JP2018008316A - Learning type robot, learning type robot system, and program for learning type robot - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a learning type robot capable of autonomously learning what action to execute according to information from outside, and performing mutual learning with another robot, a learning type robot system, and a program for the learning type robot.SOLUTION: A learning type robot 1 that learns what action to execute according information from outside includes an analysis part 40 for analyzing a content indicated by outside information which is the information from outside so that it contributes to the execution of the action of the learning type robot 1, and generating analysis result information, a learning unit 50 for learning what action the learning type robot 1 should execute according to the analysis result information, a determination part 60 for determining the action that the learning type robot 1 should execute according to a learning result by the learning unit 50, and an action control part 70 for controlling the action of the learning type robot 1 according to the result of the determination by the determination part 60.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a learning robot, a learning robot system, and a learning robot program. In particular, the present invention relates to a learning robot, a learning robot system, and a learning robot program that autonomously execute learning.

  2. Description of the Related Art Conventionally, a robot apparatus that can operate autonomously, and includes an input unit that inputs an operation of another operation subject as an image or sound, and another operation subject according to an image or sound input via the input unit. A plurality of motion generation means for generating different motions in synchronism with the motion of the motion, a motion expression means for integrating and expressing one or more of the plurality of motions generated by the plurality of motion generation means, There is known a robot apparatus including a control means for controlling the number of actions to be integrated in the means or a ratio of each action when a plurality of actions are integrated (see, for example, Patent Document 1). According to the robot apparatus described in Patent Literature 1, it is possible to flexibly cope with the operation of another operation subject such as a user, and perform an operation synchronized with the operation.

JP 2005-342873 A

  However, in the robot apparatus described in Patent Document 1, even if it is possible to synchronize with information from the outside, it is not possible to learn what operation should be performed according to the information from the outside. Moreover, in the robot apparatus as described in Patent Document 1, it is not possible to learn between a plurality of robots.

  Accordingly, an object of the present invention is to provide a learning robot, a learning robot system, and a learning robot that can autonomously learn what operation should be performed according to information from the outside and can learn from other robots. To provide a program.

  In order to achieve the above object, the present invention is a learning type robot that learns what operation is performed according to information from the outside, and the contents indicated by the external information, which is information from the outside, The analysis unit generates analysis result information by analyzing so as to contribute to the execution of the operation, the learning unit that learns what operation the learning robot performs according to the analysis result information, and the learning result of the learning unit Accordingly, a learning type robot is provided that includes a determination unit that determines an operation to be performed by the learning type robot, and an operation control unit that controls the operation of the learning type robot according to the determination result of the determination unit.

  The learning robot further includes an information storage unit that stores learning result information indicating a learning result of the learning unit, and the learning unit uses the analysis result information as the learning result information stored in the information storage unit. Can also be updated.

  In the learning robot, the analysis unit can generate analysis result information by analyzing the content indicated by an external learning robot, a communication terminal, or data acquired from a database storing predetermined data. .

  The learning robot may further include a level determination unit that determines a level indicating a learning stage of the learning robot according to the learning result of the learning unit, and the determination unit may change the operation according to the level.

  In the learning robot, the external information includes at least a program that defines information indicating how the learning robot operates, and the learning unit can learn the operation of the learning robot according to the program.

  In the learning type robot, the learning unit learns the preference information indicating the user preference of the learning type robot according to the analysis result information, and the determination unit relates the preference information to the learning type robot according to the preference information. It can also be determined that the advertisement information to be output should be output.

  In the learning robot, the learning unit learns the preference information indicating the user's preference of the learning robot according to the analysis result information, and the determination unit likes the learning robot according to the level and the preference information. It can also be determined that advertisement information related to the information should be output.

  Further, in the learning type robot, the analysis result information includes user characteristic information indicating the characteristics of the user of the learning type robot, and the learning unit generates appearance information that is information on the appearance of the user derived from the user characteristic information. The determination unit can determine exterior information indicating the exterior of the learning robot that can be used by the exterior manufacturing apparatus that manufactures the exterior of the learning robot according to the exterior information.

  In the learning robot, the operation control unit can automatically input data assumed from the determination result into a predetermined form provided by the social networking service.

  In the learning robot, external information can be exchanged with other learning robots in a form that can be perceived by the user and in a form that cannot be perceived by the user.

  In the learning robot, the analysis unit classifies the external information into predetermined categories and generates analysis result information, and the learning unit analyzes the external information exchanged in a form that is not perceptible to the user. The difference information between the analysis result information generated and categorized into the category and the already learned result is extracted, and the motion control unit cannot perceive the extracted difference information to other learning robots. In addition to being supplied in a format, the operation can be controlled based on the difference information.

  In order to achieve the above object, the present invention provides an external learning robot, a communication terminal, or a database that stores predetermined data, and a learning type that learns what operation is performed according to information from the outside. A learning robot system including a robot, and the learning robot operation according to the content indicated by data acquired from an external learning robot, a communication terminal, or a database, or the content indicated by external information as external information An analysis unit that analyzes to contribute to the execution of the analysis and generates analysis result information, a learning unit that learns what operation the learning robot performs according to the analysis result information, and a learning result of the learning unit, A determination unit that determines an operation to be performed by the learning robot, and an operation control unit that controls the operation of the learning robot according to a determination result of the determination unit; Learning robot system comprising is provided.

  In the learning type robot system, the operation control unit can also supply the external learning type robot with information indicating the learning result of the learning type robot, thereby learning the external learning type robot.

  Further, the present invention is a learning robot program that is executed in a learning robot that learns what operation is executed in accordance with information from the outside in order to achieve the above object, The analysis function that generates the analysis result information by analyzing the content indicated by the external information that is the information of the learning type to contribute to the execution of the operation of the learning type robot, and what kind of operation the learning type robot performs according to the analysis result information A learning function that learns the learning, a judgment function that determines the action to be performed by the learning robot according to the learning result in the learning function, and an action control function that controls the action of the learning robot according to the judgment result in the judgment function A learning robot program that realizes the above is provided.

  According to the learning type robot, the learning type robot system, and the learning type robot program according to the present invention, it is possible to autonomously learn what operation should be performed according to information from the outside, and to learn with other robots. Learning robot, learning robot system, and learning robot program can be provided.

It is a schematic diagram of the learning type robot concerning this embodiment. It is a functional block diagram of the learning type robot which concerns on this Embodiment. It is a functional block diagram of the external information acquisition part which concerns on this Embodiment. It is a functional block diagram of the learning unit which concerns on this Embodiment. It is a functional block diagram of the output part which concerns on this Embodiment. It is a schematic diagram in the case of changing the exterior of the learning robot according to the present embodiment. It is a schematic diagram of a learning type robot system concerning this embodiment. It is an outline figure in case a learning type robot concerning this embodiment writes information in a predetermined form of a predetermined social networking service. It is a hardware block diagram of the learning type robot which concerns on this Embodiment.

[Embodiment]
(Outline of learning robot 1)
FIG. 1 shows an outline of a learning robot according to an embodiment of the present invention. In the description of FIG. 1, two learning robots and two communication terminals are illustrated for the sake of simplicity, but the number of learning robots and / or communication terminals is one. Or it may exceed two. The learning robot 1 includes a head having eyes, ears, a mouth, and the like, a torso having a display unit and the like on the front, and limbs connected to the torso. Further, each of the plurality of learning robots has substantially the same function and configuration.

  The learning robot 1 according to the present embodiment autonomously learns what operation is performed according to information from the outside. The learning type robot 1 (or learning type robot 1a) learns based on the exchange with the external database 4 by the learning type robot 1 alone, learns based on the exchange with the user by the learning type robot 1 alone, Learning autonomously based on the exchange between the learning type robot 1 and the communication terminal 2 and / or learning based on the exchange between the learning type robot 1 and the learning type robot 1a which is another learning type robot. Run.

  For example, the learning type robot 1 acquires information related to the surrounding environment (for example, position, time, temperature, illuminance, and / or noise) of the learning type robot 1 and stores information related to the acquired information in an external database. By acquiring from 4 through the communication network 5, knowledge about the surrounding environment and / or vocabulary can be learned. The learning robot 1 learns knowledge and / or vocabulary and the like, thereby improving the learning level of the learning robot 1 and changing its own movement before and after learning. In the present embodiment, the learning level is a level at which the learning robot 1 can execute a predetermined operation. A plurality of such levels can be set.

  In addition, the learning robot 1 issues a question regarding information not stored in advance to the user. For example, the learning robot 1 has a voice information acquisition unit. The learning robot 1 analyzes the voice acquired by the voice information acquisition unit. Then, as a result of the analysis, the learning robot 1 issues a question such as “What is this sound?” To the user when information regarding the content indicated by the voice is not stored in advance. The user answers the question to the learning robot 1 by voice or the like. When the learning robot 1 acquires the user's answer by voice or the like, the learning robot 1 analyzes the acquired voice or the like and stores the analysis result to learn the answer to the question.

  In addition, the learning robot 1 can supply the communication terminal 2 with questions about information that is not stored in advance. The user supplies an answer to the question to the learning robot 1 via the communication terminal 2. The learning robot 1 analyzes the answer received from the communication terminal 2 and learns by storing the answer to the question. As a result, the learning type robot 1 improves the learning level of the learning type robot 1 by newly storing knowledge and / or vocabulary regarding information that has not been stored in advance. The learning robot 1 changes its own movement before and after learning.

  Furthermore, the learning type robot 1 improves its own learning level by exchanging information with other learning type robots 1a. For example, when the learning level of the learning type robot 1 is higher than the learning level of the learning type robot 1a, the learning type robot 1 has information that is not stored in the learning type robot 1a (for example, predetermined knowledge, vocabulary, and / or An answer to a predetermined problem) is supplied to the learning robot 1a. The learning type robot 1a can improve its own learning level by learning information acquired from the learning type robot 1. Thereby, the learning type robot 1a can change its own movement before and after learning.

  The communication terminal 2 and the communication terminal 3 are mobile information terminals such as mobile phones, tablets, and smartphones, information terminals such as PCs and notebook PCs, and the like. The communication network 5 is a mobile phone network, an Internet network, or the like. Furthermore, the communication between the learning robot 1 and the communication terminal 2 and the communication between the learning robot 1 and the learning robot 1a are performed by a short distance wireless communication such as a wired LAN or a wireless LAN, or Bluetooth (registered trademark). It is executed by communication or the like.

  The learning type robot 1 has driving parts such as an actuator (not shown) at predetermined locations on the head, the trunk, and the limbs. The learning robot 1 operates the head, the torso, and / or the limbs by operating the driving components.

(Details of learning robot 1)
FIG. 2 shows an example of functional configuration blocks of the learning robot according to the embodiment of the present invention. FIG. 3 illustrates an example of a functional configuration block of the external information acquisition unit according to the embodiment of the present invention, and FIG. 4 illustrates an example of a functional configuration block of the learning unit according to the embodiment of the present invention. FIG. 5 shows an example of a functional configuration block of the output unit according to the embodiment of the present invention.

  The learning robot 1 according to the present embodiment includes a communication unit 10 that transmits / receives data to / from the outside, a data acquisition unit 20 that acquires data from the outside, and an external information acquisition unit that acquires external information that is information from the outside. 30, an analysis unit 40 that analyzes data and external information, a learning unit 50 that performs learning using the analysis result of the analysis unit 40, and the learning robot 1 executes according to the learning result of the learning unit 50 A determination unit 60 that determines what kind of operation should be performed, an operation control unit 70 that controls the operation of the learning robot 1 according to the determination result of the determination unit 60, and predetermined information controlled by the operation control unit 70 , And a drive unit 90 that drives a predetermined portion of the learning robot 1 in accordance with an instruction from the output unit 80. The learning robot 1 also stores a level determination unit 52 that determines the learning level of the learning robot 1, a level information storage unit 54 that stores the content determined by the level determination unit 52, and the learning result of the learning unit 50. And an information storage unit 56.

(Communication unit 10)
The communication unit 10 transmits / receives data to / from the outside. Specifically, the communication unit 10 receives data from the communication terminal 2 and / or another learning robot 1a. Further, the communication unit 10 receives data from the communication terminal 2 and / or another learning type robot 1 a in response to the action from the output unit 80. Further, the communication unit 10 transmits / receives data to / from an external database via the communication network 5. The communication unit 10 supplies the acquired data to the data acquisition unit 20.

(Data acquisition unit 20)
The data acquisition unit 20 acquires data from the communication terminal 2, another learning robot 1a, and / or an external database. The data acquisition unit 20 supplies the acquired data to the analysis unit 40. In the present embodiment, the data refers to various knowledge, vocabulary, answers to problems, data according to user's preference, etc., advertisement information regarding a predetermined advertisement, a program executable in the learning robot 1, and Various data such as data (for example, coupon data used in the store) transmitted from a predetermined store or another learning robot installed in the predetermined store are included. Moreover, as data, the data (for example, stock price information, futures transaction information, etc.) which fluctuate | vary according to progress of time can also be mentioned, for example.

(External information acquisition unit 30)
The external information acquisition unit 30 acquires external information that is information from the outside of the learning robot 1. The external information acquisition unit 30 supplies the acquired external information to the analysis unit 40. In the present embodiment, external information refers to position information indicating the position where the learning robot 1 is present, time information indicating the current time, environment information indicating the state of the external environment, audio information indicating the voice of the user, etc. Image information indicating an image, and / or contact information indicating that an object has contacted the surface of the learning robot 1 are included. The environment information includes temperature information indicating the temperature around the learning robot 1, humidity information indicating the humidity around the learning robot 1, illuminance information indicating the illuminance around the learning robot 1, and / or learning. Including noise information indicating the state of noise around the robot 1.

  Specifically, the external information acquisition unit 30 includes a position information acquisition unit 300 that acquires position information of the learning robot 1, a time information acquisition unit 302 that acquires time information, and an environment information acquisition unit 304 that acquires environment information. A voice information acquisition unit 306 that acquires voice information, an imaging unit 308 that captures an image, and a tactile sensor 310 that acquires contact information. The position information acquisition unit 300 is realized using GPS, for example. The environment information acquisition unit 304 is realized by using, for example, a temperature sensor that measures temperature, a humidity sensor that measures humidity, an illuminance sensor that measures illuminance, and / or a microphone that measures ambient noise. Furthermore, the voice information acquisition unit 306 is realized using a microphone or the like that acquires the voice of the user or the like. The external information acquisition unit 30 can also acquire information related to actions such as gestures of surrounding people.

(Analysis unit 40)
The analysis unit 40 analyzes the content indicated by the external information so as to contribute to the execution of the operation of the learning robot 1 and generates analysis result information. The analysis unit 40 performs, for example, voice analysis and extracts a feature quantity such as a fundamental frequency or sound spectrogram of the voice, extracts a feature quantity such as a spatial frequency of the image, or extracts a feature quantity such as a spatial frequency in the image by face recognition. It includes an image analysis unit that analyzes an image of a person included, a morpheme analysis unit that performs speech recognition and morphologically analyzes a sentence obtained by speech recognition. The analysis unit 40 generates analysis result information by analyzing the content indicated by the external learning robot 1a, the communication terminal 2, or data acquired from a database storing predetermined data. The analysis unit 40 supplies the analysis result information to the learning unit 50.

  For example, the analysis unit 40 analyzes the voice information, so that information on the contents uttered by the user or other learning type robots to the learning type robot 1 (for example, spoken sentences, words in phrases, words, and the like) (Or information indicating vocabulary or the like) is extracted to generate analysis result information. As an example, the analysis unit 40 analyzes voice information, image information, and the like, so that information indicating characteristics of the user of the learning robot 1 (for example, user's occupation, user's favorite fashion, user's favorite accessory, etc.) ) Is generated. For example, the analysis unit 40 analyzes an image captured by the imaging unit 308 and identifies a user, a user's clothes, accessories worn by the user, and the like included in the image. The analysis unit 40 can also estimate the user's emotion by analyzing the image including the user's face and / or action (for example, gesture) captured by the imaging unit 308. And the analysis part 40 produces | generates the user characteristic information containing the characteristic and emotion in the said user's external appearance according to the identified result and / or the estimated result.

  In addition, the analysis unit 40 extracts vocabulary related to emotions (for example, “happy”, “sad”, “fun”, “dull”, “interesting”, etc.) from the contents spoken by the user to the learning robot 1. Thus, analysis result information can also be generated. Furthermore, the analysis unit 40 can extract information on the intonation of the user's utterance and generate analysis result information by analyzing the voice information. Then, the analysis unit 40 may generate analysis result information by analyzing the current state of the environment where the learning robot 1 is placed from the position information, environment information, image information, and / or contact information. it can.

  Further, the analysis unit 40 analyzes the contents indicated by the data received from the data acquisition unit 20, so that various types of knowledge, vocabulary, answers to problems, user preferences, and the like received from the outside by the learning robot 1. Analysis result information can also be generated by extracting or generating data relating to various matters. The analysis unit 40 can also analyze the content indicated by the data received from the data acquisition unit 20, classify the content indicated by the external information into a predetermined category, and generate analysis result information. Pre-defined categories include technology (eg, physics, mathematics, chemistry, engineering, astronomy, medicine, etc.), literary arts (eg, novels), academic (eg, history, linguistics, etc.), art, and / or A category such as music.

(Learning unit 50, information storage unit 56)
The learning unit 50 learns what operation the learning robot 1 performs, what information contributes to the execution of the predetermined operation, etc. according to the analysis result information. Further, the information storage unit 56 stores learning result information indicating a learning result in the learning unit 50. The learning unit 50 can also update the learning result information stored in the information storage unit 56 using the analysis result information. The information storage unit 56 not only stores the learning result information according to the learning result of the learning unit 50 but also a plurality of information sets (sets including a plurality of information and / or data) corresponding to a predetermined learning level. May be stored in advance. Further, the learning robot 1 may be configured not to include the information storage unit 56. For example, the information storage unit 56 can be provided on the cloud. In this case, the communication between the learning robot 1 and the information storage unit 56 can be executed by encrypting communication contents transmitted and received between each other.

  The learning unit 50 compares the analysis result information that is the result of analyzing the external information and / or the data acquired by the data acquisition unit 20 with the learning result information stored in the information storage unit 56. The learning unit 50 determines that the analysis result information is new learning result information when the analysis result information does not match the learning result information, that is, when the learning result information is not stored in the information storage unit 56. To do. Then, the learning unit 50 stores new learning result information in the information storage unit 56. In addition, when there is learning result information that is not stored in the information storage unit 56, the learning unit 50 tells the user or the external learning type robot 1a what the superordinate concept or subordinate concept of the learning result information is. Question information for asking questions can also be generated. The learning unit 50 is configured using a learning algorithm such as a neural network, a genetic learning algorithm, and / or a machine learning algorithm, for example.

  Specifically, when information indicating the vocabulary or knowledge included in the analysis result information is not stored in the information storage unit 56 in advance, the learning unit 50 includes a question unit 500 for asking the user about the information, and analysis result information. Knowledge learning unit 502 that learns information indicating vocabulary, knowledge, or answers to predetermined questions, a user learning unit 504 that learns preference information that indicates user preferences, and an operation unique to the learning robot 1 A personality learning unit 506 that learns features, and a suggestion unit 508 that suggests that the user should perform a predetermined action by learning the contents of the analysis result information.

(Question part 500)
The question unit 500 generates question information that is information representing a question to the user or a question to another learning robot 1a. For example, when a predetermined word is included in the analysis result information and information indicating the word is not stored in the information storage unit 56, the question unit 500 displays question information asking what the word represents. Generate. As an example, when the imaging unit 308 included in the learning robot 1 captures an image including a predetermined object, the analysis unit 40 analyzes the image and generates analysis result information including information on the object (in this case, The analysis unit 40 can include a matching image storage unit that stores a matching image used for executing the object matching process. The question unit 500 confirms whether or not the information related to the object included in the analysis result information is stored in the information storage unit 56. When the information storage unit 56 does not include the information, the question unit 500 asks what the object is (for example, information that causes the output unit 80 described later to output a voice “What is that?”) ) Is generated. The question unit 500 may include a question information database that stores text data and / or voice data used for generating question information in advance. Note that when the imaging unit 308 captures an image of a predetermined object, the analysis unit 40 extracts a difference from an image previously captured for the same object (for example, stored in the information storage unit 56), and the question unit 500 can also generate analysis result information on information related to the difference between the objects.

  In addition, when the question unit 500 acquires analysis result information including the content of data acquired by the data acquisition unit 20 from another learning type robot 1a and / or an external database, the question unit 500 stores the analysis result information and the information storage unit 56 in the analysis result information. Compare with stored information. Then, when the information storage unit 56 does not include information related to the contents of the data, the question unit 500 generates question information for inquiring other learning type robot 1a and / or an external database as to what the data is. You can also Further, when part or all of the analysis result information is stored in the information storage unit 56, the question unit 500 generates question information for further deeply asking questions about the user or other learning type robot 1a or an external database. You can also

(Knowledge learning unit 502)
The knowledge learning unit 502 is information indicating vocabulary, knowledge, an answer to a predetermined question included in the analysis result information, a connection between the vocabulary and the vocabulary, and the like and information not stored in the information storage unit 56 Learning is performed by storing the data in the storage unit 56. For example, when the analysis result information includes information indicating an answer to a predetermined quiz, the knowledge learning unit 502 displays information indicating the answer in association with an identifier for identifying a sentence, a phrase, a vocabulary, and the like constituting the quiz. The information is stored in the information storage unit 56. In addition, the knowledge learning unit 502 can generate question information for the purpose of acquiring information about a point or area represented by the position information using the position information acquired by the position information acquisition unit 300. Further, the knowledge learning unit 502 associates the position information with the time information acquired by the time information acquisition unit 302, the environment information acquired by the environment information acquisition unit 304, etc. Information indicating whether the situation is present can also be generated. The knowledge learning unit 502 stores the generated information in the information storage unit 56.

  The knowledge learning unit 502 can also learn based on the difference between the analysis result information generated by classifying into predetermined categories in the analysis unit 40 and the already learned result. For example, the knowledge learning unit 502 extracts the difference between the analysis result information and the information stored in the information storage unit 56. Then, the knowledge learning unit 502 performs learning by causing the information storage unit 56 to store the difference portion, that is, information that is not stored in the information storage unit 56. In addition, the knowledge learning unit 502 executes processing for enhancing the learning effect by causing the information storage unit 56 to store the information stored in the information storage unit 56 together with the already stored information.

(User learning unit 504)
The user learning unit 504 learns the user characteristic information indicating the characteristics of the user of the learning robot 1 and / or the preference information indicating the preference according to the analysis result information. Specifically, the user learning unit 504 analyzes information included in the analysis result information, for example, information obtained by analyzing the user's voice acquired by the voice information acquisition unit 306 (for example, the vocabulary included in the voice, the frequency of the voice, and intonation. Etc.), information included in the image captured by the imaging unit 308, and / or information such as the user's contact status with the learning robot 1 acquired by the tactile sensor 310, and the user's name, gender, age Or what is the age, occupation, personality (note that personality can be classified in advance into a predetermined number of patterns (for example, serious, bright, stubborn, hail, etc.) and / or behavior patterns, etc. Preference information (that is, information indicating user characteristics and preferences) is generated. Further, the user learning unit 504 can generate appearance information that is information related to the appearance of the user derived from the user characteristic information. The user learning unit 504 stores the user characteristic information, appearance information, and / or preference information generated in the information storage unit 56 in association with a user identifier that uniquely identifies the user.

(Personality learning unit 506)
The personality learning unit 506 learns the unique operation, how to play, how to drive, and / or how to express emotions of the learning robot 1. For example, data of an application that is a program that prescribes how the learning type robot 1 operates, how to play, how to drive, and / or how to express emotions in the data included in the external information acquired by the data acquisition unit 20 The case where is included will be described. In this case, the data of this application is converted into a format that can be executed by the learning robot 1 in the analysis unit 40, and analysis result information including the converted application data is generated. Then, the personality learning unit 506 generates operation command information including a command for instructing the operation of the learning robot 1 according to the analysis result information (that is, converted application data).

(Proposal Unit 508)
The proposal unit 508 generates proposal information that suggests what operation should be performed to the user based on the analysis result information. For example, when the data acquisition unit 20 acquires, as data, various types of information related to stock prices including fluctuations in stock prices from an external database or the like, the analysis unit 40 uses the analysis result information on the predicted price of the stock price for a predetermined brand at a predetermined time. Included. And the proposal part 508 produces | generates the proposal information which tells a user the timing which purchases the stock of the brand according to the analysis result information containing the predicted amount.

  In addition, when the data acquisition unit 20 acquires information about a predetermined event (for example, information such as a predetermined event holding time, a holding place, an event content) from an external database or the like as data, the analysis unit 40 Include information related to event holding in the analysis result information. And the proposal part 508 produces | generates the proposal information which proposes participation to the event according to the information regarding holding of the event.

  The learning unit 50 supplies learning result information, question information, preference information, appearance information, proposal information, and / or action command information to the level determination unit 52, the information storage unit 56, and / or the determination unit 60.

(Level determination unit 52, level information storage unit 54)
The level determination unit 52 determines a level indicating the learning stage of the learning robot 1 according to the learning result of the learning unit 50. For example, when the learning result in the learning unit 50 reaches a predetermined level, the level determination unit 52 determines that the learning level of the learning type robot 1 is the learning level of the level. The level determination unit 52 supplies level information, which is information indicating the determined learning level, to the level information storage unit 54. The level information storage unit 54 stores this level information.

  The learning unit 50 can refer to the level information stored in the level information storage unit 54. For example, the learning unit 50 can change or modify the question information, the proposal information, and / or the operation command information to the content corresponding to the learning level corresponding to the level information according to the referenced level information. As an example, the question unit 500 included in the learning unit 50 can change the frequency of generating question information in accordance with the improvement of the learning level. For example, the question unit 500 reduces the frequency of generating question information in response to the improvement of the learning level.

(Judgment unit 60)
The determination unit 60 determines an operation to be performed by the learning robot 1 according to the learning result of the learning unit 50. Specifically, when the determination unit 60 receives learning result information, question information, preference information, appearance information, proposal information, and / or operation command information from the learning unit 50, the determination unit 60 determines an operation corresponding to the received information as a learning type. The robot 1 is determined as an operation to be executed, and determination result information which is information indicating the determination result is supplied to the operation control unit 70. Also, the determination unit 60 can change information indicating the determination result according to the learning level of the learning robot 1 stored in the level information storage unit 54. Furthermore, the determination unit 60 can also determine that outputting part or all of the information acquired from the outside by the data acquisition unit 20 to the outside is an operation to be executed.

  For example, when receiving the question information, the determination unit 60 determines that the question represented by the question information should be transmitted to the user, and supplies determination result information including the determination result to the operation control unit 70. Further, when receiving the question information from the learning unit 50, the determination unit 60 determines that the content represented by the question information should be transmitted to the communication terminal 2 or other learning type robot 1a, and includes the determination result. The result information can also be supplied to the operation control unit 70. And the judgment part 60 can also include the instruction | command which changes the frequency which transmits the question which question information represents with respect to a user according to a learning level in judgment result information. For example, the determination unit 60 includes, in the determination result information, a command that decreases the question frequency for the user in proportion to the improvement of the learning level. As a result, the learning robot 1 can transition from a state in which frequently asked questions to the user in an initial state to a state of a listener who listens to the user's story as learning progresses.

  Furthermore, the determination unit 60 can determine that advertisement information related to the preference information should be output to the learning robot 1 according to the preference information. That is, the determination unit 60 determines that an operation for acquiring advertisement information corresponding to the user's preference from an external database or the like and displaying the advertisement information on the display unit of the learning robot 1 should be performed. Further, the determination unit 60 can also determine that the advertising information related to the preference information should be output from the learning robot 1 to the user according to the learning level and the preference information. For example, the determination unit 60 can reduce the frequency of output of advertisement information that should be output according to the preference information in response to the improvement of the learning level.

  Further, the determination unit 60 determines exterior information indicating the exterior of the learning robot 1 that can be used by an exterior manufacturing apparatus (for example, a 3D printer) that manufactures the exterior of the learning robot 1 according to the exterior information. Determination result information including information indicating the determination can be supplied to the operation control unit 70. The determination unit 60 can also determine the exterior information by using the learning level of the learning robot 1 together with the appearance information.

  For example, the determination unit 60 includes information indicated by the learning result of the knowledge learning unit 502, for example, information obtained from past exchanges between the user and the learning robot 1 and information regarding the environment where the learning robot 1 is placed. The exterior information according to can be determined. As an example, the determination unit 60 determines exterior information indicating a cool exterior if the environment where the learning robot 1 is placed is a hot and humid environment, and determines exterior information indicating a warm exterior if the environment is a cold environment. To do. In addition, when the appearance information includes information on the color of the user's clothes and includes information on the color of the clothes that the user frequently wears, the determination unit 60 includes information indicating the color in the exterior information. . Furthermore, when the learning level is higher than the predetermined level, the determination unit 60 can also include information indicating a character (for example, a university professor) reminiscent of a high learning level in the exterior information.

  Further, when receiving the proposal information that tells the user when to buy a stock of a predetermined brand, the determination unit 60 determines whether or not to present the proposal information to the user. For example, the determination unit 60 determines to present the proposal information to the user when a predetermined criterion (for example, a criterion indicating that the stock price has increased or decreased by a predetermined amount or more) is satisfied. The determination unit 60 supplies the determination result information to the operation control unit 70.

(Operation control unit 70)
The operation control unit 70 controls the operation of the learning robot 1 according to the determination result of the determination unit 60. That is, the operation control unit 70 is based on the determination result information including the result determined by the determination unit 60 as the operation corresponding to the learning result information, question information, preference information, appearance information, proposal information, and / or operation command information. Thus, command information for controlling the operation to be executed by the learning robot 1 is generated.

  For example, the operation control unit 70 generates command information that presents or supplies predetermined information to the user, the communication terminal 2, the other learning robot 1a, and / or an external database according to the determination result information. Further, the motion control unit 70 operates the head, torso, and / or limbs of the learning type robot 1, displays on the display unit, and a light emitting unit (for example, a light emitting unit) provided at a predetermined position of the learning type robot 1. Command information for controlling the operation of light emission of the light emitting unit (diode) and / or the operation of audio output from the audio output unit 802, which will be described later, is generated.

  As an example, when the determination result information includes information indicating that the question content represented by the question information should be transmitted to the user, the operation control unit 70 displays the content represented by the question information from the output unit 80 to the user. Command information to be transmitted is generated. In addition, the operation control unit 70 has information indicating that the advertisement information is acquired from the external database according to the content represented by the preference information in the determination result information and the acquired advertisement information is displayed on the display screen of the learning robot 1. If included, the command acquisition information is generated by the data acquisition unit 20 and the command information that causes the output unit 80 to output the advertisement information acquired by the data acquisition unit 20 is generated.

  Further, the operation control unit 70 indicates that the learning level of the learning robot 1 (hereinafter referred to as learning level A) is lower than the learning level of the other learning robot 1a (hereinafter referred to as learning level B) in the determination result information. Is included, the command information that causes the data acquisition unit 20 to acquire data necessary to bring the learning level A closer to the learning level B from the learning robot 1a, an external database, and / or a user is generated. To do. On the other hand, if the determination result information includes information indicating that the learning level A of the learning type robot 1 is higher than the learning level B of the other learning type robot 1a, the operation control unit 70 outputs the information to the output unit 80. Command information for causing the learning robot 1a to supply data necessary to bring the learning level B close to the learning level A is generated. Thereby, since the operation control part 70 can supply the information which shows the learning result of the learning type robot 1 to the external learning type robot 1a, it can be made to learn the external learning type robot 1a.

  In addition, the operation control unit 70 can also generate command information that presents or supplies predetermined information to other users of the learning type robot 1a and / or an external database in an unperceptible manner. Thereby, the learning type robot 1 can perform learning implicitly with respect to the user. Then, the motion control unit 70 can also generate command information that presents or supplies predetermined information to other learning robots 1a and / or an external database in a perceptible manner to the user. In this case, the learning robot 1 can appeal to the user that learning is being performed.

  As a result, information can be implicitly exchanged among a plurality of learning robots, so that each learning robot increases as the contact between one learning robot and another learning robot increases. The learning level can be improved. In this case, the learning robot 1 can also output part or all of the learned content and / or information about the learned content from the output unit 80 in a perceptible manner to the user. A user who perceives such information can grasp how the learning robot 1 owned by the user is gradually learning by talking with other learning robots. The motivation for meeting the robot 1 with various other learning robots can be improved. Thereby, according to the learning type robot 1 which concerns on this Embodiment, the opportunity which activates communication between people can also be created.

  In addition, the learning robot 1 according to the present embodiment transfers external information to other learning robots and / or in a form that can be perceived by the user (for example, voice, gesture, light emission of a light emitting unit included in the learning robot 1). Or it can be communicated to surrounding users. Furthermore, the learning type robot 1 can also transmit external information to other learning type robots in a form that cannot be perceived by the user (for example, near field communication such as Bluetooth (registered trademark)).

  Then, for example, the learning unit 50 analyzes the analysis result information generated by analyzing external information acquired by interacting with other learning type robots in a form that cannot be perceived by the user (for example, classified into a predetermined category). Analysis result information) and already learned results (for example, analysis result information classified into a predetermined category already stored in the information storage unit 56, which is generated before newly generated analysis result information) Difference information) is extracted. Then, the motion control unit 70 can supply the extracted difference information to other learning robots in a form that the user cannot perceive, and can also control the operation of the learning robot 1 based on the difference information. .

  As an example, when the learning type robot 1 indicates that the other learning type robots have more information classified into a predetermined category, the learning type robot 1 determines that learning regarding information belonging to the category should be activated. To do. For example, when the learning result information including the information indicating the difference that the other learning type robot has more information classified into the predetermined category and the determination result information are generated, The operation for causing the user to perceptively output information representing a question for acquiring information related to the category is determined. As an example, when the predetermined category is a category related to “clothing” and other learning type robots have more information about the category related to “clothing” than the learning type robot 1, the learning type robot 1 Questions about “clothing” can be spoken to other learning robots. Note that the learning robot 1 can perform the reverse operation to the above when the learning robot 1 has more information that is classified into a predetermined category than the other learning robots.

  In addition, the operation control unit 70 includes information generated based on information perceivable by the user (for example, voice information) in the analysis result information, and learning result information and determination result information are generated using the information. In this case, it is possible to determine an operation for outputting a part or all of the information perceived by the user from the learning robot 1. The information that can be perceived by the user is, for example, information obtained by exchanging information that the user cannot perceive between the learning type robot 1 and the other learning type robot. This is information (for example, voice information) output by the learning robot.

  Furthermore, the learning robot 1 changes the weight of the category content generated in the analysis unit 40 based on the information perceivable by the user output from the other learning robots, and the changed category weight. The operation corresponding to the determination result information generated according to the attachment may be determined. For example, the motion control unit 70 acquires information that can be perceived by the user, increases the weight of the category to which the information belongs, and adds information belonging to the category with the largest (or smallest) weight among the plurality of categories. It can be determined as information to be transmitted to the learning robot.

  In addition, when the determination result information indicates that the learning type robot 1 has a smaller storage amount of information belonging to one category than the other learning type robots, the operation control unit 70 determines that the other learning type robots Is determined to be “Hakugaku”. Then, when the operation control unit 70 acquires information belonging to the one category from another learning type robot, the operation control unit 70 displays information indicating the conflict (for example, voice information such as “I see” and “So”) to the output unit 80. The operation to be output can also be determined.

  In addition, when the analysis result information includes information related to the user's emotion, and the learning result information is generated based on the analysis result information, and the determination result information is generated, the motion control unit 70 is information indicating the emotion. It is also possible to determine the operation of the learning robot 1 according to the above. For example, the motion control unit 70 can determine the movement and orientation of the learning robot 1 such as the head, hands, and feet according to information indicating emotion. Further, for example, when the determination result information includes information that cannot be operated in the learning robot 1, the operation control unit 70 makes an appropriate determination as to other learning robots or external users. It is also possible to determine an operation for causing the output unit 80 to output information that is reminiscent (for example, information regarding the conflict).

  The operation control unit 70 can also generate command information for automatically inputting data assumed from the determination result information into a predetermined form provided by a predetermined social networking service. For example, the motion control unit 70 refers to learning result information, question information, or preference information, and the like, an event that has occurred around the learning robot 1, a user state (for example, a user's mood), or a learning type Command information for automatically inputting text data representing matters that the robot 1 has not learned (that is, information not stored in the information storage unit 56) or the like to the output unit 80 in a social networking service form is generated.

  Further, when the operation control unit 70 receives the determination result information determined according to the proposal information, the operation control unit 70 generates command information corresponding to the determination result information. For example, when receiving the determination result information indicating that the user is prompted to purchase the stock in accordance with the proposal information that tells the user when to buy the stock of a predetermined brand, the operation control unit 70 Then, command information for outputting information recommending the user to purchase stock from the output unit 80 is generated. The operation control unit 70 supplies command information for controlling the operation to the output unit 80.

  Further, when the operation control unit 70 determines that the determination unit 60 is to perform an operation to output a part or all of the information acquired from the outside by the data acquisition unit 20 to the outside as it is, a part of the information Alternatively, it is also possible to generate command information that causes the output unit 80 to output all the data as it is. For example, when the data acquisition unit 20 acquires information about a sentence from the outside, it is possible to generate command information that causes the output unit 80 to output a part or all of the vocabulary constituting the sentence.

(Output unit 80)
Based on the command information received from the operation control unit 70, the output unit 80 presents predetermined information from the learning robot 1 to the user, the communication terminal 2, the other learning robot 1a, and / or an external database. Or supply. Further, the output unit 80 causes the learning robot 1 to execute a predetermined operation based on the command information.

  For example, the output unit 80 includes a display unit 800 as a display screen that displays text data, image data, and the like, a voice output unit 802 that outputs voice, a data output unit 804 that outputs data, and the learning robot 1. And an operation output unit 806 that executes a predetermined operation on a predetermined portion (for example, a head, a torso, a limb, or the like).

  The display unit 800 displays text, a still image, a moving image, or the like that is perceived by the user in accordance with the command information received from the operation control unit 70. The voice output unit 802 outputs, for example, a question for the user or an answer to a predetermined question, and other voices according to the command information. The data output unit 804 executes the writing process by outputting predetermined data to another learning type robot 1a or outputting text data to a predetermined form of a predetermined social networking service according to the command information. Further, the operation output unit 806 outputs a command for operating a predetermined location of the learning robot 1 to the drive unit 90 or the predetermined location.

(Driver 90)
The drive unit 90 drives, for example, the head, body, and / or limbs of the learning robot 1. The drive unit 90 drives a predetermined portion of the learning robot 1 in accordance with the command received from the operation output unit 806. In addition, the drive unit 90 causes the light emitting unit provided at a predetermined location of the learning robot 1 to emit light in various patterns according to a command output by the operation control unit 70 according to the determination result information including the user characteristic information. The emotion of the learning robot 1 can be expressed by causing a predetermined operation of the learning robot 1 to execute a predetermined operation and / or outputting various voices from the voice output unit 802.

  FIG. 6 shows an example of an outline when changing the exterior of the learning robot according to the embodiment of the present invention.

  In the learning type robot 1 according to the present embodiment, the exterior manufacturing apparatus 6 such as a 3D printer or the like according to the characteristics or preference of the user of the learning type robot 1, the degree of learning, or the degree of improvement of the learning level. An exterior can be formed. As a variation of the exterior of the learning robot 1, for example, a learning robot 1b whose exterior color or design has been changed, or a learning type in which predetermined accessories (hats, glasses, other equipment, etc.) are added to the exterior of the learning robot 1 There are a robot 1c and a learning robot 1d in which the form of the learning robot 1 is changed.

  Specifically, first, determination result information including exterior information is supplied from the determination unit 60 to the operation control unit 70. The operation control unit 70 causes the data output unit 804 to supply exterior information to the exterior exterior manufacturing apparatus 6 via the communication unit 10. Then, the exterior manufacturing apparatus 6 to which the exterior information is supplied manufactures the exterior of the learning robot 1 corresponding to the exterior information. Thereby, the exterior of the learning robot 1 has a shape corresponding to the exterior information.

  FIG. 7 shows an example of an outline of a learning robot system according to the embodiment of the present invention.

  The learning type robot system according to the present embodiment performs an external learning type robot 1a, a communication terminal 3, or a database (not shown) for storing predetermined data, and what operation is executed according to information from the outside. And a learning type robot 1 for learning. The learning robot 1 is provided so as to be able to communicate with the communication terminal 2.

  For example, an example will be described in which the learning robot 1 and the learning robot 1a have a conversation with each other for the first time. Here, an example in which the learning type robot 1 makes an inquiry to the learning type robot 1a will be described. First, the data acquisition unit 20 of the learning type robot 1 acquires data (for example, a robot identifier that uniquely identifies the learning type robot) that identifies the learning type robot 1a that is the other learning type robot via the communication unit 10. To do. The analysis unit 40 analyzes that the data is a robot identifier. The learning unit 50 determines whether or not the robot identifier received from the analysis unit 40 is stored in the information storage unit 56. In this case, since the learning type robot 1 and the learning type robot 1 a exchange data for the first time, the robot identifier of the learning type robot 1 a is not stored in the information storage unit 56.

  Therefore, the learning unit 50 supplies learning result information indicating that the learning type robot 1 a has been contacted for the first time to the determination unit 60. The determination unit 60 determines that a predetermined relationship should be formed between the learning robot 1 and the learning robot 1a according to the learning result information. For example, the determination unit 60 determines to greet the learning robot 1a. The determination unit 60 supplies determination result information including the determination result to the operation control unit 70. The operation control unit 70 controls the output unit 80 to present or supply information indicating a greeting to the learning robot 1a. Specifically, the voice output unit 802 outputs a voice indicating a greeting, and the data output unit 804 sends data including the robot identifier of the learning type robot 1 to the learning type robot 1a and / or the learning type robot 1. Information indicating that the learning robot 1a has established a predetermined relationship is supplied.

  In addition, various information is exchanged between the learning robot 1 and the communication terminal 2, and between the learning robot 1 a and the communication terminal 3, so that the learning robot 1 and the learning robot 1 a Improve learning level. For example, the learning robot 1 issues a question to the user regarding information that is not stored in the information storage unit 56 (for example, a voice indicating the question is output from the voice output unit 802). The user answers the question. Specifically, information indicating an answer is supplied to the learning robot 1 via the communication terminal 2. Thereby, the learning type robot 1 improves the learning level. Then, the learning type robot 1 transmits the content learned from the user to the learning type robot 1a. Thereby, the learning type robot 1a can also improve the learning level. That is, according to the learning type robot system according to the present embodiment, it is possible to transmit the content learned by a plurality of learning type robots.

  Moreover, the learning robot 1 and the learning robot 1a can utter each other autonomously. For example, when the learning type robot 1 has previously learned the preference of the user of the learning type robot 1, information related to the preference is transmitted to the learning type robot 1a by voice and data. When the learning type robot 1a acquires the voice and data, the learning type robot 1a transmits to the learning type robot 1 the voice and data indicating that it is interested in the preference. In this case, when the user of the learning robot 1 and the user of the learning robot 1a exist in the vicinity of their own learning robot, each user grasps the utterance contents of the learning robot 1 and the learning robot 1a. Will do. As a result, the learning robot system can provide an opportunity to get acquainted even when the user of the learning robot 1 and the user of the learning robot 1a are not acquainted with each other. The learning robot system can also provide an opportunity to improve the familiarity between the user of the learning robot 1 and the user of the learning robot 1a.

  Although not shown, a case where the learning robot 1a is installed in a predetermined store and a user who has the learning robot 1 visits the store will be described. In this case, the learning robot 1 and the learning robot 1a spontaneously exchange data with each other. For example, the learning type robot 1 acquires coupon information and event information in the store from the learning type robot 1a. And learning type robot 1 displays the acquired coupon information and event information on a display screen, for example. Thereby, the learning type robot 1 can receive coupon information and event information from the learning type robot 1a even if the user does not talk to the store clerk.

  FIG. 8 shows an example in which the learning robot according to the embodiment of the present invention writes information in a predetermined form of a predetermined social networking service.

  For example, the operation control unit 70 of the learning robot 1 determines to input predetermined text data in the comment field 902 as a predetermined form of the social networking service according to the learning result of the learning unit 50. Then, the operation control unit 70 generates command information that causes the data output unit 804 to input the text data to the comment field 902. The data output unit 804 that has received this command information inputs the text data into the comment field 902 via the communication unit 10.

  When text data is input to the comment field 902, the server of the social networking service notifies the learning robot 1a that text data has been input. In the learning robot 1a, the data acquisition unit 20 of the learning robot 1a acquires the notification and text data. Then, the analysis unit 40 of the learning robot 1a analyzes the text data, and the learning unit 50 generates text data to be input to the comment field 904 according to the analysis result. Further, the determination unit 60 of the learning robot 1a determines that the text data should be input to the comment field 904, and the operation control unit 70 automatically inputs the text data generated by the learning unit 50 to the comment field 904. Decide to enter. Thereby, as shown in the screen 900, the learning type robot 1 and the learning type robot 1a can automatically input each comment in each comment field.

  Further, although not shown, the learning type robot 1 has a unique operation method, playing method, driving method, and / or from an external database (for example, a server that provides various application programs and contents). Alternatively, it is possible to acquire an application program or content that defines how emotions are expressed. That is, the data acquisition unit 20 acquires application programs and contents via the communication unit 10. Then, the analysis unit 40 analyzes the application and content, and converts them into a format that can be executed by the learning robot 1. Next, the learning unit 50 performs learning using the converted application or content, and generates operation command information. As a result, the learning robot 1 can acquire the application program and content from the outside, thereby improving the learning level, performing a predetermined operation, or performing an operation different from the conventional one. become.

  FIG. 9 shows an example of the hardware configuration of the learning robot according to the present embodiment.

  The learning robot 1 according to the present embodiment includes a CPU 1500, a graphic controller 1520, a memory 1530 such as a random access memory (RAM), a read-only memory (ROM), and / or a flash ROM, and a storage for storing data. A device 1540, a read / write device 1545 for reading data from and / or writing data to a recording medium, an input device 1560 for inputting data, a communication interface 1550 for transmitting / receiving data to / from an external communication device, and a CPU 1500 A chip set 15 that connects the graphic controller 1520, the memory 1530, the storage device 1540, the read / write device 1545, the input device 1560, and the communication interface 1550 so that they can communicate with each other. 0 and a.

  The chip set 1510 includes a memory 1530, a CPU 1500 that accesses the memory 1530 and executes predetermined processing, and a graphic controller 1520 that controls display on an external display device. Perform data passing. The CPU 1500 operates based on a program stored in the memory 1530 and controls each component. The graphic controller 1520 displays an image on a predetermined display device based on the image data temporarily stored on the buffer provided in the memory 1530.

  The chip set 1510 connects a storage device 1540, a read / write device 1545, and a communication interface 1550. The storage device 1540 stores programs and data used by the CPU 1500 of the learning robot 1. The storage device 1540 is, for example, a flash memory. The read / write device 1545 reads the program and / or data from the storage medium storing the program and / or data, and stores the read program and / or data in the storage device 1540. For example, the reading / writing device 1545 acquires a predetermined program from a server on the Internet via the communication interface 1550, and stores the acquired program in the storage device 1540.

  The communication interface 1550 executes data transmission / reception with an external device via a communication network. Further, when the communication network is disconnected, the communication interface 1550 can execute data transmission / reception with an external device without going through the communication network. An input device 1560 such as a voice acquisition device, a keyboard, a tablet, or a mouse is connected to the chipset 1510 via a predetermined interface.

  The learning robot 1 program stored in the storage device 1540 is provided to the storage device 1540 via a communication network such as the Internet or a recording medium such as a magnetic recording medium or an optical recording medium. The program for the learning robot 1 stored in the storage device 1540 is executed by the CPU 1500.

  The program executed by the learning type robot 1 according to the present embodiment works on the CPU 1500 to change the learning type robot 1 into the communication unit 10, the data acquisition unit 20, and the external information acquisition unit 30 described in FIGS. 1 to 8. , Analysis unit 40, learning unit 50, level determination unit 52, level information storage unit 54, information storage unit 56, determination unit 60, operation control unit 70, output unit 80, drive unit 90, position information acquisition unit 300, time information Acquisition unit 302, environment information acquisition unit 304, audio information acquisition unit 306, imaging unit 308, tactile sensor 310, question unit 500, knowledge learning unit 502, user learning unit 504, personality learning unit 506, suggestion unit 508, display unit 800 , Function as an audio output unit 802, a data output unit 804, and an operation output unit 806.

(Effect of embodiment)
The learning robot 1 according to the present embodiment can autonomously learn various knowledge, vocabulary, user characteristics, emotions, and the like in response to questions from users and questions from other learning robots 1a. . In addition, the learning robot 1 can improve the learning level of itself or another learning robot 1a in cooperation with another learning robot 1a. Thereby, according to the learning type robot 1 which concerns on this Embodiment, not only can communication between a user and the learning type robot 1 be activated, but the user and other users can be connected via the learning type robot 1. It is possible to provide an opportunity to communicate with users and to activate communication between users.

  While the embodiments of the present invention have been described above, the embodiments described above do not limit the invention according to the claims. In addition, it should be noted that not all combinations of features described in the embodiments are necessarily essential to the means for solving the problems of the invention. Furthermore, the technical elements of the above-described embodiments may be applied independently, or may be applied by being divided into a plurality of parts such as program parts and hardware parts.

DESCRIPTION OF SYMBOLS 1, 1a, 1b, 1c, 1d Learning type robot 2, 3 Communication terminal 4 Database 5 Communication network 6 Exterior manufacturing apparatus 10 Communication part 20 Data acquisition part 30 External information acquisition part 40 Analysis part 50 Learning unit 52 Level determination part 54 Level Information storage unit 56 Information storage unit 60 Judgment unit 70 Operation control unit 80 Output unit 90 Drive unit 300 Position information acquisition unit 302 Time information acquisition unit 304 Environmental information acquisition unit 306 Audio information acquisition unit 308 Imaging unit 310 Tactile sensor 500 Questioning unit 502 Knowledge learning unit 504 User learning unit 506 Personality learning unit 508 Proposal unit 800 Display unit 802 Audio output unit 804 Data output unit 806 Operation output unit 900 Screen 902, 904 Comment column 1500 CPU
1510 chip set 1520 graphic controller 1530 memory 1540 storage device 1545 read / write device 1550 communication interface 1560 input device

Claims (14)

A learning robot that learns what action to perform according to information from outside,
An analysis unit that analyzes the content indicated by external information that is information from the outside so as to contribute to the execution of the operation of the learning robot, and generates analysis result information;
A learning unit that learns what operation the learning robot performs according to the analysis result information;
A determination unit that determines the operation to be performed by the learning robot according to a learning result of the learning unit;
A learning type robot comprising: an operation control unit that controls the operation of the learning type robot according to a determination result of the determination unit. An information storage unit for storing learning result information indicating a learning result of the learning unit;
The learning robot according to claim 1, wherein the learning unit updates the learning result information stored in the information storage unit using the analysis result information.   The learning according to claim 1 or 2, wherein the analysis unit generates the analysis result information by analyzing contents indicated by data acquired from an external learning robot, a communication terminal, or a database storing predetermined data. Type robot. According to the learning result of the learning unit, further comprising a level determining unit that determines a level indicating a learning stage of the learning robot,
The learning robot according to claim 1, wherein the determination unit changes the operation according to the level. The external information includes a program that defines information indicating at least how the learning robot operates.
The learning robot according to claim 1, wherein the learning unit learns the operation of the learning robot according to the program. The learning unit learns the preference information indicating the preference of the learning robot user according to the analysis result information,
The learning robot according to claim 1, wherein the determination unit determines that advertisement information related to the preference information should be output to the learning robot according to the preference information. The learning unit learns the preference information indicating the preference of the learning robot user according to the analysis result information,
The learning type robot according to claim 4, wherein the determination unit determines that advertisement information related to the preference information should be output to the learning type robot according to the level and the preference information. The analysis result information includes user characteristic information indicating characteristics of a user of the learning robot,
The learning unit generates appearance information that is information about the user's appearance derived from the user characteristic information;
The determination unit determines exterior information indicating an exterior of the learning robot that can be used by an exterior manufacturing apparatus that manufactures the exterior of the learning robot according to the exterior information. The learning type robot according to the item.   The learning robot according to claim 1, wherein the operation control unit automatically inputs data assumed from the determination result in a predetermined form provided by a social networking service.   The learning robot according to any one of claims 1 to 9, wherein the learning robot exchanges the external information with another learning robot in a form that can be perceived by a user and in a form that cannot be perceived by a user. The analysis unit generates the analysis result information by classifying the external information into a predetermined category,
The learning unit extracts the information of the difference between the analysis result information generated by analyzing the external information exchanged in a form not perceptible to the user and classified into the category, and the already learned result. ,
The said operation control part supplies the extracted said difference information to the said other learning type | mold robot in the form which cannot be perceived to the said user, and controls the said movement based on the said difference information. Learning robot. A learning robot system comprising an external learning robot, a communication terminal, or a database that stores predetermined data, and a learning robot that learns what operation to perform according to information from the outside,
Analyzing the content indicated by data acquired from the external learning robot, the communication terminal, or the database, or the content indicated by external information that is information from the outside so as to contribute to the execution of the operation of the learning robot. An analysis unit for generating analysis result information,
A learning unit that learns what operation the learning robot performs according to the analysis result information;
A determination unit that determines the operation to be performed by the learning robot according to a learning result of the learning unit;
A learning robot system comprising: an operation control unit that controls the operation of the learning robot according to a determination result of the determination unit.   The learning type robot system according to claim 9, wherein the operation control unit causes the external learning type robot to learn by supplying information indicating a learning result of the learning type robot to the external learning type robot. A learning robot program that is executed in a learning robot that learns what action to perform according to information from outside,
On the computer,
An analysis function for generating the analysis result information by analyzing the content indicated by the external information that is information from the outside so as to contribute to the execution of the operation of the learning robot;
A learning function for learning what operation the learning robot performs according to the analysis result information;
A determination function for determining the action to be performed by the learning robot according to a learning result in the learning function;
A learning robot program for realizing an operation control function for controlling the operation of the learning robot according to a determination result in the determination function.

Images