JP7155676B2 - Naming support device, robot, naming support method and program - Google Patents

Description

The present invention relates to a naming assistance device, a robot, a naming assistance method, and a program.

A robot has been developed that recognizes a name given by a user and performs an action in response to calling the name. Such a robot analyzes the voice uttered by the user by voice recognition and recognizes that its own name has been called. For example, Patent Literature 1 discloses a robot control device having a registration means for registering an input voice as a name.

In this conventional name registration device, when a user registers a word that is acoustically similar to a word pre-registered for speech recognition as the name of the robot, the robot will not be able to recognize the robot even if its own name is called. In order to avoid such misrecognition, the voice may be misrecognized as a similar word, or the robot may misrecognize that its own name was called when the similar word was uttered. , robot name registration is performed as follows.

That is, when a word that is acoustically similar to the input name is stored in the word dictionary for speech recognition, the user is notified that the name is inappropriate for the robot, and the input name is not registered. When the name is not stored in the word dictionary for voice recognition, the user is notified that it is suitable as the name of the robot, and the input name is registered.

Japanese Unexamined Patent Application Publication No. 2002-120177

As described above, Patent Literature 1 merely states that if a word that is acoustically similar to the name represented by the input voice is registered in the word dictionary, it is not registered as a name. For this reason, the technique described in Patent Document 1 may not be able to sufficiently support determination of a name suitable for a robot.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a naming assistance device, a robot, a naming assistance method, and a program capable of sufficiently assisting a user in determining an appropriate name for a robot. do.

In order to achieve the above object, the naming assistance device of the present invention includes:
A naming assistance device for assisting naming of a voice recognition robot , comprising:
an acquisition unit that acquires a character string;
a presentation unit that calculates and presents a name that the robot can easily recognize by voice based on the character string acquired by the acquisition unit .

According to the present invention, it is possible to sufficiently assist the user in determining a suitable name for the robot.

1 is a functional block diagram of a naming support device according to Embodiment 1 of the present invention; FIG. 4 is a diagram showing an example of audio type information according to Embodiment 1 of the present invention; FIG. FIG. 4 is a diagram showing an example of sound type combination information according to Embodiment 1 of the present invention; It is a figure showing an example of the dictionary information which concerns on Embodiment 1 of this invention. 1 is a hardware configuration diagram of a naming support device according to Embodiment 1 of the present invention; FIG. It is a figure showing an example of the name input screen which concerns on Embodiment 1 of this invention. 4 is a flowchart of recommended character determination processing according to Embodiment 1 of the present invention. FIG. 9 is a diagram showing an example of a name input screen as a processing result of recommended character determination processing according to the first embodiment of the present invention; FIG. 10 is a diagram showing another example of the name input screen as a processing result of the recommended character determination processing according to the first embodiment of the present invention; 4 is a flowchart of input character evaluation processing according to Embodiment 1 of the present invention. FIG. 11 is a diagram showing another example of the name input screen as a processing result of the input character evaluation processing according to the first embodiment of the present invention; FIG. 8 is a functional block diagram of a naming support device according to Embodiment 2 of the present invention; FIG. 10 is a diagram showing an example of recommended name information according to Embodiment 2 of the present invention; FIG. 10 is a diagram showing an example of display data according to Embodiment 2 of the present invention; FIG. 4 is a hardware configuration diagram of a naming support device according to Embodiment 2 of the present invention; It is a figure showing an example of the name input screen which concerns on Embodiment 2 of this invention. 9 is a flow chart of name diagnosis result generation processing according to the second embodiment of the present invention. It is a figure showing an example of the diagnostic result screen which concerns on Embodiment 2 of this invention. FIG. 11 is a diagram showing another example of a diagnosis result screen according to Embodiment 2 of the present invention;

(Embodiment 1)
An embodiment in which the present invention is applied to determine the name of a robot will be described below with reference to the drawings.

The naming support device 10 according to this embodiment is a device for supporting a user in determining a name that is easy for a robot to recognize. A robot is a device that operates autonomously, recognizes a given name through voice recognition, and performs a predetermined action in response to it. Namely, the named name triggers the operation of the robot. As shown in FIG. 1, the naming support device 10 includes an input unit 11, a control unit 12, a vocalization index information storage unit 13, a dictionary information storage unit 14, a data storage unit 15, and an output unit 16. Prepare.

The input unit 11 receives input of a character string representing the name of the robot. The user of the naming support device 10 operates a keyboard, which will be described later, to move a cursor displayed on the name input screen to select a character at a position corresponding to the cursor, or press a character key on the keyboard to select a character. Repeat the input to enter a string that represents the robot's name.

The control unit 12 acquires characters input to the input unit 11, determines the next recommended character, and determines whether the input character string is appropriate as a name. Execute the process. Then, the control unit 12 generates information to be displayed on the name input screen and causes the output unit 16 to output the information.

The utterance index information storage unit 13 stores information indicating how easily a character string is uttered by a human. Specifically, the utterance index information storage unit 13 stores voice type information AS representing information on the type of voice for each character, and information on ease of utterance when two characters are voiced consecutively. Voice type combination information AK representing As shown in FIG. 2, the speech type information AS includes, for each character, whether it is a vowel or a consonant, a stage in the fifty syllables, a consonant type representing the articulation method of the consonant, and the like. Further, the voice type combination information AK, as shown in FIG. 3, includes an index of utterability represented by a numerical value of 0 to 100 for each of the first character type and the second character type. For example, according to the voice type information AS shown in FIG. If the characters are also "adan no vowels", the index of ease of pronunciation of these characters is zero. Therefore, these pieces of information indicate that the index of the ease of uttering a string of characters "ah" is zero. It should be noted that the larger the numerical value of the index of ease of speaking, the easier it is to speak.

The dictionary information storage unit 14 stores dictionary information DI representing meaningful words. The dictionary information DI includes words and their frequency of use, as shown in FIG. Names similar to commonly used words are substantially more likely to be misrecognized. Therefore, the dictionary information DI includes numerical values of frequency of use for each word. Meaningful words are words listed in so-called commercially available Japanese dictionaries, and may include a wide range of terms such as modern terms and technical terms. The frequency of use is set in advance based on information or the like in which natural language sentences such as a so-called corpus are structured and accumulated.

Returning to FIG. 1, the data storage unit 15 stores various character data and image data. Specifically, the data storage unit 15 stores image data, character data, and the like to be displayed on a name input screen, which will be described later. The data storage unit 15 also stores various setting values used for processing described later.

The output unit 16 outputs various information. Specifically, the output unit 16 displays a name input screen, which will be described later. In particular, when information for assisting name input is generated by the processing of the control unit 12, the output unit 16 includes and displays the generated information on the name input screen for presentation to the user.

Next, the hardware configuration of the naming support device 10 will be described with reference to FIG. The naming support device 10 includes a CPU (Central Processing Unit) 101 that executes various processes, a RAM (Random Access Memory) 102 that is a volatile memory, a ROM (Read Only Memory) 103 that is a non-volatile memory, and various It has a hard disk drive 104 that stores information, a keyboard 105 that accepts operations, and a display 106 that displays information.

The CPU 101 reads programs stored in the hard disk drive 104 into the RAM 102 and executes them, thereby executing various processes described later.

A RAM 102 is a volatile memory and is used as a work area for the CPU 101 .

The ROM 103 is a non-volatile memory and stores a control program for basic operations of the naming support device 10 executed by the CPU 101, a BIOS (Basic Input Output System), and the like.

The CPU 101, RAM 102 and ROM 103 cooperate to function as the control unit 12 described above.

The hard disk drive 104 is a medium for storing information, and stores the aforementioned various data. The hard disk drive 104 functions as the utterance index information storage unit 13, the dictionary information storage unit 14, and the data storage unit 15 described above.

The keyboard 105 is an information input device having a plurality of keys capable of executing romaji input, for example, and receives input of various types of information by user's operation. The keyboard 105 functions as the input unit 11 described above.

A display 106 is an information display device such as a liquid crystal panel or a projector. The display 106 displays information necessary for user's operation. The display 106 functions as the output unit 16 described above.

Next, the operation of the naming support device 10 will be described with reference to the drawings. When the naming support device 10 is activated by the user's operation, the control unit 12 acquires the image data and character data stored in the data storage unit 15 and generates information representing a name input screen. Then, the output unit 16 displays a name input screen as shown in FIG.

The name input screen includes a name input field 201 and an OK button 202 . The name input screen also includes an image representing hiragana. The user operates the keyboard 105 to directly input characters or moves a cursor (not shown) to select a desired hiragana to input characters representing the name.

Upon receiving the input of the characters representing the name, the naming support device 10 starts the recommended character determination process shown in FIG. The naming support device 10 performs this recommended character determination process in order to determine a character to be recommended as the next character to be input and include it in the name input screen for display. The recommended character determination process is repeatedly executed each time one character of the name is input by the user.

When the naming support device 10 starts the recommended character determination process, the control unit 12 acquires characters that have already been input via the input unit 11 (step S101). For example, when the character "a" is input first, the character acquired here is "a".

In the subsequent processing, the control unit 12 determines whether or not the character to be recommended as one character following the already input character is displayed on the name input screen shown in FIG. A plurality of characters are processed one by one. First, one character to be processed is determined from among a plurality of unprocessed characters that have not undergone determination processing (step S102). For example, if the control unit 12 processes characters starting from "a" in the order of the Japanese syllabary, "a" is determined as the first character to be processed.

Next, the control unit 12 acquires an index of the utterability of the combination of the last character of the input characters and the one character to be processed (step S103). Specifically, the control unit 12 acquires the voice type information AS and the voice type combination information AK from the utterance index information storage unit 13, and utters the combination of the last input character and the one character to be processed. Get the ease index. For example, when the last character of the input characters is "a" and "a" is being processed as one character to be processed, the control unit 12 generates the voice type information AS and the voice type combination information AK. , the record corresponding to the first character "a" and the second character "a" is obtained, and 0 is obtained as an index of the utterability, for example.

Next, the control unit 12 calculates the degree of similarity between the combination of the input character and one character to be processed and the word included in the dictionary information DI (step S104). Specifically, the control unit 12 calculates the degree of similarity between a character string that is a combination of an input character and one character to be processed and each word included in the dictionary information DI. The control unit 12 calculates the degree of similarity between character strings based on the difference in the number of characters, the number of matching characters, the types of non-matching characters, and the like. The type of the characters that do not match is determined by referring to the audio type information AS. Then, the control unit 12 sets the degree of similarity to the closest word among the words included in the dictionary information DI as the degree of similarity to the word included in the dictionary information DI. For example, if the input character is "a" and the one character to be processed is "a", the character string of the combination of the input character and the one to be processed is "a". Therefore, in this case, the control unit 12 calculates the degree of similarity between "ah" and each of the words included in the dictionary information DI. For example, the control unit 12 determines the degree of similarity with the word “aka” as the difference in the number of characters (there is no difference in the number of characters since both are two characters), the number of matching characters (one character of “a” matches), It is calculated based on the types of characters that do not match (types of "a" and "ka" that do not match). If the calculated degree of similarity is the largest among the degrees of similarity to words included in the dictionary information DI, the control unit 12 regards the degree of similarity as the processing result of step S104.

Next, the control unit 12 comprehensively calculates the adequacy of the combination of the input character and the one character to be processed (step S105). Specifically, the control unit 12 calculates the aptitude based on the index of ease of vocalization acquired in step S103 and the similarity calculated in step S104. The degree of aptitude represents a parameter representing the degree of aptitude of a name uttered by a human when the robot appropriately recognizes the name. In addition, in step S105, the usage frequency of words in the dictionary information DI determined to have the highest degree of similarity in step S104 is also used to calculate the appropriateness. Letting y be the index of ease of speaking acquired in step S103, z be the degree of similarity calculated in step S104, and b be the frequency of use of the word determined to have the highest degree of similarity in step S104, the aptitude degree x is expressed by the following formula: Calculated by

x=w ₁ y+w ₂ (100-b) (100-z)

w ₁ , w ₂ are predefined positive coefficients. For example, w ₁ =0.5 and w ₂ =0.02. As a result, the higher the ease-of-pronunciation index, the higher the aptitude x, and the higher the similarity z and the usage frequency b, the lower the aptitude x. For example, if the input character is ``a'' and the next character is ``a'', the degree of adequacy x is that the frequency of use b of the word ``a'' is 70, and the degree of similarity between ``a'' and ``a'' is If z is 60, then 0.5×0+0.02×(100−70)×(100−60)=12.

Next, the control unit 12 determines whether or not the calculated aptitude is greater than or equal to the first threshold (step S106). The first threshold is a set value stored in advance in the data storage unit 15, and is a threshold for the degree of adequacy for determining whether or not to recommend a character following an already-inputted character. For example, let the first threshold be 80.

If the controller 12 determines that the aptitude is equal to or greater than the first threshold (step S106: Yes), the character being processed is set as a recommended character (step S107). On the other hand, if it is determined that the aptitude is not equal to or greater than the first threshold (step S106: No), it is further determined whether or not the aptitude is equal to or greater than the second threshold (step S108). The second threshold is a set value stored in advance in the data storage unit 15 and is a value smaller than the first threshold. The second threshold is a threshold for adequacy for determining whether or not one character following an already-inputted character is an unrecommended character. For example, assume that the second threshold is 30.

Then, when the controller 12 determines that the aptitude is equal to or higher than the second threshold (step S108: Yes), the character being processed is set to another character (step S110). On the other hand, if the controller 12 determines that the aptitude is not equal to or greater than the second threshold (step S108: No), the character being processed is set as an unrecommended character (step S109).

After step S107, step S109, or step S110, the control unit 12 determines whether or not the suitability of all characters has been calculated (step S111). If the control unit 12 determines that the aptitude levels of all characters have not been calculated (step S111: No), the process proceeds to step S102 to determine the next unprocessed character. On the other hand, when the control unit 12 determines that the suitability of all characters has been calculated (step S111: Yes), the control unit 12 ends the recommended character determination process.

As a result of the recommended character determination processing performed by the control unit 12, the output unit 16 superimposes a gray image 203 on the character image representing the non-recommended character, and displays a thick frame image 204 around the image representing the recommended character. , and other characters are displayed as they are. For example, FIG. 8 is an example of the name input screen after inputting "a". According to the above example, if the aptitude level is 12 when the character following "a" is "a" and the second threshold is 30, "a" is a non-recommended character. is superimposed. For example, in the example of FIG. 8, since "i", "u", "e", and "o" are also determined to be non-recommended characters, the gray image 203 is superimposed on these character images, and "ki", " Since "ke", "mi", and "me" are determined to be recommended characters, a thick frame image 204 is displayed at a position surrounding these character images.

On the name input screen, place the cursor on one of the recommended characters from the beginning to make it easier to select. In addition, even if a non-recommended character is selected, it is not processed, and the selection of the non-recommended character is substantially prohibited. Furthermore, even if non-recommended characters are input from the keyboard 105, they are not processed, so that non-recommended characters cannot be input.

Next, when the user inputs "ki" as a character following "a", the control unit 12 sets "aki" as the input character and executes the recommended character determination process. As a result of the execution, the control unit 12 provisionally determines "sa", "to", "ma" and "me" as recommended characters, and "i", "ki", "ke", "ta" and "ya". is determined to be a non-recommended character, the output unit 16 displays a name input screen as shown in FIG.

Next, the user presses the OK button 202 with the intention of determining the entered character string as the name. Then, the naming support device 10 starts input character evaluation processing as shown in FIG.

When the naming support device 10 starts input character evaluation processing, the control unit 12 acquires an input character string via the input unit 11 (step S21). Next, the control unit 12 calculates the degree of similarity between the input character string and words included in the dictionary information DI (step S22). The similarity calculation method is the same as in step S104 of the recommended character determination process.

Next, the control unit 12 determines whether or not the degree of similarity is greater than or equal to the third threshold (step S23). The third threshold is a set value stored in advance in the data storage unit 15, and is a threshold for determining whether or not the entered character string is appropriate as a name. For example, assume that the third threshold is 70.

When determining that the degree of similarity is equal to or higher than the third threshold (step S23: Yes), the control unit 12 executes the above-described recommended character determination process (step S24). On the other hand, if the control unit 12 determines that the degree of similarity is not equal to or greater than the third threshold (step S23: No), it ends this input character evaluation process.

When the control unit 12 ends the input character evaluation process and determines that the degree of similarity is equal to or higher than the third threshold, the output unit 16 outputs the character data " *Because it is close to a dictionary word, it is difficult to recognize. In addition, when the control unit 12 executes in step S24 and determines recommended characters and non-recommended characters as a processing result of the recommended character determination process, the output unit 16 also displays the gray image 203 and the thick frame image 204 indicating these characters. Display on the name input screen.

As described above, the naming support device 10 according to the present embodiment presents the user with a name that can be easily recognized by the voice of the robot. This is sufficient to assist the user in determining a suitable name for the robot, and thus allows the user to give the robot a suitable name.

The naming assistance device 10 according to the present embodiment presents to the user a name that the robot can easily recognize by voice, based on the input character string. This allows the user to determine a name that is similar to the input character string and is easy to recognize by voice.

The naming assistance device 10 according to the present embodiment provides a robot with a voice produced by uttering a part of a character string that includes an input first character and a second character that follows the first character. An index representing ease of speech recognition is calculated for each of the plurality of second characters as the second character, and based on the calculated index, a recommended character that is recommended to be input among the plurality of second characters Or present the user with non-recommended characters that are recommended not to be entered. This allows the user to determine characters suitable for the character string representing the name of the robot one by one.

The naming assistance device 10 according to the present embodiment calculates an index representing the ease of speech recognition by a robot for an input character string, based on the index of ease of human vocalization for the input character string. This allows the user to determine a name that is easy to pronounce, and avoids the robot from erroneously recognizing its own name due to unclear pronunciation of the name.

The naming assistance device 10 according to this embodiment calculates an index representing ease of speech recognition based on the degree of similarity representing the degree of similarity to meaningful words stored in the dictionary information storage unit 14 . This allows the user to determine names that are not similar to meaningful words and avoids the robot misrecognizing its own name due to confusion with meaningful words.

In this embodiment, an example is shown in which the characters to be input from the name input screen are limited to hiragana. However, katakana, kanji, alphabets, etc. may be input. In particular, when inputting kanji characters, alphabets, etc., the naming support device 10 is equipped with a computer that executes a program that determines the pronunciation method based on the information that defines the pronunciation method of the input character or the input character. is desirable.

In the recommended character determination processing according to the present embodiment, an example of calculating an index of the easiness of utterance in a row between the last first character that has already been input and the second character, which is one subsequent character, has been described. However, the scope of the present invention is not limited to this. It is also possible to calculate an index of the easiness of vocalization at the time. In that case, the voice type combination information AK may store not only the ease of speaking two characters, but also an index of the ease of speaking a character string consisting of a plurality of characters. In that case, the recommended character and the non-recommended character are not limited to one character, and may be a recommended character string and a non-recommended character string including a plurality of characters.

In the name input screen according to the present embodiment, the image representing the recommended characters is surrounded by a thick frame image 204, and the image representing the non-recommended characters is superimposed with the gray image 203, so that the recommended characters and the non-recommended characters are displayed to the user. The example presented has been illustrated. However, the scope of the present invention is not limited to this, as long as the recommended characters and the non-recommended characters can be output in a manner distinguishable from other characters. For example, they may be converted into voice and output, or they may be distinguished by adding or subtracting color, light, or the like. In addition, an example of prohibiting the input of non-recommended characters was shown, but users may want to input even non-recommended characters. good.

In step S104 of the recommended character determination process according to the present embodiment, an example of calculating the aptitude for a word with the highest degree of similarity among words included in the dictionary information DI has been shown. However, instead of the degree of similarity, it is also possible to target the most influential words including the frequency of use. For example, if the frequency of use is b and the degree of similarity is z, the word that minimizes (100-b)·(100-z) may be processed. In addition, instead of one word, the average value may be calculated for a plurality of words with a large degree of similarity or small values of (100-b) and (100-z) described above. . Also in step 22 of the input character evaluation process, the control unit 12 may similarly calculate a value considering not only the degree of similarity but also the frequency of use.

In step S105 of the recommended character determination process according to the present embodiment, an example of calculating the aptitude based on the index of ease of speaking and the similarity has been shown. By calculating the aptitude level from a plurality of factors in this way, it is possible to calculate the aptitude level with high accuracy, thereby presenting recommended characters and non-recommended characters to the user with high accuracy. . However, in spite of this, the aptitude may be calculated only from the index of ease of vocalization, or the aptitude may be calculated from only the similarity. In this case, the process of step S103 or step S104 may be omitted. By omitting any of the processes in this way, the processes are simplified, and the processes can be executed with a small load.

(Embodiment 2)
In the first embodiment, an example of presenting a user with a name that is easy to recognize by voice is presented by displaying recommended characters or non-recommended characters on the name input screen for determining the name of the robot. In this embodiment, after the user has completely entered the name of the robot, the suitability of the character string representing the entered name is determined by the robot's fortunes or It is represented as a personality and presented to the user, prompting the user to re-enter a voice-friendly name. In the following, this embodiment will be described with a focus on the parts that differ from the first embodiment.

As shown in FIG. 12, the naming support device 10 according to this embodiment further includes a recommended name information storage unit 17 in addition to the functional units described in the first embodiment.

The recommended name information storage unit 17 stores recommended name information SN representing a plurality of names to be recommended to the user as alternatives when the diagnosis result of the input name is not suitable for the robot. The recommended name information SN includes, as shown in FIG. 13, a plurality of names to be recommended and an aptitude level indicating the degree of easiness of voice recognition by the robot for each of these names.

In addition, the data storage unit 15 of the naming support device 10 according to this embodiment further stores display data HD for displaying on the name input screen. As shown in FIG. 14, the display data HD includes a plurality of character data and a plurality of image data representing the health luck of the robot and a plurality of character data and a plurality of image data representing the character of the robot, which are associated with aptitude. Remember. It should be noted that the item of suitability in FIG. 14 represents the lower limit of the range of the corresponding suitability.

The data storage unit 15 also stores a threshold for the suitability. This threshold value is used in the name diagnosis result generation process, which will be described later, and is the threshold value for determining whether or not to present an alternative to the input character string. In addition, in order to present an alternative to an input character string whose suitability is less than this threshold, the suitability of the name stored in the above-mentioned recommended name information SN as an alternative must be greater than this threshold. is desirable.

Next, the hardware configuration of the naming assistance device 10 of this embodiment will be described with reference to FIG. The naming support device 10 has a network card 107 for transmitting and receiving information in addition to the configuration described in the first embodiment.

The network card 107 is a communication device that communicates information with an external device, and is communicably connected to the mobile terminal 20 described later. The network card 107 functions as the input unit 11 or the output unit 16 described above.

The mobile terminal 20 is a smart phone, a tablet, a PDA (Personal Digital Assistant), a mobile phone, or the like, and is a terminal for a user to carry and operate. The mobile terminal 20 includes a CPU 121 , a RAM 122 , a ROM 123 , an antenna 124 and a display 125 .

The CPU 121 executes various processes by executing programs stored in the ROM 123 .

A RAM 122 is a volatile memory and is used as a work area for the CPU 121 .

The ROM 123 is a non-volatile memory, and stores a control program for basic operations of the portable terminal 20 executed by the CPU 121, BIOS, and the like.

The antenna 124 is a communication device that wirelessly communicates information with an external device, and is communicably connected to the naming support device 10 via a base station or the like (not shown).

The display 125 is an information display device including liquid crystal, organic EL (Electro Luminescence), etc., and displays information received from the naming support device 10 . Further, the display 125 is capable of touch panel operation, and transmits operation information to the CPU 121 in response to user's operation.

Next, the operation of the naming support device 10 of this embodiment will be described with reference to the drawings. When the naming support device 10 is activated by the user's operation, the control unit 12 acquires the image data and character data stored in the data storage unit 15 and generates information representing a name input screen. Then, the output unit 16 outputs information representing the name input screen to the mobile terminal 20 . The mobile terminal 20 receives the information and displays a name input screen as shown in FIG. 16 on the display 125 .

The name input screen includes a name input field 301 and a diagnosis button 302 . When the user operates the display 125 to enter a name and press the diagnosis button 302 , the portable terminal 20 transmits operation information to the naming support device 10 . Upon receiving the operation information, the naming support device 10 starts the name diagnosis result generating process shown in FIG.

When the naming support device 10 starts the name diagnosis result generation process, the control unit 12 acquires the input character string through the input unit 11 (step S31).

Next, the control unit 12 calculates the degree of similarity between the input character string and words included in the dictionary information DI (step S32). The similarity calculation method is the same as step S22 of the input character evaluation process of the first embodiment.

Next, the control unit 12 calculates an index of the easiness of vocalization of the input character string when it is assumed that a human being vocalizes the input character string (step S33). Specifically, the control unit 12 calculates an index of ease of utterance when the first and second characters of the input character string are continuously uttered, and then the second and third characters are calculated. A plurality of indices of easiness to utter are calculated by repeating a process such as calculating an index of ease of utterance in the case of continuously uttering . Then, the control unit 12 calculates the average value and uses it as an index of ease of vocalization of the input character string.

Next, the control unit 12 comprehensively calculates the appropriateness of the input character string (step S34). Specifically, the control unit 12 calculates the suitability based on the degree of similarity with the dictionary information DI calculated in step S32 and the index of ease of vocalization calculated in step S33. In calculating the aptitude, the control unit 12 performs the above calculation using the frequency of use of words, coefficients, etc. as parameters, as in step S105 of the recommended character determination process of the first embodiment.

Next, the control unit 12 acquires character data and image data of the health luck and character of the robot corresponding to the aptitude calculated in step S34 from the data storage unit 15 (step S35). For example, if the aptitude obtained in step S34 is 85, the health luck character string "genki" and its image with the lower limit of the aptitude range set to 80 and the personality character string "gentle" and its image are obtained. .

Next, the control unit 12 determines whether or not the suitability is greater than or equal to the threshold value stored in the data storage unit 15 (step S36). When the control unit 12 determines that the aptitude is equal to or greater than the threshold value (step S36: Yes), the control unit 12 ends the name diagnosis result generation processing and sets the processing result as a normal diagnosis result.

On the other hand, if the control unit 12 determines that the aptitude is not equal to or greater than the threshold (step S36: No), it acquires a name similar to the name represented by the input character string from the recommended name information SN (step S37). . When obtaining similar names, the control unit 12 calculates the degree of similarity between the name in the recommended name information SN and the input character string in the same manner as in step S32, and extracts names with a degree of similarity equal to or greater than the reference. Furthermore, in step S37, the control unit 12 acquires image data of health luck and character corresponding to the suitability of the extracted name from the data storage unit 15. FIG.

With this, the control unit 12 ends the name diagnosis result generation processing. The control unit 12 further transmits information including the diagnosis result and the acquired image data and character data as a diagnosis result screen to the portable terminal 20 via the output unit 16 . The portable terminal 20 displays a diagnosis result screen on the display 125 based on the received information and presents it to the user.

As shown in FIG. 18, the diagnosis result screen includes a display area 303 for displaying character string data and image data for each of the health luck and personality obtained in step S35 of the name diagnosis result generation process.

Further, when a name similar to the input character string is acquired in step S37 of the name diagnosis result generation process, the diagnosis result screen is displayed with a plurality of recommended names and their respective names, as shown in FIG. It includes a display area 304 that displays a plurality of health and personality image data each corresponding to a suitability of each name. Each of the displayed plurality of health luck and personality image data represents the robot's fortune or personality when it is assumed that the corresponding name is used as the robot's name.

The naming assistance device 10 according to the present embodiment obtains an index of ease of vocalization of an input character string when the character string is uttered by a human, and based on the obtained index, names the robot to the user. perform a process that assists in making the decision. Thus, by prompting the user to input a name that is easy for humans to pronounce, it is possible to sufficiently assist the user in determining a suitable name for the robot. Therefore, the user can decide on a suitable name for the robot.

The naming support device 10 according to the present embodiment reads the vocalization index information corresponding to the input character string, and acquires the read vocalization index information as an index. This allows the user to grasp the ease with which the input character string can be pronounced.

The naming assistance device 10 according to the present embodiment expresses the suitability of a name represented by a character string as the fortune or personality of a robot when it is assumed that the name represented by the character string is used as the name of the robot. Present. As a result, it is possible to naturally induce the user to give a suitable name to the robot while increasing the interest in naming the robot by the user.

The naming support device 10 according to this embodiment presents to the user names similar to the input character string in the recommended name information SN. This makes it possible to determine recommended names that are similar to the character string entered by the user.

The naming assistance device 10 according to the present embodiment further presents to the user data based on the suitability of names similar to the input character string in the recommended name information SN. This allows the user to obtain information on which to select a recommended name.

(Modification)
The present invention is not limited to the embodiments described above, and various other modifications are possible.

The hardware configuration, software configuration, and the like described above are examples for facilitating understanding of the embodiments of the invention, and do not limit the invention.

In the above-described embodiments, in Embodiment 1, the output unit 16 displays an input screen containing the recommended character string or the non-recommended character string on the display 106, thereby presenting the recommended character string or the non-recommended character string to the user. showed that. In the second embodiment, the output unit 16 transmits information representing the recommended character string or the non-recommended character string to the mobile terminal 20 operated by the user, thereby presenting the recommended character string or the non-recommended character string to the user. showed that. The method by which the output unit 16 presents the recommended character string or the non-recommended character string to the user is not limited to such screen display or information transmission. Any method for presenting to the user such as

The naming assistance device 10 according to the above-described embodiment may also use elements other than the above-described elements for facilitating speech recognition of an input character string. For example, the length of the input character string may be used as an element. That is, it may be determined that voice recognition is difficult when the length of the character string is one character, and that voice recognition is easy when the length is two characters. Further, it may be determined that the longer the character string after the third character, the more difficult it is to recognize the voice. The naming support device 10 may calculate the aptitude by comprehensively considering the length of the character string as one factor and other factors.

The input unit 11 of the naming support device 10 of the first embodiment has shown an example of inputting a name character string via the keyboard 105 . The name input method is not limited to this, and for example, voice input may be performed. In this case, the naming assistance device 10 is provided with a microphone (not shown), and the CPU 101 or the like performs well-known speech recognition processing to convert voice input through the microphone into a character string. That is, in that case, the microphone and the CPU 101 function as the input section 11 . Note that the mobile terminal 20 of the second embodiment may also perform voice input. In this case, the mobile terminal 20 has a microphone (not shown), and converts voice input through the microphone into characters by voice recognition processing.

The control unit 12 of the naming support device 10 according to the above-described embodiment controls the output unit 16 to present a recommended character string to the user as processing for supporting the user in determining the name of the robot. I gave an example. The processing executed by the control unit 12 is not limited to that. For example, the output unit may be controlled to prohibit the registration of a name that is difficult to pronounce in the robot name registration process (not shown) based on the calculated index of ease of vocalization, and to present this to the user. . Alternatively, a process of changing the action pattern may be performed by accessing the control unit of the robot (not shown). For example, when trying to register a name that is difficult to pronounce, the robot may shake its head to refuse to register the name. In addition, the robot may slow down, or make anthropomorphic motion such as sadness or sluggishness. In this case, the change in robot movement prompts the user to change the name.

Also, the naming support device 10 according to the second embodiment may output a highly suitable name from the recommended name information SN regardless of the character string input by the user via the mobile terminal 20 . For example, by referring to information representing the user's taste, personality, etc., a name suitable for the user may be acquired from the recommended name information SN and presented to the user. Alternatively, a plurality of names whose aptitude is equal to or higher than the reference value may be randomly extracted from the recommended name information SN and presented to the user.

Further, in the second embodiment, the example in which the naming support device 10 presents the image data and character data stored in the data storage unit 15 to the user via the portable terminal 20 has been described. The data to be presented to the user is not limited to this, and fortune or personality may be presented by sound, or data representing other sounds, smells, and the like may be used.

The naming support device 10 can be realized using a normal computer without using a dedicated system. For example, the naming support device 10 that executes the above process can be configured by installing the program in the computer from a recording medium or the like storing the program for executing any of the above processes.

The naming support device 10 may function as a part of the components in cooperation with an external device. For example, the control unit 12 may function as the vocalization index information storage unit 13, the dictionary information storage unit 14, the data storage unit 15, or the recommended name information storage unit 17 by acquiring information from an external device.

A robot to be named may be provided with the naming support device 10 according to the above-described embodiment. In that case, information that facilitates speech recognition may be stored as the characteristics of the robot, and the appropriateness of the name may be determined by referring to the information.

Since the ease with which a character string can be pronounced and meaningful words differ depending on the language, only the Japanese example was shown in the above-described embodiment. However, since not only Japanese but also other languages such as English and Chinese can have words that are easy to pronounce and meaningful words in each language, information suitable for each language is retained. The present invention can be applied by keeping

Any method may be used to supply the program to the computer. For example, it may be supplied via a communication line, communication network, communication system, or the like.

In addition, in the case where an OS (Operating System) provides some of the functions described above, the parts other than the functions provided by the OS may be provided by a program.

Although the preferred embodiments of the present invention have been described above, the present invention is not limited to such specific embodiments, and the present invention includes the invention described in the claims and their equivalents. be The invention described in the original claims of the present application is appended below.

(Appendix 1)
A naming aid device for assisting a user in determining a name for a robot configured to operate in response to speech recognition of the user's vocally entered name of the robot, comprising:
an input unit that receives a user input of a character string representing the name of the robot;
an output unit configured to output information;
a control unit that controls the output unit to present the user with a name that is easy for the robot to recognize by voice;
Naming support device.

(Appendix 2)
The control unit controls the output unit to present the user with a name that the robot can easily recognize, based on the character string input to the input unit.
A naming support device according to appendix 1.

(Appendix 3)
The input unit receives, as part of the character string, input by a user of a first character representing part of the name of the robot,
The control unit enables the robot to perform speech recognition of a part of the character string that includes the input first character and a second character after the first character. An index representing ease of entry is calculated for each of the plurality of second characters as the second characters, and based on the calculated index, recommendation is made to recommend inputting one of the plurality of second characters controlling the output unit to present the user with characters or non-recommended characters that are recommended not to be input;
A naming support device according to appendix 2.

(Appendix 4)
further comprising a vocalization index information storage unit that stores vocalization index information representing an index of ease of vocalization of the character string;
The control unit calculates an index of ease of utterance of the part of character strings based on the utterance index information stored in the utterance index information storage unit, to calculate an index representing the ease of speech recognition,
A naming support device according to appendix 3.

(Appendix 5)
further comprising a dictionary information storage unit that stores dictionary information representing meaningful words,
Based on the dictionary information stored in the dictionary information storage unit, the control unit calculates a degree of similarity representing a degree of similarity of the part of character strings to the meaningful word, and based on the degree of similarity calculating an index representing the ease of speech recognition;
A naming support device according to appendix 3 or 4.

(Appendix 6)
The control unit determines the suitability of the name represented by the character string with respect to speech recognition of the robot, assuming that the name represented by the character string input to the input unit is used as the name of the robot. to get the
3. A naming support device according to appendix 1 or 2.

(Appendix 7)
The control unit expresses the suitability of the acquired name represented by the character string as the fortune or character of the robot when it is assumed that the name represented by the character string is used as the name of the robot. controlling the output unit to present;
A naming support device according to appendix 6.

(Appendix 8)
A naming aid device for assisting a user in determining a name for a robot configured to operate in response to speech recognition of the user's vocally entered name of the robot, comprising:
an input unit that receives a user input of a character string representing the name of the robot;
To obtain an index of ease of uttering the input character string when a human utters the input character string, and to assist the user in determining the name of the robot based on the obtained index. A control unit that executes a predetermined process of
Naming support device.

(Appendix 9)
further comprising a storage unit that stores utterance index information representing ease of uttering each of the plurality of character strings when a human utters each of the plurality of character strings;
the control unit reads from the storage unit, vocalization index information corresponding to the character string input to the input unit, and acquires the read vocalization index information as the index;
A naming support device according to appendix 8.

(Appendix 10)
further comprising an output unit capable of outputting information,
By executing the predetermined process, the control unit performs the above obtaining the suitability of the name represented by the character string based on the obtained index; controlling the output unit to represent and present the fortune or personality of the robot when assumed to be used as the name of the robot;
10. A naming support device according to appendix 8 or 9.

(Appendix 11)
an output unit capable of outputting information;
a recommended name information storage unit that stores recommended name information representing a plurality of different names that are recommended for voice recognition by the robot;
By executing the predetermined process, the control unit reads out a name similar to the character string in the recommended name information from the recommended name information storage unit, and further presents the read name to the user. controlling the output to
10. A naming support device according to appendix 8 or 9.

(Appendix 12)
the recommended name information includes, in addition to the plurality of names, a plurality of degrees of suitability each corresponding to each of the plurality of names;
each of the plurality of aptitudes represents an aptitude when each of the corresponding plurality of names is used as the name of the robot;
The control unit further reads, from the recommended name information storage unit, a suitability degree corresponding to the name to be read out of the plurality of suitability degrees by executing the predetermined processing, and stores data based on the read suitability degree. controlling the output unit to further present the user with
11. A naming support device according to appendix 11.

(Appendix 13)
A naming support device according to any one of Appendices 1 to 12,
robot.

(Appendix 14)
1. A naming assistance method for assisting a user in determining a name for a robot configured to operate in response to speech recognition of the user's vocally entered name of the robot, comprising:
Receiving a user input of a character string representing the name of the robot,
presenting the user with a name that is easy for the robot to recognize by voice;
Naming support method.

(Appendix 15)
A naming aid device for assisting a user in determining a name for a robot configured to operate in response to speech recognition of the user's vocally entered name of the robot, comprising:
Receiving a user input of a character string representing the name of the robot,
Acquiring an index of ease of uttering the input character string when a human utters the input character string,
performing a predetermined process to assist a user in determining the name of the robot based on the obtained index;
Naming support method.

(Appendix 16)
to the computer,
Receiving input of a character string representing the name of the robot;
Presenting a user with a name that the robot can easily recognize by voice;
program to run the

(Appendix 17)
to the computer,
Receiving input of a character string representing the name of the robot;
obtaining an index of ease of uttering the input character string when a human utters the input character string;
performing a predetermined process to assist a user in determining the name of the robot based on the obtained index;
program to run the

10 Naming support device 11 Input unit 12 Control unit 13 Vocalization index information storage unit 14 Dictionary information storage unit 15 Data storage unit 16 Output unit 17 Recommended name information storage unit 20 Mobile terminal 101 CPU 102 RAM 103 ROM 104 Hard disk drive 105 Keyboard 106 Display 107 Network card 121 CPU 122 RAM 123 ROM 124 Antenna , 125... Display 201... Input field 202... OK button 203... Gray image 204... Thick frame image 205... Error display field 301... Input field 302... Diagnosis button 303, 304... Display area

Claims (12)

A naming assistance device for assisting naming of a voice recognition robot , comprising:
an acquisition unit that acquires a character string;
a presentation unit that calculates and presents a name that the robot can easily recognize by voice based on the character string acquired by the acquisition unit;
A naming support device comprising: The acquisition unit acquires, as part of the character string, one character representing part of the name of the robot,
the presenting unit, for a character string including the acquired one character and a plurality of characters following the one character, a calculation unit that calculates an index representing ease of speech recognition for each of the plurality of characters;
Based on the calculated index, the presentation unit is configured to present recommended characters recommended as characters indicating a name or non-recommended characters recommended not to be input as characters indicating a name, for the plurality of characters. a control unit that controls
2. The naming support device according to claim 1, comprising : further comprising a vocalization index information storage unit for storing vocalization index information representing an index of ease of vocalization of the character string;
3. The naming support device according to claim 2, wherein said calculation unit calculates an index of ease of utterance of said character string based on said utterance index information stored in said utterance index information storage unit. . 4. The naming support device according to claim 3, wherein the calculation unit calculates the index representing the ease of voice recognition based on the index of ease of vocalization . further comprising a dictionary information storage unit that stores dictionary information representing meaningful words,
2. The calculation unit calculates a degree of similarity representing a degree of similarity between the character string and the meaningful words based on the dictionary information stored in the dictionary information storage unit. 5. A naming support device according to any one of items 1 through 4. 6. The naming support device according to claim 5 , wherein the calculation unit calculates an index representing the ease of speech recognition based on the degree of similarity . 2. The apparatus according to claim 1 , further comprising an aptitude acquisition unit that acquires an aptitude of the name for voice recognition of the robot when the character string acquired by the acquisition unit is assumed to be the name of the robot. naming support device. 8. The naming support according to claim 7, wherein the presentation unit presents the aptitude obtained by the aptitude obtaining unit as a fortune or character of the robot when the robot is named. Device. A naming assistance device for assisting naming of a voice recognition robot, comprising:
an acquisition unit that acquires a character string;
a control unit that executes a predetermined process for assisting the determination of the name of the robot based on the ease of vocalization when the character string is vocalized by a human;
A naming support device comprising: A robot comprising the naming support device according to any one of claims 1 to 9. A naming support method for supporting naming of a voice recognition robot, comprising:
a obtaining step that obtains a string;
a presentation step of calculating a name that the robot can easily recognize by voice based on the character string acquired in the acquisition step and presenting it to a presentation unit;
A naming support method characterized by comprising: the computer,
an acquisition means for acquiring a string,
Presentation means for calculating and presenting a name that the robot can easily recognize by voice based on the character string acquired by the acquisition means;
A program that acts as a

Images