JP6698423B2 - Response control device, control program, information processing method, and communication system - Google Patents

Description

  The present invention relates to a response control device, a control program, an information processing method, and a communication system including a server and a response control device.

  Conventionally, a voice recognition device for performing voice conversation with a user is known. In the voice recognition device, it is necessary to store a huge amount of question contents and response contents in advance in order to widely respond to questions from users. On the other hand, the questions from the user are rich in variety, and it is impossible to prepare the question content and the response content assuming all the questions.

  Therefore, for example, Japanese Unexamined Patent Application Publication No. 2009-251019 (Patent Document 1) discloses a recognition result for an input voice based on the reliability of the recognition result and the influence degree of a task corresponding to the recognition result. Disclosed is a voice recognition device that determines a response content.

JP, 2009-251019, A

  However, the conventional voice recognition device does not define the response content for an unexpected recognition result. For this reason, when an unexpected recognition result is obtained due to erroneous recognition or the like, it is not possible to appropriately respond, and it has not been possible to contribute to the lack of response content.

  The present disclosure has been made in view of the above problems, and an object of a certain aspect thereof is to provide a response control device, a control program, an information processing method, and a communication system capable of compensating for lack of response content. To provide.

  According to one aspect, in the response control device, the voice reception unit that receives a voice input and the phrase specified by the voice received by the voice reception unit is one of a plurality of predetermined phrases. And a response process executing means for executing a response process for a phrase corresponding to the phrase, wherein the response process executing means is one of a plurality of types of phrases in which the phrase identified from the voice accepted by the voice accepting means. When approximating any of them, the approximating response process corresponding to the approximating phrase is executed.

  According to another aspect, the control program causes a computer to function as a response control device and causes the computer to function as each of the above means.

  According to still another aspect, the information processing method includes a step of receiving a voice input, and when the phrase identified from the received voice is one of a plurality of predetermined phrases. A step of executing a response process for a phrase corresponding to the phrase, and an approximation response process corresponding to the approximate phrase when the phrase specified from the received voice approximates one of a plurality of types of phrases. Performing steps.

  According to still another aspect, the communication system includes a server and a response control device capable of communicating with the server. The response control device includes a voice receiving unit that receives a voice input, a communication unit that transmits voice information corresponding to the voice received by the voice receiving unit and receives response information from the server, and based on the received response information. Response processing executing means for executing response processing according to the present invention. The server stores a plurality of types of phrases specified from a storage unit that stores response information for phrases and response information for approximation as response information corresponding to each of a plurality of types of predetermined phrases, and a phrase specified from voice information from the response control device. Response phrase transmitting means for transmitting the phrase response information corresponding to the phrase as response information, and the phrase specified from the voice information from the response control device has a plurality of types of phrases. And an approximate response information transmitting means for transmitting, as response information, approximate response information corresponding to the approximate phrase.

  According to one aspect, it is possible to compensate for the lack of response content.

It is a figure for explaining a schematic structure of a communication system. It is a figure showing an example of exchange of a conversation between a user and a terminal. It is a figure showing an example of the hardware constitutions of a terminal. It is a figure showing an example of the hardware constitutions of a server apparatus. It is a functional block diagram for demonstrating the functional structure of a terminal. It is a figure for demonstrating the schematic structure of the response phrase DB, voice recognition result DB, and learning result DB which are memorize|stored in the memory|storage part. It is a flow chart for explaining the flow of response processing at the time of voice input. It is a functional block diagram for demonstrating the functional structure of a terminal and a server apparatus. It is a figure for demonstrating the schematic structure of the response phrase DB in which the response phrase is memorize|stored corresponding to the regular phrase and the phrase approximate.

  Hereinafter, embodiments will be described with reference to the drawings. In the following description, the same parts are designated by the same reference numerals. Their names and functions are also the same. Therefore, detailed description thereof will not be repeated.

[Embodiment 1]
<A. System configuration>
FIG. 1 is a diagram for explaining the schematic configuration of the communication system according to the present embodiment. Referring to FIG. 1, communication system 1 includes a mobile terminal 100 (hereinafter, also referred to as terminal 100) and a server device 200. The terminal 100 is an example of a response control device, and performs a process of outputting a response phrase to a user's voice (a voice input response process). In the following, as the terminal 100, a terminal (so-called robot-type terminal) capable of automatically moving a movable part forming a housing by executing a program will be described as an example.

  Specifically, the terminal 100 includes hands, feet, a head, a body, and the like. The terminal 100 is typically configured as an autonomous mobile body that can walk. The head is configured to be rotatable within a predetermined angle with respect to the body. A camera is built in the head. The terminal 100 is not limited to the humanoid robot described above.

  The terminal 100 is used in various places by being carried by the user 700. The terminal 100 communicates with the server device 200 via the base station 500 and the network 600.

<B. Outline of processing>
The outline of the processing in the communication system 1 will be described below. The terminal 100 performs voice recognition and specifies a phrase based on the voice uttered by the user 700. A phrase is, for example, a phrase, a word, a group of words, or the like. The voice recognition means converting input voice data into a corresponding phrase. The terminal 100 stores in advance response phrases corresponding to a plurality of types of supposed phrases (also referred to as regular phrases). The terminal 100 outputs the response phrase when the response phrase corresponding to the phrase specified from the voice is stored.

  Further, the terminal 100 may erroneously recognize a part of the voice due to the influence of the user's pronunciation and surrounding noise. In preparation for such an erroneous recognition, the terminal 100 stores in advance corresponding response phrases for phrases that are similar to the assumed regular phrases. An approximate phrase is a phrase that differs from a regular phrase only in the presence or absence of a dakuten (""), the presence or absence of a consonant ("t"), and the presence or absence of a long note ("-"). Say. Therefore, the terminal 100 outputs the response phrase when it stores the response phrase corresponding to the phrase close to the phrase even when the response phrase corresponding to the specified phrase is not stored. To do.

  Further, the terminal 100 performs a learning process for learning the response phrase when the learning condition is satisfied. The learning condition is satisfied when an unstored phrase is specified at a predetermined frequency (for example, twice in succession), and when a predetermined learning start phrase is specified. The outline will be described below.

  FIG. 2 is a diagram showing an example of exchange of conversation between the user 700 and the terminal 100. The balloons (steps M01 to M12) shown in FIG. 2 represent voices emitted from the user 700 or voices output from the terminal 100. Further, a square box (steps S01 to S13) shown in FIG. 2 shows an outline of the process executed by the terminal 100.

First, a case where a response phrase corresponding to a phrase specified by voice is stored in the terminal 100 will be described.
As shown in step M01, it is assumed that the user 700 utters a voice “height?” to the terminal 100. On the other hand, in the terminal 100, the message from the user 700 is voice-recognized, and the response phrase corresponding to the result of the voice recognition is extracted and output. The terminal 100 stores the phrase specified as a result of the voice recognition as a history.

In FIG. 2, as shown in step S01, the terminal 100 recognizes that the voice from the user 700 is “Shinchoha?”, and recognizes that “Shincho” is asked based on the phrase.
In step S02, a response phrase that matches the target "Shincho" is extracted. In this example, it is assumed that “height is about 19 cm” is stored as a response phrase that matches “Shincho”. Therefore, as shown in step M02, the terminal 100 outputs a response phrase such as "height is about 19 cm."

Next, although the response phrase corresponding to the phrase specified by the voice is not stored in the terminal 100, the response phrase corresponding to the phrase similar to the phrase specified by the voice (also referred to as phrase (approximate)) is stored. The case will be described.
As shown in step M03, it is assumed that the user 700 utters the voice “Weight is?” to the terminal 100. On the other hand, as shown in step S03, it is assumed that the terminal 100 erroneously recognizes that it is "daijuha?"

  However, a phrase that matches the wording that does not mean “daiju” is not assumed at the design stage and is not stored. In such a case, the terminal 100 determines whether or not a phrase similar to the phrase specified by the voice is stored, and if a similar phrase is stored, the response phrase corresponding to the similar phrase is stored. Is extracted and output. The terminal 100 determines whether or not a phrase that differs from the phrase identified based on the result of voice recognition in terms of the presence or absence of a dakuten, a consonant, a long note, etc. is stored.

  In the example of FIG. 2, it is assumed that “daiju”, which is the first character of “dai”, is stored, excluding the dakuten of “da”. In this case, the terminal 100 determines that “daiju” is close to “taiju”, and extracts a response phrase that matches the approximate “taiju” as shown in step M04. In this example, it is assumed that “maybe the weight? The weight is about 300 g.” is stored as the response phrase that matches the approximate “Taiju”. For this reason, as shown in step M04, the terminal 100 outputs a response phrase such as "maybe the weight? The weight is about 300g."

Next, a case will be described in which a response phrase corresponding to a phrase specified from a voice and a response phrase corresponding to a similar phrase are not stored.
As shown in step M05, the user 700 supposes that the user 100 utters “what is your foot size?” to the terminal 100. On the other hand, as shown in step S05, it is assumed that the terminal 100 correctly recognizes that the voice from the user 700 is “Ashino Oxah?”.

  However, when it is not assumed in the design stage that the question about “Ashino Oxaha?” is expected, the phrase “Ashino Oxaha?” is not stored, and the phrase close to the phrase is not stored.

  In this case, the terminal 100 determines that there is no response phrase corresponding to the phrase specified in step S06, and in step S07, the result itself of the voice recognition "Ashino Oxah?" is stored as a history. Then, the terminal 100 outputs a response phrase when an unknown phrase is specified. As a response phrase when an unknown phrase is specified, a phrase for prompting another utterance is defined, for example, a phrase "I didn't hear well" is defined as shown in step M06. The terminal 100 outputs the response phrase and drives the head so as to take a pose of tilting the neck.

  As shown in step M07, in a situation in which an unknown phrase is specified, when the user 700 again utters the voice “What is the size of your foot?”, the terminal 100 returns to the previous step as shown in steps S08 and S09. Similarly to, it is determined that the response phrase is not stored. Then, it is determined whether or not the result of the current voice recognition matches the result of the latest (previous) voice recognition stored in step S07.

  As shown in step S10, when the terminal 100 determines that the result of the current voice recognition matches the result of the previous voice recognition, the terminal 100 does not recognize the voice erroneously, and the user 700 intentionally reads “ It is highly probable that he is uttering "How big is it?", so the following learning process is performed.

  First, as shown in step M08, what should the terminal 100 answer when asked ""Ashino Ooxaha?", based on the specified unknown phrase. The response phrase such as "is output. In this way, since a response such as a parrot return is made, it is possible to prevent the user from inquiring about something that does not make sense. In response to this inquiry, as shown in step M09, it is assumed that the user 700 utters "5 cm.".

  As shown in step S11, the terminal 100 recognizes that the voice from the user 700 is “Gocentimeter Dayo”, and based on the result, as shown in step M10, “It is Gocentimeter”. Should i answer The response phrase such as "is output. In response to this inquiry, as shown in step M11, it is assumed that the user 700 utters a voice "OK". On the other hand, as shown in step S12, when the terminal 100 recognizes the voice as “OK”, the terminal 100 reads the phrase “gocentimeter dayo” as the response phrase of “Ashino Oxaha?” as shown in step S13. After storing, a response phrase such as "I understand." is output as shown in step M12.

  By performing such a learning process, thereafter, when the terminal 100 specifies “Ashino Oxaha?” as a result of the voice recognition, the terminal 100 can output “Gocentimeter Dayo” stored as the response phrase. .. Also, when the result of the voice recognition is similar to "Ashinoooxa" (for example, "Azinoooxa"), the response phrase "Hello by chance? You may do so.

  As described above, when the response phrase corresponding to the phrase specified based on the voice uttered by the user 700 is stored, the terminal 100 outputs the response phrase (steps S01, S02, M02). In addition, the terminal 100 outputs the response phrase even when the response phrase corresponding to the specified phrase is not stored, when the response phrase corresponding to the phrase close to the phrase is stored (step S03, S04, M04). Furthermore, when the response phrase corresponding to the approximate phrase is not stored, and the terminal 100 recognizes the specified phrase at a predetermined frequency (for example, recognizes the phrase twice in succession), the terminal 100 determines the phrase. Learning processing for learning the response phrase corresponding to is performed (steps S05 to S13, M06 to M12).

<C. Hardware configuration>
FIG. 3 is a diagram showing an example of the hardware configuration of the terminal 100. Referring to FIG. 3, terminal 100 has, as main components, a CPU (Central Processing Unit) 151 that executes a program, a ROM (Read-Only Memory) 152 that stores data in a nonvolatile manner, and a program of CPU 151. A RAM (Random Access Memory) 153 for volatile storage of data generated by execution or data input via an input device, a flash memory 154 for non-volatile storage of data, and an LED (Light Emitting Diode) 155, operation key 156, switch 157, GPS (Global Positioning System) receiver 158, communication IF (Interface) 159, power supply circuit 160, touch screen 161, microphone 162, speaker 163, camera 164, a driving device 165, and antennas 1581 and 1591. The respective constituent elements are mutually connected by a data bus.

  The touch screen 161 includes a display 1611 and a touch panel 1612. The antenna 1581 is an antenna for the GPS receiver 158. The antenna 1591 is an antenna for the communication IF 159.

  The LED 155 is various display lamps that indicate the operating state of the terminal 100. For example, the LED 155 indicates the on/off state of the main power supply of the terminal 100, the reading/writing state of the flash memory 154, and the like.

  The operation key 156 is a key (operation button) for the user of the terminal 100 to turn on or off the main power source. The switch 157 is a main power switch for switching whether or not to supply power to the power circuit 160, and various other push button switches.

  The GPS receiver 158 acquires position information of the current position of the terminal 100 based on radio waves from four or more GPS satellites. The position information acquired by the GPS receiver 158 is transmitted to the server device 200 via the communication ID 159. The start timing of acquisition of position information by the terminal 100 will be described later.

  The communication IF 159 performs a data transmission process for the server device 200 and a data reception process for the data transmitted from the server device 200.

  The power supply circuit 160 is a circuit that lowers the voltage of the commercial power supply received via the outlet and supplies power to each unit of the terminal 100.

  The touch screen 161 is a device for displaying various data and receiving an input. The display 1611 is configured to include a screen for displaying an image.

  The microphone 162 collects sounds around the terminal 100. For example, the microphone 162 collects voice based on the utterance of the user 700.

  The speaker 163 outputs a voice corresponding to the response phrase. In a certain situation, speaker 163 speaks in order to communicate with a user or the like.

  The camera 164 is an imaging device for imaging a subject around the terminal 100. The image data obtained by the image pickup by the camera 164 is transmitted to the server device 200 via the communication ID 159.

  The drive device 165 is a drive mechanism for driving the hands, feet, and head of the terminal 100. Note that the terminal 100 walks when the legs are driven by the driving device 165. Further, the orientation of the camera 164 changes as the head rotates with respect to the body by the drive device 165. In addition, the terminal 100 can make a pose of tilting the neck by changing the angle of the head by the driving device 165.

  The process (for example, voice input response process) in the terminal 100 is realized by each hardware and software (control program) executed by the CPU 151. Such software may be stored in the flash memory 154 in advance. The software may be stored in another storage medium and distributed as a program product. Alternatively, the software may be provided as a program product that can be downloaded by an information provider connected to the so-called Internet. Such software is temporarily stored in the flash memory 154 after being read from the storage medium by the reading device or downloaded via the communication IF 159 or the like. The software is read from the flash memory 154 by the CPU 151 and stored in the RAM 153 in the form of an executable program. The CPU 151 executes the program.

  The respective constituent elements that make up the terminal 100 shown in the figure are general ones. Therefore, it can be said that the essential part of the present disclosure is the software stored in the RAM 153, the flash memory 154, the storage medium, or the software downloadable via the network. Since the operation of each hardware of terminal 100 is well known, detailed description will not be repeated.

  The recording medium is not limited to a DVD (Digital Versatile Disc)-RAM, but may be a DVD-ROM, a CD (Compact Disc)-ROM, an FD (Flexible Disc), a hard disk, a magnetic tape, a cassette tape, an optical disk, or an EEPROM (Electrically). It may be a medium such as an Erasable Programmable ROM) or a semiconductor memory such as a flash ROM that fixedly carries a program. The recording medium is a non-transitory medium in which the program and the like can be read by a computer. Further, the program mentioned here includes not only a program directly executable by the CPU but also a program in a source program format, a compressed program, an encrypted program, and the like.

  FIG. 4 is a diagram showing an example of a hardware configuration of the server device 200. Referring to FIG. 4, server device 200 has, as main components, a CPU 251 that executes a program, a ROM 252 that stores data in a nonvolatile manner, data generated by execution of the program by CPU 251, or an input device. RAM 253 for volatile storage of input data, HDD (Hard Disc Drive) 254 for non-volatile storage of data, LED 255, switch 256, communication IF (Interface) 257, power supply circuit 258, It includes a display 259 and operation keys 260. The respective constituent elements are mutually connected by a data bus.

  The power supply circuit 258 is a circuit that steps down the voltage of the commercial power supply received through the outlet and supplies power to each unit of the server device 200. The switch 256 is a switch for the main power supply for switching whether to supply power to the power supply circuit 258, and various other push button switches. The display 259 is a device for displaying various data.

  The communication IF 257 performs a data transmission process for the terminal 100 and a data reception process for the data transmitted from the terminal 100.

  The LED 255 is various display lamps that indicate the operating state of the server device 200. For example, the LED 255 indicates the on/off state of the main power supply of the server device 200, the read/write state to the HDD 254, and the like. The operation keys 260 are keys (keyboard) used by the user of the server device 200 to input data to the server device 200.

  The processing in the server device 200 is realized by each hardware and software executed by the CPU 251. Such software may be stored in the HDD 254 in advance. The software may be stored in another storage medium and distributed as a program product. Alternatively, the software may be provided as a program product that can be downloaded by an information provider connected to the so-called Internet. Such software is temporarily stored in the HDD 254 after being read from the storage medium by the reading device or downloaded via the communication IF 257 or the like. The software is read from the HDD 254 by the CPU 251 and stored in the RAM 253 in the form of an executable program. The CPU 251 executes the program.

  The respective constituent elements of the server device 200 shown in the figure are general ones. Therefore, it can be said that the essential part of the present disclosure is the software stored in the RAM 253, the HDD 254, the storage medium, or the software downloadable via the network. Since the operation of each hardware of server device 200 is well known, detailed description will not be repeated.

  The recording medium is not limited to the DVD-RAM, and the program is fixedly carried such as a DVD-ROM, a CD-ROM, an FD, a hard disk, a magnetic tape, a cassette tape, an optical disk, an EEPROM, or a flash ROM. It may be a medium. The recording medium is a non-transitory medium in which the program and the like can be read by a computer. Further, the program mentioned here includes not only a program directly executable by the CPU but also a program in a source program format, a compressed program, an encrypted program, and the like.

<D. Functional configuration>
FIG. 5 is a functional block diagram for explaining the functional configuration of the terminal 100. Referring to FIG. 5, terminal 100 includes a control unit 111, a storage unit 112, a drive unit 115, a voice input unit 116, a voice output unit 117, and a communication processing unit 118. The terminal 100 also includes the position information acquisition unit 113, the image pickup unit 114, and the like, and may further include other functional configurations.

  The voice input unit 116 collects sounds around the terminal 100 and sends the collected sounds as voice data to the control unit 111. The voice input unit 116 includes, for example, a microphone 162. The voice output unit 117 outputs a voice corresponding to the response phrase. The audio output unit 117 is composed of, for example, a speaker 163.

  The storage unit 112 stores various control programs and has a response phrase DB (Data Base) 1121, a voice recognition result DB 1122, and a learning result DB 1123. The storage unit 112 is composed of, for example, the RAM 153.

  The response phrase DB 1121 stores a response phrase corresponding to a plurality of types of phrases (regular phrases) assumed from the design stage, a response phrase in the case of approximating each of the plurality of types of phrases (regular phrases), and the like. The voice recognition result DB 1122 stores the result of voice recognition based on the voice uttered by the user. The learning result DB 1123 stores the response phrase corresponding to the phrase newly added by the learning process. A specific example will be described below.

  FIG. 6 is a diagram for explaining a schematic configuration of the response phrase DB 1121, the voice recognition result DB 1122, and the learning result DB 1123 stored in the storage unit 112. Referring to FIG. 6A, the response phrase DB 1121 includes a phrase and a response phrase corresponding to the phrase.

  Examples of phrases include multiple types of phrases (phrases (matches)) such as "Shincho" and "Taiju", phrases (phrases (approximation)) that are close to each of multiple types of phrases, and "Hengio Boete" that is a learning start phrase. In addition, a response phrase is stored for each phrase.For example, for "Shincho (match)", as shown in M02 of Fig. 2, "height is about 19 cm. As for the "Taiju (approximate)", as indicated by M04 in Fig. 2, "maybe weight? Weight is about 300g." For the learning start phrase, the message "OK, please tell me the words to remember first." is stored. In addition, for unknown phrases and phrases in the process of learning On the other hand, response phrases such as those shown in steps M06, M08, M10 and M12 of FIG. 2 are stored.

  Referring to FIG. 6B, the voice recognition result DB 1122 includes a phrase specified by the result of voice recognition. In the example of FIG. 6B, the phrase specified by the result of the voice recognition in steps S01, S03, S05, S08, S11, and S12 of FIG. 2 is stored.

  With reference to FIG. 6C, the learning result DB 1123 includes a phrase added by learning and a response phrase corresponding to the phrase. In the example of FIG. 6C, in step S13 of FIG. 2, the response phrase “Gocentimeter Dayo.” is stored with respect to the additional phrase “Asino Oxaha?”.

  The stored information in the response phrase DB 1121 is updated based on the update data periodically transmitted from the server device 200. Thereby, the phrase and the response phrase can be updated. The update data is data for specifying a phrase and a response phrase input by an administrator who manages the server device 200.

  Further, the storage information of the learning result DB 1123 can be transmitted to the server device 200. The server device 200 transmits the update data including the storage information of the learning result DB 1123 from the terminal 100 to another terminal. Thereby, the content learned in the terminal 100 can be reflected in other terminals.

  Returning to FIG. 5, the control unit 111 controls the overall operation of the terminal 100. The control unit 111 includes a voice recognition unit 1110, a speech content determination unit 1111, an approximation determination unit 1112, a learning function unit 1113, a drive control unit 1114, and a display control unit 1115. The control unit 111 is composed of, for example, the CPU 151 and the like.

  The voice recognition unit 1110 has a function of performing voice recognition for identifying a phrase based on the voice data input by the voice input unit 116.

  The utterance content determination unit 1111 has a function of determining the response phrase output from the voice output unit 116. Specifically, the utterance content determination unit 1111 determines whether or not a response phrase corresponding to the phrase specified by the voice recognition unit 1110 is stored in the response phrase DB 1121 or the learning result DB 1123, and when it is stored, the corresponding phrase is stored. Decide on a response phrase.

  The approximation determination unit 1112 determines whether a regular phrase that is similar to the phrase identified by the voice recognition unit 1110 is stored in the response phrase DB 1121 or the learning result DB 1123. Specifically, the approximation determination unit 1112 determines whether or not a phrase that is different from the phrase specified by the voice recognition unit 1110 only in the presence or absence of a dakuten, a consonant, a long note, etc. is stored.

  Even if the response phrase corresponding to the specified phrase is not stored, the utterance content determination unit 1111 determines that the approximation determination unit 1112 determines that a phrase similar to the phrase is stored. The response phrase corresponding to the approximate phrase is determined.

  The learning function unit 1113 has a function of executing learning processing when a learning condition is satisfied. When the learning function unit 1113 determines that the learning condition is satisfied by, for example, recognizing a phrase that is not stored in the response phrase DB 1121 and the learning result DB 1123 twice in succession, the response corresponding to the phrase. The phrase is stored in the learning result DB 1123.

  The drive control unit 1113 has a function of driving the drive unit 115 of the terminal 100. Accordingly, the terminal 100 can move the movable part. The display control unit 1115 has a function of displaying various information on the display unit 119 of the terminal 100.

  The communication processing unit 118 is used for communication with the server device 200 via the network 600. The communication processing unit 118 has a transmitting unit 1181 for transmitting data to the server device 200 and a receiving unit 1182 for receiving data from the server device 200.

<E. Processing details>
FIG. 7 is a flowchart for explaining the flow of the voice input response process executed by the CPU 151 of the terminal 100. The CPU 151 executes a voice input response process when voice is output from the user 700 and voice data is input from the voice input unit 116. The voice recognition unit 1110 of the CPU 151 performs voice recognition based on the input voice data and specifies a phrase.

  Referring to FIG. 7, in step S100, a process of searching for the specified phrase is performed. Specifically, it is determined whether the specified phrase or a similar phrase is stored in the response phrase DB 1121 and the learning result DB 1123.

  In step S101, the CPU 151 determines whether a phrase that matches the specified phrase itself is stored. When it is determined in step S101 that the matching phrase is stored, the CPU 151 outputs the response phrase stored corresponding to the phrase in step S102. As a result, the voice output unit 117 can output the response phrase. Thereby, the terminal 100 can make a response to the phrase specified from the utterance from the user 700.

  On the other hand, when it is determined in step S101 that the matching phrase is not stored, in step S103, the CPU 151 determines whether or not a phrase similar to the specified phrase is stored. When it is determined in step S103 that the approximate phrase is stored, in step S104, the CPU 151 outputs the response phrase stored corresponding to the approximate phrase. As a result, even when the phrase specified by the utterance from the user 700 is not stored, the terminal 100 can make a response to a phrase that is similar to the phrase. As a result, even when the response phrase corresponding to the phrase itself specified from the voice is not prepared, the terminal 100 can respond to the user 700 and can supplement the lack of the response phrase.

  When it is determined in step S103 that a similar phrase is not stored, in step S105, the CPU 151 determines whether the identified phrase is a learning start phrase for starting the learning process. The learning start phrase is, for example, “Remember Me (Hengio Boete)” or “Remember Me (Kotoba Oboete)”.

  When it is not determined in step S105 that the phrase is the learning start phrase, in step S106, the CPU 151 stores the phrase of the result of the current voice recognition in the voice recognition result DB 1122. Thereby, the terminal 100 can accumulate the history of the result of the voice recognition. The result of voice recognition is stored as a history even when a matching phrase or a similar phrase is stored.

  In step S107, the CPU 151 determines whether or not the result of the current voice recognition matches the result of the previous voice recognition. That is, it is determined whether the same phrase is specified twice consecutively. When it is determined in step S107 that the result does not match the result of the previous voice recognition, in step S109, the CPU 151 outputs "I didn't hear well" as a response phrase and at the same time, puts the head in a leaning pose. Drive the department. This can prompt the user to speak again.

  On the other hand, when it is determined in step S107 that the result of the current voice recognition matches the result of the previous voice recognition and the learning condition is satisfied, the CPU 151 shifts the control to step S108 and executes the learning process. In the learning process executed by identifying the same phrase twice consecutively, the CPU 151 performs the utterance/response illustrated in steps M08 to M12 and S11 to S13 of FIG. The response phrase corresponding to the phrase based on is stored in the learning result DB 1123. In this way, since the learning process is executed when the unknown phrase is specified with a predetermined frequency, it is possible to prevent inappropriate questions and learning. After that, when the phrase specified from the voice becomes the phrase added in the learning process, the terminal 100 can output the corresponding response phrase.

Returning to step S105, when it is determined that the phrase is the learning start phrase, the CPU 151 shifts the control to step S108, and executes the learning process. In the learning process executed by becoming the learning start phrase, for example, the following utterance/response is performed.
Response from terminal 100: Okay, first of all, please tell me the words to remember.
Utterance content of the user 700: It is “○Δ×□”.
Response content of the terminal 100: "○△×□", right? What should I reply when asked "○△×□"? Please tell me the words to reply.
Utterance content of the user 700: “ΔΔ×*○□” is acceptable.
The response content of the terminal 100: "△△×※○□". Okay, I remember.

  By performing such learning processing, the terminal 100 stores in the learning result DB 1123 the response phrase (ΔΔ×*◯□) corresponding to the phrase (◯Δ×□) based on the result of voice recognition. This makes it possible to output the corresponding response phrase (ΔΔ×*○□) when the phrase (○Δ×□) added later in the learning process is reached.

[Second Embodiment]
In the first embodiment, the example in which the terminal 100 alone can execute the voice input response process has been described, but the present invention is not limited to this, and the voice input response process can be executed by communicating with the server device 200. You may do it.

  For example, the storage device 112, the utterance content determination unit 1111, and the learning function unit 1113 illustrated in FIG. 5 may be included in the server device 200. A functional configuration of the terminal 100 and the server device 200 in this case will be illustrated. FIG. 8 is a functional block diagram for explaining the functional configurations of the terminal 100 and the server device 200.

  As shown in FIG. 8, the server device 200 includes a control unit 211, a storage unit 212, and a communication processing unit 213. The storage unit 212 has a response phrase DB 2121, a voice recognition result DB 2122, and a learning result DB 2123. Response phrase DB2121, voice recognition result DB2122, and learning result DB2123 correspond to response phrase DB1121, voice recognition result DB1122, and learning result DB1123, respectively, in the first embodiment.

  The control unit 211 has, for example, an utterance content determination unit 2111, an approximation determination unit 2112, and a learning function unit 2113. The utterance content determination unit 2111, the approximation determination unit 2112, and the learning function unit 2113 correspond to the utterance content determination unit 1111, the approximation determination unit 1112, and the learning function unit 1113 in the first embodiment, respectively.

  The communication processing unit 213 is used for communication with the terminal 100 via the network 600. The communication processing unit 213 includes a transmitting unit 2131 for transmitting data to the terminal 100 and a receiving unit 2132 for receiving data from the terminal 100.

  Next, an outline of the voice input response process will be described. The terminal 100 specifies a phrase based on the voice uttered by the user 700, and transmits phrase data capable of specifying the phrase to the server device 200 via the transmission unit 1181.

  When the server device 200 receives the phrase data, the utterance content determination unit 2111 determines the response phrase based on the phrase specified from the phrase data. The utterance content determination unit 2111 determines whether or not the response phrase corresponding to the specified phrase is stored in the storage unit 212, and when the response phrase corresponding to the phrase is stored, specifies the response phrase. The possible response data is transmitted to the terminal 100 via the transmission unit 2131. Thereby, the terminal 100 can output the response phrase corresponding to the specified phrase.

  The utterance content determination unit 2111 stores the response phrase corresponding to the phrase determined to be approximate to the phrase by the approximation determination unit 2112 even when the response phrase corresponding to the specified phrase is not stored. In the meantime, the response data capable of specifying the response phrase is transmitted to the terminal 100 via the transmission unit 2131. As a result, the terminal 100 can output the response phrase corresponding to the phrase close to the specified phrase.

  Further, even when the utterance content determination unit 2111 determines that the response phrase corresponding to the specified phrase and the similar phrase is not stored, the specified phrase is recognized at a predetermined frequency (for example, twice. When continuously recognized), the learning function unit 2113 performs a learning process for learning a response phrase corresponding to the phrase. Specifically, the learning function unit 2113 executes the processing for performing the utterance/response illustrated in steps M08 to M12 and S11 to S13 of FIG.

  Further, the utterance content determination unit 2111 also executes the processing for performing the utterance/response at the time of determining the learning start phrase described in the first embodiment even when the identified phrase is the learning start phrase.

  In this case, the storage information of the learning result DB 2123 may be stored so that it can be specified for each terminal (for example, for each identification number that can identify the terminal), and can be shared among all the terminals. May be stored in.

  As an example in which the response process at the time of voice input can be executed by communicating with the server device 200, not only the storage unit 112, the utterance content determination unit 1111 and the learning function unit 1113 illustrated in FIG. As for the above, the server device 200 may be provided. In this case, the terminal 100 transmits voice data capable of specifying the voice emitted from the user 700 to the server device 200 via the transmitting unit 1181. When the server device 200 receives the voice data, the voice recognition unit may perform voice recognition on the basis of the voice data to identify a phrase, and perform a process based on the phrase.

[Third Embodiment]
In the above-described first and second embodiments, the phrase that is different only in the presence or absence of a dakuten or the like has been illustrated as an approximate phrase. It may be a phrase that approximates the phrase. For example, as a phrase similar to "Shincho", instead of or in addition to "Jincho" or the like, "Shincho" or "Ncho" may be included. Further, as a phrase similar to “taiju”, “daiju” or “idue” may be included instead of or in addition to “daiju” or the like.

  In addition, in the above-described first and second embodiments, an example has been described in which the approximate determination unit is provided and it is determined by the approximate determination unit whether or not the phrase is approximate. However, without the approximate determination unit, FIG. As shown in, the response phrase DB may be configured such that the response phrase is stored for the approximate phrase itself.

  FIG. 9 is a diagram for explaining a schematic configuration of a response phrase DB in which response phrases are stored in correspondence with regular phrases as phrases and similar phrases. For example, a response phrase corresponding to a regular phrase such as “Shincho” or “Taiju” is stored, and response phrases corresponding to “Jincho”, “Shincho”, “Ncho”, etc. are similar to “Shincho”. In addition to being stored, a response phrase corresponding to “daiju”, “taiju”, “idue”, etc. is stored as a phrase similar to “taiju”.

  When the response phrase DB is configured in this way, the utterance content determination unit includes the approximation determination unit by determining whether or not the phrase specified by the result of voice recognition is stored in the response phrase DB. Of course, not only the response phrase corresponding to the regular phrase but also the response phrase corresponding to the approximate phrase can be extracted.

  Further, the response phrase corresponding to the phrase approximate to the regular phrase may be a common (shared) response phrase regardless of the approximate phrase. Specifically, as a common response phrase in the case of approximation, “Hottotto…?” is stored as a response phrase, and as the response phrase, the regular phrase itself is inserted in the part of “...” The response phrase corresponding to the phrase may be added thereafter. For example, "Hottotto... means?" is defined for phrases that are similar to "Shincho" or "Taiju", and when a phrase that is similar to "Shincho" is specified, the response phrase is " Maybe it's Shincho? He's about 19 cm tall." This can reduce the storage capacity for storing the response data corresponding to the approximated phrase.

[Embodiment 4]
Although the learning process in the first to third embodiments has been described with respect to the example executed when the unknown phrase is specified twice consecutively, the learning process is executed by specifying the unknown phrase at a predetermined frequency. If so, it is not limited to this. The learning process may be executed, for example, by identifying the same unknown phrase three times in the history of the latest 10 times in the voice recognition result DB. Further, the determination may be made not only in the number of times but also in a period in which the first and second intervals are within 1 minute.

[Other]
In the above-described first to fourth embodiments, an example in which the response phrase is determined by either the terminal 100 or the server device 200 has been described. The response phrase may be determined. In this case, the terminal 100 also acquires a response phrase for responding to the voice from the user from the server device 200, and determines the importance of information (response level) from the response phrase and the response phrase determined by itself. A higher response phrase may be selected and output as the response phrase to be output.

  In the above-described first to fourth embodiments, an example of outputting a response phrase corresponding to the approximate phrase when the approximate phrase is specified has been described, but the present invention is not limited to this, and the approximate phrase is specified at a predetermined frequency. When the specified phrase is specified twice (for example, two consecutive times), the specified phrase may be pretended to be a regular phrase, and the response phrase for the specified phrase may be learned.

  In the above-described first to fourth embodiments, as the response process corresponding to the phrase specified from the voice, the process of outputting the response phrase and the learning process are illustrated, but the process is not limited to this as long as it is a process associated in advance, For example, it may be a process of driving the terminal 100 in a predetermined mode, a process of capturing an image with the camera 164.

[Summary]
Hereinafter, the main processing of the above-mentioned processing and the advantages obtained by the processing will be described.

  (1) When the phrase specified by the voice from the user 700 is one of the phrases stored in the response phrase DB or the learning result DB, the terminal 100 outputs the response phrase corresponding to the phrase. Learning to execute the process to perform output processing and output a response phrase corresponding to the unknown phrase after that when the unknown phrase is identified at a predetermined frequency. Execute the process. Accordingly, when the unknown phrase is specified, the learning process is not immediately executed, but when the predetermined frequency is reached, it is possible to assume that the user intentionally outputs the unknown phrase and execute the learning process. As a result, it is possible to widely respond to the utterance from the user in the future, but it is possible to prevent inappropriate questions and learning.

  (2) The terminal 100 has a response phrase DB that stores response phrases corresponding to a plurality of types of expected phrases and similar phrases, and a learning result DB that updates and stores response phrases corresponding to phrases by learning processing. .. As a result, it is possible to shorten as much as possible from the time when the user utters the voice to the time when the user responds.

  (3) The predetermined frequency that triggers the learning process is the frequency that is reached when an unstored unknown phrase is specified twice in succession. As a result, it is not necessary to perform a special voice or operation for starting the learning process, so that the learning hurdle can be reduced. As a result, the learning frequency can be improved.

  (4) When an unknown phrase that is not stored is specified, a response such as "I didn't hear well." is output, as indicated by M06 in FIG. This can prompt the user to speak again.

  (5) The learning process corresponds to the process of urging the utterance of the response phrase corresponding to the unknown phrase that triggered the learning (M08 in FIG. 2) and the phrase itself identified from the utterance of the user as the unknown phrase. The process of storing as a response phrase (S13 of FIG. 2) is included. This allows any phrase to be stored as a response phrase.

  (6) When it is the learning start phrase, the response phrase corresponding to the phrase can be learned thereafter. Thereby, it is possible to positively learn based on the intention of the user.

  (7) When the phrase specified by the voice from the user 700 matches the regular phrase stored in the response phrase DB or the learning result DB, the terminal 100 outputs the response phrase corresponding to the regular phrase. Is executed to output a response phrase corresponding to the approximate phrase when the regular phrase stored in the response phrase DB or the learning result DB is approximated. Thereby, even if the response phrase corresponding to the phrase itself specified from the voice of the user 700 is not prepared, it is possible to respond. As a result, the lack of response phrases can be compensated.

  (8) In the embodiment including the approximation determining unit, it is determined whether or not the phrase specified from the voice of the user 700 is close to any of the regular phrases. When the phrase specified from the voice of the user 700 approximates any of the regular phrases, the utterance content determination unit outputs a response phrase stored corresponding to the case. Thus, by preparing a response phrase that matches the regular phrase and a case that approximates the regular phrase, it is possible to widely respond to the utterance of the user.

  (9) In the embodiment that does not have the approximation determining unit, some phrases included in the regular phrase are pretended to be phrases close to the regular phrase, and then, as shown in the response phrase DB of FIG. By providing a response phrase corresponding to a legitimate phrase and a response phrase corresponding to a part of the phrases included in the legitimate phrase, it is possible to widely respond to the user's utterance while reducing the processing load. You can

  (10) Among the regular phrases, for example, the response phrase when approximating “Shincho” and the response phrase when approximating “Taiju” include a common phrase such as “hyotto”.

  In addition, in the case of approximating "Shincho", using the common "Hyotto" and the response phrase corresponding to "Shincho", for example, "Hyotto Shincho? Height is about 19 cm. Is output. As a result, the storage capacity for storing the response phrase can be reduced as compared with the case where a different response phrase is prepared for each approximate phrase.

  (11) The communication system includes a server device 200 and a terminal 100 capable of communicating with the server device 200. Then, terminal 100 in the second and third embodiments transmits voice information corresponding to the voice from the user (for example, phrase data and voice data specified from the result of voice recognition), and then the server device. A process of outputting a response phrase is executed based on the response information (response data) transmitted from 200.

  On the other hand, when the phrase specified from the voice information from the terminal 100 is one of the phrases stored in the response phrase DB or the learning result DB, the server device 200 outputs the response information corresponding to the phrase. To execute the process of outputting and output response information corresponding to the unknown phrase after that when the unknown phrase is not stored and the unknown phrase is specified at a predetermined frequency. Perform learning processing. Accordingly, when the unknown phrase is specified, the learning process is not immediately executed, but when the predetermined frequency is reached, it is possible to assume that the user intentionally outputs the unknown phrase and execute the learning process. As a result, it is possible to widely respond to the utterance from the user in the future, but it is possible to prevent inappropriate questions and learning.

  Further, the server device 200 performs a process of outputting the response information corresponding to the phrase when the phrase specified from the voice information from the terminal 100 matches the phrase stored in the response phrase DB or the learning result DB. When executing and approximating the phrase stored in the response phrase DB or the learning result DB, a process of outputting response information corresponding to the approximating phrase is executed. As a result, it is possible to respond even if the response information corresponding to the phrase itself specified from the user's voice is not prepared. As a result, the lack of response information can be compensated.

  The embodiments disclosed this time are to be considered as illustrative in all points and not restrictive. The scope of the present invention is shown not by the above description but by the claims, and is intended to include meanings equivalent to the claims and all modifications within the scope.

  1 communication system, 100 communication terminal, 111, 211 control unit, 112, 212 storage unit, 115 drive unit, 116 voice input unit, 117 voice output unit, 118, 213 communication processing unit, 119 display unit, 158 GPS receiver, 162 microphones, 163 speakers, 164 cameras, 165 driving devices, 200 server devices, 500 base stations, 600 networks, 700 users, 1110 voice recognition units, 1111 and 1111 utterance content determination units, 1112 and 2112 approximation determination units, 1113 and 2113 Learning function unit, 1114 drive control unit, 1115 display control unit, 1121,121 response phrase DB, 1122, 2122 voice recognition result DB, 1123, 2123 learning result DB, 1181,2131 transmission unit, 1182, 2132 reception unit.

Claims (9)

A voice receiving means for receiving voice input,
When the phrase specified by the voice accepted by the voice accepting unit is one of a plurality of predetermined phrases, a response process executing unit that executes a phrase response process corresponding to the phrase. With and
The response process executing means, when a phrase specified by the voice received by the voice receiving device approximates any one of the plurality of types of phrases, executes a response process for approximation corresponding to the approximate phrase. Then
Further comprising a storage means for storing information capable of specifying a phrase response process and an approximation response process corresponding to each of the plurality of types of phrases,
The response process execution means executes a phrase response process or an approximation response process corresponding to a phrase identified from the voice received by the voice reception device, based on the storage information of the storage device,
Further comprising an approximate determination means for determining whether or not to approximate the one of the phrases in the phrase is the plurality of types identified from the voice received by the voice receiving unit,
The storage means stores the response processing for approximation in association with a phrase approximate to each of the plurality of types of phrases,
The response processing execution means, when the approximation determination means determines that the phrase is approximated to any one of the plurality of types of phrases, the response processing for approximation stored in the storage means corresponding to the approximated phrase. It is executed, response control device. A voice receiving means for receiving voice input,
When the phrase specified by the voice accepted by the voice accepting unit is one of a plurality of predetermined phrases, a response process executing unit that executes a phrase response process corresponding to the phrase. With and
The response process executing means, when a phrase specified by the voice received by the voice receiving device approximates any one of the plurality of types of phrases, executes a response process for approximation corresponding to the approximate phrase. Then
Further comprising a storage means for storing information capable of specifying a phrase response process and an approximation response process corresponding to each of the plurality of types of phrases,
The response process execution means executes a phrase response process or an approximation response process corresponding to a phrase identified from the voice received by the voice reception device, based on the storage information of the storage device,
The storage means stores approximate response processing in association with some of the phrases included in each of the plurality of types of phrases,
The response process executing means, when the phrase specified by the voice accepted by the voice accepting means is not any of the plurality of types of phrases and includes the part of the phrase, selects the part of the phrase. performing approximation for response processing stored in the storage means in response, response control device. The plurality of types of phrases include a first phrase and a second phrase,
The response control device according to claim 1 , wherein the approximation response process corresponding to the first phrase and the approximation response process corresponding to the second phrase include common processes. The response processing execution means, when the phrase specified from the voice received by the voice receiving means approximates any one of the plurality of types of phrases, only the response processing for approximation corresponding to the approximate phrase. The response control device according to any one of claims 1 to 3 , which also executes a phrase response process corresponding to the phrase. A control program for causing a computer to function as the response control device according to any one of claims 1 to 4, a control program for causing a computer to function as each means described above. A step of receiving voice input,
When the phrase specified from the received voice is one of a plurality of types of predetermined phrases, a step of executing a phrase response process corresponding to the phrase,
When the phrase specified from the received voice is approximated to any one of the plurality of types of phrases, a step of performing an approximate response process corresponding to the approximated phrase is provided ,
The step of executing the phrase response process may include executing the phrase response process based on storage information of a storage unit that stores information capable of specifying the phrase response process and the approximation response process corresponding to each of the plurality of types of phrases. Including performing a response process,
The step of performing the approximation response process,
Determining whether or not the phrase specified from the received voice in the step of receiving the input of the voice is similar to any of the plurality of types of phrases;
Executing an approximation response process stored in the storage means in correspondence with the approximate phrase when it is determined to be approximate to any one of the plurality of types of phrases. .. A step of receiving voice input,
When the phrase specified from the received voice is one of a plurality of types of predetermined phrases, a step of executing a phrase response process corresponding to the phrase,
When the phrase specified from the received voice is approximated to any one of the plurality of types of phrases, a step of performing an approximate response process corresponding to the approximated phrase is provided,
The step of executing the phrase response process is information capable of specifying the phrase response process corresponding to the plurality of types of phrases and the approximation response process corresponding to some of the phrases included in each of the plurality of types of phrases. Including executing the phrase response process based on storage information of a storage unit that stores
The step of executing the response processing for approximation is performed when the phrase specified from the voice received in the step of receiving the input of the voice is not any of the plurality of types of phrases and includes the partial phrase. An information processing method , comprising: executing an approximate response process stored in the storage means in correspondence with the part of the phrases . A communication system comprising a server and a response control device capable of communicating with the server,
The response control device,
A voice receiving means for receiving voice input,
A communication unit for transmitting voice information corresponding to the voice received by the voice receiving unit and receiving response information from the server;
And a response process executing means for executing a response process based on the received response information,
The server is
A storage unit that stores phrase response information and approximation response information as response information corresponding to each of a plurality of predetermined phrases.
When the phrase specified from the voice information from the response control device is any of the plurality of types of phrases, response information transmitting means for transmitting the phrase response information corresponding to the phrase as response information,
Approximate response information transmission for transmitting, as response information, approximate response information corresponding to the approximate phrase when the phrase specified from the voice information from the response control device approximates any of the plurality of types of phrases and means only including,
The storage means stores approximate response information in association with a phrase that is similar to each of the plurality of types of phrases,
The server further includes an approximation determination unit that determines whether or not the phrase specified from the voice information from the response control device is similar to any one of the plurality of types of phrases,
The response process executing means, when the approximation determining means determines that the phrase is approximate to any one of the plurality of types of phrases, the response information for approximation stored in the storage means corresponding to the approximate phrase. Is transmitted as the response information . A communication system comprising a server and a response control device capable of communicating with the server,
The response control device,
A voice receiving means for receiving voice input,
Communication means for transmitting voice information corresponding to the voice accepted by the voice accepting means and receiving response information from the server;
A response process executing means for executing a response process based on the received response information,
The server is
A storage unit that stores phrase response information and approximation response information as response information corresponding to each of a plurality of predetermined phrases.
When the phrase specified from the voice information from the response control device is one of the plurality of types of phrases, response information transmitting means for transmitting the response information for phrase corresponding to the phrase as response information,
Approximate response information transmission for transmitting, as response information, approximate response information corresponding to the approximate phrase when the phrase specified from the voice information from the response control device approximates any one of the plurality of types of phrases And means,
The storage means stores approximate response processing in association with some of the phrases included in each of the plurality of types of phrases,
When the phrase specified from the voice information from the response control device is not any of the plurality of types of phrases and includes the partial phrase, the approximate response information transmitting unit selects the partial phrase. A communication system which transmits the response information for approximation correspondingly stored in the storage means as the response information.

Images