprising an acquisition unit (132) for acquiring episode data (D1) related to topic information included in utterance data (D30) of a speaker from a storage unit (120) configured to store the episode data (D1) of the speaker, and a dialog control unit (133) for controlling dialog with the speaker so as to include an episode based on the episode data (D1).SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] In recent years, devices that perform speech recognition of user speech and conduct conversations based on the recognition results have become widespread. For example, Patent Document 1 discloses a technique for realizing conversations according to a specific field using a dictionary for each field.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, since it conducts specialized conversations in the fields recorded in the dictionaries for each field, it is difficult to realize daily conversations. For this reason, in the prior art, it has been desired to realize conversations with which users feel a sense of familiarity.

[0005] Therefore, the present disclosure proposes an information processing apparatus, an information processing method, and an information processing program that can realize conversations with which users feel a sense of familiarity.

Means for Solving the Problems

[0006] In order to solve the above problems, an information processing apparatus according to one aspect of the present disclosure includes a storage unit that stores episode data of a speaker, an acquisition unit that acquires the episode data related to topic information included in the utterance data of the speaker from the storage unit, a dialogue control unit that controls a dialogue with the speaker of an agent device so as to include an episode based on the episode data, and a recognition unit that recognizes the speaker based on sensor information of the agent device. The acquisition unit acquires the episode data that satisfies the acquisition conditions when the speaker is recognized, and the dialogue control unit controls the dialogue with the speaker of the agent device so as to spontaneously utter the episode indicated by the episode data acquired by the acquisition unit.

[0007] Also, an information processing method according to one aspect of the present disclosure includes a computer acquiring the episode data related to topic information included in the utterance data of a speaker from a storage unit that stores the episode data of the speaker, controlling a dialogue with the speaker of an agent device so as to include an episode based on the episode data, and recognizing the speaker based on sensor information of the agent device. The acquiring includes acquiring the episode data that satisfies the acquisition conditions when the speaker is recognized, and the controlling includes controlling the dialogue with the speaker of the agent device so as to spontaneously utter the episode indicated by the episode data acquired by the acquiring.

[0008] Also, an information processing program according to one aspect of the present disclosure causes a computer to acquire, from a storage unit that stores speaker episode data, the episode data related to topic information included in the utterance data of the speaker; control an interaction with the speaker of the agent device so as to include an episode based on the episode data; and recognize the speaker based on sensor information of the agent device. When recognizing the speaker, the acquiring acquires the episode data that satisfies the acquisition conditions, and the controlling controls the interaction with the speaker of the agent device so as to spontaneously utter the episode indicated by the episode data acquired by the acquiring.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[0011] (Embodiment) [Outline of Information Processing System According to Embodiment] FIG. 1 is a diagram for explaining an example of an information processing system according to an embodiment. The information processing system 1 shown in FIG. 1 is a dialogue processing system that realizes dialogue between a user U and an agent device 10. The user U is an example of a speaker of the agent device 10 in the information processing system 1. For example, if the user U finds no originality or freshness in the dialogue with the agent device 10, the user U may get bored. For example, the user U may stop using the agent device 10 that has become boring. Therefore, the information processing system 1 has an episode talk function that realizes dialogue based on the user U's episode so as not to bore the user U with the dialogue with the agent device 10 and to have a sense of familiarity.

[0012] The information processing system 1 includes an agent device 10 and an information processing device 100. The information processing system 1 may include, for example, a plurality of agent devices 10 that interact with each of a plurality of users U. The agent device 10 and the information processing device 100 are configured to be able to communicate via a network or directly without going through the network. The information processing device 100 may be incorporated into the agent device 10, for example. In the following description, an example in which the agent device 10 interacts with the user U when the agent device 10 and the information processing device 100 cooperate will be described.

[0013] The agent device 10 is a so-called IoT (Internet of Things) device and performs various information processes in cooperation with the information processing device 100. The voice recognition and dialogue processing by voice executed by the agent device 10 may be referred to as an agent function. The agent device 10 can, for example, perform various responses to the utterance of the user U. For example, the responses include responses based on episodes, responses based on scenarios, responses based on the verbalization of situations, responses based on knowledge bases, casual conversation responses, and the like.

[0014] The agent device 10 includes, for example, an autonomous mobile body, a smartphone, a tablet terminal, a game device, a home speaker, household electrical appliances, an automobile, and the like. Smartphones, tablet terminals, etc. realize the above-mentioned agent function by executing a program (application) having an agent function. In this embodiment, the case where the agent device 10 is an autonomous mobile body will be described.

[0015] In an example shown in FIG. 1, the agent device 10 can be various devices that perform autonomous operations based on environmental recognition. The agent device 10 is an agent-type robot device in an oval shape that performs autonomous driving by wheels. The agent device 10 includes, for example, two wheels and a drive mechanism for driving the two wheels. The agent device 10 controls the drive mechanism so as to move while maintaining an upright state. The agent device 10 realizes various communications with the user U, for example, by performing autonomous operations according to the user U, the surroundings, or its own situation. The agent device 10 may be a small robot having a size and weight such that it can be easily lifted by the user U with one hand.

[0016] In an embodiment, the agent device 10 executes information processing on the collected voice. For example, the agent device 10 recognizes the speech of the user U and executes information processing on the speech. In an example shown in FIG. 1, it is assumed that the agent device 10 is installed at the home, company, school, etc. of the user U to be used.

[0017] The agent device 10 may have various sensors for obtaining various other information in addition to collecting ambient sound. For example, in addition to a microphone, the agent device 10 may have a camera for obtaining in space, an illuminance sensor for detecting illuminance, a gyro sensor for detecting inclination, an infrared sensor for detecting an object, and the like.

[0018] The information processing device 100 is a so-called cloud server, which is a server device that executes information processing in cooperation with the agent device 10. The information processing device 100 acquires the speech data of the user U collected by the agent device 10, and analyzes the speech data using natural language understanding (NLU), natural language processing (NLP), etc. When the information processing device 100 extracts topic information from the speech data, it acquires episode data related to the topic information from the episode DB (database). The topic information includes, for example, information indicating classification of episodes, words such as keywords, character strings, etc. That is, the topic information is information for acquiring episode data. The episode DB has, for example, episode data related to the user U and is stored in a storage device. The information processing device 100 has a function of conducting a dialogue with the user U so as to include an episode based on the episode data.

[0019] In an example shown in FIG. 1, when the agent device 10 recognizes the absent user U, it issues the speech C11 instructed by the information processing device 100. The speech C11 is, for example, "Welcome home." In response to the speech C11, the user U issues the speech C12. The speech C12 is, for example, "I was at work at the company." The agent device 10 transmits the speech data of the speech C12 to the information processing device 100.

[0020] The information processing device 100 analyzes the utterance data of utterance C12 and extracts the topic information of "company" and "I've been going there". The information processing device 100 acquires the episode data corresponding to the extracted topic information from the episode DB, and instructs the agent device 10 to generate an utterance C13 based on the episode data. For example, the information processing device 100 acquires the episode data related to "company" and "going". In this case, the episode data is, for example, data indicating an episode that the speaker went to the company yesterday and the day before yesterday. The agent device 10 is uttering utterance C13 to the user U. Utterance C13 is, for example, "That's right. You go there every day." Note that the dialogue method based on the episode data will be described later. The user U is uttering utterance C14 in response to utterance C13. Utterance C14 is, for example, "That's what work is all about." The agent device 10 transmits the utterance data of utterance C14 to the information processing device 100.

[0021] The information processing device 100 analyzes the utterance data of utterance C14 and controls the agent device 10 to utter a response to the user U. For example, the information processing device 100 generates utterance data suitable for the character of the agent device 10 based on a dialogue model, a dialogue scenario, etc. for responding to the utterance data. In an example shown in FIG. 1, the agent device 10 is uttering utterance C15 in response to the utterance data of utterance C14. Utterance C15 is, for example, "I'll work hard too."

[0022] As described above, when the information processing device 100 according to the embodiment acquires the episode data related to the topic information included in the utterance data of the user U, it can cause the agent device 10 to execute a dialogue including the episode of the user U based on the episode data. Thereby, the information processing device 100 can provide the episode based on the episode data of the user U in the dialogue with the user U. As a result, the information processing device 100 can realize a dialogue that the user U feels close to by including the episode of the user U in the dialogue.

[0023] [Configuration Example of Agent Device According to Embodiment] FIG. 2 is a diagram showing an example of the configuration of an agent device 10 according to an embodiment. As shown in FIG. 2, the agent device 10 includes a sensor unit 11, an input unit 12, a light source 13, an output unit 14, a drive unit 15, a control unit 16, and a communication unit 17.

[0024] The sensor unit 11 has a function of collecting various sensor information related to the user U and the surroundings. The sensor unit 11 according to the present embodiment includes, for example, a camera, a ToF (Time of Flight) sensor, a microphone, an inertial sensor, etc. The sensor unit 11 may include various sensors such as, for example, a geomagnetic sensor, a touch sensor, an infrared sensor, a temperature sensor, a humidity sensor, etc. The sensor unit 11 supplies the collected sensor information to the control unit 16. The sensor unit 11 has a function of collecting sounds such as voices by a microphone. The sensor unit 11 can store the collected sounds such as voices in a storage device.

[0025] The input unit 12 has a function of detecting a physical input operation by the user U. The input unit 12 includes, for example, buttons such as a power switch. The input unit 12 supplies input information indicating the detected input operation to the control unit 16.

[0026] The light source 13 expresses the eye movement of the agent device 10 which is an autonomous mobile body. The light source 13 includes, for example, two eye parts. The light source 13 expresses rich eye movements according to the situation and the operation according to an instruction from the control unit 16.

[0027] The output unit 14 has a function of outputting various sounds including voices. The output unit 14 includes, for example, a speaker, an amplifier, etc. The output unit 14 outputs the sound instructed by the control unit 16.

[0028] The drive unit 15 expresses an operation by driving the drive mechanism of the agent device 10 which is an autonomous mobile body. The drive unit 15 includes, for example, two wheels, a plurality of motors, etc. The drive unit 15 is driven according to an instruction from the control unit 16.

[0029] The control unit 16 controls the agent device 10. The control unit 16 has a function of controlling each component included in the agent device 10. The control unit 16 controls, for example, the startup and stop of each component. The control unit 16 controls the light source 13, the output unit 14, the drive unit 15, etc. based on control information from the information processing device 100 and the like.

[0030] When the control unit 16 collects the speech of the user U by the sensor unit 11, the control unit 16 performs control to transmit speech data indicating the speech to the information processing device 100. The control unit 16 controls the output unit 14 to output the dialogue data instructed by the information processing device 100. The control unit 16 realizes dialogue with the user U by outputting dialogue data for the collected speech data.

[0031] The communication unit 17 communicates with, for example, the information processing device 100, other external devices, etc. The communication unit 17 transmits and receives various data via, for example, a wired or wireless network or the like. When speech is collected, for example, the communication unit 17 transmits speech information to the information processing device 100. The communication unit 17 may transmit, for example, not only speech data but also identification information for identifying the user U to the information processing device 100. The communication unit 17 supplies various data received from the information processing device 100 to the control unit 16.

[0032] The functional configuration example of the agent device 10 according to the present embodiment has been described above. Note that the above configuration described with reference to FIG. 3 is merely an example, and the functional configuration of the agent device 10 according to the present embodiment is not limited to such an example. The functional configuration of the agent device 10 according to the present embodiment can be flexibly deformed according to specifications and operations.

[0033] [Structural Example of Agent Device According to Embodiment] FIG. 3 is a diagram showing an example of the structure of the agent device 10 according to the present embodiment. The left diagram in FIG. 3 is a side view showing the posture of the agent device 10 in a standing position (including when stationary and traveling). The right diagram in FIG. 3 is a side view showing the posture of the agent device 10 in a seated position.

[0034] As shown in the right diagram of FIG. 3, in the present embodiment, when the agent device 10 is stationary in the seated state, a part of the bottom is grounded on the floor surface. As a result, at least three points among the two wheels 570 and the grounded bottom contact the floor surface, and the agent device 10 assumes a seated state at three points. Therefore, the agent device 10 can be stably stationary in the seated state. Further, when the agent device 10 moves in the standing position, the bottom is not placed on the floor surface.

[0035] The center of gravity CoG of the agent device 10 is located on the vertical line V1 above the axle of the wheels 570 when the agent device 10 is in a forward-leaning posture (standing position) (see the left diagram of FIG. 3). Thereby, the agent device 10 is kept in balance and the standing position is maintained.

[0036] On the other hand, in the seated state, as shown in the right diagram of FIG. 3, by tilting the agent device 10 backward, at least three points among the two wheels 570 and the bottom (protrusion 701) are brought into contact with the floor surface. At that time, the center of gravity CoG of the agent device 10 is located between the vertical line V1 passing through the axle of the wheels 570 and the vertical line V2 passing through the contact portion between the bottom (protrusion 701) and the floor surface. The agent device 10 can stably stationary the agent device 10 in the seated state by positioning the center of gravity CoG of the agent device 10 between the vertical line V1 passing through the axle of the wheels 570 and the vertical line V2 passing through the contact portion between the bottom (protrusion 701) and the floor surface when in the seated state.

[0037] [Configuration Example of Information Processing Apparatus According to Embodiment] FIG. 4 is a diagram showing an example of the configuration of the information processing apparatus 100 according to the embodiment. As shown in FIG. 4, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The control unit 130 is electrically connected to the communication unit 110 and the storage unit 120.

[0038] The communication unit 110 communicates with, for example, the agent device 10 and other external devices. The communication unit 110 transmits and receives various data via, for example, a wired or wireless network or the like. The communication unit 110 supplies, for example, the data received from the agent device 10 to the control unit 130. The communication unit 110 transmits, for example, the data instructed by the control unit 130 to the instructed transmission destination.

[0039] The storage unit 120 stores various data and programs. For example, the storage unit 120 is, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, or the like. The storage unit 120 stores the information received via the communication unit 110. The storage unit 120 stores various data such as, for example, episode data D1, template data D2, user data D3, question data D4, dialogue data D5, knowledge data D10, management data D20, utterance data D30, and the like.

[0040] Episode data D1 is data indicating the episodes of user U. Episodes include, for example, past events of user U, future plans of user U, information regarding user U's hobbies, etc. Template data D2 is data indicating an algorithm for generating dialogue data D5 from episode data D1. User data D3 is data indicating information regarding user U. Information regarding user U includes, for example, personal information of user U, authentication information, setting information, etc. Question data D4 is data indicating questions, etc. for eliciting episodes from user U. Question data D4 is data used, for example, at the time of generating episode data D1. Dialogue data D5 is data used for dialogue with user U. Knowledge data D10 is data for realizing dialogue based on knowledge, scenarios, etc. Knowledge data D10 includes information such as, for example, intention identification, common sense knowledge, specialized knowledge, corpora, etc. Management data D20 is data indicating the correspondence relationship between user U and agent device 10 used by the user U. Utterance data D30 is utterance data from agent device 10, to which an analysis result is associated.

[0041] In the present embodiment, information processing apparatus 100 realizes an episode DB by storing and managing episode data D1 in storage unit 120. Information processing apparatus 100 may be configured to store the episode DB in an external storage device, etc. of the own apparatus.

[0042] Control unit 130 is, for example, a dedicated or general-purpose computer. Control unit 130 is, for example, an integrated control unit that controls information processing apparatus 100. Control unit 130 includes each functional unit for agent device 10 to realize dialogue with user U by cooperating with agent device 20.

[0043] The control unit 130 includes each functional unit of a recognition unit 131, an acquisition unit 132, a dialogue control unit 133, a generation unit 134, a collection unit 135, and an operation control unit 140. Each functional unit of the control unit 130 is realized, for example, by a program stored inside the information processing apparatus 100 being executed with a RAM or the like as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Further, each functional unit may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array).

[0044] The recognition unit 131 has a function of authenticating the user U based on the sensor information of the agent device 10. The recognition unit 131 performs personal authentication, for example, by face authentication, voice authentication, fingerprint authentication, etc., and recognizes the user U with whom the agent device 10 communicates. When the recognition unit 131 authenticates an available user U of the agent device 10 based on the sensor information of the agent device 10, user data D3, management data D20, etc., the recognition unit 131 enables dialogue between the user U and the agent device 10.

[0045] The recognition unit 131 converts the utterance data received from the agent device 10 into a character string. For example, the recognition unit 131 can use automatic speech recognition (ASR) processing or the like. The recognition unit 131 analyzes the recognized character string using NLU, NLP processing, etc. In the present embodiment, the recognition unit 131 analyzes the dependency structure of the character string and stores the analysis information indicating the analysis result in the storage unit 120 in association with the utterance data D30. The analysis information has, for example, information indicating a dependency structure such as clauses and cases.

[0046] The acquisition unit 132 acquires the episode data D1 related to the topic information included in the utterance data D30 of the user U from the storage unit 120 that stores the episode data D1 of the user U. The acquisition unit 132 extracts, for example, topic information from the utterance data D30. The topic information is information for acquiring the episode of the user U and includes information such as preset keywords, words, character strings, etc.

[0047] The acquisition unit 132 acquires the episode data D1 for which the topic information satisfies the dialogue condition. The dialogue condition is set, for example, in the user data D3, the management data D20, etc. The dialogue condition includes, for example, the condition for extracting the episode data D1 based on the topic information. For example, when the condition is that the words or character strings included in the episode data D1 match the topic information by a set number or more, the acquisition unit 132 acquires the episode data D1 that satisfies the dialogue condition from the storage unit 120.

[0048] When the acquisition unit 132 recognizes the user U, it acquires the episode data D1 that satisfies the acquisition condition regardless of the utterance of the user U. The acquisition condition includes, for example, the condition for acquiring the episode data D1 indicating the most recent episode of the user U, the episode of the time zone, the episode of the date or season, etc. The most recent episode is, for example, the latest episode of the user U. The episode of the time zone includes, for example, the episode related to today's schedule, yesterday's events, etc. when the time zone is in the morning. The episode of the time zone includes, for example, the episode related to the afternoon schedule, the night schedule, etc. when the time zone is at noon. The episode of the time zone includes, for example, the episode related to today's events, tomorrow's schedule, etc. when the time zone is at night. The episode of the date or season includes, for example, the episode within the set period. The acquisition unit 132 supplies the acquired episode data D1 to the dialogue control unit 133. When the acquisition unit 132 cannot acquire the episode data D1, it notifies the dialogue control unit 133 that it could not be acquired.

[0049] The dialogue control unit 133 controls the dialogue with the user U (the speaker) so as to include an episode based on the episode data D1 acquired by the acquisition unit 132. Controlling the dialogue includes, for example, controlling to utter a speech to the user U, controlling to talk face to face with the user U, and the like. For example, the dialogue control unit 133 generates dialogue data D5 including an episode, and controls the agent device 10 to output voice based on the dialogue data D5. The dialogue control unit 133 instructs the agent device 10 to output the voice of the dialogue data D5 via the communication unit 110. Thereby, the agent device 10 outputs the voice based on the dialogue data D5 from the output unit 14, thereby realizing the dialogue with the user U.

[0050] The dialogue control unit 133 generates dialogue data D5 including an episode based on, for example, the episode data D1 and an algorithm for generating a dialogue sentence. The algorithm can be realized by, for example, a template, an application, a program, or the like. In the present embodiment, the case of generating the dialogue data D5 using the template data D2 will be described.

[0051] The dialogue control unit 133 generates the dialogue data D5 by setting the data of the episode data D1 in the template. The dialogue control unit 133 controls the dialogue with the user U so that the agent device 10 spontaneously utters an episode. For example, when the user U is recognized, the dialogue control unit 133 controls the agent device 10 to utter the voice of the episode based on the episode data D1 that satisfies the acquisition condition.

[0052] When the acquisition unit 132 is not acquiring the episode data D1, the dialogue control unit 133 controls the dialogue with the user U based on the dialogue data D5 that is different from the episode. That is, the dialogue control unit 133 generates the dialogue data D5 that does not include the episode based on the knowledge data D10, and controls the agent device 10 to output the voice based on the dialogue data D5. The dialogue data D5 that does not include the episode is data for making a response based on the knowledge data D10 such as, for example, scenario dialogue, verbalization of a situation, knowledge base dialogue, and casual conversation response. The scenario dialogue includes, for example, responses according to a pre-designed scenario. The verbalization of a situation includes, for example, responses based on a corpus for speaking spontaneously according to the current situation, situation definition, etc. The knowledge base dialogue includes, for example, personalized responses based on the knowledge data D10. The dialogue control unit 133 selects scenario dialogue, verbalization of a situation, knowledge base dialogue, and casual conversation response according to the dialogue with the user U, and generates the dialogue data D5 indicating the selected knowledge base response.

[0053] When the dialogue control unit 133 authenticates the user U of the agent device 10, in order to elicit the episode of the user U, it controls the dialogue with the user U based on the question data D4. The dialogue control unit 133 can, for example, select the question data D4 according to the time zone. The dialogue control unit 133 controls the agent device 10 to output the voice based on the question data D4.

[0054] The generation unit 134 generates the episode data D1 based on the analysis result of the utterance data D30. The generation unit 134 generates the episode data D1 based on, for example, the analysis result of the utterance data D30 and the state and situation of the agent device 10. By paying attention to the state and situation of the agent device 10, the generation unit 134 generates the episode data D1 based on information that cannot be recognized from the analysis result of the utterance data D30.

[0055] The generation unit 134 generates episode data D1 based on the question data D4 that the dialogue control unit 133 is asking the user U, and the analysis result of the utterance data D30 corresponding to the question. For example, the generation unit 134 generates the episode data D1 by combining the question content of the question data D4 and the user U's response. For example, in the case of the question data D4 of "Where are you going today?", the generation unit 134 can generate the episode data D1 indicating the user's episode today based on the response to the user U's question. That is, the generation unit 134 can generate the episode data D1 based on the response elicited from the user U by the question. The generation unit 134 stores the generated episode data D1 in the storage unit 120 in association with the user U.

[0056] The collection unit 135 collects relevant information about the recognized user U. The relevant information includes, for example, information indicating the user U's past situations and the like. The collection unit 135 collects, for example, information indicating the situation of the user U recognized based on the sensor information of the agent device 10. The collection unit 135 collects, for example, relevant information indicating "Yesterday, Mr. Suzuki came to the house". The collection unit 135 collects, for example, relevant information indicating "On the weekend, mom was watching TV". The collection unit 135 can collect, for example, the user U's schedule, information about the user U in the social network, etc. as relevant information. The collection unit 135 supplies the collected relevant information to the generation unit 134.

[0057] The generation unit 134 generates the episode data D1 of the user U based on the collected relevant information and stores it in the storage unit 120. For example, the generation unit 134 analyzes the relevant information and generates the episode data D1 based on information about people, animals, etc. related to the user U.

[0058] The operation control unit 140 controls the operation of the agent device 10. For example, the operation control unit 140 controls the operation of the agent device 10 based on an action plan based on the situation of the user U, learned knowledge, and the like. For example, the operation control unit 140 performs control to cause the agent device 10 having an oval outer shape to move while maintaining the standing state. The movement operation includes, for example, forward and backward movement, turning movement, rotational movement, and the like. The operation control unit 140 performs control to actively cause the agent device 10 to execute an inducement operation that induces communication between the user U and the agent device 10. The inducement operation includes, for example, an operation for inducing a dialogue between the user U and the agent device 10.

[0059] The functional configuration example of the information processing apparatus 100 according to the embodiment has been described above. Note that the above-described configuration described with reference to FIG. 4 is merely an example, and the functional configuration of the information processing apparatus 100 according to the embodiment is not limited to such an example. The functional configuration of the information processing apparatus 100 according to the embodiment can be flexibly modified according to specifications and operations.

[0060] [Example of Data Structure of Episode Data] FIG. 5 is a diagram showing an example of episode data D1 according to the embodiment. As shown in FIG. 5, the information processing apparatus 100 has a plurality of pieces of episode data D1 regarding the user U. In the example shown in FIG. 5, the case of having six pieces of episode data D1 will be described, but the number of episode data D1 varies according to the number created and registered. The episode data D1 has, for example, items such as Ep_id, When, Who, Where, Action, State, Target, Why, How, With, and Cause.

[0061] In the Ep_id item, information that can identify the episode data D1 of user U is set. In the When item, information regarding the date and time, season, etc. of the episode data D1 is set. In the Who item, information regarding the name, proper nouns, etc. of the episode data D1 is set. In the Where item, information regarding the location of the episode data D1 is set. In the Action item, information regarding the predicate of the episode data D1 is set. In the State item, information regarding the state of the episode data D1 is set. In the Target item, in the Why item, information regarding the cause of the episode data D1 is set. In the How item, information regarding the means, method, procedure, etc. of the episode data D1 is set. In the With item, information regarding the people, animals, objects, etc. related to the episode data D1 is set. In the Cause item, information regarding the cause of the episode data D1 is set. That is, in the Cause item, information that associates the episode data D1 with each other is set. For the episode data D1, among the plurality of items, information is set in the items corresponding to the episode, and the items that do not correspond are blank.

[0062] In an example shown in FIG. 5, the information processing apparatus 100 manages six pieces of episode data D1 from Ep1 to Ep6 as episode data D1 regarding the user U. The episode data D1 with the item of Ep_id being Ep1 is data indicating the episode of "Tanaka petted aibo at home yesterday". Since the item of "Ep2" is set in the Cause item of the episode data D1 of Ep1, it indicates that it is the cause of the episode data D1 of Ep2. The episode data D1 with the item of Ep_id being Ep2 is data indicating the episode of "Aibo was happy at home yesterday". That is, the episode data D1 of Ep1 and EP2 indicates the episode that Aibo was happy because Tanaka petted aibo at home yesterday. The episode data D1 with the item of Ep_id being Ep3 is data indicating the episode of "This morning, since Tanaka was hungry, he hurriedly ate curry with Yamada". Since the Cause item of the episode data D1 of Ep3 is blank, it indicates that it is not related to other episode data D1.

[0063] The episode data D1 with the item of Ep_id being Ep4 is data indicating the episode of "Yamada ran to the toilet in a dash the other day". Since the item of "Ep5" is set in the Cause item of the episode data D1 of Ep4, it indicates that it is the cause of the episode data D1 of Ep5. The episode data D1 with the item of Ep_id being Ep5 is data indicating the episode of "Yamada fell". That is, the episode data D1 of Ep4 and EP5 indicates the episode that Yamada fell because he ran to the toilet in a dash the other day. The episode data D1 with the item of Ep_id being Ep6 is data indicating the future episode of "Tomorrow, everyone will take a hot spring in Izu". Since the Cause item of the episode data D1 of Ep6 is blank, it indicates that it is not related to other episode data D1.

[0064] In this embodiment, for the sake of simplicity of explanation, the When item of the episode data D1 will explain the case of setting information such as yesterday and this morning, but the date and time information may also be set. In this case, when creating the dialogue data D5 based on the episode data D1, the information processing apparatus 100 may replace the date and time with yesterday, the day before yesterday, tomorrow, etc.

[0065] The above configuration described with reference to FIG. 5 is merely an example, and the data structure of the episode data D1 according to the embodiment is not limited to such an example. The data structure of the episode data D1 according to the embodiment can be flexibly deformed according to the specifications and operations. For example, the episode data D1 may have items such as the purpose and destination related to the episode.

[0066] [Example of the data structure of template data] FIG. 6 is a diagram showing an example of the template data D2 according to the embodiment. As shown in FIG. 6, the template data D2 has items such as classification and template, for example. The classification has, for example, classifications of episodes such as past, future, and during conversation (currently recognized). The template has data for conducting a dialogue based on the items of the episode data D1. The template is an example of an algorithm. In this embodiment, the information processing apparatus 100 will explain the case of generating the dialogue data D5 using the template, but the dialogue data D5 may also be generated using an application, a module, etc. for executing the algorithm.

[0067] In an example shown in FIG. 6, the template data D2 with classification in the past (1) shows an algorithm of “(when)(who)(where+at)(why+from)(with) and (target)(how)(action+ta) right?”. The template data D2 with classification in the past (2) shows an algorithm of “(when)(who)(where+at)(why+from)(with) and (target)(how)(action+te)(state+ta) right?”. The template data D2 with classification in the future shows an algorithm of “(when)(who)(where+at)(why+from)(with) and (target)(how)(action plain form) n desho”. The template data D2 with classification during conversation shows an algorithm of “(when)(who)(where+at)(why+from)(with) and (target)(how)(action plain form) ne”.

[0068] The information processing apparatus 100 generates the dialogue data D5 indicating the episode by setting the information of the items set in the episode data D1 to the corresponding items of the algorithm of the template data D2. For example, in the case of the episode data D1 of Ep1 shown in FIG. 5, the information processing apparatus 100 uses the template data D2 in the past to generate the dialogue data D5 of “Yesterday, I petted aibo at Tanaka's house right?”. The information processing apparatus 100 stores the template data D2 corresponding to the character of the agent apparatus 10 in the storage unit 120, thereby enabling a dialogue of an episode suitable for the character. The information processing apparatus 100 can enable a dialogue of an episode with a sense of familiarity by storing the template data D2 corresponding to the language of the region where the user U lives in the storage unit 120.

[0069] [Example of generating episode data] FIGS. 7 and 8 are diagrams for explaining an example of generating the episode data D1 based on the utterance data D30 according to the embodiment.

[0070] In an example shown in the left figure of FIG. 7, for the utterance data 30, the dependency structure of "yesterday", "Taro", "at home", "because it was cold", "heating", "immediately", "turned on, right" has been analyzed by syntactic analysis. "Yesterday" has a noun phrase as the clause and a time case. "Taro" has a noun phrase as the clause and a nominative case. "At home" has a noun phrase as the clause and a causal case. "Because it was cold" has an adjective phrase as the clause and an adverbial modifier clause. "Heating" has a noun phrase as the clause and an accusative case. "Immediately" has an adverbial phrase as the clause and an adverbial modifier clause. "Turned on, right" has a verb phrase as the clause and a predicate clause. In this case, based on the analysis result of the utterance data D30, the information processing apparatus 100 generates the episode data D1 shown in the right figure of FIG. 7 and stores it in the storage unit 120 as the episode data D1 of the user U. In the episode data D1, "yesterday" is set in the When item, "Taro" is set in the Who item, "turn on" is set in the Action item, "heating" is set in the Target item, "because it was cold" is set in the Why item, and "immediately" is set in the How item, and the other items are blank.

[0071] In an example shown in the left figure of FIG. 8, for the utterance data D30, the dependency structure of "last weekend", "with family", "zoo", "went, right" has been analyzed by syntactic analysis. "Last weekend" has a noun phrase as the clause and a time case. "With family" has a noun phrase as the clause and a causal case. "Zoo" has a noun phrase as the clause and an accusative case. "Went, right" has a verb phrase as the clause and a predicate clause. In this case, based on the analysis result of the utterance data D30, the information processing apparatus 100 generates the episode data D1 shown in the right figure of FIG. 8 and stores it in the storage unit 120 as the episode data D1 of the user U. In the episode data D1, "last weekend" is set in the When item, "speaker" is set in the Who item, "go" is set in the Action item, and "zoo" is set in the Target item, and the other items are blank. When the nominative case is not included in the utterance data D30, the speaker of the agent device 10 is set in the Who item of the episode data D1.

[0072] [Example of the processing procedure of the information processing apparatus according to the embodiment (1)] FIG. 9 is a flowchart showing an example (1) of a processing procedure of the information processing apparatus 100 according to the embodiment. The processing procedure shown in FIG. 9 is realized by the control unit 130 of the information processing apparatus 100 executing a program. The processing procedure shown in FIG. 9 is repeatedly executed when the information processing apparatus 100 controls the dialogue of the agent apparatus 10. That is, the processing procedure shown in FIG. 9 is repeatedly executed by the information processing apparatus 100, for example, during the dialogue with the user U.

[0073] As shown in FIG. 9, the control unit 130 of the information processing apparatus 100 extracts topic information from the analysis result of the utterance data D30 (step S101). For example, the control unit 130 extracts words, character strings, etc. that satisfy extraction conditions such as when, where, who, what was done, what was the state, what, what, who with, why, how, purpose, and what was the result as topic information. When the control unit 130 stores the extraction result in the storage unit 120, the process proceeds to step S102.

[0074] The control unit 130 acquires the episode data D1 related to the topic information from the storage unit 120 (step S102). For example, the control unit 130 searches for the episode data D1 having the topic information and acquires the episode data D1 that satisfies the dialogue conditions from the storage unit 120. The dialogue conditions include, for example, that the number, ratio, etc. of the words included in the episode data D1 that match the topic information are equal to or greater than a preset threshold. When the control unit 130 acquires a plurality of episode data D1, it uses the episode data D1 with the highest degree of match or the episode data D1 not used in the past dialogue. When the control unit 130 stores in the storage unit 120 an acquisition result indicating whether or not the episode data D1 has been acquired, the process proceeds to step S103.

[0075] Based on the acquisition result of the storage unit 120, the control unit 130 determines whether the episode data D1 has been acquired (step S103). If the control unit 130 determines that the episode data D1 has been acquired (Yes in step S103), the process proceeds to step S104. The control unit 130 generates the dialogue data D5 based on the episode data D1 and the template data D2 (step S104). For example, the control unit 130 acquires from the storage unit 120 the template data D2 of the classification corresponding to the information in the when item of the episode data D1. When the when item indicates the past, the control unit 130 acquires the template data D2 whose classification is the past. The control unit 130 generates the dialogue data D5 by setting the information set in the item of the episode data D1 into the template of the acquired template data D2. After storing the generated dialogue data D5 in the storage unit 120, the control unit 130 proceeds to step S106 described later.

[0076] Also, when the control unit 130 determines that the episode data D1 has not been acquired (No in step S103), the process proceeds to step S105. The control unit 130 generates the dialogue data D5 different from the episode (step S105). For example, the control unit 130 selects one from the scenario dialogue, the verbalization of the situation, the knowledge-based dialogue, and the casual conversation based on the history of the previous conversations with the user U and generates the dialogue data D5. When the control unit 130 selects the scenario dialogue, it generates the dialogue data D5 based on the scenario corresponding to the utterance content of the user U. When the control unit 130 selects the verbalization of the situation, it generates the dialogue data D5 corresponding to the current situation recognized via the agent device 10. When the control unit 130 selects the knowledge-based dialogue, it generates the dialogue data D5 based on the utterance content of the user U and the knowledge data D10. When the control unit 130 selects the casual conversation, it generates the dialogue data D5 that responds to the utterance content of the user U. After storing the generated dialogue data D5 in the storage unit 120, the control unit 130 proceeds to step S106.

[0077] Based on the generated dialogue data D5, the control unit 130 controls the dialogue with the speaker (step S106). For example, the control unit 130 instructs the agent device 10 to conduct a dialogue based on the dialogue data D5 via the communication unit 110. As a result, the agent device 10 realizes a dialogue with the user U by making an utterance based on the instructed dialogue data D5. When the process of step S106 is completed, the control unit 130 ends the processing procedure shown in FIG. 9.

[0078] In the processing procedure shown in FIG. 9, the control unit 130 functions as the acquisition unit 132 by executing step S102. The control unit 130 functions as the dialogue control unit 133 by executing the processes from step S103 to step S106.

[0079] In this way, when the information processing apparatus 100 acquires the episode data D1 regarding the topic information included in the utterance data D30 of the user U, it can realize a dialogue including the episode of the speaker based on the episode data D1. The information processing apparatus 100 can provide the episode based on the episode data D1 of the user U during the dialogue with the user U. As a result, the information processing apparatus 100 can realize a dialogue that the user U feels close to by including the episode of the user U in the dialogue.

[0080] [Example of the processing procedure of the information processing apparatus according to the embodiment (2)] FIG. 10 is a flowchart showing an example of the processing procedure (2) of the information processing apparatus 100 according to the embodiment. The processing procedure shown in FIG. 10 is realized when the control unit 130 of the information processing apparatus 100 executes a program. The processing procedure shown in FIG. 10 is executed by the information processing apparatus 100 in order to spontaneously engage in a dialogue with the user U when the user U (the speaker) of the agent device 10 is recognized and no dialogue has been conducted with the user U.

[0081] As shown in FIG. 10, the control unit 130 of the information processing apparatus 100 determines whether or not the speaker of the agent apparatus 10 has been recognized (step S201). For example, the control unit 130 acquires the sensor information of the agent apparatus 10 via the communication unit 110, and performs recognition processing such as the face and voiceprint of the speaker based on the sensor information and the user data D3 associated with the agent apparatus 10. When the control unit 130 determines that the speaker has not been recognized based on the result of the recognition processing (No in step S201), the control unit 130 ends the processing procedure shown in FIG. 10.

[0082] When the control unit 130 determines that the speaker has been recognized based on the result of the recognition processing (Yes in step S201), the control unit 130 advances the processing to step S202. The control unit 130 acquires the episode data D1 that satisfies the acquisition condition from the storage unit 120 (step S202). The acquisition condition has, for example, conditions for acquiring the most recent episode of the speaker, an episode corresponding to the time zone, etc. For example, when the acquisition condition is a condition for acquiring the most recent episode, the control unit 130 acquires the latest episode data D1 from the storage unit 120. For example, when the acquisition condition is a condition for acquiring an episode corresponding to the time zone, the control unit 130 refers to the When item of the episode data D1 and acquires the episode data D1 suitable for the time zone from the storage unit 120. For example, when the time zone is morning, the control unit 130 acquires the episode data D1 indicating today's schedule, yesterday's events, etc. from the storage unit 120. For example, when the time zone is noon, the control unit 130 acquires the episode data D1 indicating the afternoon schedule, the night schedule, etc. from the storage unit 120. For example, when the time zone is night, the control unit 130 acquires the episode data D1 indicating today's events, tomorrow's schedule, etc. from the storage unit 120. When the processing of step S202 is completed, the control unit 130 advances the processing to step S203.

[0083] The control unit 130 generates the dialogue data D5 based on the episode data D1 and the template data D2 (step S203). For example, the control unit 130 acquires from the storage unit 120 the template data D2 of the classification corresponding to the information in the when item of the episode data D1. The control unit 130 generates the dialogue data D5 for the agent device 10 to speak spontaneously by setting the information set in the item of the episode data D1 into the template of the acquired template data D2. When the control unit 130 stores the generated dialogue data D5 in the storage unit 120, it proceeds with the process to step S204.

[0084] Based on the generated dialogue data D5, the control unit 130 controls the dialogue with the speaker (step S204). For example, the control unit 130 instructs the agent device 10 to have a dialogue based on the dialogue data D5 via the communication unit 110. Thereby, the agent device 10 has a spontaneous dialogue with the user U by making a speech based on the instructed dialogue data D5. When the process of step S204 is completed, the control unit 130 ends the processing procedure shown in FIG. 10.

[0085] In the processing procedure shown in FIG. 10, the control unit 130 functions as the acquisition unit 132 by executing step S202. The control unit 130 functions as the dialogue control unit 133 by executing the processes from step S203 to step S204.

[0086] In this way, the information processing device 100 can acquire the episode data D1 that satisfies the acquisition conditions regardless of the speaker's speech data D30, and can spontaneously provide the episode based on the episode data D1. Further, since the information processing device 100 can acquire various episode data D1 according to the acquisition conditions, it can spontaneously provide various episodes. As a result, the information processing device 100 can provide the user U's episode even when not in dialogue with the user U, thereby making the user U feel a sense of familiarity.

[0087] [Example of data structure of question data] FIG. 11 is a diagram showing an example of question data D4 according to an embodiment. As shown in FIG. 11, the question data D4 has items such as, for example, time zones and question contents. The time zone is, for example, a time zone for asking questions such as morning, noon, and night. The question content has data for asking questions according to the time zone.

[0088] In the example shown in FIG. 11, the question data D4 with the time zone being morning has question contents such as, for example, "Are you going anywhere today?", "What are your plans for today?", "What are you going to do today?", "What did you do yesterday?", "Where did you go yesterday?", etc. The question data D4 with the time zone being noon has question contents such as, for example, "What are you going to eat for dinner?", "What are you going to do this afternoon?", etc. The question data D4 with the time zone being night has question contents such as, for example, "What are you going to do tomorrow?", "What did you do today?", etc.

[0089] [Processing Procedure of Information Processing Apparatus for Generating Episode Data Using Questions] FIG. 12 is a flowchart showing the processing procedure of the information processing apparatus 100 for generating episode data using questions. The processing procedure shown in FIG. 12 is realized by the control unit 130 of the information processing apparatus 100 executing a program. The processing procedure shown in FIG. 12 is executed by the information processing apparatus 100 when the user U (speaker) of the agent apparatus 10 is recognized.

[0090] As shown in FIG. 12, the control unit 130 of the information processing apparatus 100 determines whether the speaker of the agent apparatus 10 has been recognized (step S301). If the control unit 130 determines that the speaker has not been recognized (No in step S301), the control unit 130 ends the processing procedure shown in FIG. 12. Also, if the control unit 130 determines that the speaker has been recognized (Yes in step S301), the control unit 130 proceeds to step S302.

[0091] Based on the question data D4, the control unit 130 controls the dialogue with the speaker (step S302). For example, the control unit 130 acquires the question data D4 corresponding to the current time zone from the storage unit 120, and via the communication unit 110, instructs the agent device 10 to conduct a dialogue based on the said question data. Thereby, the agent device 10 issues a question sentence to the user U by making an utterance based on the instructed dialogue data D5. When the process of step S302 is completed, the control unit 130 advances the process to step S303.

[0092] The control unit 130 acquires the analysis result of the utterance data D30 corresponding to the question data D4 (step S303). For example, the control unit 130 acquires the analysis result of the utterance data D30 after instructing a dialogue based on the question data D4. When the control unit 130 acquires the analysis result of the utterance data D30, it advances the process to step S304.

[0093] Based on the analysis result of the utterance data D30, the control unit 130 generates the episode data D1 (step S304). For example, the control unit 130 generates the episode data D1 as shown in FIGS. 7 and 8 based on the analysis result of the utterance data D30. For example, when the analysis result of the utterance data D30 contains information regarding an episode, the control unit 130 generates the episode data D1. For example, when the analysis result of the utterance data D30 does not contain information for generating an episode, the control unit 130 does not generate the episode data D1. Information for generating an episode includes, for example, information corresponding to items such as Action, When, etc. Returning to FIG. 12, by executing step S304, the control unit 130 functions as the generation unit 134. When the process of step S304 is completed, the control unit 130 advances the process to step S305.

[0094] The control unit 130 determines whether the episode data D1 has been generated in step S304 (step S305). If the control unit 130 determines that the episode data D1 has not been generated (No in step S305), it ends the processing procedure shown in FIG. 12. Also, if the control unit 130 determines that the episode data D1 has been generated (Yes in step S305), it advances the processing to step S306. The control unit 130 stores the generated episode data D1 in the storage unit 120 in association with the speaker (step S306). For example, the control unit 130 stores the episode data D1 in the storage unit 120 in association with the user data D3 of the speaker who recognized the episode data D1. When the processing in step S306 is completed, the control unit 130 ends the processing procedure shown in FIG. 12.

[0095] [Example of Generation of Episode Data Using Questions] FIG. 13 is a diagram showing an example of generation of episode data using questions of the information processing apparatus 100 according to the embodiment.

[0096] In an example shown in FIG. 13, when the agent device 10 recognizes the user U, it is instructed from the information processing apparatus 100 and issues a speech C21 based on the question data D4. The speech C21 is, for example, "Where are you going today?" In response to the speech C21, the user U issues a speech C22. The speech C22 is, for example, "Picnicking with friends." The agent device 10 transmits the speech data of the speech C22 to the information processing apparatus 100.

[0097] The information processing apparatus 100 analyzes the speech data D30 of the utterance C22 and extracts the topic information of "friends" and "picnic". Also, the question sentence of the utterance C21 includes the topic information of "today" and "go". In this case, the information processing apparatus 100 generates the episode data D1 shown in the lower right of FIG. 13 based on the analysis result of the speech data D30 and the question data D4, and stores it in the storage unit 120 as the episode data D1 of the user U. In the episode data D1, "today" is set in the When item, "the speaker" is set in the Who item, "go" is set in the Action item, "picnic" is set in the Target item, and "friends" is set in the With item, and the other items are blank.

[0098] In this way, since the information processing apparatus 100 can ask the user U questions based on the question data D4 and generate the episode data D1 from the analysis result of the speech data D30 corresponding to the questions and the question data D4, various episode data D1 of the user U can be constructed. As a result, the information processing apparatus 100 can maintain the freshness of the episodes provided to the user U by enriching the episodes that can be provided to the user U.

[0099] [Processing Procedure of Information Processing Apparatus for Generating Episode Data Using Related Information] FIG. 14 is a flowchart showing a processing procedure related to the generation of episode data based on the related information of the information processing apparatus 100. The processing procedure shown in FIG. 14 is realized by the control unit 130 of the information processing apparatus 100 executing a program. The processing procedure shown in FIG. 14 is executed by the information processing apparatus 100 when the user U (speaker) of the agent apparatus 10 is recognized.

[0100] As shown in FIG. 14, the control unit 130 of the information processing apparatus 100 collects related information about the user U via the communication unit 110 (step S401). The related information includes, for example, sensor information of the agent device 10 indicating the situation of the user U. The related information is information for telling the past situation of the user U as an episode. The related information includes, for example, information indicating that a friend of the user U has come, information indicating that parents or relatives were watching television on the weekend, etc. The related information may include, for example, the schedule of the user U, information such as SNS (Social Networking Service). When the control unit 130 stores the collected related information in the storage unit 120, the process proceeds to step S402.

[0101] The control unit 130 generates episode data D1 based on the collected related information (step S402). For example, the control unit 130 analyzes the related information and generates episode data D1 indicating the past situation based on the analysis result. For example, when the related information is information indicating that "a friend came yesterday", the control unit 130 generates episode data D1 in which "yesterday" is set in the When item, "friend" is set in the Who item, "come" is set in the Action item, and "home" is set in the Where item, and the other items are blank. When the process of step S402 is completed, the control unit 130 proceeds to step S403.

[0102] The control unit 130 determines whether the episode data D1 has been generated in step S402 (step S403). If the control unit 130 determines that the episode data D1 has not been generated (No in step S403), the control unit 130 ends the processing procedure shown in FIG. 14. Also, if the control unit 130 determines that the episode data D1 has been generated (Yes in step S403), the process proceeds to step S404. The control unit 130 stores the generated episode data D1 in the storage unit 120 in association with the speaker (step S404). When the process of step S404 is completed, the control unit 130 ends the processing procedure shown in FIG. 14.

[0103] [Example of Using Episode Data Based on Related Information] FIG. 15 is a diagram showing an example of using episode data based on related information of the information processing apparatus 100 according to the embodiment.

[0104] In an example shown in FIG. 15, based on the collected related information, the information processing apparatus 100 generates episode data D1 shown at the lower right of FIG. 15 and stores it in the storage unit 120 as the episode data D1 of the user U. In the episode data D1, “yesterday” is set in the When item, “friend” is set in the Who item, “home” is set in the Where item, and “come” is set in the Action item, and the other items are blank.

[0105] When the information processing apparatus 100 recognizes the user U via the agent apparatus 10, it generates dialogue data D5 based on the episode data D1 and the template data D2 in FIG. 15 showing the past situation of the user U. The information processing apparatus 100 instructs the agent apparatus 10 to make a speech based on the generated dialogue data D5. The agent apparatus 10 makes a speech S31 based on the dialogue data D5. The speech C31 is, for example, “A friend came to my home yesterday.” In response to the speech C31, the user U makes a speech C32. The speech C32 is, for example, “That's right.”

[0106] As described above, since the information processing apparatus 100 can collect the related information of the user U and generate the episode data D1 based on the related information, it can construct the episode data D1 corresponding to the past situation of the user U. As a result, the information processing apparatus 100 can maintain the freshness of the episodes provided to the user U by further enriching the episodes that can be provided to the user U.

[0107] [Generalization Function of Episode Data of Information Processing Apparatus] The information processing apparatus 100 further has a function of generating generalized episode data D1 based on the common data of a plurality of episode data D1. FIG. 16 is a diagram for explaining the generalization of a plurality of episode data D1. As shown in FIG. 16, assume that the information processing apparatus 100 has, as the episode data D1 of the user U, episode data D1 in which the item of Ep_id is Ep11, Ep12, and Ep13. The episode data D1 of Ep11 is data indicating the episode of "On September 1st, Yamada goes to the company by taxi". The episode data D1 of Ep12 is data indicating the episode of "On September 2nd, Yamada goes to the company with a subordinate because of a chance meeting". The episode data D1 of Ep13 is data indicating the episode of "On September 3rd, Yamada goes to the company late".

[0108] In this case, for the episode data D1 of Ep11, Ep12, and Ep13, the information in the items of Who, Where, and Action matches. When the control unit 130 of the information processing apparatus 100 detects a group of episode data D1 in which the number of matching items is equal to or greater than a preset threshold among the plurality of episode data D1, it performs generalization of the episode data D1. In an example shown in FIG. 16, the information processing apparatus 100 generates episode data D1 in which the three items of Who, Where, and Action are generalized, with the item of Ep_id being Ep20. That is, in the episode data D1 of Ep20, "Yamada" is set in the item of Who, "the company" is set in the item of Where, and "goes" is set in the item of Action, and the other items are blank.

[0109] In this way, when there are a plurality of similar episode data D1, the information processing apparatus 100 can generate episode data D1 that generalizes the tendency of the user U's behavior. As a result, the information processing apparatus 100 can realize a dialogue with the user U based on the generalized episode using the generalized episode data D1. For example, when generating generalized episode data D1 of Ep20, the information processing apparatus 100 can realize a dialogue based on dialogue data D5 such as "Are you going to the company again today?", "Aren't you going to the company today?", "How was the company today?".

[0110] [Hardware Configuration] The information device of the information processing system 1 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in FIG. 17, for example. Hereinafter, the information processing apparatus 100 according to the embodiment will be described as an example. FIG. 17 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing apparatus 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface 1500, and an input / output interface 1600. Each part of the computer 1000 is connected by a bus 1050.

[0111] The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each part. For example, the CPU 1100 expands a program stored in the ROM 1300 or the HDD 1400 into the RAM 1200 and executes processing corresponding to various programs.

[0112] The ROM 1300 stores a boot program such as BIOS (Basic Input Output System) executed by the CPU 1100 when the computer 1000 starts up, and a program dependent on the hardware of the computer 1000.

[0113] The HDD 1400 is a computer-readable recording medium that non-temporarily records programs executed by the CPU 1100, data used by such programs, and the like. Specifically, the HDD 1400 is a recording medium that records an information processing program according to the present disclosure, which is an example of program data 1450.

[0114] The communication interface 1500 is an interface for connecting the computer 1000 to an external network 1550 (for example, the Internet). For example, the CPU 1100 receives data from other devices or transmits data generated by the CPU 1100 to other devices via the communication interface 1500.

[0115] The input / output interface 1600 is an interface for connecting the input / output device 1650 and the computer 1000. For example, the CPU 1100 receives data from an input device such as a keyboard or a mouse via the input / output interface 1600. Also, the CPU 1100 transmits data to an output device such as a display, a speaker, or a printer via the input / output interface 1600. Further, the input / output interface 1600 may function as a media interface for reading a program or the like recorded on a predetermined recording medium (media). The media is, for example, an optical recording medium such as a DVD (Digital Versatile Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0116] For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes functions such as the recognition unit 131, the acquisition unit 132, the dialogue control unit 133, the generation unit 134, the collection unit 135, and the operation control unit 140 by executing the information processing program loaded on the RAM 1200. In addition, the HDD 1400 stores the information processing program according to the present disclosure and the data in the storage unit 120. Note that the CPU 1100 reads and executes the program data 1450 from the HDD 1400. As another example, these programs may be acquired from other devices via the external network 1550.

[0117] In the above-described embodiment, the information processing system 1 has been described for the case where the agent device 10 and the information processing apparatus 100 cooperate to execute the dialogue process, but it is not limited thereto. For example, in the information processing system 1, the agent device 10 may execute the dialogue process alone. In this case, the agent device 10 may realize the acquisition unit 132, the dialogue control unit 133, the generation unit 134, the collection unit 135, the operation control unit 140, etc. of the information processing apparatus 100 with the control unit 16.

[0118] As described above, the preferred embodiments of the present disclosure have been described in detail with reference to the accompanying drawings, but the technical scope of the present disclosure is not limited to such examples. It is obvious that those having ordinary knowledge in the technical field of the present disclosure can conceive of various modification examples or correction examples within the scope of the technical idea described in the claims, and these are also naturally understood to belong to the technical scope of the present disclosure.

[0119] In addition, the effects described in this specification are merely illustrative or exemplary and not restrictive. That is, the technology according to the present disclosure may exhibit other effects obvious to those skilled in the art from the description of this specification, together with or instead of the above-described effects.

[0120] Also, a program for causing hardware such as a CPU, ROM, and RAM incorporated in a computer to exhibit functions equivalent to those of the information processing apparatus 100 can be created, and a computer-readable recording medium storing the program can also be provided.

[0121] Also, each step related to the processing of the information processing apparatus 100 in this specification does not necessarily have to be processed in time series in the order described in the flowchart. For example, each step related to the processing of the information processing apparatus 100 may be processed in an order different from the order described in the flowchart or may be processed in parallel.

[0122] Although the information processing apparatus 100 in this specification has been described for the case of providing the episode data D1 through interaction (voice) with the user U via the agent apparatus 10, it is not limited thereto. For example, the information processing apparatus 100 may be configured to provide the episode data D1 via a display device, or to provide the episode data D1 in a combination of display and voice output.

[0123] (Effect) The information processing apparatus 100 includes an acquisition unit 132 that acquires episode data D1 related to the topic information included in the speaker's utterance data D30 from a storage unit 120 that stores the speaker's episode data D1, and an interaction control unit 133 that controls the interaction with the speaker so as to include an episode based on the episode data D1.

[0124] Thereby, when the information processing apparatus 100 acquires the episode data D1 related to the topic information included in the speaker's utterance data D30, it can realize an interaction including the speaker's episode based on the episode data D1. The information processing apparatus 100 can provide an episode based on the speaker's episode data D1 during the interaction with the speaker. As a result, the information processing apparatus 100 can realize an interaction that the speaker feels a sense of familiarity by including the speaker's episode in the interaction.

[0125] In the information processing apparatus 100, the dialogue control unit 133 generates dialogue data D5 including an episode based on the episode data D1 and an algorithm for generating a dialogue sentence, and controls the dialogue based on the dialogue data D5.

[0126] As a result, the information processing apparatus 100 can generate the dialogue data D5 including the speaker's episode based on the episode data D1 and the algorithm, so that the configuration of the episode data D1 can be simplified. As a result, the information processing apparatus 100 can construct various episode data D1 of the speaker, so that various episodes can be included in the dialogue with the speaker, and a dialogue with which the speaker has a stronger sense of familiarity can be realized.

[0127] In the information processing apparatus 100, the algorithm has a template according to the classification of the episode, and the dialogue control unit 133 sets the data of the episode data D1 in the template to generate the dialogue data D5.

[0128] As a result, the information processing apparatus 100 can set the data of the episode data D1 in the template to generate the dialogue data D5, so that the process of generating the episode data D1 can be simplified. Further, the information processing apparatus 100 can obtain the episode data D1 suitable for the speaker's utterance content by classifying the episode data D1. As a result, the information processing apparatus 100 can include an episode suitable for the speaker's utterance content in the dialogue, so that a dialogue with which the speaker has a stronger sense of familiarity can be realized.

[0129] In the information processing apparatus 100, the acquisition unit 132 acquires the episode data D1 in which the topic information satisfies the dialogue condition.

[0130] As a result, the information processing apparatus 100 can acquire episode data D1 suitable for the topic information according to the dialogue conditions, and generate dialogue data D5 based on the episode data D1. As a result, since the information processing apparatus 100 can include an episode that satisfies the dialogue conditions in the dialogue, it is possible to realize a dialogue in which the speaker has a stronger sense of familiarity.

[0131] In the information processing apparatus 100, when the acquisition unit 132 recognizes the speaker, the acquisition unit 132 acquires episode data D1 that satisfies the acquisition conditions, and the dialogue control unit 133 controls the dialogue with the speaker so as to spontaneously utter the episode indicated by the acquired episode data D1.

[0132] As a result, the information processing apparatus 100 can acquire episode data D1 that satisfies the acquisition conditions regardless of the utterance of the speaker, and can spontaneously provide an episode based on the episode data D1. In addition, since the information processing apparatus 100 can acquire various episode data D1 according to the acquisition conditions, it can spontaneously provide various episodes. As a result, even when not in dialogue with the speaker, the information processing apparatus 100 can provide the speaker's episode, thus making the speaker feel a sense of familiarity.

[0133] In the information processing apparatus 100, when the acquisition unit 132 does not acquire the episode data D1, the dialogue control unit 133 controls the dialogue with the speaker based on dialogue data D5 different from the episode.

[0134] As a result, when the information processing apparatus 100 cannot acquire episode data D1 suitable for the utterance content of the speaker, it can realize a dialogue based on dialogue data D5 that does not include an episode. As a result, when there is no episode suitable for the utterance content of the speaker, the information processing apparatus 100 can suppress the interruption of the dialogue with the speaker by having a dialogue different from the episode.

[0135] The information processing apparatus 100 further includes a generation unit 134 that generates episode data D1 based on the analysis result of the utterance data D30, and a storage unit 120 that stores the episode data D1 in association with the speaker.

[0136] Thereby, when the information processing apparatus 100 generates the episode data D1 based on the analysis result of the speaker's utterance data D30, the episode data D1 can be stored in the storage unit 120 in association with the speaker. As a result, the information processing apparatus 100 can enrich the episodes included in the dialogue with the speaker by constructing the episode data D1 corresponding to the speaker's utterance content, so that a dialogue in which the speaker has a stronger sense of intimacy can be realized.

[0137] In the information processing apparatus 100, the dialogue control unit 133 controls the dialogue with the speaker based on the question data D4 for questioning the speaker, and the generation unit 134 generates the episode data D1 based on the analysis result of the utterance data D30 corresponding to the question data D4 and the question data D4.

[0138] Thereby, the information processing apparatus 100 can question the speaker based on the question data D4 and generate the episode data D1 from the analysis result of the utterance data D30 corresponding to the question and the question data D4, so that various episode data D1 of the speaker can be constructed. As a result, the information processing apparatus 100 can maintain the freshness of the episodes provided to the speaker by enriching the episodes that can be provided to the speaker.

[0139] The information processing apparatus 100 further includes a collection unit 135 that collects related information about the speaker's past situation, and the generation unit 134 generates the episode data D1 based on the related information.

[0140] As a result, the information processing apparatus 100 can collect the relevant information of the speaker and generate the episode data D1 based on the relevant information, so that the episode data D1 corresponding to the past situation of the speaker can be constructed. As a result, the information processing apparatus 100 can maintain the freshness of the episodes provided to the speaker by further enriching the episodes that can be provided to the speaker.

[0141] In the information processing apparatus 100, the generation unit 134 generates generalized episode data d1 based on the common data of the episode data D1 in the storage unit 120.

[0142] As a result, when the information processing apparatus 100 includes common data in the speaker's episode data D1, the information processing apparatus 100 can generate episode data D1 obtained by generalizing the common data. As a result, the information processing apparatus 100 can realize a conversation including generalized speaker episodes, so that it can provide a conversation with a sense of intimacy without interruption of the conversation with the speaker.

[0143] The information processing system 1 is an information processing system 1 including an agent device 10 that collects the utterance data D30 of the speaker and an information processing apparatus 100. The information processing apparatus 100 includes an acquisition unit 132 that acquires, from the storage unit 120 that stores the speaker's episode data D1, the episode data D1 related to the topic information included in the utterance data D30, and a dialogue control unit 133 that controls the dialogue with the speaker so as to include an episode based on the episode data D1.

[0144] As a result, when the information processing system 1 acquires the episode data D1 related to the topic information included in the utterance data D30 of the speaker, the information processing system 1 can realize a conversation including the speaker's episode based on the episode data D1. The information processing system 1 can provide an episode based on the speaker's episode data D1 during the conversation with the speaker. As a result, the information processing system 1 can realize a conversation in which the speaker has a sense of intimacy by including the speaker's episode in the conversation.

[0145] In the information processing system 1, the agent device 10 is a movable robot, and the dialogue control unit 133 controls the dialogue with the speaker via the agent device 10.

[0146] As a result, the information processing system 1 can collect the speaker's utterance data D30 via the agent device 10 and realize a dialogue including the speaker's episode based on the episode data D1. As a result, the information processing system 1 can realize a friendly dialogue between the speaker and the robot by including the speaker's episode in the dialogue with the movable robot.

[0147] The information processing method includes: the computer obtaining, from the storage unit 120 that stores the speaker's episode data D1, the episode data D1 related to the topic information included in the speaker's utterance data D30; and controlling the dialogue with the speaker so as to include the episode based on the episode data D1.

[0148] As a result, when the information processing method obtains the episode data D1 related to the topic information included in the speaker's utterance data D30, the computer can realize a dialogue including the speaker's episode based on the episode data D1. The information processing method can provide the episode based on the speaker's episode data D1 during the dialogue with the speaker. As a result, the information processing method can realize, by the computer, a dialogue in which the speaker has a sense of familiarity by including the speaker's episode in the dialogue.

[0149] Note that the following configurations also belong to the technical scope of the present disclosure. (1) An acquisition unit that acquires, from a storage unit that stores the speaker's episode data, the episode data related to the topic information included in the speaker's utterance data; A dialogue control unit that controls the dialogue with the speaker so as to include the episode based on the episode data; An information processing apparatus comprising: (2) The dialogue control unit generates dialogue data including the episode based on the episode data and an algorithm for generating dialogue sentences, and controls the dialogue based on the dialogue data. The information processing apparatus according to (1) above. (3) The algorithm has a template according to the classification of the episode. The dialogue control unit generates the dialogue data by setting the data of the episode data in the template. The information processing apparatus according to (2) above. (4) The acquisition unit acquires the episode data for which the topic information satisfies the dialogue conditions. The information processing apparatus according to any one of (1) to (3) above. (5) When the acquisition unit recognizes the speaker, the acquisition unit acquires the episode data that satisfies the acquisition conditions. The dialogue control unit controls the dialogue with the speaker so as to spontaneously utter the episode indicated by the acquired episode data. The information processing apparatus according to (4) above. (6) When the acquisition unit is not acquiring the episode data, the dialogue control unit controls the dialogue with the speaker based on dialogue data different from the episode. The information processing apparatus according to any one of (1) to (5) above. (7) A generation unit that generates the episode data based on the analysis result of the utterance data, A storage unit that stores the episode data in association with the speaker, and further includes The information processing apparatus according to any one of (1) to (6) above. (8) The dialogue control unit controls the dialogue with the speaker based on question data for questioning the speaker. The generation unit generates the episode data based on the analysis result of the utterance data corresponding to the question data and the question data. The information processing apparatus according to (7) above. (9) Further comprising a collection unit that collects related information regarding the past situation of the speaker, The generation unit generates the episode data based on the related information. The information processing apparatus according to (8) above. (10) The generation unit generates the generalized episode data based on the common data of the episode data in the storage unit. The information processing apparatus according to (8) or (9) above. (11) An information processing system comprising an agent device that collects the speaker's speech data and an information processing apparatus, The information processing apparatus An acquisition unit that acquires the episode data related to the topic information included in the speech data from a storage unit that stores the episode data of the speaker, A dialogue control unit that controls the dialogue with the speaker so as to include an episode based on the episode data, An information processing system comprising the same. (12) The agent device is a movable robot, The dialogue control unit controls the dialogue with the speaker via the agent device. The information processing system according to (11) above. (13) A computer Acquiring the episode data related to the topic information included in the speech data of the speaker from a storage unit that stores the episode data of the speaker, Controlling the dialogue with the speaker so as to include an episode based on the episode data, An information processing method comprising the same. (14) To a computer Acquiring the episode data related to the topic information included in the speech data of the speaker from a storage unit that stores the episode data of the speaker, Controlling the conversation with the speaker so as to include an episode based on the episode data A computer-readable recording medium storing a program for realizing the above (15) Causing a computer to Obtain, from a storage unit that stores the speaker's episode data, the episode data related to the topic information included in the speaker's utterance data Controlling the conversation with the speaker so as to include an episode based on the episode data A program for realizing the above

Explanation of Signs

[0150] 1 Information processing system 10 Agent device 11 Sensor unit 12 Input unit 13 Light source 14 Output unit 15 Driving unit 16 Control unit 17 Communication unit 100 Information processing apparatus 110 Communication unit 120 Storage unit 130 Control unit 131 Recognition unit 132 Acquisition unit 133 Conversation control unit 134 Generation unit 135 Collection unit 140 Operation control unit D1 Episode data D2 Template data D3 User data D4 Question data D5 Conversation data D10 Knowledge data D20 Management data D30 Utterance data

Claims

1. A storage unit that stores speaker episode data; An acquisition unit that acquires, from the storage unit, the episode data related to topic information included in the speaker's utterance data; A dialogue control unit that controls the dialogue between the agent device and the speaker so as to include an episode based on the episode data; A recognition unit that recognizes the speaker based on the sensor information of the agent device; Comprising: When recognizing the speaker, the acquisition unit acquires the episode data that satisfies the acquisition conditions; The dialogue control unit controls the dialogue between the agent device and the speaker so as to spontaneously utter the episode indicated by the episode data acquired by the acquisition unit; An information processing device.

2. The agent device is an automobile, The information processing device according to Claim 1.

3. The dialogue control unit further controls an utterance suitable for the character set in the agent device; The information processing device according to Claim 1.

4. A collection unit that collects related information about the speaker; A generation unit that generates the episode data based on the related information; Further comprising: The information processing device according to Claim 1.

5. The related information of the speaker is information related to the past or future situation of the speaker; The information processing device according to Claim 4.

6. The related information of the speaker includes information of at least one of persons and animals related to the speaker; The information processing device according to Claim 4.

7. The generation unit generates the generalized episode data based on the common data of the episode data in the storage unit; The information processing device according to Claim 4.

8. The dialogue control unit adds a specific episode to the episode data related to the speaker based on the dialogue with the speaker; The information processing device according to Claim 1.

9. The episode data is stored in the storage unit in association with a location; The information processing device according to Claim 1.

10. The location includes a destination; The information processing device according to Claim 9.

11. When the acquisition unit is not acquiring the episode data, the dialogue control unit controls the dialogue with the speaker based on dialogue data different from the episode; The information processing device according to Claim 1.

12. The dialogue control unit generates dialogue data by converting the date and time data included in the episode data into relative date and time. The information processing apparatus according to claim 1.

13. A computer obtains, from a storage unit that stores the speaker's episode data, the episode data related to the topic information included in the speaker's utterance data; controls the dialogue with the speaker of the agent device so as to include an episode based on the episode data; recognizes the speaker based on the sensor information of the agent device; including when recognizing the speaker, the obtaining obtains the episode data that satisfies the obtaining conditions; the controlling controls the dialogue with the speaker of the agent device so that the agent device spontaneously utters the episode indicated by the episode data obtained by the obtaining. Information processing method.

14. A computer obtains, from a storage unit that stores the speaker's episode data, the episode data related to the topic information included in the speaker's utterance data; controls the dialogue with the speaker of the agent device so as to include an episode based on the episode data; recognizes the speaker based on the sensor information of the agent device; causes to execute when recognizing the speaker, the obtaining obtains the episode data that satisfies the obtaining conditions; the controlling controls the dialogue with the speaker of the agent device so that the agent device spontaneously utters the episode indicated by the episode data obtained by the obtaining. An information processing program for

Images