JP7429194B2 - Dialogue device and dialogue program - Google Patents

Description

The present invention relates to a dialogue device and a dialogue program.

2. Description of the Related Art Techniques are known for operating and controlling devices such as so-called IoT (Internet of Things) devices including home appliances through speech. In such technology, the content of the instruction is determined by voice recognition and morphological analysis of the user's utterance, and control information is output. Patent Document 1 describes a technique in which a server that manages home appliances provides a terminal device with an operation screen corresponding to each home appliance.

Japanese Patent Application Publication No. 2002-186057

In a system in which a device is controlled by a user's utterance, it is difficult for the user to recognize what kind of utterance the user should make in a situation where information regarding the device to be controlled and options regarding the content of the utterance are not presented. There is a technology that guides the user to the content of the utterance based on a scenario that is pre-stored as the utterance content for controlling the device, but even with such technology, the guidance is based on the pre-stored scenario. Therefore, it is not possible to flexibly and dynamically present the utterance content in response to changes in the device to be controlled, changes in the user's situation, and the like.

The technique described in Patent Document 1 only displays an operation screen for operating home appliances, and does not support the user's speech. Further, since this operation screen is stored in advance, the display contents cannot be dynamically changed depending on the situation.

The present invention has been made in view of the above-mentioned problems, and is a technology for controlling a device by user's utterances, by guiding suitable utterance contents according to the state of the device to be controlled and the user. The purpose is to improve convenience.

In order to solve the above problems, an interaction device according to one embodiment of the present invention is an interaction device that receives user utterances consisting of voice or text to generate control information for controlling a device, and includes an operating state of the device. a device status acquisition unit that acquires device status information indicating a device status, an instruction phrase representing a device control instruction including at least one word or sentence, and an operating status of the device with reference to vocabulary information; , a phrase extraction unit that extracts one or more instruction phrases associated with the operating state of the device indicated in the device status information, and an utterance for controlling the device based on the instruction phrases extracted by the phrase extraction unit. and a presentation unit that presents the utterance generated by the generation unit to the user.

In order to solve the above problems, an interaction program according to one embodiment of the present invention causes a computer to function as an interaction device that receives user utterances consisting of voice or text to generate control information for controlling a device. An interactive program that includes a device status acquisition function that acquires device status information indicating the operating status of the device, an instruction phrase that represents a device control instruction and includes at least one or more words or sentences, and the operating status of the device; a phrase extraction function that extracts one or more instruction phrases associated with the operating state of the device indicated in the device status information by referring to vocabulary information associated with the device status information; This realizes a generation function that generates an utterance for controlling a device, and a presentation function that presents the utterance generated by the generation function to a user.

According to the above embodiment, the operating state of the device is obtained, and the utterance is generated based on the instruction phrase associated with the obtained operating state of the device, so that the utterance is suitable for the operating state of the device. can be presented to the user. By speaking the presented utterance sentence, the user can perform appropriate control according to the operating state of the device, thereby improving convenience. Furthermore, since the utterances presented to the user are limited based on the device status information, the processing load and communication amount associated with presenting the utterances are reduced.

In order to solve the above problems, an interaction device according to one embodiment of the present invention is an interaction device that receives user utterances consisting of voice or text for generating control information for controlling a device, and includes: a user information acquisition unit that acquires user identification information that identifies the original user; and attribute information of the user identified by the user identification information acquired by the user information acquisition unit, the user's preference regarding the control state of the device being determined. A user attribute acquisition unit that acquires attribute information including information indicating the device, an instruction phrase representing a device control instruction and including at least one word or sentence, and a user's preferred control state regarding the device are associated. a phrase extraction section that refers to the vocabulary information and extracts one or more instruction phrases associated with the user's preferred control state indicated by the attribute information; The present invention includes a generation unit that generates an utterance for controlling the utterance, and a presentation unit that presents the utterance generated by the generation unit to the user.

In order to solve the above problems, an interaction program according to one embodiment of the present invention causes a computer to function as an interaction device that receives user utterances consisting of voice or text to generate control information for controlling a device. An interaction program, comprising a user information acquisition function for acquiring user identification information for identifying a user who has uttered user utterances, and user attribute information identified by the user identification information acquired by the user information acquisition function. , a user attribute acquisition function that acquires attribute information including information indicating the user's preferences regarding the control state of the device; an instruction phrase representing a device control instruction and including at least one word or sentence; A phrase extraction function that extracts one or more instruction phrases associated with the user's favorite control state indicated by the attribute information by referring to vocabulary information that associates the user's favorite control state; A generation function that generates an utterance for controlling a device based on the extracted instruction phrase, and a presentation function that presents the utterance generated by the generation function to a user are realized.

According to the above embodiment, attribute information indicating preferences regarding the control state of the device of the user who has uttered the user utterance is acquired, and instruction phrases associated with the user's preferences are extracted, so that the user can find information suitable for the user. It is possible to present utterances that are likely to result in device control. When the user utters the utterances presented in this manner, the device is controlled to the operating state preferred by the user, thereby improving convenience. Furthermore, since the utterances presented to the user are limited based on the user's attribute information, the processing load and communication amount associated with presenting the utterances are reduced.

In a technology for controlling a device based on a user's utterances, it is possible to improve convenience by guiding suitable utterance content depending on the state of the device to be controlled and the user.

1 is a diagram showing a device configuration of a dialogue system including a dialogue device according to the present embodiment. FIG. 2 is a functional block diagram showing the functional configuration of the dialogue device according to the present embodiment. FIG. 2 is a hardware block diagram of the dialogue device. FIG. 3 is a diagram showing an example of the configuration of a setting information storage unit and stored data. FIG. 3 is a diagram illustrating an example of device status information. FIG. 3 is a diagram showing an example of user attribute information. FIG. 3 is a diagram showing an example of the configuration of a vocabulary information storage unit and stored data. FIG. 3 is a diagram illustrating an example of a screen of a user's terminal on which an uttered sentence is displayed. It is a flowchart which shows the processing content of the interaction method of this embodiment. It is a flowchart which shows the processing content of the interaction method of this embodiment. FIG. 2 is a diagram showing the configuration of an interaction program.

Embodiments of a dialogue device and a dialogue program according to the present invention will be described with reference to the drawings. In addition, if possible, the same parts are given the same reference numerals and redundant explanations will be omitted.

FIG. 1 is a diagram showing the device configuration of a dialogue system according to this embodiment. The dialogue system 1 includes a dialogue device 10, an external system 30, and a terminal 50. The dialogue device 10 and the terminal 50 can communicate with each other. Further, the dialogue device 10 and the external system 30 can communicate with each other.

The dialogue device 10 is a device that receives user utterances consisting of voice or text to generate control information for controlling a device. Furthermore, the interaction device 10 may transmit control information to the external system 30 in order to operate a device managed by the external system 30. The dialogue device 10 is configured by, for example, a computer such as a server, but the devices that make up the dialogue device 10 are not limited.

The external system 30 constitutes a device management system that manages devices such as so-called IoT (Internet of Things) devices including home appliances and the like. The external system 30 is capable of communicating with multiple devices according to their respective communication standards.

The external system 30 has setting information for each device that can configure an interface for controlling each device, and by using and referring to the setting information, the external system 30 can control the device under management based on the control information received from the interaction device 10. You can control any of the devices in the .

The external system 30 can include a setting information storage section 31 and a device status management section 32. The setting information storage unit 31 is a storage means that stores setting information of a device to be controlled. Setting information is information used and referenced for controlling a device. Details of the setting information will be described later. In the example shown in FIG. 1, the setting information storage unit 31 is configured within the external system 30, but the configuration is not limited to this, and as long as it is accessible from the external system 30, the configuration information storage unit 31 is configured within the external system 30. It may also be configured outside.

The device status management unit 32 manages device status information indicating the operating status of the device managed by the external system 30. Specifically, the device status management unit 32 can acquire and store device status information. The device status information will be described in detail later.

The terminal 50 is a device that constitutes an interface with the user in controlling the device by speech, and is composed of, for example, a stationary or portable personal computer, a high-performance mobile phone (smartphone), etc. The device constituting the device is not limited, and may be, for example, a mobile terminal such as a mobile phone or a personal digital assistant (PDA).

The terminal 50 can transmit data of the voice uttered by the user to the dialogue device as user utterance. Further, the terminal 50 may transmit data obtained by converting the user's voice into text through voice recognition processing to the dialogue device 10 as the user's utterance.

Further, the terminal 50 can present the utterance transmitted from the dialogue device 10 to the user, as will be described later. Specifically, the terminal 50 presents the utterance to the user by displaying text indicating the utterance on the display. Further, the terminal 50 may display, on the display, an operation object that is associated with text indicating the uttered sentence and that can be instructed. The operation object may be displayed in the form of a button that can be operated by the user. When an operation for the displayed operation object is accepted, the terminal 50 transmits information indicating that the operation object has been operated, text data or audio data of the utterance associated with the operation object to the dialog device as user utterances. It may be sent to 10.

FIG. 2 is a diagram showing the functional configuration of the dialogue device 10 according to this embodiment. As shown in FIG. 2, the dialogue device 10 includes an external system information acquisition section 11, a user information acquisition section 12, a device extraction section 13, a user attribute acquisition section 14, a phrase extraction section 15, a generation section 16, a presentation section 17, an utterance It includes a reception section 18 and a control instruction transmission section 19. The external system information acquisition section 11 includes a setting information acquisition section 11A and a device status acquisition section 11B. The dialogue device 10 also includes a vocabulary information storage section 20 and a user attribute storage section 21. Each functional unit included in the dialog device 10 may be configured to be distributed among multiple devices, or, for example, some of the functional units may be configured in the terminal 50.

Note that the block diagram shown in FIG. 2 shows blocks in functional units. These functional blocks (components) are realized by any combination of hardware and/or software. Further, the means for realizing each functional block is not particularly limited. That is, each functional block may be realized by one physically and/or logically coupled device, or may be realized by directly and/or indirectly implementing two or more physically and/or logically separated devices. It may also be realized by a plurality of devices connected to each other (for example, by wire and/or wirelessly).

Functions include judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, These include, but are not limited to, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning. I can't. For example, a functional block (configuration unit) that performs transmission is called a transmitting unit or a transmitter. In either case, as described above, the implementation method is not particularly limited.

For example, the interaction device 10 in one embodiment of the present invention may function as a computer. FIG. 3 is a diagram showing an example of the hardware configuration of the dialog device 10 according to the present embodiment. The interaction device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

In addition, in the following description, the word "apparatus" can be read as a circuit, a device, a unit, etc. The hardware configuration of the dialog device 10 may be configured to include one or more of each device shown in FIG. 3, or may be configured not to include some of the devices.

Each function in the dialogue device 10 is performed by loading predetermined software (programs) onto hardware such as a processor 1001 and a memory 1002, so that the processor 1001 performs calculations, performs communication by the communication device 1004, and performs communication by the memory 1002 and storage 1003. This is realized by controlling reading and/or writing of data in.

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured with a central processing unit (CPU) that includes interfaces with peripheral devices, a control device, an arithmetic device, registers, and the like. Further, the processor 1001 may include a GPU (Graphics Processing Unit). For example, each of the functional units 11 to 19 shown in FIG. 2 may be implemented by the processor 1001.

Further, the processor 1001 reads programs (program codes), software modules, and data from the storage 1003 and/or the communication device 1004 to the memory 1002, and executes various processes in accordance with these. As the program, a program that causes a computer to execute at least part of the operations described in the above embodiments is used. For example, each of the functional units 11 to 19 of the dialog device 10 may be realized by a control program stored in the memory 1002 and operated by the processor 1001. Although the various processes described above have been described as being executed by one processor 1001, they may be executed by two or more processors 1001 simultaneously or sequentially. Processor 1001 may be implemented with one or more chips. Note that the program may be transmitted from a network via a telecommunications line.

The memory 1002 is a computer-readable recording medium, and includes at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. may be done. Memory 1002 may be called a register, cache, main memory, or the like. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing the interaction method according to an embodiment of the present invention.

The storage 1003 is a computer-readable recording medium, such as an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (such as a compact disk, a digital versatile disk, or a Blu-ray disk). (registered trademark) disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device. The storage medium mentioned above may be, for example, a database including memory 1002 and/or storage 1003, a server, or other suitable medium.

The communication device 1004 is hardware (transmission/reception device) for communicating between computers via a wired and/or wireless network, and is also referred to as, for example, a network device, network controller, network card, communication module, or the like.

The input device 1005 is an input device (eg, keyboard, mouse, microphone, switch, button, sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).

Further, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured as a single bus or may be configured as different buses between devices.

The dialogue device 10 also includes hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA). A part or all of each functional block may be realized by the hardware. For example, processor 1001 may be implemented with at least one of these hardware.

Referring again to FIG. 2, each functional section of the dialog device 10 will be described. The external system information acquisition unit 11 acquires various information from the external system 30. Specifically, the external system information acquisition unit 11 includes a configuration information acquisition unit 11A and a device status acquisition unit 11B, and acquires configuration information and device status information.

The setting information acquisition unit 11A acquires setting information. Specifically, the configuration information acquisition unit 11A acquires configuration information from the configuration information storage unit 31 of the external system 30. The setting information includes attributes of each device and is referenced for controlling the devices.

FIG. 4 shows information showing an example of the configuration of the setting information storage section 31 and stored data. As shown in FIG. 4, the setting information storage unit 31 stores various attributes as setting information in association with a device ID that identifies a device. In the example shown in FIG. 4, the setting information storage unit 31 stores setting information such as a device, a nickname, and a group indicating the category of the device for each device ID.

The nickname is a name set by the user for the device, and is a name used to indicate the device in the utterance. In the example shown in FIG. 4, one nickname is set for each device, but unique nicknames may be set for one device by each of a plurality of users. The nickname setting only needs to uniquely identify each device from the user's perspective. The group can be information indicating the location where the device is installed. Furthermore, the group may be other information for grouping multiple devices.

For example, the setting information storage unit 31 stores setting information such as a device "TV", a nickname "Dad's TV", and a group "Living" in association with the device ID "1".

The setting information acquisition unit 11A may acquire a predetermined amount of setting information all at once at a predetermined timing in a standby state for accepting user utterances. Further, the setting information acquisition unit 11A may acquire necessary setting information each time the setting information is referenced in the device extraction unit 13, phrase extraction unit 15, etc., which will be described in detail later.

The device status acquisition unit 11B acquires device status information. The device status information is information indicating the operating status of a device managed by the external system 30. The device status information is managed, for example, by the device status management section 32 of the external system 30. The device status management unit 32 acquires and stores the operating status of each device under management. The device state management unit 32 provides the stored information indicating the operating state of the device to the interaction device 10 as device state information.

The device status acquisition unit 11B can acquire device status information from the device status management unit 32. FIG. 5 is a diagram illustrating an example of device status information. As shown in FIG. 5, the device status information includes a device category and a device operating status for each device ID that identifies the device. For example, the category of the device with device ID "1" is "TV", and the device operating status is "power: ON, channel: 4, volume level: 18".

The user information acquisition unit 12 acquires user identification information that identifies the user who is the source of user utterances. Specifically, the user information acquisition unit 12 can acquire user identification information from the user's terminal 50. The user information acquisition unit 12 can acquire, for example, user identification information transmitted from the terminal 50 to the interaction device 10 for processing such as account authentication.

Further, the user information acquisition unit 12 may acquire location information indicating the user's location as part of the user's information. Specifically, the user information acquisition unit 12 acquires position information acquired by, for example, a GPS device (not shown) included in the user's terminal 50. The user information acquisition unit 12 acquires position information of the user based on detection information detected by a human sensor (not shown) provided in a space where the dialogue system 1 of the present embodiment is applied. good. Further, when the terminal 50 is a mobile radio communication terminal, the user information acquisition unit 12 may acquire the location information of the terminal 50 as position information. The user information acquisition unit 12 may acquire the user's location information using other known methods.

For example, when the user information acquisition unit 12 acquires the user's location information, the device extraction unit 13 refers to the setting information in order to narrow down the devices to be controlled before extracting the instruction phrase and generating the utterance. Then, the device associated with the location information acquired by the user information acquisition unit 12 may be extracted. Note that the device extraction unit 13 is not an essential component in this embodiment, and device extraction processing is not essential.

As described above, since the setting information includes an association between a device and a group indicating the location of the device, the device extraction unit 13 can extract the device located at the user's location by referring to the setting information. . For example, when the location information acquired by the user information acquisition unit 12 indicates that the user's location is in the living room, the device extraction unit 13 refers to the setting information shown in FIG. Extract "TV" with device ID "1", "Light" with device ID "2", "Light" with device ID "3", and "Air conditioner" with device ID "5", which are devices associated with "Living Room". do.

The user attribute acquisition unit 14 acquires attribute information of the user identified by the user identification information acquired by the user information acquisition unit 12. The user attribute information includes information indicating the user's preferences regarding the control state of the device, and is stored in the user attribute storage unit 21 in the present embodiment, for example. The user attribute acquisition unit 14 acquires user attribute information from the user attribute storage unit 21.

FIG. 6 is a diagram illustrating a configuration of attribute information stored in the user attribute storage unit 21 and an example of stored data. As shown in FIG. 6, the user attribute storage unit 21 stores attribute information such as temperature, humidity, brightness, volume level, and TV channel in association with a user ID (user identification information) and user name that identify the user. I remember.

Temperature and humidity of the attribute information are referenced, for example, when extracting instruction phrases for controlling an air conditioner. Further, the brightness of the attribute information is referred to when extracting an instruction phrase for controlling the light (lighting device). Furthermore, the volume level and television channel of the attribute information are referred to when extracting an instruction phrase for controlling the television.

For example, the user "father" identified by the user ID "0001" has the following settings: temperature "22℃-25℃", humidity "30%-50%", brightness "500-1000lux", and volume level "30℃". -35'' and television channels ``1, 2, 4, 7'' are associated as attribute information indicating preferences regarding the control state of the device.

The phrase extraction unit 15 refers to the vocabulary information and extracts one or more instruction phrases associated with the operating state of the device indicated by the device state information. Vocabulary information is information that associates each device with an instruction phrase that represents a control instruction for the device and includes at least one or more words or sentences. The phrase extraction unit 15 refers to the vocabulary information stored in the vocabulary information storage unit 20 and extracts the instruction phrase.

FIG. 7 is a diagram showing an example of the configuration of the vocabulary information storage section 20 and stored data. As shown in FIG. 7, the vocabulary information storage unit 20 stores vocabulary information in which at least an instruction phrase is associated with a device category indicating the type of device. The vocabulary information may further include control details and setting items in association with the device category. The control content is the purpose to be achieved by uttering the associated instruction phrase, and indicates the content of the control performed on the device. The setting item is a phrase related to the parameter change range, etc., which is added as an option to the instruction phrase, for example, when the control content is related to changing the parameter of the device.

As shown in FIG. 7, each instruction phrase in the vocabulary information is associated with a device operating state. For example, considering that it is necessary to control the TV to the ON state when the power is OFF, the instruction phrase "Turn on" is used to control the device "TV" to the control content "ON". ” is associated with the device operating state “Power: OFF”.

In addition, considering that it is necessary to control the air conditioner to raise the set temperature when the set temperature is low, we have created an instruction phrase to control the device "air conditioner" to the control content "increase the set temperature". "Raise the temperature" is associated with the device operating states "Power: ON and set temperature: 25 degrees or less" and "Power: ON and set temperature: 23 degrees or less".

As shown in FIG. 5, the device status information may include information indicating that the device is operating (eg, "power ON") or non-operating (eg, "power OFF"). In such a case, the phrase extracting unit 15 extracts an instruction phrase for controlling the device to a non-operating state when the device is in operation, and extracts an instruction phrase for controlling the device to a non-operating state when the device is in a non-operating state. It is possible to extract instruction phrases for controlling the operating state.

Specifically, the device status acquisition unit 11B acquired the device status information “device ID “1”, device “TV”, and device operating status “power: ON, . . .” as shown in FIG. In this case, the phrase extraction unit 15 refers to the vocabulary information (see FIG. 7) to determine whether the phrase is associated with the device operating state "Power: ON" and which is associated with the device operating state "Power: ON" and which is used to control the device "TV" to the control content "OFF". Extract the instruction phrase "Keshite".

Further, for example, if the device status acquisition unit 11B acquires device status information “device ID “2”, device “light”, and device operating status “power: OFF, . . .” as shown in FIG. , the phrase extracting unit 15 refers to the vocabulary information (see FIG. 7) and extracts an instruction to control the device "Light" to the control content "ON", which is associated with the device operating state "Power: OFF". Extract the phrase "put on".

Further, as shown in FIG. 5, the device status information can include predetermined parameters regarding the operation of the device. Specifically, for example, the device state information of the device ID "1" and the device "TV" includes parameters regarding the operation of the TV, such as channel "4" and volume level "18", as the device state information. Further, for example, the device state information of the device ID "5" and the device "air conditioner" includes parameters related to the operation of the air conditioner, such as the set temperature "24 degrees" and the set humidity "50%".

In such a case, if the parameters included in the device status information are included in the first range, the phrase extraction unit 15 controls the parameters of the device to a second range different from the first range. It is possible to extract instruction phrases for

Specifically, the device status acquisition unit 11B acquires device status information such as shown in FIG. , the phrase extraction unit 15 refers to the lexical information (see FIG. 7) and associates the device operating state with "set temperature: 25 degrees or less", and changes the device "air conditioner" to the control content "set temperature". Extract the instruction phrase ``Raise the temperature'' to control the temperature. That is, since the set temperature in the device operating state is included in the range of less than 25 degrees (first range), such an instruction phrase is used to control the set temperature to a range of 25 degrees or higher (second range). is extracted.

In addition, when extracting this instruction phrase, "Set temperature: 24 degrees" in the device operating state is changed to each of the two setting items "a little" and "2 degrees" associated with the instruction phrase "Raise the temperature". Since it corresponds to the device operating state associated with "a little" out of the associated device operating states, the optional phrase "a little" set in the setting item may be further extracted.

Furthermore, the phrase extraction unit 15 may refer to the vocabulary information to extract one or more instruction phrases associated with the user's preferred control state indicated by the user's attribute information.

As shown in FIG. 7, the vocabulary information includes user attributes associated with each instruction phrase. For example, considering that it is necessary to control the setting temperature of an air conditioner to increase when the user prefers a high temperature setting, the control content ``increase the setting temperature'' is implemented for the device ``air conditioner.'' The instruction phrase "Raise the temperature" is associated with the user attribute of high temperature "26 degrees or higher."

For example, the user information acquisition unit 12 acquires the user ID “0001,” and the user attribute acquisition unit 14 associates the user ID “0001” with the user attributes “user name: father, temperature: 22-25 degrees, . . . ” is acquired, the phrase extraction unit 15 refers to the lexical information to determine whether the phrase is associated with the user attribute “temperature 25 degrees or less” and controls the device “air conditioner” to the control content “lower the temperature”. Extract the instruction phrase "lower the temperature."

Further, for example, the user information acquisition unit 12 acquires the user ID “0002”, and the user attribute acquisition unit 14 acquires the user attributes “user name: mother, temperature: 26-28 degrees,” which is associated with the user ID “0002.” ...'' is acquired, the phrase extracting unit 15 refers to the lexical information and associates with the user attribute "temperature 26 degrees or higher", and sets the device "air conditioner" to the control content "increase temperature". Extract the command phrase "Raise the temperature" for control.

Further, the phrase extraction unit 15 refers to the vocabulary information and extracts one or more instruction phrases that are associated with the operating state of the device indicated by the device state information and the control state preferred by the user indicated by the user attribute information. may be extracted.

For example, the user information acquisition unit 12 acquires the user ID “0003,” and the user attribute acquisition unit 14 creates the user attributes associated with the user ID “0003” such as “user name: daughter, . . . , volume level: 10-20.” ,...'' is acquired, and the device status acquisition unit 11B acquires device status information ``Device ID ``1'', device ``TV'', and device operating status ``Power: ON, . . . , Volume level: 18''. In this case, the phrase extraction unit 15 refers to the vocabulary information and selects the user attribute "Volume level: 20 or less" and the device operating state "Power: ON and The instruction phrase "lower the volume" and the optional setting item "slightly" associated with "volume level: 15 or higher" are extracted.

Further, when the device extracting unit 13 has extracted a device located at the user's location, the phrase extracting unit 15 refers to the vocabulary information and associates the phrase with the device extracted by the device extracting unit 13. Alternatively, one or more instruction phrases may be extracted. For example, when the device extracted by the device extraction unit is "TV", the phrase extraction unit 15 extracts instruction phrases such as "turn on", "turn off", and "volume" associated with the device category "TV". "Turn up the volume," "Turn the volume down," and "Change the channel" are extracted from the vocabulary information.

The generation unit 16 generates an utterance for controlling the device based on the instruction phrase extracted by the phrase extraction unit 15. Specifically, the generation unit 16 may generate the instruction phrase extracted by the phrase extraction unit 15 as an utterance.

Further, the generation unit 16 may generate the utterance by adding the device category associated with the instruction phrase extracted by the phrase extraction unit 15 to the instruction phrase as a phrase indicating the control target. For example, when the phrase extraction unit 15 extracts the instruction phrase “turn on” that corresponds to the control content “ON” of the device “TV”, the generation unit 16 extracts “TV” and the particle indicating the control target. The utterance sentence "Turn on the TV" may be generated by adding it to the instruction phrase "Turn on".

Further, the generation unit 16 may generate the utterance based on the instruction phrase extracted by the phrase extraction unit 15 and the nickname of the device to be controlled by the instruction phrase. For example, when the phrase extraction unit 15 extracts the instruction phrase “turn on” that corresponds to the control content “ON” of the device “TV”, the generation unit 16 extracts the nickname “ON” of the device “TV”. The utterance sentence ``Turn on Dad's TV'' may be generated by adding ``Dad's TV'' and a particle to the instruction phrase ``Turn on Dad.''

Furthermore, when the instruction phrase extracted by the phrase extraction section 15 is for the purpose of changing the parameters of the device, the generation section 16 adds a phrase indicating the range of change to the instruction phrase and generates the utterance. may be generated. For example, when the phrase extracting unit 15 extracts the instruction phrase “increase the temperature” corresponding to the control content “increase the set temperature” of the device “air conditioner”, the generating unit 16 extracts the instruction phrase “increase the temperature” that corresponds to the control content “increase the set temperature” of the device “air conditioner”. By adding the phrases "a little" and "2 degrees", which are stored in the setting items as words indicating the range of change in temperature, to the instruction phrase, the utterances "Raise the temperature a little" and "Raise the temperature 2 degrees" can be created. ” may be generated. Note that either of these two utterances may be generated depending on the device operating state or the like.

The presentation unit 17 presents the utterance generated by the generation unit 16 to the user. Specifically, the presentation unit 17 transmits text information indicating the utterance to the user's terminal 50, and displays the text indicating the utterance on the display of the terminal 50.

FIG. 8 is a diagram showing an example of the screen of the user's terminal 50 on which the utterance is displayed. As shown in FIG. 8, the display D of the terminal 50 includes a text b1 "lower the temperature of the air conditioner in the living room by 2 degrees" and a text b2 "turn on your father's TV", which are utterances. In this way, by presenting the text indicating the generated utterance on the user's terminal 50, the user can utter the utterance.

Further, the presentation unit 17 may display, on the user's terminal 50, an operation object that is associated with text indicating the uttered sentence and that can be instructed and operated. In this case, the presentation unit 17 configures each of the text b1 and the text b2 as an operation object such as a button that can be operated by the user in the screen example of FIG. 8, and causes the display D to display the text b1 and the text b2. When the presentation unit 17 displays such an operation object on the terminal 50, the dialogue device 10 accepts user utterances consisting of audio of text content when the operation object is operated on the user's terminal 50. Generates the same device control information as when

The utterance reception unit 18 receives a user's utterance as a user utterance. Specifically, the utterance reception unit 18 receives, via the terminal 50, audio or text representing an utterance uttered to the terminal 50 by a user who is presented with the utterance as a user utterance.

Further, when an operation object such as a button with which an utterance is associated is presented on the terminal 50 and an instruction operation for the operation object is accepted at the terminal 50, the utterance reception unit 18 sends a message indicating that the operation object has been operated. Receive information as user utterances.

The control instruction transmitter 19 transmits control information for controlling a device managed by the external system 30 based on user utterances. Specifically, when the user utterance consisting of voice data is accepted by the utterance receiving unit 18, the control instruction transmitting unit 19 performs voice recognition processing, morphological analysis, and predetermined analysis processing on the user utterance. By doing so, control information for controlling the device is generated, and the generated control information is transmitted to the external system 30. Note that if the user's utterance is accepted as text data, voice recognition processing is not necessary.

When information indicating that the operation object has been operated is received as a user utterance, the control instruction transmitter 19 assumes that the text data of the utterance associated with the operation object has been accepted as a user utterance. , generates control information for controlling the device by performing morphological analysis and predetermined analysis processing on the text data.

Next, with reference to FIG. 9, processing contents in the dialog device 10 will be explained. FIG. 9 is a flowchart showing the processing contents of the interaction method of this embodiment.

In step S1, the user information acquisition unit 12 acquires user identification information that identifies the user who is the source of the user's utterance. The dialogue device 10 is then controlled to be in a standby state for accepting user utterances. Specifically, the utterance reception unit 18 is controlled to be in a state of waiting for reception of user utterances.

In step S2, the configuration information acquisition unit 11A acquires configuration information from the configuration information storage unit 31 of the external system 30.

In step S3, the device status acquisition unit 11B acquires device status information from the device status management unit 32. In step S4, the device state acquisition unit 11B determines whether or not the device state information has been successfully acquired. If it is determined that the device status information has been successfully acquired, the process proceeds to step S5. On the other hand, if it is not determined that the device state information has been successfully acquired, the process proceeds to step S6.

In step S5, the phrase extraction unit 15 refers to the vocabulary information and extracts one or more instruction phrases associated with the operating state of the device indicated by the device state information.

On the other hand, in step S6, the phrase extraction unit 15 extracts the instruction phrase without depending on the operating state of the device. Specifically, the phrase extraction unit 15 may, for example, randomly extract instruction phrases from vocabulary information. Further, the phrase extraction unit 15 may refer to the extraction history of instruction phrases and extract the most recently accepted instruction phrase, the instruction phrase that has been extracted many times, and the like, for example.

In step S7, the generation unit 16 generates an utterance for controlling the device based on the instruction phrase extracted by the phrase extraction unit 15 in step S5 or step S6.

In step S8, the presentation unit 17 presents the utterance generated by the generation unit 16 to the user. Specifically, the presentation unit 17 transmits text information indicating the utterance to the user's terminal 50, and displays the text indicating the utterance on the display of the terminal 50.

Next, with reference to FIG. 10, another example of processing contents in the dialog device 10 will be described. FIG. 10 is a flowchart showing the processing contents of the interaction method of this embodiment. The process shown in FIG. 9 uses device status information, whereas the process shown in FIG. 10 uses user attribute information.

In step S11, the user information acquisition unit 12 acquires user identification information that identifies the user who is the source of the user's utterance. The dialogue device 10 is then controlled to be in a standby state for accepting user utterances. Specifically, the utterance reception unit 18 is controlled to be in a state of waiting for reception of user utterances.

In step S12, the configuration information acquisition unit 11A acquires configuration information from the configuration information storage unit 31 of the external system 30.

In step S13, the user attribute acquisition unit 14 acquires attribute information of the user identified by the user identification information acquired by the user information acquisition unit 12. In step S14, the user attribute acquisition unit 14 determines whether or not the user's attribute information has been successfully acquired. If it is determined that the user's attribute information has been successfully acquired, the process proceeds to step S15. On the other hand, if it is not determined that the user's attribute information has been successfully acquired, the process proceeds to step S16.

In step S15, the phrase extraction unit 15 refers to the vocabulary information and extracts one or more instruction phrases associated with the user's preferred device control state indicated in the user's attribute information.

On the other hand, in step S16, the phrase extraction unit 15 extracts the instruction phrase without depending on the user's attribute information. Specifically, the phrase extraction unit 15 may, for example, randomly extract instruction phrases from the vocabulary information. Further, the phrase extracting unit 15 may, for example, refer to the extraction history of instruction phrases and extract instruction phrases that have been accepted most recently, instruction phrases that have been extracted many times, and the like.

In step S17, the generation unit 16 generates an utterance for controlling the device based on the instruction phrase extracted by the phrase extraction unit 15 in step S15 or step S16.

In step S18, the presentation unit 17 presents the utterance generated by the generation unit 16 to the user. Specifically, the presentation unit 17 transmits text information indicating the utterance to the user's terminal 50, and displays the text indicating the utterance on the display of the terminal 50.

Next, a dialogue program for causing a computer to function as the dialogue apparatus 10 of this embodiment will be explained. FIG. 11 is a diagram showing the configuration of the dialog program P1.

The dialogue program P1 includes a main module m10 that comprehensively controls dialogue processing in the dialogue device 10, an external system information acquisition module m11, a user information acquisition module m12, a device extraction module m13, a user attribute acquisition module m14, a phrase extraction module m15, It includes a generation module m16, a presentation module m17, an utterance reception module m18, and a control instruction transmission module m19. The external system information acquisition module m11 includes a setting information acquisition module m11A and a device status acquisition module m11B.

Then, the modules m11 to m19, m11A, and m11B control the external system information acquisition unit 11, user information acquisition unit 12, device extraction unit 13, user attribute acquisition unit 14, phrase extraction unit 15, generation unit 16, and Each function for the presentation section 17, the speech reception section 18, the control instruction transmission section 19, the setting information acquisition section 11A, and the device status acquisition section 11B is realized. Note that the dialogue program P1 may be transmitted via a transmission medium such as a communication line, or may be stored in a recording medium M1 as shown in FIG. 11.

In the dialog device 10 of the present embodiment described above, the operating state of the device is acquired, and the utterance is generated based on the instruction phrase associated with the obtained operating state of the device. It is possible to present a suitable utterance to the user. By speaking the presented utterance sentence, the user can perform appropriate control according to the operating state of the device, thereby improving convenience. Furthermore, since the utterances presented to the user are limited based on the device status information, the processing load and communication amount associated with presenting the utterances are reduced.

Furthermore, in the dialog device 10 of the present embodiment, attribute information indicating the preferences regarding the control state of the device of the user who uttered the user utterance is acquired, and instruction phrases associated with the preferences of the user are extracted. It is possible to present an utterance that is highly likely to result in a device being controlled in a way that is suitable for the user. When the user utters the utterances presented in this manner, the device is controlled to the operating state preferred by the user, thereby improving convenience. Furthermore, since the utterances presented to the user are limited based on the user's attribute information, the processing load and communication amount associated with presenting the utterances are reduced.

Further, an interaction device according to another embodiment further includes a device status acquisition unit that acquires device status information indicating an operational status of the device, and the vocabulary information further associates the operational status of the device with the instruction phrase, and the vocabulary information further associates the operational status of the device with the instruction phrase. The extraction unit may refer to the vocabulary information to extract one or more instruction phrases associated with the user's preferred control state indicated by the device operating state and attribute information indicated by the device state information. .

According to the above embodiment, the operating state of the device is acquired in addition to the user's attribute information, and the utterance is generated based on the user's preferences shown in the attribute information and the instruction phrase associated with the operating state of the device. , suitable utterances can be presented to the user.

In another aspect of the dialog device, the device status information includes information indicating whether the device is in operation or not, and the phrase extraction unit is configured to detect whether the device is in operation or not. An instruction phrase for controlling the device to be in an inactive state may be extracted, and when the device is in an inactive state, an instruction phrase for controlling the device to be in an operating state may be extracted.

According to the above embodiment, the user is presented with an utterance for controlling the device to the non-operating state when the device is in operation, and a statement for controlling the device to the operating state when the device is in the non-operating state is presented to the user. The utterance is presented to the user. That is, an utterance for controlling the device to a different operating state from the current operating state is presented to the user. Therefore, it is possible to present an utterance for realizing control that is likely to be desired by the user to the target device.

Further, in the dialog device according to another embodiment, the device status information includes a predetermined parameter regarding the operation of the device, and the phrase extraction unit is configured to: An instruction phrase for controlling a parameter of the device to a second range different from the first range may be extracted.

According to the above aspect, when a predetermined parameter regarding the operation of the device is included in the first range, an utterance for controlling the parameter to the second range is presented to the user. That is, an utterance for controlling the device using parameter values different from the current parameter values is presented to the user. Therefore, it is possible to present an utterance for realizing control that is likely to be desired by the user to the target device.

Further, an interaction device according to another embodiment further includes a setting information acquisition unit that acquires setting information associating each device with a nickname of the device, and the generation unit includes instructions extracted by the phrase extraction unit. The utterance may be generated based on the phrase and the nickname of the device to be controlled by the instruction phrase.

According to the above embodiment, an uttered sentence including a nickname set for a device to be controlled is generated. This makes it easier for the user to recognize the device to be controlled in the presented utterance.

Further, in another type of dialogue device, the presentation unit may display text indicating the utterance on the user's terminal.

According to the above embodiment, the text indicating the generated utterance is presented on the user's terminal, so the user can utter the utterance.

Further, in another aspect of the dialog device, the presentation unit displays on the user's terminal an operation object that is associated with text indicating an uttered sentence and can be operated as an instruction; In this case, the same device control information as in the case where a user's utterance consisting of audio of text content is received may be generated.

According to the above embodiment, an operation object to which text indicating a generated utterance is associated is displayed on the user terminal, and when the operation object is operated, the content of the utterance is uttered by voice. Since similar control information is generated, the user can easily carry out desired control instructions.

Although this embodiment has been described in detail above, it is clear for those skilled in the art that this embodiment is not limited to the embodiment described in this specification. This embodiment can be implemented as modifications and changes without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description in this specification is for the purpose of illustrative explanation and does not have any restrictive meaning with respect to this embodiment.

Each aspect/embodiment described in this disclosure is applicable to LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA ( (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), other suitable systems, and/or next-generation systems expanded based on these.

The order of the processing procedures, sequences, flowcharts, etc. of each aspect/embodiment described in this disclosure may be changed as long as there is no contradiction. For example, the methods described herein present elements of the various steps in an exemplary order and are not limited to the particular order presented.

Information etc. can be output from an upper layer (or lower layer) to a lower layer (or upper layer). It may be input/output via multiple network nodes.

The input/output information may be stored in a specific location (eg, memory) or may be managed in a management table. Information etc. to be input/output may be overwritten, updated, or additionally written. The output information etc. may be deleted. The input information etc. may be transmitted to other devices.

Judgment may be made using a value expressed by 1 bit (0 or 1), a truth value (Boolean: true or false), or a comparison of numerical values (for example, a predetermined value). (comparison with a value).

Each aspect/embodiment described in this disclosure may be used alone, in combination, or may be switched and used in accordance with execution. In addition, notification of prescribed information (for example, notification of "X") is not limited to being done explicitly, but may also be done implicitly (for example, not notifying the prescribed information). Good too.

Software includes instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, whether referred to as software, firmware, middleware, microcode, hardware description language, or by any other name. , should be broadly construed to mean an application, software application, software package, routine, subroutine, object, executable, thread of execution, procedure, function, etc.

Additionally, software, instructions, etc. may be sent and received via a transmission medium. For example, if the software uses wired technologies such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and/or wireless technologies such as infrared, radio and microwave to When transmitted from a remote source, these wired and/or wireless technologies are included within the definition of transmission medium.

The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may refer to voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. It may also be represented by a combination of

Note that terms explained in this disclosure and/or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

Further, the information, parameters, etc. described in this disclosure may be expressed as absolute values, relative values from a predetermined value, or other corresponding information.

As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of operations. "Judgment" and "decision" include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, search, and inquiry. (e.g., searching in a table, database, or other data structure), and regarding an ascertaining as a "judgment" or "decision." In addition, "judgment" and "decision" refer to receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and access. (accessing) (e.g., accessing data in memory) may include considering something as a "judgment" or "decision." In addition, "judgment" and "decision" refer to resolving, selecting, choosing, establishing, comparing, etc. as "judgment" and "decision". may be included. In other words, "judgment" and "decision" may include regarding some action as having been "judged" or "determined." Further, "judgment (decision)" may be read as "assuming", "expecting", "considering", etc.

As used in this disclosure, the phrase "based on" does not mean "based solely on" unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Where this disclosure uses the terms "first," "second," etc., any reference to the elements does not generally limit the amount or order of those elements. These designations may be used herein as a convenient way of distinguishing between two or more elements. Thus, reference to a first and second element does not imply that only two elements may be employed therein or that the first element must precede the second element in any way.

To the extent that the words "include," "including," and variations thereof are used in this specification or in the claims, these terms are synonymous with the term "comprising." is intended to be comprehensive. Furthermore, the term "or" as used in this specification or in the claims is not intended to be exclusive or.

In this disclosure, a plurality of devices is also included unless it is clear from the context or technology that only one device exists.

Throughout this disclosure, the plural is intended to be included unless the context clearly dictates otherwise.

DESCRIPTION OF SYMBOLS 1...Dialogue system, 10...Dialogue device, 11...External system information acquisition unit, 11A...Setting information acquisition unit, 11B...Device status acquisition unit, 12...User information acquisition unit, 13...Device extraction unit, 14...User attribute acquisition Parts, 15...phrase extraction unit, 16...generation unit, 17...presentation unit, 18...utterance reception unit, 19...control instruction transmission unit, 20...vocabulary information storage unit, 21...user attribute storage unit, 30...external system, 31...Setting information storage unit, 32...Device status management unit, 50...Terminal, M1...Recording medium, m10...Main module, m11...External system information acquisition module, m11A...Setting information acquisition module, m11B...Device status acquisition module, m12...user information acquisition module, m13...device extraction module, m14...user attribute acquisition module, m15...phrase extraction module, m16...generation module, m17...presentation module, m18...utterance reception module, m19...control instruction transmission module, P1 ...Dialogue program.

Claims (2)

An interaction device that receives user utterances consisting of voice or text for generating control information for controlling a device,
a device status acquisition unit that acquires device status information indicating the operating status of the device;
The operating state of the device indicated in the device state information is determined by referring to vocabulary information that associates an instruction phrase representing a control instruction for the device and including at least one word or sentence and the operating state of the device. a phrase extraction unit that extracts one or more associated instruction phrases;
a generation unit that generates an utterance for controlling the device based on the instruction phrase extracted by the phrase extraction unit;
a presentation unit that presents the utterance generated by the generation unit to the user ,
The device state information includes predetermined parameters regarding the operation of the device,
When the parameter included in the device state information is included in a first range, the phrase extracting unit is configured to control the parameter of the device to a second range different from the first range. Extract instruction phrases,
Dialogue device. An interaction device that receives user utterances consisting of voice or text for generating control information for controlling a device,
a user information acquisition unit that acquires user identification information that identifies a user who has uttered the user utterance;
a user attribute acquisition unit that acquires attribute information of a user identified by the user identification information acquired by the user information acquisition unit, the attribute information including information indicating the user's preference regarding the control state of the device;
a device status acquisition unit that acquires device status information indicating the operating status of the device;
The user indicated by the attribute information refers to vocabulary information that associates an instruction phrase representing a control instruction for the device and including at least one word or sentence and the user's preferred control state regarding the device. a phrase extractor that extracts one or more instruction phrases associated with the preferred control state of the
a generation unit that generates an utterance for controlling the device based on the instruction phrase extracted by the phrase extraction unit;
a presentation unit that presents the utterance generated by the generation unit to the user ,
the lexical information further associates an operational state of the device with the instruction phrase;
The phrase extraction unit refers to the vocabulary information and extracts one or more of the instruction phrases that are associated with the operating state of the device indicated by the device state information and the control state preferred by the user indicated by the attribute information. extract,
The device state information includes predetermined parameters regarding the operation of the device,
When the parameter included in the device status information is included in a first range, the phrase extraction unit is configured to control the parameter of the device to a second range different from the first range. Extract instruction phrases,
Dialogue device.

Images