Robot action expression apparatus and robot action expression program

Abstract

To provide a robot action expression apparatus capable of properly controlling emotional action of a robot in accordance with video content that the robot is viewing with a user.SOLUTION: A robot action expression apparatus 2 includes: a user score acquisition unit 321 which acquires a user keyword score; a robot score acquisition unit 322 which acquires a robot keyword score; a program data extraction unit 331 which extracts a keyword from information on a program being watched; a program score calculation unit 332 which calculates a user program score and a robot program score by summing the user keyword scores and the robot keyword scores for the extracted keyword group; an action determination unit 352 which uniquely selects predefined emotional action of the robot for a combination of the user program score and the robot program score; and a robot action communication unit 353 which instructs the robot to perform the selected emotional action.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technology for controlling emotional actions of a robot that watches video content such as television programs together with a person. [Background technology]

[0002] 2. Description of the Related Art Research and development of communication robots capable of conversing with humans has been progressing. For example, Patent Document 1 proposes a television viewing robot that extracts keywords from the video, audio, or subtitle data of a television program and generates utterances, allowing the robot to speak related to the program and interact with people while watching television. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-185400 A [Patent Document 2] JP 2003-205179 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology allows robots and humans to have conversations related to programs, but in order for humans and robots to enjoy watching television programs, etc., it is necessary for the robot to behave with rich emotion. In particular, it is necessary for the robot to change its emotional expression according to the emotions it feels in response to the content of the program.

[0005] For example, Patent Document 2 proposes a method for controlling the emotional behavior of a pet robot, with the aim of ensuring that users do not tire of the robot and continue to use it. In this method, the more the user loves the robot, the more the robot gradually behaves in a way that shows it is attached to the user. However, this technology of changing the robot's behavior according to the user's behavior history could not be applied to cases where it was desired to express emotions according to the content of the program. In particular, while there are genres where the emotions felt from the images are easy to understand, such as expressing a "scary" emotion when watching a horror movie, it was difficult for the robot to express emotions when watching genres where the emotions felt from the images are difficult to understand, such as news and documentaries.

[0006] An object of the present invention is to provide a robot motion expression device and a robot motion expression program that can appropriately control the emotional motion of a robot according to video content being viewed together with a user. [Means for solving the problem]

[0007] The robot movement expression device of the present invention includes a user score acquisition unit that acquires a user keyword score based on the frequency of appearance of each keyword extracted from programs viewed by a user during a specified period of time, a robot score acquisition unit that acquires a robot keyword score obtained by weighting a score based on the frequency of appearance of each keyword extracted from programs viewed by a user other than the user during a specified period of time with the user keyword score, a program data extraction unit that extracts keywords from information of the program being viewed, a program score calculation unit that calculates a user program score and a robot program score that indicate the degree of interest of the user and the robot in the program being viewed by adding up the user keyword score and the robot keyword score, respectively, for a group of keywords extracted from the program being viewed by the program data extraction unit, a movement determination unit that uniquely selects a predefined emotional movement of a robot for a combination of the user program score and the robot program score, and a robot movement communication unit that instructs the robot to the emotional movement selected by the movement determination unit.

[0008] The user score acquisition unit may further acquire a user genre score based on the frequency of appearance of each genre of programs viewed by the user during a specified period, the robot score acquisition unit may further acquire a robot genre score obtained by weighting a score based on the frequency of appearance of each genre of programs viewed by the other users during a specified period by the user genre score, the program data extraction unit may further extract genres from information of the program being viewed, and the program score calculation unit may sum up the user genre score and the robot genre score for the genre group extracted from the program being viewed by the program data extraction unit, and add the sum to the user program score and the robot program score.

[0009] The robot motion expression device may include a motion determination update unit that divides a coordinate plane whose axes are the user program score and the robot program score based on the distribution of the scores, and uniquely associates the emotional motion with each of the divided areas.

[0010] The behavior decision update unit may, with the user program score on the vertical axis and the robot program score on the horizontal axis, use a representative value of the distribution of each score as the origin, and divide the first quadrant into one or more regions corresponding to emotional behavior when both the user and the robot are interested in the program being viewed, the second quadrant into one or more regions corresponding to emotional behavior when only the user is interested in the program being viewed, the third quadrant into one or more regions corresponding to emotional behavior when neither the user nor the robot are interested in the program being viewed, and the fourth quadrant into one or more regions corresponding to emotional behavior when only the robot is interested in the program being viewed.

[0011] A robot motion expression program according to the present invention is for causing a computer to function as the robot motion expression device. Effect of the Invention

[0012] According to the present invention, the emotional behavior of a robot can be appropriately controlled in accordance with the video content being viewed together with a user. [Brief description of the drawings]

[0013] [Figure 1] 1 is a block diagram showing a functional configuration of a robot motion expression device according to an embodiment. [Diagram 2] 1 is a block diagram showing a functional configuration of an interest program acquisition device according to an embodiment; [Diagram 3] 5 is a diagram illustrating processing content of a viewing data extraction unit in the embodiment. FIG. [Figure 4] 11 is a diagram illustrating a process of a score generating unit according to an embodiment. FIG. [Diagram 5] 11 is a diagram illustrating a processing content of a weighting value update unit in the embodiment. FIG. [Figure 6] 13 is a flowchart showing a processing procedure of an adding score unit in the embodiment. [Figure 7] 13 is a diagram illustrating an example of the processing content of an interest score unit in the embodiment. FIG. [Figure 8] 11 is a diagram illustrating a process performed by a program determination unit in the embodiment. FIG. [Figure 9] 11 is a diagram illustrating a process of a score calculation unit according to an embodiment. FIG. [Figure 10] 11 is a diagram illustrating the processing content of an interest program score calculation unit in the embodiment. FIG. [Figure 11] 11 is a diagram illustrating a process of an operation determination update unit according to an embodiment. FIG. [Figure 12] 10 is a flowchart showing a process for calculating parameters for determining an emotional movement in the embodiment. [Figure 13] 11 is a diagram illustrating an example of processing content of an operation determination unit in the embodiment. FIG. [Figure 14] 10 is a flowchart showing a process for extracting an emotional action to be executed by a robot according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] An example of an embodiment of the present invention will now be described. In order for a user and a robot to enjoy watching video content such as television programs, the robot movement expression device of this embodiment determines the emotional movements to be implemented by the robot based on the degree of interest in the video content of the user and the robot, respectively, in addition to the emotions felt by the content.

[0015] That is, the robot movement expression device is a device for controlling the movement of a communication robot that watches television programs and the like together with a person, and selects an emotion to be expressed by the robot from among a number of emotions (fun, sad, scary, etc.) using the interest levels of the robot and the viewer (user) in each program (video content) that they have previously watched.The robot movement expression device then controls the emotional expression of the robot according to the program being watched by instructing the robot, which has movements implemented for each emotion, with the selected emotion.

[0016] FIG. 1 is a block diagram showing the functional configuration of a robot motion expression device 2 in this embodiment. The robot motion expression device 2 is an information processing device (computer) equipped with a control unit 30 and a memory unit 40, and is incorporated into the robot or communicatively connected to the robot to determine the robot's emotions based on the robot's own interest in the program and the user's interest. The robot motion display device 2 receives inputs from a television (television receiver) of subtitle data of a program being reproduced by the television, and data included in an electronic program guide (EPG) for the program. In addition, the robot motion display device 2 acquires the user's and robot's interest in keywords and genres for programs viewed in the past by a predetermined method. In this embodiment, as an example, the interest score database (DB) 24 obtained by the interest program acquisition device 1 proposed by the applicant (Japanese Patent Application No. 2023-094031) is appropriately expanded and used.

[0017] The interesting program acquisition device 1 is a device for a robot that watches content such as television programs together with a person, and acquires program content (interesting programs) that the robot itself wants to watch, and utilizes the program content for communication with the user. As the personality of the robot, an interest keyword and genre are initially set based on the viewing history of people other than the user of the robot, and this personality is weighted based on the viewing history of the user, thereby changing the robot's interest programs.

[0018] FIG. 2 is a block diagram showing a functional configuration of the interesting program acquisition device 1 in this embodiment. The interesting program acquisition device 1 is an information processing device (computer) equipped with a control unit 10 and a storage unit 20, and is incorporated in a robot or communicatively connected to the robot to output program information acquired as the robot's own interesting program. The interesting program acquisition device 1 also receives input from a television (television receiver) of subtitle data of a program being played on the television and data included in an electronic program guide (EPG) for this program. The interesting program acquisition device 1 is also connected via a network to a database (EPG information DB) that stores EPG data and is provided in an external server or the like, and data stored in the EPG information DB is input to the interesting program acquisition device 1.

[0019] The control unit 10 operates as each of the following functional units by reading and executing software (interesting program acquisition program) stored in the storage unit 20. In addition, the storage unit 20 stores various databases (DBs) in addition to the interesting program acquisition program.

[0020] Specifically, the control unit 10 includes a viewing data extraction unit 11, a score generation unit 12, a score addition unit 13, an interest score unit 14, and a program determination unit 15. The storage unit 20 also includes a viewing DB 21, a unique score DB 22, a weighting value DB 23, and an interest score DB 24.

[0021] The viewing data extraction section 11 includes a keyword extraction section 111 and a genre extraction section 112, and stores information about programs in the viewing DB 21 according to the user's television program viewing history.

[0022] The keyword extraction unit 111 extracts keywords from the subtitle data and electronic program guide (EPG) data of a program viewed by a user. Here, the keywords are words and phrases such as proper nouns contained in the subtitle data and the EPG data, and those registered in a dictionary prepared in advance may be extracted.

[0023] The genre extraction unit 112 extracts the genre of a program viewed by the user from the EPG data of the program. The keywords extracted by the keyword extraction unit 111 and the genres extracted by the genre extraction unit 112 are stored in the viewing DB 21. Here, the genre is one or more categories that are set for each program according to its contents, and for example, a medium category (sub-genre) in the EPG data may be extracted.

[0024] FIG. 3 is a diagram illustrating the processing contents of the viewing data extracting section 11 in this embodiment. The subtitle data includes time information and text data for displaying the subtitles. The EPG data also includes time information for each program, as well as codes for classifying the contents of the programs (major classification, medium classification, etc.), and the program title or introductory text.

[0025] The keyword extraction unit 111 extracts a plurality of keywords from the text data. The genre extraction unit 112 extracts genres, such as "0x4f" (variety / other) and "0x01" (weather), from the EPG data. Note that, for example, in "0x4f", "4" is a code indicating a major category and "f" is a code indicating a medium category.

[0026] The score generation unit 12 includes a keyword score generation unit 121 and a genre score generation unit 122, and calculates scores indicating the frequency of occurrence of each of the keywords and genres extracted from the viewing history of users other than the user using the target robot, and stores the scores in the unique score DB22.

[0027] Here, the viewing history of other users (viewing DB21) is selected from the viewing histories of all robot users shared on the network by a plurality of robots of the same model, and is set as the personality of the robot. If the average viewing history of all users were used, the robot would have average interests, and users would find it difficult to sense individuality in the robot. Therefore, the score generation unit 12 selects the viewing histories of the individual users. In addition, if the viewing history of an individual whose hobbies and tastes are different from those of the user is selected, the user will be less likely to feel that his or her viewing history is affecting the creation of the robot's personality. Therefore, the score generation unit 12 may select the viewing history of an individual who matches, for example, the age or gender of the user, rather than being completely random.

[0028] The keyword score generating unit 121 calculates, for example, a TF value as a score indicating the appearance frequency of each keyword. The genre score generating unit 122 calculates the viewing ratio as a score indicating the frequency of appearance of the genre. These scores, which indicate the frequency of occurrence of keywords and genres, are stored in the unique score DB 22 .

[0029] FIG. 4 is a diagram illustrating the process contents of the score generating unit 12 in this embodiment. The keyword score generating unit 121 converts information on the subtitle data and EPG data of all programs viewed by a user v (another user) during a predetermined period (for example, one week) into a single document d. v Document d v Keyword in w i Number of occurrences of n w_i,d_v , the sum of the frequency of occurrence of all keywords Σ j n w_i,d_vUsing the keyword w i TF value (tf w_i,d_v ) is calculated as follows:

number

[0030] For example, if the number of times the genre "weather" appears is 140 and the total number of genres extracted from all programs is 2000, the genre score generation unit 122 calculates that the viewing ratio of "weather" is 140÷2000=0.07 (7%).

[0031] The score addition unit 13 includes a keyword score generation unit 131, a genre score generation unit 132, and a weighting value update unit 133, and uses the user's viewing history, i.e., the viewing DB21, as input, updates the weighting values ​​to be added to each score in the unique score DB22, and stores them in the weighting value DB23.

[0032] The keyword score generation unit 131 and the genre score generation unit 132, like the keyword score generation unit 121 and the genre score generation unit 122 provided in the score generation unit 12, calculate scores indicating the frequency of occurrence of each keyword and genre as weighting values ​​based on the user's viewing history stored in the viewing DB21.

[0033] The weighting value update unit 133 calculates weighting values ​​for the scores of each keyword and genre stored in the unique score DB 22 as follows, and stores the calculated weighting values ​​in the weighting value DB 23.

[0034] FIG. 5 is a diagram illustrating the processing contents of the weighting value update unit 133 in this embodiment. Although the procedure for calculating the weighting value of a keyword is exemplified here, the same applies to the updated score of a genre.

[0035] First, the weighting value update unit 133 calculates the weighting value of a certain keyword w in the user's viewing history (viewing DB 21). xCount the number of occurrences for each predetermined period (e.g., monthly), and find the difference x i (1 < i ≤ n) as the absolute value. Then, the average value of the difference in the number of occurrences is

Number

[0036] Next, consider the subtitle data and EPG data of all the programs watched as a single document d v and let the sum of the number of occurrences of all keywords in document d v be Σ j n w_j,d_v When this is done, for keyword w x define the update score l w_x,d_v as follows.

Number

[0037] The method for calculating the update score for a genre is the same as that for a keyword. That is, the weight value update unit 133 first calculates the number of occurrences of the genre, for example, on a monthly basis, and finds the difference in the number of occurrences for each month. Subsequently, the weight value update unit 133 calculates the average value of all the differences and uses the value obtained by dividing it by the number of occurrences of all keywords as the update score.

[0038] Here, the update score is a value that is subtracted from the score each time the corresponding keyword or genre appears once in the user's viewing history. That is, the new interest that is originally weighted to the robot's interest is updated using the law of diminishing marginal utility each time a program related to the corresponding keyword or genre is actually viewed. As a result, the way the interest increases changes between when seeing a keyword or genre of interest for the first time (the first time) and when seeing it many times (e.g., the 100th time). The more the number of viewings increases, the weight value for the corresponding keyword or genre decreases by the amount of the update score, expressing a decrease in interest (boredom).

[0039] FIG. 6 is a flowchart showing the processing procedure of the score adding unit 13 in this embodiment. In step S1, score adding section 13 extracts from viewing DB 21 the viewing history of a user for a predetermined period (for example, one week). In step S2, the score adding unit 13 calculates the TF value for each keyword and the viewing ratio for each genre, using the keyword score generating unit 131 and the genre score generating unit 132, as scores indicating the frequency of appearance, respectively.

[0040] In step S3, the score adding unit 13 causes the weighting value updating unit 133 to calculate a weighting value for each keyword and genre. In step S4, the score adding unit 13 stores the calculated weighting value in the weighting value DB 23.

[0041] The interest score unit 14 includes an interest keyword score generation unit 141 and an interest genre score generation unit 142, and calculates interest keyword scores and interest genre scores by adding the weighting values ​​in the weighting value DB23 to the scores of each keyword and genre stored in the unique score DB22, and stores them in the interest score DB24.

[0042] FIG. 7 is a diagram illustrating the processing contents of the interest score unit 14 in this embodiment. The interest keyword score generation unit 141 calculates an interest keyword score indicating the robot's current interests, which is the robot's original interests (unique score DB22) plus the user's interests (weighting value DB23), by adding the respective weighting values ​​to the score (TF value) of each keyword.

[0043] The interest genre score generating unit 142, like the interest keyword score generating unit 141, calculates an interest genre score by adding a weighting value to the score (viewing ratio) of each genre.

[0044] Here, the interest keyword score and the interest genre score are, for example, the maximum value x max and the minimum value x min may be normalized to a value between 0 and 1 as follows:

number

[0045] The degree of weighting can be changed as appropriate, and the score (TF value or viewing ratio) in the unique score DB22 and the score (TF value or viewing ratio) in the weighting value DB23 may be added equally (1:1), or, for example, the score (TF value or viewing ratio) in the weighting value DB23 may be reduced to a predetermined ratio (1:0.1, etc.).

[0046] The program determination unit 15 determines programs of interest to the robot based on the scores of each keyword and genre stored in the interest score DB 24. Specifically, the program determination unit 15 first obtains one week's worth of EPG data from the EPG information DB, and extracts keywords and genres from the introductions of each program. Next, the program determination unit 15 calculates the sum of the interest scores for each program based on the interest scores stored in the interest score DB 24, and sets the program with the largest sum of interest scores as the program in which the robot itself is interested.

[0047] FIG. 8 is a diagram illustrating the process contents of the program determination unit 15 in this embodiment. The interest score DB 24 stores interest scores for keywords 1, 2, 3, . . . and interest scores for genres 1, 2, 3, . At this time, genres 1 and 3 and keywords 1, 5, ... are extracted from program 1 obtained from the EPG information DB. By summing up the interest scores of these genres and keywords, a score of 0.102 for program 1 and a score of 0.1358 for program 2 are obtained. In this example, program 2, which has the largest sum of interest scores, is determined to be the interesting program.

[0048] In this way, the program determination unit 15 selects a program that matches the robot's current interests based on the interest score DB 24. The interest score DB24 is a result of weighting the original personality of the robot (unique score DB22) with the interest based on the user's viewing history (weighting value DB23), and is updated, for example, at the following times:

[0049] First, the viewing DB21, which serves as the source of weighting values ​​and is provided as the personality of other robots, is updated in real time each time a user (robot) watches a program, or at a predetermined interval (for example, daily, weekly, etc.).

[0050] The unique score DB22 set as the personality of the robot may not be updated after the initial setting, but may be updated at predetermined intervals (e.g., one year, half a year, etc.). In this case, in order to avoid excessively large changes, the viewing history of the same user as the previous time may be used.

[0051] On the other hand, the weighting value DB23 based on the user's viewing history is updated every month, which is the calculation unit for the update score, and is further updated each time a keyword or genre stored in the database appears in a newly viewed program. The interest score DB24 is updated whenever the weighting value DB23 is updated, or at a fixed cycle of one month, so that the interests of the robot itself change.

[0052] Here, the interest score DB 24 described above stores the robot's interest scores for keywords and genres, but in this embodiment, it is assumed that the interest score of the user is also stored. The robot motion expression device 2 utilizes the interest scores of both the user and the robot.

[0053] Returning to Fig. 1, the control unit 30 of the robot motion expression device 2 in this embodiment operates as each of the following functional units by reading and executing software (robot motion expression program) stored in the storage unit 40. The storage unit 40 also stores various databases in addition to the robot motion expression program.

[0054] Specifically, the control unit 30 includes a program information acquisition unit 31, an interest score acquisition unit 32, a score calculation unit 33, an interest program score calculation unit , and an action display unit . The storage unit 40 also includes a viewed program score DB 41 and an interesting program score DB 42.

[0055] The program information acquisition unit 31 acquires EPG data of a program that the robot and the user are watching together in real time. At this time, the program information acquisition unit 31 may acquire the EPG data on the condition that the power of the television is ON and the camera sensor or the like recognizes that the user is in front of the television.

[0056] The interest score acquisition unit 32 includes a user score acquisition unit 321 and a robot score acquisition unit 322, and acquires the interest scores of the user and the robot with respect to the keywords and genres from the interest program acquisition device 1 described above.

[0057] The user score acquisition unit 321 acquires, from the interest score DB 24 of the interest program acquisition device 1, a user keyword score based on the frequency of appearance of each keyword extracted from the programs viewed by the user during a specified period, and a user genre score based on the frequency of appearance of each genre.

[0058] The robot score acquisition unit 322 acquires, from the interest score DB24 of the interest program acquisition device 1, a robot keyword score obtained by weighting by the user keyword score a score based on the frequency of appearance of each keyword extracted from programs viewed by other users during a specified period, and a robot genre score obtained by weighting by the user genre score a score based on the frequency of appearance of each genre of programs viewed by other users during a specified period.

[0059] The score calculation unit 33 includes a program data extraction unit 331 and a program score calculation unit 332, and calculates scores indicating the degree of interest of the user and the robot in the program being viewed. The program data extraction unit 331 extracts the genre (subgenre) and keywords of the program being viewed from the EPG data acquired by the program information acquisition unit 31. The extracted keywords are registered in a predetermined dictionary, and the keyword dictionary used in the interest program acquisition device 1 may be referenced.

[0060] The program score calculation unit 332 calculates a user program score and a robot program score that indicate the degree of interest of the user and the robot in the program being watched by adding up the user keyword scores and robot keyword scores obtained by the interest score acquisition unit 32 for the group of keywords extracted by the program data extraction unit 331 from the program being watched. Furthermore, the program score calculation unit 332 adds up the user genre scores and robot genre scores obtained by the interest score acquisition unit 32 for the genre group extracted from the program being watched by the program data extraction unit 331, and adds them to the user program score and robot program score. The calculated user program scores and robot program scores are stored in the viewed program score DB 41.

[0061] FIG. 9 is a diagram illustrating the process contents of the score calculation unit 33 in this embodiment. The program data extraction unit 331 extracts a plurality of keywords and a plurality of genres (sub-genres) from the EPG data of the programs viewed by the user and the robot. The program score calculation unit 332 refers to the interest scores of each user and robot acquired by the interest score acquisition unit 32 for each of the extracted multiple keywords and multiple genres, and by adding these up, calculates the level of interest in the target program for each user and robot.

[0062] The interest program score calculation unit 34 calculates the maximum value of the user program score a from among the programs viewed during a predetermined period (for example, the past week), where a is the user's interest in the program (user program score) and b is the robot's interest in the program (robot program score). max and the minimum value a min , the maximum robot program score b max and the minimum value b min Extract. The extracted maximum and minimum values ​​of a and b are stored in the interest program score DB 42.

[0063] FIG. 10 is a diagram illustrating the process of the interest program score calculation unit 34 in this embodiment. The user program score a and the robot program score b are extracted from the viewed program score DB 41 for all programs (program 1, . . . , program m) viewed by the user and the robot in one week. The interest program score calculation unit 34 calculates the scores (a1, b1), ..., (a m ,b m ) the maximum and minimum values ​​of a and b are obtained as follows:

number

[0064] The action expression unit 35 includes an action decision update unit 351, an action decision unit 352, and a robot action communication unit 353, and decides an emotional action of the robot based on the degree of interest of the user and the robot in the program being watched, and instructs the robot.

[0065] The movement determination update section 351 determines parameters for determining an emotional movement according to a predetermined rule. In this embodiment, the action determination update unit 351 divides a coordinate plane with the user program score a and the robot program score b as axes based on the distribution of the scores, and uniquely associates an emotional action with each of the divided multiple regions.

[0066] FIG. 11 is a diagram illustrating the process of the action determination update unit 351 in this embodiment. First, the action decision update unit 351 checks the interest program score DB 42 for max ,a min ,b max ,b min are set as the maximum and minimum values ​​of the vertical axis (a-axis) and horizontal axis (b-axis) of the coordinate plane. Here, a max =16,a min =2,b max =45,b min = 3 as an example.

[0067] Four emotions are assigned to each quadrant of the coordinate plane, and a range of values ​​for a and b is defined for each. The first quadrant corresponds to the emotional behavior of the robot when both the user and the robot are interested in the program being watched. In this example, the four emotions of "joy," "surprise," "happiness," and "excitement" are assigned to the four regions, respectively. The second quadrant corresponds to the robot's emotional behavior when the user is only interested in the program being watched, and similarly, four emotions are assigned to the four regions, respectively. The third quadrant corresponds to the emotional behavior of the robot when neither the user nor the robot is interested in the program being watched, and similarly, the four emotions are assigned to the four regions, respectively. The fourth quadrant corresponds to the emotional movements of the robot when only the robot is interested in the program being watched. Similarly, four emotions are respectively assigned to four regions.

[0068] To determine each range, the motion decision update unit 151 first sets the origin (a0, b0) of the coordinate plane to, for example, a0 = (a max + a min ) / 2 = 9, b0 = (b max + b min ) / 2 = 24.

[0069] Next, for example, in the first quadrant, the motion decision update unit 351 determines the range of values corresponding to each of the four emotions within the range where the a-axis extends from the origin a0 to a max and the b-axis extends from the origin b0 to b max . For example, each region may be equally divided. The range of "joy" is set as 9 < a ≤ 12.5, 24 < b ≤ 34.5, the range of "surprise" is set as 12.5 < a, 24 < b ≤ 34.5, the range of "happiness" is set as 9 < a ≤ 12.5, 34.5 < b, and the range of "excitement" is set as 12.5 < a, 34.5 < b. The motion decision update unit 351 similarly determines the ranges corresponding to each of the four emotions for the second to fourth quadrants.

[0070] Here, a max , a min , b max , b min are extracted from the degree of interest in the programs for one week and are updated weekly. Therefore, the range to which each emotion is assigned is updated each time. Also, here, the coordinate plane is divided into 16 equal parts in a grid pattern, but the method of determining the regions is not limited to this. For example, depending on the distribution of scores, each region may be provided with a statistical representative value (for example, the average value, or the median, etc.) as the boundary.

[0071] FIG. 12 is a flowchart showing the flow of the process for calculating the parameters for determining the emotional movements in the present embodiment.

[0072] In step S11, the interest program score calculation unit 34 acquires, from the viewed program score DB 41, the user program scores and the robot program scores for the programs viewed in one week. In step S12, the interest program score calculation unit 34 extracts the maximum and minimum values ​​from the user program scores and robot program scores acquired in step S11. In step S13, the interest program score calculation unit 34 stores the maximum and minimum value data extracted in step S12 in the interest program score DB 42. In step S14, the action determination update unit 351 calculates an area on the coordinate plane (the range of the user program score a and the robot program score b) to which each emotional action is assigned, from the maximum and minimum value data stored in the interest program score DB 42.

[0073] The action determination unit 352 uniquely selects an emotional action of the robot predefined by the action determination update unit 351 for the combination of the user program score a and the robot program score b for the program being viewed. Specifically, the action determination unit 352 judges in which area on a predefined coordinate plane the user program score a and the robot program score b for the program being viewed are included, and determines the corresponding emotional action. It should be noted that, in this example, if the score of the program being watched is on the a-axis or the b-axis including the origin, no emotional action is implemented, but this is not limited to this.

[0074] FIG. 13 is a diagram illustrating the process contents of the operation determination unit 352 in this embodiment. Here, as in FIG. 11, 16 types of emotional actions are assigned to respective lattice-like regions on the coordinate plane.

[0075] At this time, when a user program score a=10 and a robot program score b=27 are obtained for the newly started program, it is determined in which divided area the corresponding coordinates on the coordinate plane are located. In this example, both the user and the robot are watching a program that interests them, and "joy" is selected as the emotion to be implemented in the robot.

[0076] The robot action communication unit 353 instructs the robot to perform the emotion action selected by the action determination unit 352 while the user and the robot are watching the program.

[0077] FIG. 14 is a flowchart showing the flow of a process for extracting an emotional action to be executed by a robot in this embodiment.

[0078] In step S21, the program information acquisition unit 31 acquires EPG data of the program being viewed by the user and the robot. In step S22, the program data extraction unit 331 extracts genres and keywords from the EPG data acquired in step S21. In step S23, the program score calculation unit 332 calculates a user program score and a robot program score for the program being viewed by summing up the interest scores for the genres and keywords extracted in step S22.

[0079] In step S24, the movement determining unit 352 determines an emotional movement of the robot based on the user program score and the robot program score calculated in step S23. In step S25, the robot action communication unit 353 transmits an instruction command for the emotional action determined in step S24 to the robot. In step S26, the robot executes the emotional action instructed in step S25.

[0080] According to this embodiment, the robot motion expression device 2 calculates a user program score and a robot program score indicating the user's and the robot's respective degrees of interest in programs by summing up the degrees of interest in keywords and genres based on the viewing history for programs viewed by the user and the robot. Then, the robot motion expression device 2 uniquely selects an emotional motion of the robot and instructs the robot based on the combination of the user program score and the robot program score. Therefore, the robot motion expression device 2 can appropriately control the emotional motion of the robot according to the video content being viewed together with the user. By determining the emotional motion based on the robot's own interests, it is possible to give psychological effects such as enjoyment and attachment to the user who is watching TV together. In addition, for example, the robot can express emotions such as joy when the user and the robot both watch a program they like, and boredom when both are watching a program they are not interested in, making it possible for the robot to perform "empathy" motions.

[0081] The robot motion expression device 2 may calculate the score only from keywords, without using the interest score related to the genre of the program. Here, the amount of information in the EPG data used as program information varies depending on the program. Therefore, for a program with a short introductory text in the EPG, the number of extracted keywords is small, and the reliability of the score tends to be low. Therefore, the robot motion expression device 2 can appropriately calculate the user program score and the robot program score for each program by calculating and using the interest scores for the genres assigned to all programs, in addition to the keywords.

[0082] The robot motion display device 2 divides a coordinate plane having the user program score and the robot program score as axes based on the distribution of these scores, and uniquely associates an emotional motion with each of the divided regions. In this way, the robot motion expression device 2 can represent the degree of interest in a program of the user and the robot on the coordinate plane, and can easily select a pre-assigned emotional motion.

[0083] In this case, on a coordinate plane, the user program score is the vertical axis and the robot program score is the horizontal axis, and the representative value of the distribution of each score (the midpoint between the minimum and maximum values, the average or median value of the distribution, etc.) is set as the origin. As a result, the first quadrant is divided into one or more regions corresponding to the emotional behavior when both the user and the robot are interested in the program, the second quadrant is divided into one or more regions corresponding to the emotional behavior when only the user is interested in the program, the third quadrant is divided into one or more regions corresponding to the emotional behavior when neither the user nor the robot are interested in the program, and the fourth quadrant is divided into one or more regions corresponding to the emotional behavior when only the robot is interested in the program. As a result, the emotional movement derived from the relationship between the interest levels of the user and the robot is appropriately assigned to each area on the coordinate plane, so that the robot movement expression device 2 can appropriately control the emotional movement of the robot.

[0084] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. Furthermore, the effects described in the above-described embodiments are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments.

[0085] The types of emotional actions of a robot can be changed as appropriate depending on the purpose. Increasing the types of emotional actions implemented will help to prevent users from becoming bored with the robot. In addition, in this embodiment, the emotional actions implemented are not limited. For example, a speech action may be associated with each emotion. In this way, for example, when only the user is watching a program that interests him, the robot can be made to say "I want to watch another program" or "This is boring", etc., depending on the relationship between the interest levels of the user and the robot.

[0086] In this embodiment, the configuration and operation of the robot motion expression device 2 have been mainly described, but the present invention is not limited to this and may be configured as a method or program having each component for expressing emotional motion of a robot.

[0087] Furthermore, the functions of the robot motion output device 2 may be realized by recording a program for realizing the functions of the robot motion output device 2 on a computer-readable recording medium, and reading and executing the program recorded on the recording medium into a computer system.

[0088] The term "computer system" here includes hardware such as the OS and peripheral devices. Additionally, "computer-readable recording media" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into computer systems.

[0089] Furthermore, the term "computer-readable recording medium" may include a recording medium that dynamically stores a program for a short period of time, such as a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line, and a recording medium that stores a program for a certain period of time, such as a volatile memory in a computer system that serves as a server or client in such a case. The above program may be a program for realizing part of the above-mentioned functions, or may be a program that can realize the above-mentioned functions in combination with a program already recorded in the computer system. [Explanation of symbols]

[0090] 1. Device for acquiring programs of interest 2. Robot motion expression device 24 Interest Score DB 30 Control section 31 Program Information Acquisition Unit 32 Interest score acquisition section 33 Score Calculation Section 34 Interest Program Score Calculation Section 35 Movement expression section 40 Storage section 41 Viewing Program Score DB 42 Interesting Program Score DB 321 User Score Acquisition Department 322 Robot Score Acquisition Department 331 Program Data Extraction Unit 332 Program Score Calculation Department 351 Operation decision update section 352 Action Decision Unit 353 Robot Motion and Communication Department

Claims

1. a user score acquisition unit that acquires a user keyword score based on the appearance frequency of each keyword extracted from the programs that the user has viewed during a predetermined period; a robot score acquisition unit that acquires a robot keyword score by weighting a score based on an appearance frequency of each keyword extracted from programs viewed by other users different from the user during a predetermined period by the user keyword score; a program data extraction unit that extracts keywords from information of a program being viewed; a program score calculation unit that calculates a user program score and a robot program score that indicate the degree of interest of the user and the robot in the program being viewed by adding up the user keyword score and the robot keyword score, respectively, for a group of keywords extracted from the program being viewed by the program data extraction unit; an action determination unit that uniquely selects a predefined emotional action of the robot for a combination of the user program score and the robot program score; a robot action communication unit that instructs the robot to perform the emotional action selected by the action determination unit.

2. The user score acquisition unit further acquires a user genre score based on an appearance frequency of each genre of programs viewed by the user during a predetermined period, The robot score acquisition unit further acquires a robot genre score obtained by weighting a score based on the frequency of appearance of each genre of the programs viewed by the other user during a predetermined period by the user genre score, The program data extraction unit further extracts a genre from the information of the program being viewed, The robot movement display device of claim 1, wherein the program score calculation unit sums up the user genre score and the robot genre score for each genre group extracted from the program being viewed by the program data extraction unit, and adds the sum to the user program score and the robot program score.

3. 3. The robot movement expression device according to claim 1, further comprising a movement determination and update unit that divides a coordinate plane having axes of the user program score and the robot program score based on a distribution of the scores, and uniquely associates the emotional movement with each of the divided regions.

4. The operation decision update unit, when the user program score is on the vertical axis and the robot program score is on the horizontal axis, sets a representative value of the distribution of each score as an origin, Dividing the first quadrant into one or more regions corresponding to emotional actions when both the user and the robot are interested in the program being viewed; Dividing the second quadrant into one or more regions corresponding to emotional actions when only the user is interested in the program being viewed; Dividing the third quadrant into one or more regions corresponding to emotional actions when both the user and the robot are not interested in the program being viewed; 4. The robot motion expression device according to claim 3, wherein the fourth quadrant is divided into one or more regions corresponding to emotional motions when only the robot is interested in the program being viewed.

5. A robot motion expression program for causing a computer to function as the robot motion expression device according to claim 1 or 2.

Images