JP6867939B2 - Computers, language analysis methods, and programs - Google Patents

Description

The present invention relates to a computer system that analyzes a voice (language) emitted by a user and responds to the user based on the analysis result.

In recent years, a technology utilizing a dialogue device such as a robot installed in a facility has attracted attention. The dialogue device acquires voice information (voice signal) uttered by the user and analyzes the voice signal to identify the user's utterance intention. In addition, the dialogue device communicates with the user or provides a service to the user according to the intention of speaking.

In order to properly provide services or communicate, it is necessary to accurately identify the user's utterance intention. As a method of understanding the user's utterance intention, for example, the techniques described in Patent Document 1 and Patent Document 2 are known.

In Patent Document 1, "The voice processing device is recognized by a voice input unit that acquires a voice signal, a voice recognition unit that performs voice recognition for the voice signal acquired by the voice input unit, and a voice recognition unit. It is equipped with an intention understanding unit that understands the user's intention based on the recognition result and a question unit that asks a question to the user based on the understanding result understood by the intention understanding department. The content of the question to the user will be changed according to the result and the predetermined priority. "

Patent Document 2 describes, "Sequential analysis processing unit 10 that executes analysis processing sequentially and in parallel in each analysis processing unit each time a part of a natural language sentence of an analyzable unit is input, and sequential analysis processing. It is provided with output units 3 and 4 for obtaining an output such as a dialogue response sentence based on the analysis result in each analysis processing unit of the unit. Each processing unit prepared in the sequential analysis processing unit is in its own processing unit. The analysis result of the past immediately before or before and the analysis result of the past immediately before or before at another processing unit are acquired, and the analysis result is obtained while pre-reading while referring to the acquired analysis result. "Is stated.

Japanese Unexamined Patent Publication No. 2017-58545 Japanese Unexamined Patent Publication No. 2017-102771

In the techniques described in Patent Document 1 and Patent Document 2, fillers and intervals in the user's utterance are not taken into consideration. When an utterance containing a filler and a gap is made, the dialogue device cannot correctly recognize the utterance break. That is, the audio signal (character string) of the processing unit cannot be specified. Therefore, when the utterance including the filler and the interval is performed, the conventional dialogue device cannot accurately identify the user's utterance intention.

The present invention provides devices, methods, and programs that realize fillers and intervening language analysis in order to provide appropriate services or communicate.

A typical example of the invention disclosed in the present application is as follows. That is, it is a computer that processes a voice signal corresponding to a voice uttered by a user, and includes a calculation device, a storage device connected to the calculation device, and a communication interface connected to the calculation device. , The voice signal is received via the communication interface, the received voice signal is converted into a text composed of a plurality of character strings, and the converted text is analyzed to continue the utterance of the user. It is determined whether or not the utterance continuation character string indicating that the utterance is inside is included in the converted text, and when it is determined that the utterance continuation character string is included in the converted text, the storage device stores the utterance continuation character string. When the converted text is accumulated and it is determined that the utterance continuation character string is not included in the converted text, an output text is generated using one or more of the converted texts, and the output is described. Based on the text, the utterance intention of the user who has emitted the voice corresponding to the received voice signal is specified, and information indicating the utterance intention of the specified user is transmitted to the device that responds to the user's utterance. It is characterized by doing.

According to the present invention, it is possible to realize a language analysis in consideration of fillers and spaces. Therefore, it is possible to appropriately identify the user's utterance intention and provide a service or communicate. Issues, configurations and effects other than those mentioned above will be clarified by the description of the following examples.

It is a figure which shows the configuration example of the computer system of Example 1. FIG. It is a figure which shows an example of the hardware configuration of the computer of Example 1. FIG. It is a figure which shows an example of the data structure of the utterance continuation character string information held by the computer of Example 1. FIG. It is a figure which shows an example of the data structure of the utterance continuation character string information held by the computer of Example 1. FIG. It is a figure which shows an example of the data structure of the intention understanding information held by the computer of Example 1. FIG. It is a figure which shows an example of the data structure of the answer generation information held by the computer of Example 1. FIG. It is a flowchart explaining an example of the process executed by the text transmission determination part of Example 1. FIG. It is a sequence diagram which shows an example of the processing flow in the computer system of Example 1. FIG. It is a sequence diagram which shows an example of the processing flow in the computer system of Example 1. FIG. It is a flowchart explaining an example of the process executed by the text transmission determination part of Example 2. FIG.

Hereinafter, examples of the present invention will be described with reference to the drawings. However, the present invention is not construed as being limited to the description of the embodiments shown below. It is easily understood by those skilled in the art that a specific configuration thereof can be changed without departing from the idea or gist of the present invention.

In the configurations of the invention described below, the same or similar configurations or functions are designated by the same reference numerals, and duplicate description will be omitted.

The notations such as "first", "second", and "third" in the present specification and the like are attached to identify the components, and do not necessarily limit the number or order.

The position, size, shape, range, etc. of each configuration shown in the drawings and the like may not represent the actual position, size, shape, range, etc., in order to facilitate understanding of the invention. Therefore, the present invention is not limited to the position, size, shape, range, etc. disclosed in the drawings and the like.

FIG. 1 is a diagram showing a configuration example of the computer system of the first embodiment.

The computer system includes a computer 100, a communication device 101, and a dialogue device 102. The computer 100 and the communication device 101 are connected to each other via the network 105. Further, the communication device 101 and the dialogue device 102 are connected to each other via a wireless network (not shown). The communication device 101 and the dialogue device 102 may be connected via a wired network.

The network 105 is a LAN (Local Area Network), a WAN (Wide Area Network), or the like, and the connection method may be either wireless or wired.

The dialogue device 102 is a device that communicates with the user 103. The dialogue device 102 is, for example, a robot, a tablet terminal, or the like. The dialogue device 102 is a voice acquisition device (not shown) that acquires voice emitted by the user 103, a voice output device (not shown) that outputs voice to the user 103, and a network interface for communicating with the communication device 101 (not shown). (Not shown).

The communication device 101 is a device that controls communication between the computer 100 and the dialogue device 102. The communication device 101 is, for example, a router, a gateway device, or the like.

The computer 100 identifies the utterance intention of the user 103 and generates information (text) for communicating according to the utterance intention. The hardware configuration of the computer 100 will be described with reference to FIG. Here, the text is data composed of one or more character strings.

The computer 100 has a voice processing unit 110 and a language processing unit 111. Further, the computer 100 holds the utterance continuation character string information 130, the intention understanding information 131, and the answer generation information 132.

The utterance continuation character string information 130 is information for managing the utterance continuation character string. Here, the utterance continuation character string is a character string for detecting an utterance including a filler and an interval. As will be described later, the computer 100 determines whether or not the utterance of the user 103 is continued based on the presence or absence of the utterance continuation character string in the text. The data structure of the utterance continuation character string information 130 will be described with reference to FIGS. 3A and 3B.

The intention understanding information 131 is information for specifying the utterance intention of the user 103. The data structure of the intention understanding information 131 will be described with reference to FIG.

The answer generation information 132 is information for generating a response to the utterance of the user 103. The data structure of the answer generation information 132 will be described with reference to FIG.

The voice processing unit 110 converts a voice signal corresponding to the voice emitted by the user 103 into a text, and also converts the text generated by the computer 100 into a voice signal.

The language processing unit 111 identifies the utterance intention of the user 103 based on the analysis result of the text, and generates an answer text for outputting the answer to the user 103 as a voice from the dialogue device 102. The language processing unit 111 includes a text receiving unit 120, a text transmission determining unit 121, an intention understanding unit 122, and an answer generating unit 123.

The text receiving unit 120 receives the text transmitted by the voice processing unit 110, and transmits the received text to the text transmission determining unit 121.

When the text transmission unit 121 receives the text from the text reception unit 120, the text transmission determination unit 121 analyzes the received text and determines the transmission timing of the text to the intention understanding unit 122 based on the utterance continuation character string information 130 and the analysis result. .. Further, when the text transmission determination unit 121 transmits the text to the intention understanding unit 122, the text transmission determination unit 121 generates an output text corresponding to one set of voices processed by the intention understanding process, and transmits the output text to the intention understanding unit 122. To do.

The intention understanding unit 122 executes an intention understanding process for identifying the utterance intention of the user 103 based on the output text and the intention understanding information 131 received from the text transmission determination unit 121. As a processing result, the intention understanding unit 122 transmits the intention information (see FIG. 4) indicating the utterance intention of the user 103 to the response generation unit 123.

The answer generation unit 123 refers to the answer generation information 132 based on the intention information transmitted from the intention understanding unit 122, and generates the answer text of the answer output by the dialogue device 102.

The computer system of this embodiment outputs a response (voice) as a response to the utterance of the user 103. As a result, communication is performed between the user 103 and the dialogue device 102. The response to the utterance of the user 103 is not limited to this, and various things such as reproduction of video and music, provision of products, assistance of actions, and the like can be considered.

In addition, each functional unit may be arranged in a plurality of computers 100. For example, a computer system may be composed of a first computer having a voice processing unit 110, a text receiving unit 120, a text transmission determining unit 121, and an intention understanding unit 122, and a second computer having an answer generating unit 123. Further, the information held by the computer 100 may be stored in a storage system accessible to a plurality of computers.

In each functional unit included in the computer 100, a plurality of functional units may be combined into one functional unit, or one functional unit may be divided into a plurality of functional units for each function.

FIG. 2 is a diagram showing an example of the hardware configuration of the calculator 100 of the first embodiment.

The computer 100 has a processor 200, a memory 201, and a network interface 202. The hardware configurations are connected to each other via an internal bus. The calculator 100 may have a storage device such as an HDD (Hard Disk Drive) and an SSD (Solid State Drive). Further, the computer 100 may have an input device such as a keyboard, a mouse, and a touch panel, and an output device such as a display.

The processor 200 is an arithmetic unit and executes a program stored in the memory 201. When the processor 200 executes processing according to a program, it operates as a functional unit (module) that realizes a specific function. In the following description, when the process is described with the functional unit as the subject, it is shown that the processor 200 is executing the program that realizes the functional unit.

The memory 201 is a storage device, and stores a program executed by the processor 200 and information used by the program. The memory 201 of this embodiment stores a program that realizes the voice processing unit 110 and the language processing unit 111. Further, the memory 201 stores the utterance continuation character string information 130, the intention understanding information 131, and the answer generation information 132. The memory 201 also includes a work area used by the program and a buffer for accumulating text.

The network interface 202 is an interface for connecting to an external device via a network.

3A and 3B are diagrams showing an example of a data structure of the utterance continuation character string information 130 held by the computer 100 of the first embodiment.

In this embodiment, the utterance continuation character string information 130 exists for each language type. FIG. 3A shows Japanese utterance continuation character string information 130-1, and FIG. 3B shows English utterance continuation character string information 130-2.

The utterance continuation character string information 130 includes one or more entries composed of the utterance continuation character string 301 and the position 302.

The utterance continuation character string 301 is a field for storing the utterance continuation character string. The position 302 is a field for storing the position where the voice corresponding to the utterance continuation character string appears in the voice uttered by the user. At the position 302 of this embodiment, the position (detection range) of the utterance continuation character string in the text to which the voice signal is converted is stored. The process using the position 302 will be described in the second embodiment.

In this embodiment, it is assumed that the utterance continuation character string information 130 is set in advance. The utterance continuation character string information 130 may be manually set by the administrator or the like, or may be generated by executing machine learning using the conversation history of the user 103 and the dialogue device 102.

FIG. 4 is a diagram showing an example of the data structure of the intention understanding information 131 held by the computer 100 of the first embodiment.

The intention understanding information 131 includes one or more entries composed of the utterance content 401 and the intention 402.

The utterance content 401 is a field in which a text indicating the utterance content is stored. The intent 402 is a field for storing information indicating the utterance intention of the user 103 who has made an utterance corresponding to the utterance content 401. In the following description, the value stored in the intention 402 is described as the intention information.

In this embodiment, it is assumed that the intention understanding information 131 is set in advance. The intention understanding information 131 is manually set by the administrator or the like.

FIG. 5 is a diagram showing an example of the data structure of the answer generation information 132 held by the computer 100 of the first embodiment.

The answer generation information 132 includes one or more entries composed of the intent 501 and the answer content 502.

Intention 501 is the same field as intent 402. The answer content 502 is a field for storing the answer text (answer text) output as voice by the dialogue device 102. It should be noted that a plurality of answer texts may be associated with one utterance intention. In this case, a method of randomly selecting the answer text, a method of selecting the answer text based on the attributes of the user 103, and the like can be considered.

FIG. 6 is a flowchart illustrating an example of processing executed by the text transmission determination unit 121 of the first embodiment.

The text transmission determination unit 121 receives the text from the text reception unit 120 (step S101). The received text is temporarily stored in the work area.

Next, the text transmission determination unit 121 executes morphological analysis on the text (step S102). Since a known technique may be used for the morphological analysis, detailed description thereof will be omitted.

Next, the text transmission determination unit 121 determines whether or not the utterance continuation character string exists at the end of the text corresponding to the voice uttered by the user 103 based on the result of the morphological analysis and the utterance continuation character string information 130. (Step S103).

Specifically, the text transmission determination unit 121 compares the utterance continuation character string 301 of each entry of the utterance continuation character string information 130 with the character string appearing at the end of the text, and matches the utterance continuation character string 301. Determines if the string is at the end of the text.

When it is determined that the utterance continuation character string does not exist at the end of the text, the text transmission determination unit 121 determines that the utterance has ended. The text transmission determination unit 121 generates an output text using the text stored in the memory 201 (work area and buffer), and transmits the output text to the intention understanding unit 122 (step S108). After that, the text transmission determination unit 121 ends the process.

Specifically, the text transmission determination unit 121 deletes the utterance continuation character string from each text stored in the work area and the buffer, and generates the output text by combining the texts in chronological order. After the output text is generated, the text stored in memory 201 is deleted. The text transmission determination unit 121 may delete the text at the time of generating the output text, or may delete the text after the series of processing is completed.

When the text is not stored in the buffer, the text transmission determination unit 121 generates the text stored in the work area as the output text.

When it is determined that the utterance continuation character string exists at the end of the text, the text transmission determination unit 121 determines that the utterance is continuing and stores the received text in the buffer (step S104). That is, the text before the meaning understanding process is executed is stored in the memory 201.

Next, the text transmission determination unit 121 determines whether or not the timer is running (step S105). The timer of this embodiment measures the waiting time for adjusting the output timing of the text to the intention understanding unit 122.

If it is determined that the timer is not running, the text transmission determination unit 121 starts the timer (step S107), and then returns to step S101. In this case, the text transmission determination unit 121 shifts to the waiting state until the text is received.

When it is determined that the timer is running, the text transmission determination unit 121 determines whether or not the waiting time measured by the timer is larger than the threshold value (step S106).

When it is determined that the waiting time is equal to or less than the threshold value, the text transmission determination unit 121 initializes the measurement time and continues the measurement of the waiting time. After that, the text transmission determination unit 121 returns to step S101. In this case, the text transmission determination unit 121 shifts to the waiting state until the next text is received.

When it is determined that the waiting time is larger than the threshold value, the text transmission determination unit 121 determines that the utterance has ended. Further, the text transmission determination unit 121 generates an output text using the text stored in the memory 201 (work area and buffer), and transmits the output text to the intention understanding unit 122 (step S108). At this time, the text transmission determination unit 121 stops the timer. After that, the text transmission determination unit 121 ends the process.

Next, the processing flow in the computer system will be described. 7A and 7B are sequence diagrams showing an example of a processing flow in the computer system of the first embodiment. FIG. 7A shows a processing flow when an utterance including an utterance continuation character string is performed. FIG. 7B shows a processing flow when an utterance that does not include the utterance continuation character string is performed.

First, the flow of processing shown in FIG. 7A will be described.

The dialogue device 102 acquires the voice emitted by the user 103 and generates an audio signal of the voice. Further, the dialogue device 102 communicates with the communication device 101 and transmits an audio signal to the computer 100 connected via the network 105 (step S201).

The voice processing unit 110 of the computer 100 converts the voice signal transmitted from the dialogue device 102 into text, and transmits the text to the text receiving unit 120 (step S202). The text is transmitted from the text receiving unit 120 to the text transmission determining unit 121. It is assumed that the utterance continuation character string exists at the end of the text.

When the text transmission determination unit 121 receives the text, the text transmission determination unit 121 executes the process shown in FIG. Since the utterance continuation character string exists at the end of the text, the text transmission determination unit 121 stores the received text in the memory 201 (step S203). That is, the text is stored in the buffer. Further, the text transmission determination unit 121 activates the timer because the timer has not been activated (step S204).

After the waiting time becomes larger than the threshold value, the dialogue device 102 acquires a new voice corresponding to the text having the utterance continuation character string at the end from the user 103, and generates a voice signal of the voice. The dialogue device 102 transmits an audio signal to the computer 100 (step S205).

The voice processing unit 110 converts the received voice signal into text, and transmits the text to the text transmission determination unit 121 via the text receiving unit 120 (step S206).

Since the utterance character string exists at the end of the text, the text transmission determination unit 121 stores the received text in the memory 201 (step S207). At this point, since the timer is running and the waiting time is larger than the threshold value, the text transmission determination unit 121 generates an output text using the two texts stored in the buffer, and causes the intention understanding unit 122 The output text is transmitted (step S208).

If the utterance character string does not exist at the end of the text, the text transmission determination unit 121 generates an output text using the text stored in each of the work area and the buffer.

When the intention understanding unit 122 receives the output text, the intention understanding unit 122 executes the intention understanding process (step S209).

In the intention understanding process, the intention understanding unit 122 searches for an entry in which the utterance content 401 of the intention understanding information 131 matches the output text. The intent understanding unit 122 acquires the value stored in the intent 402 of the searched entry as the processing result. At this time, the intention understanding unit 122 may use information other than the intention understanding information 131 such as a similar dictionary.

The intention understanding unit 122 transmits the intention information to the response generation unit 123 (step S210).

When the answer generation unit 123 receives the intention information, the answer generation unit 123 executes the answer generation process (step S211).

In the answer generation process, the answer generation unit 123 refers to the answer generation information 132 and searches for an entry whose intention 501 matches the intention information. The answer generation unit 123 acquires the answer text stored in the answer content 502 of the searched entry.

The answer generation unit 123 transmits the answer text to the voice processing unit 110 (step S212).

The voice processing unit 110 converts the answer text into a voice signal and transmits the voice signal to the dialogue device 102 via the network 105 (step S213).

As shown in FIG. 7A, when the utterance continuation character string for detecting the utterance including the filler and the interval exists at the end of the text, the computer 100 determines that the utterance is continuing, and stores the text in the memory 201 ( Accumulate in the buffer). When the computer 100 detects the end of the utterance, the computer 100 uses one or more texts stored in the memory 201 (work area and buffer) to generate an output text which is a processing unit of the intention understanding process.

In this way, the computer 100 can accurately identify the utterance intention of the user 103 by generating the output text which is the processing unit of the intention understanding process in consideration of the filler and the interval. Therefore, the computer 100 can generate an answer in line with the utterance intention of the user 103.

Next, the flow of processing shown in FIG. 7B will be described.

The dialogue device 102 acquires the voice emitted by the user 103 and generates an audio signal of the voice. Further, the dialogue device 102 communicates with the communication device 101 and transmits an audio signal to the computer 100 connected via the network 105 (step S301).

The voice processing unit 110 of the computer 100 converts the voice signal transmitted from the dialogue device 102 into text, and transmits the text to the text receiving unit 120 (step S302). The text is transmitted from the text receiving unit 120 to the text transmission determining unit 121. It is assumed that there is no utterance continuation character string at the end of the text.

When the text transmission determination unit 121 receives the text, the text transmission determination unit 121 executes the process shown in FIG. Since there is no utterance continuation character string at the end of the text, the text transmission determination unit 121 generates the text stored in the work area as the output text, and transmits the output text to the intention understanding unit 122 (step S303). ..

When the intention understanding unit 122 receives the output text, the intention understanding unit 122 executes the intention understanding process (step S304). The intention understanding unit 122 transmits the intention information to the response generation unit 123 (step S305).

When the answer generation unit 123 receives the intention information, the answer generation unit 123 executes the answer generation process (step S306). The answer generation unit 123 transmits the answer text to the voice processing unit 110 (step S307).

The voice processing unit 110 converts the answer text into a voice signal and transmits the voice signal to the dialogue device 102 via the network 105 (step S308).

As shown in FIG. 7B, when the utterance continuation character string does not exist at the end of the text, the computer 100 executes the process according to the same processing procedure as in the prior art.

In this embodiment, a buffer is provided as a storage area for storing texts, but a plurality of texts may be stored in the work area. In this case, it is not necessary to provide a buffer.

According to the first embodiment, the computer 100 can generate an output text corresponding to one cohesive voice that is a processing unit of the intention understanding process even when an utterance including a filler and an interval is performed. The computer 100 can correctly identify the utterance intention of the user 103 by executing the intention understanding process in which the output text is input. Therefore, the dialogue device 102 can output an appropriate answer (voice) according to the utterance intention of the user 103.

In the second embodiment, the processing executed by the text transmission determination unit 121 is partially different. Hereinafter, Example 2 will be described with a focus on the differences from Example 1.

The configuration of the computer system of the second embodiment is the same as the configuration of the computer system of the first embodiment. The hardware configuration and software configuration of the computer 100 of the second embodiment are the same as the hardware configuration and software configuration of the computer 100 of the first embodiment. Further, the data structure of the information held by the computer 100 of the second embodiment is the same as the data structure of the information held by the computer 100 of the first embodiment.

FIG. 8 is a flowchart illustrating an example of processing executed by the text transmission determination unit 121 of the second embodiment.

The processes of steps S101 and S102 are the same as those of the first embodiment.

After the process of step S102 is executed, the text transmission determination unit 121 determines whether or not the utterance continuation character string is included in the text (step S151).

Specifically, the text transmission determination unit 121 searches for the utterance continuation character string included in the text based on the result of the morphological analysis and the utterance continuation character string 301 of the utterance continuation character string information 130.

When it is determined that the text does not include the utterance continuation character string, the text transmission determination unit 121 generates an output text using the text stored in the memory 201 (work area and buffer), and causes the intention understanding unit 122 to generate an output text. The output text is transmitted (step S108). After that, the text transmission determination unit 121 ends the process.

When it is determined that the text includes the utterance continuation character string, the text transmission determination unit 121 determines whether or not the utterance continuation character string exists in the detection range (step S152).

Specifically, the text transmission determination unit 121 specifies the position of the utterance continuation character string included in the text. The text transmission determination unit 121 reads out the value at the position 302 of the entry corresponding to the utterance continuation character string searched in step S103. The text transmission determination unit 121 determines whether or not the position of the utterance continuation character string in the text exists in the detection range set at the entry position 302.

When it is determined that the utterance continuation character string does not exist in the detection range, the text transmission determination unit 121 generates an output text using the text stored in the memory 201 (work area and buffer), and causes the intention understanding unit 122 to generate an output text. The output text is transmitted (step S108). After that, the text transmission determination unit 121 ends the process.

When it is determined that the utterance continuation character string exists in the detection range, the text transmission determination unit 121 proceeds to step S104. The processes from steps S104 to S108 are the same as those in the first embodiment.

The processing flow of the computer system of the second embodiment is the same as the processing flow of the computer system of the first embodiment.

According to the second embodiment, the utterance intention of the user 103 can be more accurately specified by adjusting the output timing of the text based on the utterance continuation character string and the appearance position of the utterance continuation character string. In addition, the judgment criteria can be adjusted according to the type of language.

The present invention is not limited to the above-described examples, and includes various modifications. Further, for example, the above-described embodiment describes the configuration in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations. In addition, a part of the configuration of each embodiment can be added, deleted, or replaced with another configuration.

Further, each of the above configurations, functions, processing units, processing means and the like may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. The present invention can also be realized by a program code of software that realizes the functions of the examples. In this case, a storage medium in which the program code is recorded is provided to the computer, and the processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiment, and the program code itself and the storage medium storing the program code itself constitute the present invention. Examples of the storage medium for supplying such a program code include a flexible disk, a CD-ROM, a DVD-ROM, a hard disk, an SSD (Solid State Drive), an optical disk, a magneto-optical disk, a CD-R, and a magnetic tape. Non-volatile memory cards, ROMs, etc. are used.

In addition, the program code that realizes the functions described in this embodiment can be implemented in a wide range of programs or script languages such as assembler, C / C ++, perl, Shell, PHP, and Java (registered trademark).

Further, by distributing the program code of the software that realizes the functions of the examples via the network, it is stored in a storage means such as a hard disk or memory of a computer or a storage medium such as a CD-RW or a CD-R. , The processor provided in the computer may read and execute the program code stored in the storage means or the storage medium.

In the above-described embodiment, the control lines and information lines show what is considered necessary for explanation, and do not necessarily indicate all the control lines and information lines in the product. All configurations may be interconnected.

100 Computer 101 Communication device 102 Dialogue device 103 User 105 Network 110 Voice processing unit 111 Language processing unit 120 Text receiving unit 121 Text transmission judgment unit 122 Intention understanding unit 123 Answer generation unit 130 Speech continuation character string information 131 Intention understanding information 132 Answer generation Information 200 Processor 201 Memory 202 Network Interface

Claims (15)

A computer that processes audio signals corresponding to user-generated audio.
It includes an arithmetic unit, a storage device connected to the arithmetic unit, and a communication interface connected to the arithmetic unit.
The arithmetic unit
The audio signal is received via the communication interface and
The received audio signal is converted into a text composed of a plurality of character strings, and the received audio signal is converted into a text composed of a plurality of character strings.
By analyzing the converted text, it is determined whether or not the utterance continuation character string indicating that the user's utterance is continuing is included in the converted text.
When it is determined that the utterance continuation character string is included in the converted text, the converted text is stored in the storage device, and the converted text is stored.
If it is determined that the utterance continuation character string is not included in the converted text, the output text is generated using one or more of the converted texts.
Based on the output text, the utterance intention of the user who emitted the voice corresponding to the received voice signal is specified.
A computer characterized by transmitting information indicating the utterance intention of the specified user to a device that responds to the utterance of the user. The computer according to claim 1.
The computer holds the utterance continuation character string information for managing the utterance continuation character string, and holds the utterance continuation character string information.
The arithmetic unit
With reference to the utterance continuation character string information, it is determined whether or not the utterance continuation character string exists at the end of the converted text.
A computer characterized in that when it is determined that the utterance continuation character string exists at the end of the converted text, the converted text is stored in the storage device. The computer according to claim 1.
The computer holds the utterance continuation character string information for managing the utterance continuation character string, and holds the utterance continuation character string information.
The utterance continuation character string information includes a plurality of entries composed of the utterance continuation character string and the appearance position of the utterance continuation character string in the text.
The arithmetic unit
With reference to the utterance continuation character string information, it is determined whether or not the converted text includes the utterance continuation character string.
When it is determined that the converted text includes the utterance continuation character string, the position of the utterance continuation character string included in the converted text in the converted text becomes the utterance continuation character string. Determines whether or not it matches the appearance position set in the corresponding entry,
When it is determined that the position of the utterance continuation character string included in the converted text in the converted text matches the appearance position set in the entry corresponding to the utterance continuation character string, the storage device. A computer characterized by accumulating the converted text in. The computer according to claim 1.
The arithmetic unit
After accumulating the converted text in the storage device, it is determined whether or not the timer for measuring the waiting time is running.
If it is determined that the timer is not running, the timer is started and the timer is started.
When it is determined that the timer is running, it is determined whether or not the waiting time is larger than the threshold value.
When it is determined that the waiting time is equal to or less than the threshold value, the waiting time is initialized and the measurement of the waiting time is continued.
A computer characterized in that when it is determined that the waiting time is larger than a threshold value, the output text is generated. The computer according to claim 1.
The arithmetic unit
When a plurality of the converted texts are stored in the storage device, the output texts are generated by deleting and combining the utterance continuation character strings from the plurality of converted texts.
A computer characterized in that when one of the converted texts is stored in the storage device, the one converted text is generated as the output text. A language analysis method executed by a computer that processes a voice signal corresponding to a voice emitted by a user.
The computer includes an arithmetic unit, a storage device connected to the arithmetic unit, and a communication interface connected to the arithmetic unit.
The language analysis method is
A first step in which the arithmetic unit receives the audio signal via the communication interface and converts the received audio signal into a text composed of a plurality of character strings.
The second arithmetic unit analyzes the converted text to determine whether or not the utterance continuation character string indicating that the user's utterance is continuing is included in the converted text. Steps and
When the arithmetic unit determines that the utterance continuation character string is included in the converted text, a third step of accumulating the converted text in the storage device, and
When the arithmetic unit determines that the utterance continuation character string is not included in the converted text, a fourth step of generating an output text using one or more of the converted texts,
A fifth step in which the arithmetic unit identifies the utterance intention of the user who has emitted a voice corresponding to the received voice signal based on the output text.
A language analysis method, wherein the arithmetic unit includes a sixth step of transmitting information indicating the utterance intention of the specified user to a device that responds to the utterance of the user. The language analysis method according to claim 6.
The computer holds the utterance continuation character string information for managing the utterance continuation character string, and holds the utterance continuation character string information.
The second step includes a step in which the arithmetic unit refers to the utterance continuation character string information and determines whether or not the utterance continuation character string exists at the end of the converted text.
In the third step, when the arithmetic unit determines that the utterance continuation character string exists at the end of the converted text, the language is characterized by accumulating the converted text in the storage device. analysis method. The language analysis method according to claim 6.
The computer holds the utterance continuation character string information for managing the utterance continuation character string, and holds the utterance continuation character string information.
The utterance continuation character string information includes a plurality of entries composed of the utterance continuation character string and the appearance position of the utterance continuation character string in the text.
The second step is
A step in which the arithmetic unit refers to the utterance continuation character string information and determines whether or not the utterance continuation character string is included in the converted text.
When the arithmetic unit determines that the converted text includes the utterance continuation character string, the position of the utterance continuation character string included in the converted text in the converted text is the utterance. Including a step of determining whether or not it matches the appearance position set in the entry corresponding to the continuation character string.
In the third step, the arithmetic unit sets the position of the utterance continuation character string included in the converted text in the converted text to the entry corresponding to the utterance continuation character string. A language analysis method characterized by accumulating the converted text in the storage device when it is determined that the positions match. The language analysis method according to claim 6.
The third step is
A step of determining whether or not the timer for measuring the waiting time is running after the arithmetic unit stores the converted text in the storage device.
When it is determined that the timer is not running, the arithmetic unit starts the timer, and
When it is determined that the timer is running, the arithmetic unit determines whether or not the waiting time is greater than the threshold value.
When it is determined that the waiting time is equal to or less than the threshold value, the arithmetic unit initializes the waiting time and continues the measurement of the waiting time.
A language analysis method comprising the step of generating the output text by the arithmetic unit when it is determined that the waiting time is larger than the threshold value. The language analysis method according to claim 6.
The fourth step is
When a plurality of the converted texts are stored in the storage device, the arithmetic unit generates the output text by deleting the utterance continuation character string from the plurality of converted texts and combining them. When,
A language analysis method comprising: when the storage device stores one of the converted texts, the arithmetic unit includes a step of generating the one converted text as the output text. A program for a computer that processes a voice signal corresponding to a voice emitted by a user to be executed.
The computer includes an arithmetic unit, a storage device connected to the arithmetic unit, and a communication interface connected to the arithmetic unit.
The program
The first procedure of receiving the voice signal via the communication interface and converting the received voice signal into a text composed of a plurality of character strings, and
A second procedure for determining whether or not the converted text includes a speech continuation character string indicating that the user's utterance is ongoing by analyzing the converted text.
When it is determined that the utterance continuation character string is included in the converted text, a third step of accumulating the converted text in the storage device, and
When it is determined that the utterance continuation character string is not included in the converted text, a fourth step of generating an output text using one or more of the converted texts, and
A fifth step of identifying the utterance intention of the user who has emitted a voice corresponding to the received voice signal based on the output text, and
A program for causing the computer to execute a sixth step of transmitting information indicating the specified user's utterance intention to a device that responds to the user's utterance. The program according to claim 11.
The computer holds the utterance continuation character string information for managing the utterance continuation character string, and holds the utterance continuation character string information.
The second procedure includes a procedure for determining whether or not the utterance continuation character string exists at the end of the converted text by referring to the utterance continuation character string information.
The third procedure is a program characterized in that when it is determined that the utterance continuation character string exists at the end of the converted text, the converted text is stored in the storage device. The program according to claim 11.
The computer holds the utterance continuation character string information for managing the utterance continuation character string, and holds the utterance continuation character string information.
The utterance continuation character string information includes a plurality of entries composed of the utterance continuation character string and the appearance position of the utterance continuation character string in the text.
The second procedure is
With reference to the utterance continuation character string information, a procedure for determining whether or not the utterance continuation character string is included in the converted text, and
When it is determined that the converted text includes the utterance continuation character string, the position of the utterance continuation character string included in the text in the converted text is an entry corresponding to the utterance continuation character string. Including the procedure for determining whether or not it matches the appearance position set in
In the third step, it is determined that the position of the utterance continuation character string included in the converted text in the converted text matches the appearance position set in the entry corresponding to the utterance continuation character string. If so, a program comprising storing the converted text in the storage device. The program according to claim 11.
The third procedure is
After accumulating the converted text in the storage device, a procedure for determining whether or not the timer for measuring the waiting time is running, and
If it is determined that the timer is not running, the procedure for starting the timer and the procedure for starting the timer
When it is determined that the timer is running, the procedure for determining whether or not the waiting time is larger than the threshold value and
When it is determined that the waiting time is equal to or less than the threshold value, the procedure of initializing the waiting time and continuing the measurement of the waiting time, and
A program comprising a procedure for generating the output text when it is determined that the waiting time is greater than a threshold value. The program according to claim 11.
The fourth procedure is
When a plurality of the converted texts are stored in the storage device, a procedure for generating the output texts by deleting and combining the utterance continuation character strings from the plurality of converted texts.
A program comprising, when one of the converted texts is stored in the storage device, a procedure of generating the one converted text as the output text.

Images