JP2021135412A - Information processing device, information processing method, and program - Google Patents

Abstract

To provide a device and method that enable one user utterance corresponding to an information processing device to be selected from among a plurality of user utterance candidates.SOLUTION: An information processing device includes a data processing unit that, from among a plurality of user utterance candidates generated as a voice analysis result of user utterance, selects one user utterance corresponding to the information processing device. The data processing unit determines a context type which is a type of context which is current status information, selects a context type having high similarity to or correlation with the determined context type, and selects a user utterance having the same slot as or a similar slot to a slot registered in a database in association with the selected context type as one user utterance corresponding to the information processing device.SELECTED DRAWING: Figure 2

Description

The present disclosure relates to an information processing device, an information processing method, and a program. More specifically, the present invention relates to an information processing device that executes processing and a response according to a user's utterance, an information processing method, and a program.

In recent years, the use of voice dialogue systems that perform voice recognition of user utterances and perform various processes and responses based on the recognition results is increasing.
In this voice dialogue system, the user's utterance input via the microphone is analyzed, and processing is performed according to the analysis result.

For example, when the user says "Tell me the weather tomorrow", the weather information is acquired from the weather information providing server, a system response based on the acquired information is generated, and the generated response is output from the speaker. Specifically, for example
System utterance = "Tomorrow's weather will be sunny, but there may be thunderstorms in the evening."
Output such a system utterance.

Information processing devices that interact with users in this way are called agent devices and smart speakers.

The agent device and the smart speaker recognize and understand the user's utterance input through the microphone, and perform processing accordingly.
However, the system may not be able to uniquely determine the action, such as when the reliability of the voice recognition result or the intention estimation result of the user's utterance is low, or when there are multiple interpretations of the recognition result.
That is, it may be difficult to accurately read the user's utterance intention and perform a response or processing.

As a conventional technique that discloses a method for solving such a problem, for example, Patent Document 1 (Japanese Unexamined Patent Publication No. 2007-108407) is available.
This Patent Document 1 discloses a configuration in which when a user utterance is long, a high-priority utterance portion is selected from the long user utterance and response processing is performed for the selected utterance portion.

However, this document only discloses a configuration for analyzing the user's intention presumed to have high priority from the user's long utterance, and when the reliability of the voice recognition result or the intention estimation result is low. The response is not disclosed.

JP-A-2007-108407

The present disclosure has been made in view of the above problems, for example, and even when the reliability of the voice recognition result or the intention estimation result for the user utterance is low, the response or processing for the user utterance can be executed with high accuracy. It is an object of the present invention to provide an information processing device, an information processing method, and a program that enable it.

In addition, a process that analyzes the context (situation information) using information observed through a camera or the like and estimates user utterances using the analysis results, an information processing device that predicts the next process, and an information processing device. The purpose is to provide information processing methods and programs.

The first aspect of the disclosure is
It has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a voice analysis result of the user utterance.
The data processing unit
It is in an information processing device that analyzes a context that is current status information and executes a user utterance selection process in which the information processing device selects one corresponding user utterance from the plurality of user utterance candidates using the context analysis result. ..

Further, the second aspect of the present disclosure is
It has a data processing unit that determines the next processing candidate, which is the next processing candidate to be executed by the information processing device.
The data processing unit
It is in an information processing device that analyzes a context that is current status information and determines the next processing candidate by using the context analysis result.

Further, the third aspect of the present disclosure is
It is an information processing method executed in an information processing device.
The information processing device has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of user utterances.
The data processing unit
It is an information processing method that analyzes a context that is current situation information and executes a user utterance selection process in which an information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates using the context analysis result. ..

Further, the fourth aspect of the present disclosure is
It is an information processing method executed in an information processing device.
The information processing device
The information processing apparatus has a data processing unit that determines a next processing candidate that is a candidate for processing to be executed next.
The data processing unit
It is an information processing method that analyzes the context which is the current situation information and determines the next processing candidate by using the context analysis result.

Further, the fifth aspect of the present disclosure is
A program that executes information processing in an information processing device.
The information processing device has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of the user utterance.
The program is installed in the data processing unit.
It is in a program that analyzes a context which is current situation information and executes a user utterance selection process in which an information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates by using the context analysis result.

Further, the sixth aspect of the present disclosure is
A program that executes information processing in an information processing device.
The information processing device
The information processing apparatus has a data processing unit that determines a next processing candidate that is a candidate for processing to be executed next.
The program is installed in the data processing unit.
It is in a program that analyzes the context which is the current situation information and determines the next processing candidate by using the context analysis result.

The program of the present disclosure is, for example, a program that can be provided by a storage medium or a communication medium that is provided in a computer-readable format to an information processing device or a computer system that can execute various program codes. By providing such a program in a computer-readable format, processing according to the program can be realized on an information processing device or a computer system.

Still other objectives, features and advantages of the present disclosure will become apparent by more detailed description based on the examples of the present disclosure and the accompanying drawings described below. In the present specification, the system is a logical set configuration of a plurality of devices, and the devices having each configuration are not limited to those in the same housing.

According to the configuration of one embodiment of the present disclosure, a device and a method that enable the information processing device to select one corresponding user utterance from a plurality of user utterance candidates are realized.
Specifically, for example, it has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of user utterances. The data processing unit determines the context type, which is the type of context that is the current status information, selects a context type that is similar to or highly related to the determined context type, and associates it with the selected context type in the database. A user utterance having a slot that is the same as or similar to the slot registered in is selected as one corresponding user utterance by the information processing apparatus.
With this configuration, a device and a method that enable the information processing device to select one corresponding user utterance from a plurality of user utterance candidates are realized.
The effects described in the present specification are merely exemplary and not limited, and may have additional effects.

It is a figure explaining the structure of the information processing apparatus which performs the response and processing based on the user's utterance, and the processing example. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the stored data of a context information database. It is a figure explaining an example of the stored data of the inter-context distance table. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure which shows the flowchart explaining the processing sequence executed by an information processing apparatus. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the stored data of the inter-context distance table. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure explaining an example of the process executed by the information processing apparatus of this disclosure. It is a figure which shows the flowchart explaining the processing sequence executed by an information processing apparatus. It is a figure explaining the structural example of the information processing apparatus of this disclosure. It is a figure explaining in the example of the network configuration which has the information processing apparatus and a server of this disclosure. It is a figure explaining the configuration example of the information processing apparatus and Saha of this disclosure. It is a figure explaining the configuration example of the information processing apparatus and a server of this disclosure. It is a figure explaining the hardware configuration example of the information processing apparatus of this disclosure.

Hereinafter, the details of the information processing apparatus, the information processing method, and the program of the present disclosure will be described with reference to the drawings. The explanation will be given according to the following items.
1. 1. Outline of information processing device that performs processing according to user's utterance 2. (Example 1) Regarding the process executed by the information processing apparatus of the present disclosure when the reliability of the voice recognition result or the intention estimation result of the user's utterance is low. Specific examples of user utterance selection processing based on context analysis 4. 5. Specific examples of user utterance selection processing based on context analysis when there are many user utterance candidates. 6. Regarding the sequence of processing executed by the information processing apparatus of the present disclosure. (Example 2) Example of performing processing control using the distance between contexts 7. 8. Regarding the processing sequence of Example 2 executed by the information processing apparatus. About other examples and modifications 9. About the configuration example of the information processing device 10. About hardware configuration example of information processing device 11. Summary of the structure of this disclosure

[1. Overview of information processing equipment that performs processing according to user utterances]
First, with reference to FIGS. 1 and 1 and below, an outline of the information processing device of the present disclosure, that is, an information processing device that performs processing according to a user's utterance will be described.
As described above, the information processing device that interacts with the user is called, for example, an agent device or a smart speaker.

FIG. 1 is a diagram showing an example of processing of an information processing apparatus 10 that recognizes a user's utterance uttered by the user 1 and makes a response.
The information processing device 10 is a user's utterance, for example,
User utterance = "Tell me the weather in Osaka tomorrow and afternoon"
The voice recognition process of this user utterance is executed.

Further, the information processing device 10 executes a process based on the voice recognition result of the user's utterance.
In the example shown in FIG. 1, the speaker 14 is used to acquire data for responding to user utterance = "Tell me the weather tomorrow and afternoon in Osaka" and generate a response based on the acquired data. Output via.
In the example shown in FIG. 1, the information processing apparatus 10 makes the following system response.
System response = "Tomorrow in Osaka, the weather will be fine in the afternoon, but there may be a shower in the evening."
The information processing device 10 executes voice synthesis processing (TTS: Text To Speech) to generate and output the above system response.

The information processing device 10 generates and outputs a response by using the knowledge data acquired from the storage unit in the device or the knowledge data acquired via the network.
The information processing device 10 shown in FIG. 1 includes a camera 11, a microphone 12, a display unit 13, a speaker 14, and a sensor 15, and has a configuration capable of audio input / output and image input / output. The sensor 15 is composed of various sensors such as a distance sensor, a temperature sensor, GPS, and the like.

The voice recognition process and the semantic analysis process for the user's utterance may be performed in the information processing device 10 or may be executed in the server on the cloud side.

The information processing device 10 recognizes the utterance of the user 1 and performs a response based on the utterance of the user. In addition, for example, various processes according to the utterance of the user, for example, control of an external device such as a television or an air conditioner in the house. Also run.
For example, when the user utterance is a request such as "change the TV channel to 1" or "set the temperature of the air conditioner to 20 degrees", the information processing apparatus 10 is based on the voice recognition result of the user utterance. A control signal (Wi-Fi, infrared light, etc.) is output to an external device to execute control according to the user's utterance.

[2. (Example 1) Regarding the process executed by the information processing apparatus of the present disclosure when the reliability of the voice recognition result or the intention estimation result of the user's utterance is low]
Next, as the first embodiment, the processing executed by the information processing apparatus of the present disclosure when the reliability of the voice recognition result or the intention estimation result of the user's utterance is low will be described.

As described with reference to FIG. 1, the information processing apparatus 10 of the present disclosure recognizes and understands the user's utterance input via the microphone, and performs processing accordingly.
However, when the reliability of the voice recognition result or the intention estimation result of the user utterance is low, or when there are a plurality of interpretations of the recognition result, the information processing device 10 performs a response or processing to the user utterance. It may not be possible to determine uniquely.
That is, it may be difficult to perform a response or processing that accurately reflects the user's utterance intention.

The information processing apparatus of the present disclosure solves this problem, and even when the reliability of the voice recognition result or the intention estimation result for the user utterance is low, the response and processing reflecting the intention of the user utterance can be performed with high accuracy. It has a configuration that allows it to be executed.

The processing sequence executed by the information processing apparatus 10 of the present disclosure will be described with reference to FIG.
As shown in FIG. 2, first, it is assumed that the user 1 makes the following user utterance.
User utterance = "** Nki, please"
In the above user utterance, "**" means that the utterance cannot be clearly heard.

The information processing device 10 that has input the user utterance sequentially executes the processes of steps S01 to S04 shown in FIG. The processing of each step will be described below.

(Step S01)
First, in step S01, the information processing device 10 executes a voice recognition process for the input user utterance.

The voice analysis unit of the information processing device 10 inputs the user-spoken voice input from the microphone 12 which is a voice input unit to a voice recognition unit having an automatic voice recognition (ASR: Automatic Speech Recognition) function, and inputs the voice data to text data. Convert to.

The text data generated here is the user-spoken voice recognition result 21 shown in FIG. 2, and is, for example, the following text data.
Text data = "XXenki onegai"
In the text data, "XX" indicates a voice section determined to be unconvertible to text data, or an utterance section converted into converted text having a reliability of less than or equal to a default threshold.

(Step S02)
Next, in step S02, the voice analysis unit of the information processing apparatus 10 further executes an utterance semantic analysis process based on the text data = "XXenki one gei" generated in step S01.

The voice analysis unit of the information processing device 10 performs analysis processing of text data = "XXenki onegai" and this text.
The voice analysis unit has a speech meaning analysis function. For example, it has a natural language understanding function such as NLU (Natural Language Understanding), and estimates the intention of the user's utterance (Intent) and the meaningful significant element (slot) included in the utterance from the text data. Execute the process.
Specifically, for example, the analysis of the user's intention based on the text data is executed by using a corpus or the like in which various utterance sentence examples are recorded together with the syntactic analysis data.

If the intention (entity) and the significant element (slot) can be accurately estimated and acquired from the user utterance, the information processing apparatus 10 accurately interprets the user utterance and processes a response or the like based on the interpretation result. It can be performed.

However, the text data = "XXenki onegai" generated in step S01 includes a voice section determined to be unconvertible to text data, or an utterance section converted to converted text having a reliability equal to or lower than the default threshold value. ..
In such a case, the voice analysis unit of the information processing apparatus 10 generates a plurality of user utterance candidates based on the text data = "XXenki onegai".

Specifically, the user utterance candidates a and b shown in FIG. 2 and these user utterance candidates. That is,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
The voice analysis unit of the information processing device 10 generates these two user utterance candidates.

(Step S03)
Next, in step S03, the information processing device 10 selects one user utterance candidate to be the response target from the plurality of user utterance candidates based on the context (situation information).

This process is executed by the context analysis unit of the information processing apparatus 10.
The context analysis unit of the information processing device 10 first receives observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device 10, information displayed on the display unit 13, and external information via the communication unit. Information obtained from a server or the like, that is, the context (situation information) 23 shown in FIG. 2 is acquired and analyzed, and the current type of context is determined.

The type of context is, for example,
(A) While user 1 is executing a schedule search,
(B) While the information processing device 10 is providing weather information to the user 1,
(C) It is detected that the user has returned home and the smart lock of the house has been released.
There are various types of contexts like this.

Various context types are registered in advance in the context information database 18, and in the context analysis unit of the information processing apparatus 10, the context (situation information) 23 acquired via the camera 11 or the like is registered in the context information database 18. Performs processing to determine which context type corresponds to.

An example of stored data in the context information database 18 will be described with reference to FIG.
As shown in FIG. 3, the following data are recorded in association with each other in the context information database 18.
(A) Context ID
(B) Context type (c) Context-compatible main slot (significant element)

(A) The context ID is an identifier of the context type.
(B) The context type is the type of context. For example, as shown in FIG. 3, various context (situation information) types such as "schedule search", "map information provision", "schedule change processing", and "smart lock control detection" are registered.

The context analysis unit of the information processing apparatus 10 is based on the type of context (situation information) registered in the context information database 18, real-time observation information obtained from the camera 11 or the like shown in FIG. 2, that is, the context (situation information). ) 23 determines which context type corresponds to.

(C) The context-compatible main slot (significant element) is the main slot corresponding to the context type registered in (b), specifically, the user referred to when the information processing apparatus 10 performs response processing to the user's utterance. This is the area where the main slots in the utterance are recorded.
As described above, the slot is a meaningful and significant element included in the user's utterance.

In the example shown in FIG. 3, for example
(B) When the context type = "schedule search"
(C) As the main context-compatible slots (significant elements), "Search, October, × day, morning, afternoon, ..."
These slots (user utterance words) are registered.

For example, when the information processing device 10 inputs a user utterance and executes a response process corresponding to the input user utterance while the user is performing a "schedule search", the user referred to for determining the processing content. The main slots (significant elements) in the utterance are "Search, October, X-day, morning, afternoon, ..." registered as the main context-compatible slots (significant elements), these slots.

Further, in the example shown in FIG. 3, for example,
(B) When the context type = "Map information provision"
(C) As the main context-compatible slots (significant elements), "Nearby, 〇m, station, directions, ..."
These slots (user utterance words) are registered.

For example, when the information processing device 10 is performing "map information provision" to the user 1, the information processing device 10 inputs a user utterance and executes a response process corresponding to the input user utterance. The main slots (significant elements) in the user utterance referred to to determine the processing content are registered as context-compatible main slots (significant elements), "near, 〇m, station, directions, ...", these It becomes a slot of.

In this way, various context types for which IDs (identifiers) have been set are registered in the context information database 18, and "(c) context-compatible main slots (significant elements)" corresponding to each context type are registered. Has been done.
(C) The main slot corresponding to the context (significant element) is (b) the main slot corresponding to the context type, specifically, the main slot in the user utterance referred to when the information processing apparatus 10 performs response processing to the user utterance. This is the area where the slot is recorded.

In step S03, the context analysis unit of the information processing device 10 first obtains information from the camera 11, microphone 12, and sensor 15 of the information processing device 10, information displayed on the display unit 13, and an external server via the communication unit. It is determined which context type the real-time observation information obtained from the above, that is, the context (situation information) 23 corresponds to.
In this context type determination, the context information database 18 described with reference to FIG. 3 is used.

Further, the context analysis unit of the information processing apparatus 10 acquires the context type of the context (situation information) 23 and the distance value between various other context types as the latter half of the process of step S03.

As described with reference to FIG. 3, various context types are recorded together with IDs in the context information database 18.
These various context types include a mixture of context types that are highly similar or highly related to each other and context types that are less similar or related to each other.

The distance value between context types with high mutual similarity and relevance is small, and the distance value between context types with low mutual similarity and relevance is large.
The table in which the distance values between each of these context types are registered is the inter-context distance table 19.

An example of the recorded data configuration of the inter-context distance table 19 will be described with reference to FIG.
As shown in FIG. 4, the inter-context distance table 19 is a table in which distance values between two context types are recorded.

for example,
The distance values between the context ID = 001 (schedule search) and each context (ID = 001,002,003 ...) Are as follows.
Distance value between 001 (schedule search) and 001 (schedule search) = 0
Distance value between 001 (schedule search) and 002 (map information provided) = 4
Distance value between 001 (schedule search) and 003 (schedule change processing) = 2
Distance value between 001 (schedule search) and 004 (weather information provided) = 3
・ ・ ・ ・ ・ ・ ・

As described above, the distance value between the two context types (IDs) is recorded in the inter-context distance table 19.
The smaller the value of the distance value between the two context types (ID), the higher the similarity and relevance of the two context types.
On the other hand, the larger the value of the distance value between the two context types (ID), the lower the similarity and relevance of the two context types.

In step S03 shown in FIG. 2, the context analysis unit of the information processing device 10 first obtains information from the camera 11, microphone 12, and sensor 15 of the information processing device, information displayed on the display unit 13, and a communication unit. Various contexts (status information) 23 such as information obtained from an external server or the like are acquired via the above.

Next, the context type of the acquired context (situation information) 23 is determined based on the context information database 18 described with reference to FIG.
Next, the distance values between the acquired context type (status information) 23 and the other context types are acquired from the inter-context distance table 19 described with reference to FIG.

Next, the context analysis unit of the information processing apparatus 10 selects a context type that includes a slot that is the same as or has a high degree of similarity to the slot (significant element) included in the user utterance candidate as the context-corresponding main slot.
This process is executed with reference to the context information database 18 described with reference to FIG.

Next, the context type having the smallest distance value is selected from the context types including the slots having the same or high similarity as the slots (significant elements) included in the user utterance candidates as the context-compatible main slots.

That is, the distance value from the context type of the context (situation information) 23 acquired via the camera 11 or the like is the largest among the context types including the slots (significant elements) included in the user utterance candidates as the context-compatible main slots. Select one small context type.

The information processing apparatus 10 finally executes response processing for a user utterance candidate including a slot (significant element) that is the same as or has a high degree of similarity to the context-compatible main slot of one finally selected context type. Select as one user utterance.

An example of user utterance candidate selection processing based on a specific acquisition context will be described later with reference to FIG. 5 and below.

In step S03 shown in FIG. 2, the information processing apparatus 10 is a user utterance candidate to be one response processing target from a plurality of user utterance candidates based on the context (situation information) 23 acquired from the observation information of the camera 11 or the like. When the process of selecting is completed, the process proceeds to step S04.

(Step S04)
Finally, in step S04, the information processing device 10 executes a response or process corresponding to one user utterance candidate selected by the context analysis unit of the information processing device 10 in step S03.

In this example,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
One of these two user utterance candidates is selected based on the context, and the process corresponding to the selected user utterance candidate is executed.

For example, when the user utterance candidate a = "weather, please" is selected, the information processing device 10 acquires the weather information from an external server or the like and notifies the user 1. Specifically, the weather information is output as voice information via the microphone 12, and processing such as showing a weather map on the display unit 13 is performed.

On the other hand, for example, when the user utterance candidate b = "electricity, please" is selected, the information processing device 10 performs processing such as executing ON / OFF control of the electric switch in the room.

[3. Specific example of user utterance selection processing based on context analysis]
Next, a specific example of the user utterance selection process based on the context analysis executed by the information processing apparatus 10 of the present disclosure will be described.

Hereinafter, with reference to FIGS. 5 to 8, the same user utterance as described above with reference to FIG. 2, that is, the same user utterance, that is,
User utterance = "** Nki, please"
The information processing device 10 inputs a user utterance including the above-mentioned unclear utterance portion (**), and as a result of voice analysis by the voice analysis unit,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
A specific example of the user utterance selection process based on the context analysis when these two user utterance candidates are generated will be described.

The following two processing examples will be described below.
(Processing example 1) As a result of user utterance selection based on context analysis,
User utterance candidate a = "Weather, please"
Processing sequence when this user utterance candidate a is selected

(Processing example 2) As a result of user utterance selection based on context analysis,
User utterance candidate b = "Electricity, please"
Processing sequence when this user utterance candidate b is selected

(3-1 (Processing example 1) Processing sequence when user utterance candidate a = "weather, please" is selected based on context analysis)
First, with reference to FIGS. 5 and 6, a processing sequence when the user utterance candidate a = "weather, please" is selected based on the context analysis will be described.

FIG. 5 shows the result of user utterance selection based on context analysis.
User utterance candidate a = "Weather, please"
It is a figure explaining the specific example of the processing sequence when this user utterance candidate a is selected.

The processes of (step S03) and (step S04) shown in FIG. 5 correspond to the processes of (step S03) and (step S04) described with reference to FIG.
Specific processing of these processing steps will be described.

(Step S03)
In step S03, the information processing device 10 selects one user utterance candidate to be targeted for response processing from a plurality of user utterance candidates based on the context (situation information).

The example shown in FIG. 5 is a processing example when the user utterance candidate a = "weather, please" is selected.

In step S03, the context analysis unit of the information processing device 10 includes observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device, information displayed on the display unit 13, and external information via the communication unit. Various contexts (status information) 23 such as information obtained from the server of the above are acquired, and the processes of steps S03a to S03d shown in FIG. 5 are executed.
These processing steps will be described.

(Step S03a)
First, in step S03a, the context analysis unit of the information processing apparatus 10 determines the context type of the context (situation information) 23 acquired from the observation information of the camera 11 or the like.

This context type determination process is executed with reference to the context information database 18 described with reference to FIG.

(Step S03b)
Next, in step S03b, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type of the acquired context (situation information) 23 and various other context types.

This inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 described with reference to FIG.

(Step S03c)
Next, in step S03c, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.

(Step S03d)
Next, in step S03d, the context analysis unit of the information processing apparatus 10 selects a user utterance candidate including the same or similar slot as the main slot of the context type selected in step S03c as the response processing target user utterance.
In this example, the user utterance candidate a "weather request" is selected as the response processing target user utterance.

Specific examples of the processes in steps S03a to 03d will be described with reference to FIG.
The process shown in FIG. 6 (steps S01 to S02) corresponds to the process of (steps S01 to S02) described above with reference to FIG. 2, and is a voice analysis process of user utterance.
The information processing device 10 inputs the user's utterance, and as a result of voice analysis by the voice analysis unit,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
It shows that these two user utterance candidates have been generated.

FIG. 6 shows the details of the processes of steps S03a to S03d described with reference to FIG.
The processing example shown in FIG. 6 is a processing example in which the user utterance candidate a "weather request" is selected as the response processing target user utterance by the context analysis processing.
Hereinafter, specific examples of the processes of steps S03a to S03d described with reference to FIG. 5 will be described with reference to FIG.

(Step S03a)
In step S03a, the context analysis unit of the information processing device 10 includes observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device, information displayed on the display unit 13, and external information via the communication unit. Various contexts (status information) 23 such as information obtained from the server of the above are acquired, and the context type of the acquired context is determined.

That is, it is determined which of the (b) context types registered in the context information database 18 described with reference to FIG. 3 the context (situation information) 23 obtained from the camera 11 or the like of the information processing device corresponds to. ..

As a result of this analysis processing, in this processing example, as shown at the tip of the arrow in FIG. 6 (S03a), the context type of the acquired context (situation information) 23 is
Context type = 001 (schedule search)
Is determined to be.

(Step S03b)
Next, in step S03b, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type (ID = 001) of the acquired context (situation information) 23 and various other context types.

This inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 described with reference to FIG.

FIG. 6 shows the context types of the acquired context (situation information) 23, that is,
The distance value between the context type = 001 (schedule search) and the plurality of context types (001,002,003,004,012) registered in the context information database 18 shown in FIG. 3 is shown.

Distance value between 001 (schedule search) and 001 (schedule search) = 0
Distance value between 001 (schedule search) and 002 (map information provided) = 4
Distance value between 001 (schedule search) and 003 (schedule change processing) = 2
Distance value between 001 (schedule search) and 004 (weather information provided) = 3
Distance value between 001 (schedule search) and 012 (smart lock control detection) = 12
These distance values are distance values obtained from the inter-context distance table 19 shown in FIG.

(Step S03c)
Next, in step S03c, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.

For this process, the registration data of the context information database 18 described above with reference to FIG. 3 and the registration data of the context distance table 19 described with reference to FIG. 4 are used.

First, the context analysis unit of the information processing apparatus 10 acquires slots (significant elements) included in the user utterance candidates.
The user utterance candidates are the following two candidates.
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"

The slots (significant elements) included in the user utterance candidate a = "weather, please" are "weather" and "request".
Further, the slots (significant elements) included in the user utterance candidate b = "electricity, please" are "electricity" and "request".

The context analysis unit of the information processing apparatus 10 then refers to the context information database 18 described with reference to FIG.
(C) As a context-compatible main slot (significant element)
Select a context type that includes the same slot (significant element) as the slot (significant element) included in the above user utterance candidate.

In this example, the slots (significant elements) acquired from the user utterance candidates a and b are "weather", "request", "electricity", and "request".
The same slot (significant element) as the slot (significant element) included in the above user utterance candidate is included in the context information database 18 shown in FIG.
(C) Context-enabled major slots (significant elements)
Select the context type registered in.

"Weather" is included in the main slot of "context type = 004 (weather information provision)" of the context information database 18 shown in FIG.
Further, "electricity" is included in the main slot of "context type = 012 (smart lock control detection)" of the context information database 18 shown in FIG.

Thus, in the example shown in FIG. 3,
Slots (significant elements) acquired from user utterance candidates a and b,
Slot (significant element) = "weather"
This slot (significant element)
Context type = 004 (weather information provided)
(C) It is registered as a context-compatible main slot (significant element).

In addition, the slots (significant elements) acquired from the user utterance candidates a and b,
Slot (significant element) = "electricity"
This slot (significant element)
Context type = 012 (smart lock control detection)
(C) It is registered as a context-compatible main slot (significant element).

Thus, in this processing example,
Slots (significant elements) included in user utterance candidates = "weather", "request", "electricity", "request"
The context type that contains these slots (significant elements) is
Context type = 004 (weather information provided)
Context type = 012 (smart lock control detection)
These two context types.

The context analysis unit of the information processing apparatus 10 has these two context types, that is,
Context type = 004 (weather information provided)
Context type = 012 (smart lock control detection)
From these two context types, the context type having the smallest distance value from the context type of the acquired context (situation information) 23 is selected.

As shown in FIG.
Distance value between 001 (schedule search) and 004 (weather information provided) = 3
Distance value between 001 (schedule search) and 012 (smart lock control detection) = 12
Is.

The context analysis unit of the information processing apparatus 10 sets the context type having the smallest distance value from the context type of the acquired context (situation information) 23 as the context type.
Context type = 004 (weather information provided)
Select this context type.

This process is executed with reference to the context information database 18 described with reference to FIG. 3 and the inter-context distance table 19 described with reference to FIG.

As described above, in step S03c, the context analysis unit of the information processing apparatus 10 includes the same or similar slot as the slot in the user utterance candidate as the main slot, and the context of the context type acquisition context (situation information) 23 having the minimum distance value. As the context type with the shortest distance to the type,
Context type = 004 (weather information provided)
Select.

(Step S03d)
Finally, in step S03d, the context analysis unit of the information processing apparatus 10 determines the context type selected in step S03c, that is,
Context type = 004 (weather information provided)
A user utterance candidate including the same or similar slot as the main slot of this context type (004 (weather information provision)) is selected as the response processing target user utterance.

The main slots of the context type = 004 (weather information provision) are recorded in the context information database 18 shown in FIG.
As shown in FIG. 3, the main slots of the context type = 004 (weather information provision) include "weather", "precipitation probability", "sunny", "rain", "○ station", and so on. Is included and the "weather" is
User utterance candidate a = Matches the slot "weather" of "weather, please".
As a result, the context analysis unit of the information processing apparatus 10 in step S03d
User utterance candidate a = "Weather, please"
The user utterance candidate a is selected as the user utterance candidate for which the information processing apparatus 10 should execute the corresponding processing.

Thus, in this processing example,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
When these two user utterance candidates are generated, the context analysis unit of the information processing apparatus 10 performs the processes of steps S03a to 03d to perform the processes.
User utterance candidate a = "Weather, please"
This one user utterance candidate is selected as the user utterance for which response processing should be executed.

As described above, the context analysis unit of the information processing apparatus 10 executes the processes of steps S03a to S03d described with reference to FIG. 6, and is one of the plurality of user utterance candidates based on the acquired context (situation information). Performs a process of selecting a user utterance candidate as a response target.
When this process is completed, the process proceeds to step S04 shown in FIG.

(Step S04)
The process of step S04 shown in FIG. 5 will be described.
Finally, in step S04, the information processing device 10 executes a response or process corresponding to one user utterance candidate selected by the context analysis unit of the information processing device 10 in step S03.

In this example,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
From these two user utterance candidates, in step S03,
User utterance candidate a = "Weather, please"
This one user utterance candidate is selected based on the context.

In this way, when the user utterance candidate a = "weather, please" is selected, the information processing apparatus 10 acquires weather information from, for example, an external server, and notifies the user 1 in step S04. Specifically, the weather information is output as voice information via the microphone 12, and processing such as showing a weather map on the display unit 13 is performed.

(3-2 (Processing example 2) Processing sequence when user utterance candidate b = "electricity, please" is selected based on context analysis)
Next, with reference to FIGS. 7 and 8, a processing sequence when the user utterance candidate b = “electricity, please” is selected based on the context analysis will be described.

FIG. 7 shows the result of user utterance selection based on context analysis.
User utterance candidate b = "Electricity, please"
It is a figure explaining the specific example of the processing sequence when this user utterance candidate b is selected.

The processes of (step S03) and (step S04) shown in FIG. 7 correspond to the processes of (step S03) and (step S04) described with reference to FIG.
Specific processing of these processing steps will be described.

(Step S03)
In step S03, the information processing device 10 selects one user utterance candidate to be targeted for response processing from a plurality of user utterance candidates based on the context (situation information).

The example shown in FIG. 7 is a processing example when the user utterance candidate b = "electricity, please" is selected.

In step S03, the context analysis unit of the information processing device 10 includes observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device, information displayed on the display unit 13, and external information via the communication unit. Various contexts (status information) 23 such as information obtained from the server of the above are acquired, and the processes of steps S03a to S03d shown in FIG. 7 are executed.
These processing steps will be described.

(Step S03a)
First, in step S03a, the context analysis unit of the information processing apparatus 10 determines the context type of the context (situation information) 23 acquired from the observation information of the camera 11 or the like.

This context type determination process is executed with reference to the context information database 18 described with reference to FIG.

(Step S03b)
Next, in step S03b, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type of the acquired context (situation information) 23 and various other context types.

This inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 described with reference to FIG.

(Step S03c)
Next, in step S03c, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.

(Step S03d)
Next, in step S03d, the context analysis unit of the information processing apparatus 10 selects a user utterance candidate including the same or similar slot as the main slot of the context type selected in step S03c as the response processing target user utterance.
In this example, the user utterance candidate b "electricity request" is selected as the response processing target user utterance.

Specific examples of the processes of steps S03a to 03d will be described with reference to FIG.
The process shown in FIG. 8 (steps S01 to S02) corresponds to the process of (steps S01 to S02) described above with reference to FIG. 2, and is a voice analysis process of user utterance.
The information processing device 10 inputs the user's utterance, and as a result of voice analysis by the voice analysis unit,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
It shows that these two user utterance candidates have been generated.

FIG. 8 shows the details of the processes of steps S03a to S03d described with reference to FIG.

The processing example shown in FIG. 8 is a processing example in which the user utterance candidate b “electrical request” is selected as the response processing target user utterance by the context analysis processing.
Hereinafter, specific examples of the processes of steps S03a to S03d described with reference to FIG. 7 will be described with reference to FIG.

(Step S03a)
In step S03a, the context analysis unit of the information processing device 10 includes observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device, information displayed on the display unit 13, and external information via the communication unit. Various contexts (status information) 23 such as information obtained from the server of the above are acquired, and the context type of the acquired context is determined.

That is, it is determined which of the (b) context types registered in the context information database 18 described with reference to FIG. 3 the context (situation information) 23 obtained from the camera 11 or the like of the information processing device corresponds to. ..

As a result of this analysis processing, in this processing example, as shown at the tip of the arrow in FIG. 8 (S03a), the context type of the acquired context (situation information) 23 is
Context type = 012 (smart lock control detection)
Is determined to be.

(Step S03b)
Next, in step S03b, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type (ID = 012) of the acquired context (situation information) 23 and various other context types.

This inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 described with reference to FIG.

FIG. 8 shows the context types of the acquired context (situation information) 23, that is,
The distance value between the context type = 012 (smart lock control detection) and the plurality of context types (001,002,003,004,012) registered in the context information database 18 shown in FIG. 3 is shown.

Distance value between 012 (smart lock control detection) and 001 (schedule search) = 12
Distance value between 012 (smart lock control detection) and 002 (map information provision) = 13
Distance value between 012 (smart lock control detection) and 003 (schedule change processing) = 11
Distance value between 012 (smart lock control detection) and 004 (weather information provided) = 10
Distance value between 012 (smart lock control detection) and 012 (smart lock control detection) = 0
These distance values are distance values obtained from the inter-context distance table 19 shown in FIG.

(Step S03c)
Next, in step S03c, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.

For this process, the registration data of the context information database 18 described above with reference to FIG. 3 and the registration data of the context distance table 19 described with reference to FIG. 4 are used.

First, the context analysis unit of the information processing apparatus 10 acquires slots (significant elements) included in the user utterance candidates.
The user utterance candidates are the following two candidates.
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"

The slots (significant elements) included in the user utterance candidate a = "weather, please" are "weather" and "request".
Further, the slots (significant elements) included in the user utterance candidate b = "electricity, please" are "electricity" and "request".

The context analysis unit of the information processing apparatus 10 then refers to the context information database 18 described with reference to FIG.
(C) As a context-compatible main slot (significant element)
Select a context type that includes the same slot (significant element) as the slot (significant element) included in the above user utterance candidate.

In this example, the slots (significant elements) acquired from the user utterance candidates a and b are "weather", "request", "electricity", and "request".
In the context analysis unit of the information processing device 10, a slot (significant element) that is the same as or similar to at least one of the slots (significant element) included in the user utterance candidate is described in the context information database 18 shown in FIG.
(C) Context-enabled major slots (significant elements)
Select the context type registered in.

"Weather" is included in the main slot of "context type = 004 (weather information provision)" of the context information database 18 shown in FIG.
Further, "electricity" is included in the main slot of "context type = 012 (smart lock control detection)" of the context information database 18 shown in FIG.

Thus, in the example shown in FIG. 3,
Slots (significant elements) acquired from user utterance candidates a and b,
Slot (significant element) = "weather"
This slot (significant element)
Context type = 004 (weather information provided)
(C) It is registered as a context-compatible main slot (significant element).

In addition, the slots (significant elements) acquired from the user utterance candidates a and b,
Slot (significant element) = "electricity"
This slot (significant element)
Context type = 012 (smart lock control detection)
(C) It is registered as a context-compatible main slot (significant element).

Thus, in this processing example,
Slots (significant elements) included in user utterance candidates = The context type in which at least one of "weather", "request", "electricity", and "request" is registered as the main slot corresponding to the context type is
Context type = 004 (weather information provided)
Context type = 012 (smart lock control detection)
These two context types.

The context analysis unit of the information processing apparatus 10 has these two context types, that is,
Context type = 004 (weather information provided)
Context type = 012 (smart lock control detection)
From these two context types, the context type having the smallest distance value from the context type of the acquired context (situation information) 23 is selected.

As shown in FIG.
Distance value between 012 (smart lock control detection) and 004 (weather information provided) = 10
Distance value between 012 (smart lock control detection) and 012 (smart lock control detection) = 0
Is.

The context analysis unit of the information processing apparatus 10 sets the context type having the smallest distance value from the context type of the acquired context (situation information) 23 as the context type.
Context type = 012 (smart lock control detection)
Select this context type.

This process is executed with reference to the context information database 18 described with reference to FIG. 3 and the inter-context distance table 19 described with reference to FIG.

As described above, in step S03c, the context analysis unit of the information processing apparatus 10 includes the same or similar slot as the slot in the user utterance candidate as the main slot, and the context of the context type acquisition context (situation information) 23 having the minimum distance value. As the context type with the shortest distance to the type,
Context type = 012 (smart lock control detection)
Select.

(Step S03d)
Finally, in step S03d, the context analysis unit of the information processing apparatus 10 determines the context type selected in step S03c, that is,
Context type = 012 (smart lock control detection)
A user utterance candidate including the same or similar slot as the main slot of this context type (012 (smart lock control detection)) is selected as the response processing target user utterance.

The main slot of the context type = 012 (smart lock control detection) is recorded in the context information database 18 shown in FIG.
As shown in FIG. 3, in the main slots of the context type = 012 (smart lock control detection), "electricity", "turn on", "turn off", "dark", "bright" ... Includes slots, "electricity",
User utterance candidate b = Matches the slot "electricity" of "electricity, please".
As a result, the context analysis unit of the information processing apparatus 10 in step S03d
User utterance candidate b = "Electricity, please"
The user utterance candidate b is selected as the user utterance candidate for which the information processing apparatus 10 should execute the corresponding processing.

Thus, in this processing example,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
When these two user utterance candidates are generated, the context analysis unit of the information processing apparatus 10 performs the processes of steps S03a to 03d to perform the processes.
User utterance candidate b = "Electricity, please"
This one user utterance candidate is selected as the user utterance for which response processing should be executed.

In this way, the context analysis unit of the information processing apparatus 10 executes the processes of steps S03a to S03d described with reference to FIG. 8, and based on the acquired context (situation information), one from a plurality of user utterance candidates. Performs a process of selecting a user utterance candidate as a response target.
When this process is completed, the process proceeds to step S04 shown in FIG.

(Step S04)
The process of step S04 shown in FIG. 7 will be described.
Finally, in step S04, the information processing device 10 executes a response or process corresponding to one user utterance candidate selected by the context analysis unit of the information processing device 10 in step S03.

In this example,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
From these two user utterance candidates, in step S03,
User utterance candidate b = "Electricity, please"
This one user utterance candidate is selected based on the context.

In this way, when the user utterance candidate b = "electricity, please" is selected, the information processing apparatus 10 performs processing such as executing ON / OFF control of the electric switch in the room in step S04.

[4. Specific example of user utterance selection processing based on context analysis when there are many user utterance candidates]
Next, a specific example of the user utterance selection process based on the context analysis when there are many user utterance candidates will be described.

The processing examples described with reference to FIGS. 2 and 5 to 8 are processing examples when there are two user utterance candidates.
The information processing device 10 of the present disclosure selects one user utterance to be supported by the information processing device 10 based on the context analysis not only when there are two user utterance candidates but also when there are a large number of three or more user utterance candidates. can do.

Hereinafter, an example of user utterance selection processing based on context analysis when there are three user utterance candidates will be described with reference to FIGS. 9 and 10.

In FIGS. 9 and 10, the information processing device 10 inputs the user's utterance, and as a result of voice analysis by the voice analysis unit,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
User utterance candidate c = "Postponed, please"
These three user utterance candidates are generated, and as a result of user utterance selection based on context analysis,
User utterance candidate c = "Postponed, please"
It is a figure explaining the specific example of the processing sequence when this user utterance candidate c is selected.

The processes of (step S03) and (step S04) shown in FIG. 9 correspond to the processes of (step S03) and (step S04) described with reference to FIG.
Specific processing of these processing steps will be described.

(Step S03)
In step S03, the information processing device 10 selects one response target user utterance candidate corresponding to the information processing device 10 from a plurality of user utterance candidates based on the context (situation information).

The example shown in FIG. 9 is a processing example when the user utterance candidate c = "postponement, please" is selected.

In step S03, the context analysis unit of the information processing device 10 includes observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device, information displayed on the display unit 13, and external information via the communication unit. Various contexts (status information) 23 such as information obtained from the server of the above are acquired, and the processes of steps S03a to S03d shown in FIG. 7 are executed.
These processing steps will be described.

(Step S03a)
First, in step S03a, the context analysis unit of the information processing apparatus 10 determines the context type of the context (situation information) 23 acquired from the observation information of the camera 11 or the like.

This context type determination process is executed with reference to the context information database 18 described with reference to FIG.

(Step S03b)
Next, in step S03b, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type of the acquired context (situation information) 23 and various other context types.

This inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 described with reference to FIG.

(Step S03c)
Next, in step S03c, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.

(Step S03d)
Next, in step S03d, the context analysis unit of the information processing device 10 selects a user utterance candidate including a slot that is the same as or similar to the main slot of the context type selected in step S03c, and the response target user utterance corresponding to the information processing device 10. Select as.
In this example, the user utterance candidate c = "postponement, please" is selected as the response target user utterance corresponding to the information processing apparatus 10.

Specific examples of the processes in steps S03a to 03d will be described with reference to FIG.
The process shown in FIG. 10 (steps S01 to S02) corresponds to the process of (steps S01 to S02) described above with reference to FIG. 2, and is a voice analysis process of user utterance.
The information processing device 10 inputs the user's utterance, and as a result of voice analysis by the voice analysis unit,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
User utterance candidate c = "Postponed, please"
It shows that these three user utterance candidates have been generated.

FIG. 10 shows the details of the processes of steps S03a to S03d described with reference to FIG.

The processing example shown in FIG. 10 is a processing example in which the user utterance candidate c "postponement request" is selected as the corresponding response target user utterance by the information processing apparatus 10 by the context analysis processing.
Hereinafter, specific examples of the processes of steps S03a to S03d described with reference to FIG. 9 will be described with reference to FIG.

(Step S03a)
In step S03a, the context analysis unit of the information processing device 10 includes observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device, information displayed on the display unit 13, and external information via the communication unit. Various contexts (status information) 23 such as information obtained from the server of the above are acquired, and the context type of the acquired context is determined.

That is, it is determined which of the (b) context types registered in the context information database 18 described with reference to FIG. 3 the context (situation information) 23 obtained from the camera 11 or the like of the information processing device corresponds to. ..

As a result of this analysis processing, in this processing example, as shown at the tip of the arrow in FIG. 10 (S03a), the context type of the acquired context (situation information) 23 is
Context type = 001 (schedule search)
Is determined to be.

(Step S03b)
Next, in step S03b, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type (ID = 001) of the acquired context (situation information) 23 and various other context types.

This inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 described with reference to FIG.

In FIG. 10, the context type of the acquired context (situation information) 23, that is,
The distance value between the context type = 001 (schedule search) and the plurality of context types (001,002,003,004,012) registered in the context information database 18 shown in FIG. 3 is shown.

Distance value between 001 (schedule search) and 001 (schedule search) = 0
Distance value between 001 (schedule search) and 002 (map information provided) = 4
Distance value between 001 (schedule search) and 003 (schedule change processing) = 2
Distance value between 001 (schedule search) and 004 (weather information provided) = 3
Distance value between 001 (schedule search) and 012 (smart lock control detection) = 12
These distance values are distance values obtained from the inter-context distance table 19 shown in FIG.

(Step S03c)
Next, in step S03c, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.

For this process, the registration data of the context information database 18 described above with reference to FIG. 3 and the registration data of the context distance table 19 described with reference to FIG. 4 are used.

First, the context analysis unit of the information processing apparatus 10 acquires slots (significant elements) included in the user utterance candidates.
The user utterance candidates are the following three candidates.
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
User utterance candidate c = "Postponed, please"

The slots (significant elements) included in the user utterance candidate a = "weather, please" are "weather" and "request".
Further, the slots (significant elements) included in the user utterance candidate b = "electricity, please" are "electricity" and "request".
Further, the slots (significant elements) included in the user utterance candidate c = "postponement, please" are "postponement" and "request".

The context analysis unit of the information processing apparatus 10 then refers to the context information database 18 described with reference to FIG.
(C) As a context-compatible main slot (significant element)
Select a context type that includes the same slot (significant element) as the slot (significant element) included in the above user utterance candidate.

In this example, the slots (significant elements) acquired from the user utterance candidates a and b are "weather", "request", "electricity", "request", "postponement", and "request".
The same slot (significant element) as the slot (significant element) included in the above user utterance candidate is included in the context information database 18 shown in FIG.
(C) Context-enabled major slots (significant elements)
Select the context type registered in.

"Weather" is included in the main slot of "context type = 004 (weather information provision)" of the context information database 18 shown in FIG.
Further, "electricity" is included in the main slot of "context type = 012 (smart lock control detection)" of the context information database 18 shown in FIG.
Further, the main slot of "context type = 003 (schedule change processing)" of the context information database 18 shown in FIG. 3 includes "postponement".

in this way,
In the example shown in FIG.
Slots (significant elements) acquired from user utterance candidates a, b, c,
Slot (significant element) = "weather"
This slot (significant element)
Context type = 004 (weather information provided)
(C) It is registered as a context-compatible main slot (significant element).

Further, it is a slot (significant element) acquired from user utterance candidates a, b, and c.
Slot (significant element) = "electricity"
This slot (significant element)
Context type = 012 (smart lock control detection)
(C) It is registered as a context-compatible main slot (significant element).

Further, it is a slot (significant element) acquired from user utterance candidates a, b, and c.
Slot (significant factor) = "postponed"
This slot (significant element)
Context type = 003 (schedule change process)
(C) It is registered as a context-compatible main slot (significant element).

Thus, in this processing example,
Slots (significant elements) included in user utterance candidates = "weather", "request", "electricity", "request", "postponement", "request"
The context type that contains these slots (significant elements) is
Context type = 003 (schedule change process)
Context type = 004 (weather information provided)
Context type = 012 (smart lock control detection)
These three context types.

The context analysis unit of the information processing apparatus 10 has these three context types, that is,
Context type = 003 (schedule change process)
Context type = 004 (weather information provided)
Context type = 012 (smart lock control detection)
From these two context types, the context type having the smallest distance value from the context type of the acquired context (situation information) 23 is selected.

As shown in FIG.
Distance value between 001 (schedule search) and 003 (schedule change processing) = 2
Distance value between 001 (schedule search) and 004 (weather information provided) = 3
Distance value between 001 (schedule search) and 012 (smart lock control detection) = 12
Is.

The context analysis unit of the information processing apparatus 10 sets the context type having the smallest distance value from the context type of the acquired context (situation information) 23 as the context type.
Context type = 003 (schedule change process)
Select this context type.

This process is executed with reference to the context information database 18 described with reference to FIG. 3 and the inter-context distance table 19 described with reference to FIG.

As described above, in step S03c, the context analysis unit of the information processing apparatus 10 includes the same or similar slot as the slot in the user utterance candidate as the main slot, and the context of the context type acquisition context (situation information) 23 having the minimum distance value. As the context type with the shortest distance to the type,
Context type = 003 (schedule change process)
Select.

(Step S03d)
Finally, in step S03d, the context analysis unit of the information processing apparatus 10 determines the context type selected in step S03c, that is,
Context type = 003 (schedule change process)
The information processing apparatus 10 selects a user utterance candidate including the same or similar slot as the main slot of the context type (003 (schedule change process)) as the corresponding response target user utterance.

The main slots of the context type = 003 (schedule change processing) are recorded in the context information database 18 shown in FIG.
As shown in FIG. 3, the main slots of the context type = 003 (schedule change processing) include "October", "x day", "am", ... "postponed" ..., these slots. Included, "Postponed",
User utterance candidate c = Matches the slot "postponement" of "postponement, please".
As a result, the context analysis unit of the information processing apparatus 10 in step S03d
User utterance candidate c = "Postponed, please"
The user utterance candidate c is selected as the user utterance candidate for which the information processing apparatus 10 should execute the corresponding processing.

Thus, in this processing example,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
User utterance candidate c = "Postponed, please"
When these three user utterance candidates are generated, the context analysis unit of the information processing apparatus 10 performs the processes of steps S03a to 03d to perform the processes.
User utterance candidate c = "Postponed, please"
This one user utterance candidate is selected by the information processing device 10 as the corresponding user utterance of the response target.

As described above, the context analysis unit of the information processing apparatus 10 executes the processes of steps S03a to S03d described with reference to FIG. 10, and is one of the plurality of user utterance candidates based on the acquired context (situation information). The information processing apparatus 10 performs a process of selecting a user utterance candidate as a corresponding response target.
When this process is completed, the process proceeds to step S04 shown in FIG.

(Step S04)
The process of step S04 shown in FIG. 9 will be described.
Finally, in step S04, the information processing device 10 executes a response or process corresponding to one user utterance candidate selected by the context analysis unit of the information processing device 10 in step S03.

In this example,
User utterance candidate a = "Weather, please"
User utterance candidate b = "Electricity, please"
User utterance candidate c = "Postponed, please"
From these three user utterance candidates, in step S03,
User utterance candidate c = "Postponed, please"
This one user utterance candidate is selected based on the context.

In this way, when the user utterance candidate c = "postponement, please" is selected, the information processing apparatus 10 executes the user's scheduled postponement processing in step S04.

[5. Sequence of processing executed by the information processing apparatus of the present disclosure]
Next, a sequence of processes executed by the information processing apparatus 10 of the present disclosure will be described.

The processing sequence executed by the information processing apparatus 10 of the present disclosure will be described with reference to the flowchart shown in FIG.
The process according to the flowchart shown in FIG. 11 is executed according to the program stored in the storage unit of the information processing apparatus 10. For example, it can be executed as a program execution process by a processor such as a CPU having a program execution function.
The processing of each step of the flow shown in FIG. 11 will be described.

(Step S101)
First, the information processing device 10 inputs the user's utterance in step S101.

The information processing device 10 inputs the user's utterance through the microphone 12 which is a voice input unit.

(Step S102)
Next, in step S102, the information processing device 10 executes a voice analysis process for the input user utterance.

The voice analysis unit of the information processing device 10 inputs the user-spoken voice input from the microphone 12, which is a voice input unit, into a voice recognition unit having an automatic voice recognition (ASR: Automatic Speech Recognition) function, and inputs the voice data to text data. Convert to.
Further, the voice analysis unit performs utterance semantic analysis processing of the generated text data. For example, by using a natural language understanding function such as NLU (Natural Language Understanding), the intention of the user's utterance (Intent) and the meaningful significant element (slot) included in the utterance can be obtained from the text data. Perform estimation processing.

If the intention (entity) and the significant element (slot) can be accurately estimated and acquired from the user utterance, the information processing apparatus 10 accurately interprets the user utterance and processes a response or the like based on the interpretation result. It can be performed.

(Step S103)
Next, in step S103, the information processing device 10 determines whether or not there is only one user utterance candidate obtained as the voice analysis result in step S102.

If the user utterance is clear, there is often only one user utterance candidate obtained as a voice analysis result. However, as described above, when the user utterance is unclear, the number of user utterance candidates obtained as the voice analysis result may be two or more.

If there is only one user utterance candidate obtained as the voice analysis result in step S102, the process proceeds to step S108.
On the other hand, if there are two or more user utterance candidates obtained as the voice analysis result in step S102, the process proceeds to step S104.

(Step S104)
If it is determined in step S103 that there are two or more user utterance candidates obtained as the voice analysis result in step S102, the processes of steps S104 to S107 are executed.

First, the information processing device 10 acquires the context (situation information) in step S104.
Observation information acquired from the camera 11, microphone 12, and sensor 15 of the information processing device 10, information displayed on the display unit 13, and information obtained from an external server or the like via the communication unit, that is, shown in FIG. The context (situation information) 23 is acquired, and the type of the acquired context is determined.

This context type determination process is executed with reference to the context information database 18 described with reference to FIG.

(Step S105)
Next, in step S105, the information processing apparatus 10 acquires a distance value between the context type of the context (situation information) 23 acquired in step S104 and various other context types.

This inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 described with reference to FIG.

(Step S106)
Next, in step S106, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.

(Step S107)
Next, in step S107, the context analysis unit of the information processing device 10 responds to the user utterance candidate including the same or similar slot as the main slot of the context type selected in step S106 by the information processing device 10. Select as an utterance.

The processes of steps S104 to S107 correspond to the processes of steps S03a to S03d described above with reference to FIGS. 5 to 10.

(Step S108)
In step S103, when it is determined that there is only one user utterance candidate obtained as the voice analysis result in step S102, or
On the other hand, it is determined that there are two or more user utterance candidates obtained as the voice analysis result in step S102, and one user utterance candidate is selected from a plurality of user utterance candidates based on the context analysis result in steps S104 to S107. Then, the process of step S108 is executed.

In step S108, the information processing device 10 executes a response or processing corresponding to one user utterance candidate.

As described above, the information processing apparatus 10 of the present disclosure is based on the context analysis even when a plurality of user utterance candidates are acquired as a voice analysis result for the user utterance because the user utterance is unclear. One of the most probable user utterance candidates according to the observation situation can be selected, and the information processing apparatus 10 can perform response processing, for example, response processing to the selected one user utterance candidate.

[6. (Example 2) Example of performing processing control using the distance between contexts]
Next, as Example 2, an example in which processing control using the inter-context distance is performed will be described.

As described above with reference to FIG. 4, the inter-context distance table 19 is a table in which the distance values between two contexts are recorded.
In the above-described embodiment, the user utterance estimation process is performed when the user utterance is unclear by referring to the distance value between the context types recorded in the inter-context distance table 19.
Hereinafter, as the second embodiment, an embodiment in which the information processing apparatus 10 controls the processing executed by the information processing apparatus 10 with reference to the distance values between the context types recorded in the inter-context distance table 19 will be described. ..

For example, the user 1 or the information processing device 10 determines the process currently being executed by context analysis, and the process to be executed next by the information processing device 10 is determined between the context types recorded in the inter-text distance table 19. The process of determining according to the distance value is performed.

By selecting another context type that has a small distance value from the context type that corresponds to the processing that is currently being executed, the processing efficiency that the information processing device 10 executes next is limited to these context types. It is intended to be converted.

A specific processing example of the second embodiment will be described with reference to FIG.
Each process of (step S51) to (step S53) shown in FIG. 12 will be described.

(Step S51)
First, in step S51, the information processing device inputs the user's utterance and executes the voice analysis process.
The information processing device 10 inputs the user's utterance, and as a result of voice analysis by the voice analysis unit,
One user utterance candidate = "Tell me a recommended restaurant in Shibuya"
It shows that this one user utterance candidate has been generated.

In this case, the data processing unit of the information processing device 10 starts the restaurant search process in the Shibuya area as a process based on the user's utterance, that is, a response process.

(Step S52)
Next, in step S52, the context analysis unit of the information processing device 10 obtains the observation information acquired from the camera 11, the microphone 12, and the sensor 15 of the information processing device, the information displayed on the display unit 13, and the communication unit. Acquire various contexts (status information) such as information obtained from an external server or the like via the system.

That is, the same context (situation information) as the context (situation information) 23 described with reference to FIG. 2 is acquired, and the context type of the acquired context is determined.
It is determined which of the (b) context types registered in the context information database 18 described with reference to FIG. 3 the context (situation information) obtained from the camera 11 or the like of the information processing apparatus corresponds to.

As a result of this analysis processing, in this processing example, as shown at the tip of the arrow in FIG. 12 (S52), the context type of the acquired context (situation information) 23 is
Context type = 001 (data search)
Is determined to be.

(Step S53)
Next, in step S53, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type (ID = 001) of the acquired context (situation information) and various other context types, and obtains a distance value. The context type whose value is equal to or less than the predetermined threshold value is determined as the next processing candidate.

The inter-text distance value acquisition process is executed with reference to the inter-context distance table 19.
A specific example of the inter-context distance table 19 used in the second embodiment is shown in FIG.

The inter-context distance table 19 shown in FIG. 13 is a table that stores distance values between context types, similar to the inter-context distance table 19 described above with reference to FIG. 4.
However, the context type registered in the inter-text distance table 19 shown in FIG. 13 is a context type having a finer particle size than the context type registered in the inter-text distance table 19 described with reference to FIG. 4 above.

As for the context types registered in the inter-text distance table 19 shown in FIG. 13, all the processing types related to the search processing are registered as the context types.
As shown in FIG.
ID = 001 (data search)
ID = 002 (specify search detailed conditions)
ID = 003 (change search genre)
ID = 004 (search result output)
ID = 005 (search narrowing down)
・ ・ ・
These are all processes related to data retrieval.

The information processing device 10 performs data processing according to these processes (context types). For example, the display data switching process of the display unit 13 and the communication process with the data search server are performed.
Since the processing executed by the information processing device 10 differs depending on the context type registered in the inter-context distance table 19, when the processing switching involving the transition between different processes is executed, the next processing is predicted and switched. Therefore, a faster processing transition can be performed.

The information processing apparatus 10 uses the inter-context distance table 19 shown in FIG. 13 in order to predict such a next processing candidate.
For example, in the example shown in FIG. 12, the current context type is
Context type = 001 (data search)
Is.

The information processing device 10 has a context type of the acquired context (situation information) 23, that is,
Obtain the distance value between the context type = 001 (data search) and a plurality of other context types, select only the context type whose distance value is less than or equal to the predetermined threshold value, and then select the selected context type. Determine the next processing candidate with a high probability of execution.

Based on this determination of the next processing candidate, the information processing apparatus 10 can start preparations for executing the processing that has become the next processing candidate in advance, and promptly responds when an actual processing transition occurs. It can be performed.

In the example shown in FIG. 12, the context type of the acquired context (situation information) 23, that is,
The distance values between the context type = 001 (data search) and a plurality of other context types are as follows.
Distance value between 001 (data search) and 002 (search detailed condition specification) = 1
Distance value between 001 (data search) and 003 (search genre change) = 2
Distance value between 001 (data search) and 004 (search result output) = 3
Distance value between 001 (data search) and 005 (search narrowing down) = 4
Distance value between 001 (data search) and 006 (SNS sharing of search results) = 5
Distance value between 001 (data search) and 007 (sort of search results) = 6
Distance value between 001 (data search) and 008 (enter search results in the schedule) = 7
These distance values are distance values obtained from the inter-context distance table 19 shown in FIG.

In step S53, the context analysis unit of the information processing apparatus 10 determines, for example, a threshold value of 3 and a context type having a distance threshold = 3 or less as a next processing candidate.

In the example shown in FIG. 12, the context type with the distance threshold value = 3 or less is set.
002 (Specify search detailed conditions)
003 (change search genre)
004 (search result output)
These three context types are selected.

The information processing device 10 predicts that these three selected context types are processes (next processing candidates) having a high probability of being executed next, and executes the processing that has become the next processing candidate based on this prediction. Start preparations in advance.
With these pre-processing, when an actual processing transition occurs, it is possible to take a prompt response.

A processing example involving an actual processing transition will be described with reference to FIGS. 14 and 15.
First, each process of (step S71) to (step S73) shown in FIG. 14 will be described.

(Step S71)
First, in step S71, the information processing device inputs the user's utterance and executes the voice analysis process.
The information processing device 10 inputs the user's utterance, and as a result of voice analysis by the voice analysis unit,
One user utterance candidate = "Tell me a French restaurant"
It shows that this one user utterance candidate has been generated.

In this case, the data processing unit of the information processing device 10 starts the French restaurant search process as a process based on the user's utterance, that is, a response process of the information processing device 10.

(Step S72)
Next, in step S72, the context analysis unit of the information processing device 10 obtains the observation information acquired from the camera 11, the microphone 12, and the sensor 15 of the information processing device, the information displayed on the display unit 13, and the communication unit. Acquire various contexts (status information) such as information obtained from an external server or the like via the system.

That is, the same context (situation information) as the context (situation information) 23 described with reference to FIG. 2 is acquired, and the context type of the acquired context is determined.
It is determined which of the (b) context types registered in the context information database 18 described with reference to FIG. 3 the context (situation information) obtained from the camera 11 or the like of the information processing apparatus corresponds to.

As a result of this analysis processing, in this processing example, as shown at the tip of the arrow in FIG. 14 (S72), the context type of the acquired context (situation information) 23 is
Context type = 001 (data search)
Is determined to be.

(Step S73)
Next, in step S73, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type (ID = 001) of the acquired context (situation information) and various other context types, and obtains a distance value. The context type whose value is equal to or less than the predetermined threshold value is determined as the next processing candidate.

The inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 shown in FIG.
For example, in the example shown in FIG. 14, the current context type is
Context type = 001 (data search)
Is.

The information processing device 10 has a context type of the acquired context (situation information) 23, that is,
Obtain the distance value between the context type = 001 (data search) and a plurality of other context types, select only the context type whose distance value is less than or equal to the predetermined threshold value, and then select the selected context type. Determine the next processing candidate with a high probability of execution.

Based on this determination of the next processing candidate, the information processing apparatus 10 can start preparations for executing the processing that has become the next processing candidate in advance, and promptly responds when an actual processing transition occurs. It can be performed.

In the example shown in FIG. 14, the context type of the acquired context (situation information) 23, that is,
The distance values between the context type = 001 (data search) and a plurality of other context types are as follows.
Distance value between 001 (data search) and 002 (search detailed condition specification) = 1
Distance value between 001 (data search) and 003 (search genre change) = 2
Distance value between 001 (data search) and 004 (search result output) = 3
Distance value between 001 (data search) and 005 (search narrowing down) = 4
Distance value between 001 (data search) and 006 (SNS sharing of search results) = 5
Distance value between 001 (data search) and 007 (sort of search results) = 6
Distance value between 001 (data search) and 008 (enter search results in the schedule) = 7
These distance values are distance values obtained from the inter-context distance table 19 shown in FIG.

In step S73, the context analysis unit of the information processing apparatus 10 determines, for example, a threshold value of 3 and a context type having a distance threshold = 3 or less as a next processing candidate.

In the example shown in FIG. 14, the context type with the distance threshold value = 3 or less is set.
002 (Specify search detailed conditions)
003 (change search genre)
004 (search result output)
These three context types are selected.

The information processing device 10 predicts that these three selected context types are processes (next processing candidates) having a high probability of being executed next, and executes the processing that has become the next processing candidate based on this prediction. Start preparations in advance.
With these pre-processing, when an actual processing transition occurs, it is possible to take a prompt response.

Next, by the processing of user 1, as an actual processing transition,
004 (search result output)
The process after the transition to this process will be described with reference to FIG.

In FIG. 15, after the data search process shown in FIG. 14, the output of the search result is executed, and further, the processes (step S81) to (step S83) shown in FIG. 15 are executed.
Each process of (step S81) to (step S83) shown in FIG. 15 will be described.

(Step S81)
First, in step S81, the information processing device inputs the user's utterance and executes the voice analysis process.
The information processing device 10 inputs the user's utterance, and as a result of voice analysis by the voice analysis unit,
One user utterance candidate = "Tell me a recommended restaurant in Shibuya"
It shows that this one user utterance candidate has been generated.

(Step S82)
Next, in step S82, the context analysis unit of the information processing device 10 obtains the observation information acquired from the camera 11, the microphone 12, and the sensor 15 of the information processing device, the information displayed on the display unit 13, and the communication unit. Acquire various contexts (status information) such as information obtained from an external server or the like via the system.

That is, the same context (situation information) as the context (situation information) 23 described with reference to FIG. 2 is acquired, and the context type of the acquired context is determined.
It is determined which of the (b) context types registered in the context information database 18 described with reference to FIG. 3 the context (situation information) obtained from the camera 11 or the like of the information processing apparatus corresponds to.

As a result of this analysis processing, in this processing example, as shown at the tip of the arrow in FIG. 15 (S82), the context type of the acquired context (situation information) 23 is
Context type = 004 (search result output)
Is determined to be.

(Step S83)
Next, in step S83, the context analysis unit of the information processing apparatus 10 acquires a distance value between the context type (ID = 004) of the acquired context (situation information) and various other context types, and obtains a distance value. The context type whose value is equal to or less than the predetermined threshold value is determined as the next processing candidate.

The inter-text distance value acquisition process is executed with reference to the inter-context distance table 19 shown in FIG.
For example, in the example shown in FIG. 15, the current context type is
Context type = 004 (search result output)
Is.

The information processing device 10 has a context type of the acquired context (situation information) 23, that is,
Obtain the distance value between the context type = 004 (search result output) and a plurality of other context types, select only the context type whose distance value is less than or equal to the predetermined threshold value, and select the selected context type as follows. Determine the next processing candidate that has a high probability of being executed.

Based on this determination of the next processing candidate, the information processing apparatus 10 can start preparations for executing the processing that has become the next processing candidate in advance, and promptly responds when an actual processing transition occurs. It can be performed.

In the example shown in FIG. 15, the context type of the acquired context (situation information) 23, that is,
The distance values between the context type = 004 (search result output) and a plurality of other context types are as follows.
Distance value between 004 (search result output) and 001 (data search) = 3
Distance value between 004 (search result output) and 002 (search detailed condition specification) = 6
Distance value between 004 (search result output) and 003 (search genre change) = 7
Distance value between 004 (search result output) and 005 (search narrowing down) = 1
Distance value between 004 (search result output) and 006 (SNS sharing of search results) = 2
Distance value between 004 (search result output) and 007 (sort search results) = 3
Distance value between 004 (search result output) and 008 (search result input in schedule) = 4
These distance values are distance values obtained from the inter-context distance table 19 shown in FIG.

In step S83, the context analysis unit of the information processing apparatus 10 determines, for example, a threshold value of 5 and a context type having a distance threshold = 5 or less as a next processing candidate.

In the example shown in FIG. 15, the context type with the distance threshold value = 5 or less is set.
001 (data search)
005 (search narrowing down)
006 (SNS sharing of search results)
007 (Sort search results)
008 (Enter search results in the schedule)
These five context types are selected.

The information processing device 10 predicts that these five selected context types are processes (next processing candidates) having a high probability of being executed next, and executes the processing that has become the next processing candidate based on this prediction. Start preparations in advance.
With these pre-processing, when an actual processing transition occurs, it is possible to take a prompt response.

[7. About the processing sequence of the second embodiment executed by the information processing apparatus]
Next, a processing sequence in the case where the information processing apparatus 10 of the present disclosure executes the processing of the second embodiment described with reference to FIGS. 12 to 14 will be described.

The processing sequence of the second embodiment executed by the information processing apparatus 10 of the present disclosure will be described with reference to the flowchart shown in FIG.
The process according to the flowchart shown in FIG. 16 is executed according to the program stored in the storage unit of the information processing apparatus 10. For example, it can be executed as a program execution process by a processor such as a CPU having a program execution function.
The processing of each step of the flow shown in FIG. 16 will be described.

In the flow shown in FIG. 16, the processes of steps S101 to S108 are the same as the processes of steps S101 to S108 in the process flow of the first embodiment described above with reference to FIG.
In the second embodiment, the sequence is obtained by adding the process of step S109 to the process flow of the first embodiment described above with reference to FIG.

(Steps S101 to S108)
As described above, the processes of steps S101 to S108 are the same as the processes of steps S101 to S108 in the process flow of the first embodiment described above with reference to FIG. 11, and will be briefly described.

First, the information processing device 10 inputs the user's utterance in step S101.
Next, in step S102, the information processing device 10 executes a voice analysis process for the input user utterance.
Next, in step S103, the information processing device 10 determines whether or not there is only one user utterance candidate obtained as the voice analysis result in step S102.

If it is determined in step S103 that there are two or more user utterance candidates obtained as the voice analysis result in step S102, the processes of steps S104 to S107 are executed.

First, the information processing apparatus 10 acquires the context (situation information) in step S104, and obtains the distance value between the context type of the acquired context (situation information) 23 and various other context types in step S105. get.

Next, in step S106, the context analysis unit of the information processing apparatus 10 includes a slot that is the same as or similar to the slot in the user utterance candidate as the main slot, and selects the context type having the smallest distance value.
Next, in step S107, the context analysis unit of the information processing device 10 requests a user utterance candidate including a slot that is the same as or similar to the main slot of the context type selected in step S106, and the user to be responded to by the information processing device 10. Select as an utterance.

In step S103, when it is determined that there is only one user utterance candidate obtained as the voice analysis result in step S102, or
On the other hand, it is determined that there are two or more user utterance candidates obtained as the voice analysis result in step S102, and one user utterance candidate is selected from a plurality of user utterance candidates based on the context analysis result in steps S104 to S107. Then, the process of step S108 is executed.

In step S108, the information processing device 10 executes a response or processing corresponding to one user utterance candidate.

(Step S109)
Finally, in step 109, the information processing apparatus 10 determines the context category in which the distance from the acquired context is equal to or less than the threshold value as the next processing candidate.

By performing the process of step S109, the information processing apparatus 10 can start preparations for executing the process that is the next process candidate in advance, and when an actual process transition occurs, the information processing device 10 can start the preparation in advance. A quick response can be taken.

[8. About other examples and modifications]
Next, an example different from the above-mentioned example and a modified example will be described.

In Example 1 of the above-described embodiment, when a plurality of user utterance candidates are generated as a result of voice analysis processing, the distance value from the context type of the current context (situation information) acquired via a camera or the like is set. In this embodiment, the information processing apparatus 10 performs a process of selecting a user utterance candidate including a main slot of a similar context type as a corresponding response target user utterance candidate.

Further, in the second embodiment, the context type whose distance value is close to the context type of the current context (situation information) acquired via the camera or the like is determined as the next processing candidate to be executed by the information processing apparatus, and the next processing is performed. This is an example in which the transition to is made possible efficiently.
Both are examples in which processing is performed with reference to the distance value of the context type.

When acquiring the distance value of this context type, the inter-context distance table 19 shown in FIGS. 4 and 13 was used in the embodiment described above.
In addition, the context information database 18 shown in FIG. 3 was used to specify the context type.

These context distance tables and context information databases are not limited to configurations that use one fixed table or database, for example, a place where a user speaks or a place where processing by the information processing device 10 is executed. The configuration may be changed according to the above.

For example, when the place where the user speaks by the user or the place where the processing by the information processing device 10 is executed is the kitchen, a unique inter-text distance table corresponding to the kitchen or a context information database is used.
In addition, when the place where the user speaks by the user or the place where the processing by the information processing device 10 is executed is the living room, a unique inter-context distance table corresponding to the living room is used. The configuration may be such that the table of the above and the context information database are used.

Further, a configuration may be configured in which a unique inter-text distance table according to a time zone or season, for example, a time zone such as morning, daytime, or night, or a season, or a context information database is used.

Further, the user who is interacting with the information processing apparatus 10 may be identified, and the identified user-specific inter-text distance table or the context information database may be used.

In addition, by referring to the user database in which the connection between users, for example, the user relationship such as parent and child, friends, etc. is registered, the speech selection and the next processing giving priority to the person who has a strong relationship with the user who is interacting with the information processing device 10. The configuration may be such that a context information database or a context distance table considering the user-user relationship that enables the decision to be executed is used.

Further, in the above-described embodiment, the voice analysis process has been described as a processing example of executing the voice analysis process inside the information processing device 10, but the voice analysis is performed in an external device such as an external server capable of communicating with the information processing device 10, for example. It may be configured to be performed.

In addition, a plurality of external devices may be used to acquire voice analysis results from each of them.
In this way, when a plurality of external devices are used and the voice analysis results are acquired from each of them, different voice analysis results (user utterance candidates) may be obtained from each external device. In this case, by performing the process of the first embodiment described above, one voice analysis result (user utterance candidate) to be supported by the information processing apparatus 10 is selected from a plurality of voice analysis results (user utterance candidates). Can be done.

Further, for example, it is assumed that the voice analysis result acquired from the external device may generate the voice analysis result in which the unclear part is not converted into text without generating a plurality of user utterance candidates. for example,
"× enki, onegai"
An external device that generates text data in which the above-mentioned unclear utterance portion is set as an unrecognizable portion (x) is also assumed.

In such a case, the information processing device 10 selects a pronunciation-similar word from the database by referring to the pronunciation-similar word database in which the pronunciation-similar words are recorded for the unrecognizable portion included in the speech recognition result acquired from the external device. Then, a user speech candidate is generated, and then the process according to the first embodiment is executed.

[9. Information processing device configuration example]
Next, a configuration example of the information processing device 10 of the present disclosure will be described.
FIG. 17 is a diagram showing a configuration example of an information processing device 10 that inputs a user utterance and performs a process or a response corresponding to the user utterance.

As shown in FIG. 17, the information processing device 10 includes an input unit 110, an output unit 120, a data processing unit 130, a storage unit 170, and a communication unit 180.
The data processing unit 130 includes an input data analysis unit 140, a data processing execution unit 150, and an output information generation unit 160.
Further, the storage unit 170 has a user information DB (database) 171, a context information database 172, and an inter-text distance table 173.

The data processing unit 130 and the storage unit 170 other than the input unit 110 and the output unit 120 may not be configured in the information processing device 10 but may be configured in an external server. In the case of a configuration using a server, the information processing apparatus 10 transmits the input data input from the input unit 110 to the server via the network, receives the processing result of the server data processing unit 130, and receives the processing result of the server data processing unit 130, and outputs the output unit 120. Output via.

Next, the components of the information processing apparatus 10 shown in FIG. 17 will be described.
The input unit 110 includes a voice input unit (microphone) 111, an image input unit (camera) 112, and a sensor 113.
The output unit 120 includes an audio output unit (speaker) 121 and an image output unit (display unit) 122.
The information processing device 10 has at least these components.

The voice input unit (microphone) 111 corresponds to the microphone 12 of the information processing device 10 shown in FIG.
The image input unit (camera) 112 corresponds to the camera 11 of the information processing device 10 shown in FIG.
The sensor 113 corresponds to the sensor 15 of the information processing device 10 shown in FIG. The sensor 113 is composed of various sensors such as a distance sensor, a position sensor such as GPS, and a temperature sensor.

The audio output unit (speaker) 121 corresponds to the speaker 14 of the information processing device 10 shown in FIG.
The image output unit (display unit) 122 corresponds to the display unit 13 of the information processing device 10 shown in FIG.
The image output unit (display unit) 122 can be configured by, for example, a projector or the like, or can be configured by using the display unit of a television of an external device.

The data processing unit 130 includes an input data analysis unit 140, a data processing execution unit 150, and an output information generation unit 160.

The input data analysis unit 140 includes a voice analysis unit 141, an image analysis unit 142, and a sensor information analysis unit 14.
The output information generation unit 160 includes an output voice generation unit 161 and a display information generation unit 162.

The user's spoken voice is input to a voice input unit 111 such as a microphone.
The voice input unit (microphone) 111 inputs the input user-spoken voice to the voice analysis unit 141.
The voice analysis unit 141 has, for example, an ASR (Automatic Speech Recognition) function, and converts voice data into text data composed of a plurality of words.

The voice analysis unit 141 further executes an utterance semantic analysis process for the text data. The voice analysis unit 141 has a natural language understanding function such as NLU (Natural Language Understanding), and the intention (intent) of the user's utterance from the text data and a meaningful significant element (slot) included in the utterance. : Slot) is estimated. If the intention (intent) and the significant element (slot) can be accurately estimated and acquired from the user utterance, the information processing apparatus 10 can perform accurate processing for the user utterance.
The analysis result of the voice analysis unit 141 is input to the data processing execution unit 150.

The image input unit 112 captures an image of the speaking user and its surroundings and inputs the image to the image analysis unit 162.
The image analysis unit 142 analyzes the facial expression of the speaking user, the user's behavior, the surrounding information of the speaking user, and the like, and inputs the analysis result to the data processing execution unit 150.

The sensor 113 is composed of various sensors such as a distance sensor, a position sensor such as GPS, and a temperature sensor, and the acquired information of the sensor 113 is input to the sensor information analysis unit 143.
The sensor information analysis unit 143 acquires data such as the current position and temperature based on the sensor acquisition information, and inputs the analysis result to the data processing execution unit 150.

The data processing execution unit 150 includes a user identification unit 151, a context analysis unit 152, and a processing execution unit 153.
The user identification unit 151 identifies the user included in the image captured by the camera based on the information input from the input data analysis unit 140, for example, the input information from the image analysis unit 142. Information to be applied to user identification, such as user face information, is stored in the user information DB (database) 171 of the storage unit 170.

The context analysis unit 152 analyzes the current situation (context) based on the information input from the input data analysis unit 140, for example, the input information from the image analysis unit 142.
The context is information indicating the user and the surrounding situation grasped based on the input information of the microphone, the camera, and various sensors constituting the input unit 110. For example, it is data showing the current situation such as "the user is eating" and "the user is making a phone call".

The context analysis unit 152 further performs the process described in the above-described embodiment, that is, the following process.
As the process according to the first embodiment described above, when a plurality of user utterance candidates are generated as a result of the voice analysis process, the distance value from the context type of the current context (situation information) acquired via the camera or the like. The information processing apparatus 10 performs a process of selecting a user utterance candidate including a main slot of a context type close to the same as the corresponding user utterance candidate of the response target.

Further, as the process according to the second embodiment, the context type whose distance value is close to the context type of the current context (situation information) acquired via the camera or the like is determined as the next processing candidate to be executed by the information processing apparatus. Perform processing.
Both are examples in which processing is performed with reference to the distance value of the context type.

When acquiring the distance value of this context type, the inter-context distance table 173 stored in the storage unit 170 and the context information database 172 are used.
The inter-context distance table 173 is a table having the data structure shown in FIGS. 4 and 13. The context information database 172 has the data structure shown in FIG.

The user utterance candidate (Example 1) and the next processing candidate (Example 2) selected as the context analysis result by the context analysis unit 152 are input to the processing execution unit 153.

The processing execution unit 153 performs processing corresponding to the user utterance based on the user utterance candidate (Example 1) selected as the context analysis result by the context analysis unit 152 and the next processing candidate (Example 2). Performs preparatory processing and the like for the processing determined as the next processing candidate.

The output information generation unit 160 includes an output voice generation unit 161 and a display information generation unit 162.
The output voice generation unit 161 generates a system speech voice associated with the processing executed by the processing execution unit 153 of the data processing execution unit 150.
The response voice information generated by the output voice generation unit 161 is output via the voice output unit 121 such as a speaker.

The display information generation unit 162 displays the text information of the system utterance to the user and other presentation information.
For example, when the user makes a user utterance to show the world map, the world map is displayed.
The world map can be obtained from, for example, a service providing server.

The user information DB 171 of the storage unit 170 is a database that records, for example, face information for identifying a user interacting with the information processing device 10, a user profile such as age and gender, and relationship information between users.

The context information database 172 is a database in which the following data are associated and recorded as described above with reference to FIG.
(A) Context ID
(B) Context type (c) Context-compatible main slot (significant element)

Further, the inter-context distance table 173 is a table in which distance values between two context types are recorded, as described above with reference to FIGS. 4 and 13.
The smaller the value of the distance value between the two context types (ID), the higher the similarity and relevance of the two context types.
On the other hand, the larger the value of the distance value between the two context types (ID), the lower the similarity and relevance of the two context types.

The context information database 172 and the inter-text distance table 173 are used in the processing executed by the context analysis unit 152.

Although FIG. 17 has been described as a configuration example of the information processing device 10, as described above, the data processing unit 130 and the storage unit 170 other than the input unit 110 and the output unit 120 in the configuration shown in FIG. 17 have information. It may not be configured in the processing device 10 but may be configured in an external server.

For example, as shown in FIG. 18, a large number of information processing devices 10 which are user terminals and a data processing server 50 are connected via a network. Each information processing device 10 is composed of terminals such as smartphones and PCs owned by each individual and user terminals such as smart speakers in each house. Each information processing device 10 transmits to the data processing server 50 the dialogue information with each user executed by the information processing device 10, the image information, the voice information, the sensor detection information, etc. acquired via the input unit. The data processing server 50 receives various information from each information processing device 10 and performs analysis. Such a configuration can be made.

In the network connection configuration as shown in FIG. 18, various settings can be made for the classification of the processing executed by each of the information processing apparatus 10 and the data processing server 50.
For example, as shown in FIG. 19, the information processing apparatus 10 can have an input unit 110 and an output unit 120, and the data processing server 50 can have a data processing unit 130 and a storage unit 170.

Alternatively, as shown in FIG. 20, the information processing apparatus 10 has an input unit 110 and an input data analysis unit 140, and further has an output information generation unit 160 and an output unit 120, and the data processing server 50 stores the data processing execution unit 150 and storage. It is also possible to have a configuration having a unit 170.

In the case of the network connection configuration as shown in FIG. 18, the data processing server 50 can input and analyze the dialogue information with the user in a large number of information processing devices 10 connected to the network, and is more accurate. It is possible to perform high-level analysis.

[10. Information processing device hardware configuration example]
Next, a hardware configuration example of the agent device (information processing device) will be described with reference to FIG.
The hardware described with reference to FIG. 21 is one specific hardware configuration example of the information processing apparatus 10 described above with reference to FIGS. 17, 19 and 20, and also with reference to FIG. It is also an example of the hardware configuration of the information processing apparatus constituting the data processing server 50 described with reference to FIG.

The CPU (Central Processing Unit) 301 functions as a control unit or a data processing unit that executes various processes according to a program stored in the ROM (Read Only Memory) 302 or the storage unit 308. For example, the process according to the sequence described in the above-described embodiment is executed. The RAM (Random Access Memory) 303 stores programs and data executed by the CPU 301. These CPU 301, ROM 302, and RAM 303 are connected to each other by a bus 304.

The CPU 301 is connected to the input / output interface 305 via the bus 304, and the input / output interface 305 is connected to an input unit 306 consisting of various switches, a keyboard, a mouse, a microphone, a sensor, etc., and an output unit 307 consisting of a display, a speaker, and the like. Has been done. The CPU 301 executes various processes in response to a command input from the input unit 306, and outputs the process results to, for example, the output unit 307.

The storage unit 308 connected to the input / output interface 305 is composed of, for example, a hard disk or the like, and stores a program executed by the CPU 301 and various data. The communication unit 309 functions as a transmission / reception unit for Wi-Fi communication, Bluetooth (registered trademark) (BT) communication, and other data communication via a network such as the Internet or a local area network, and communicates with an external device.

The drive 310 connected to the input / output interface 305 drives a removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory such as a memory card, and records or reads data.

[11. Summary of the structure of this disclosure]
As described above, the examples of the present disclosure have been described in detail with reference to the specific examples. However, it is self-evident that one of ordinary skill in the art can modify or substitute the examples without departing from the gist of the present disclosure. That is, the present invention has been disclosed in the form of an example, and should not be construed in a limited manner. In order to judge the gist of this disclosure, the column of claims should be taken into consideration.

The technology disclosed in the present specification can have the following configuration.
(1) It has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of user utterances.
The data processing unit
An information processing device that analyzes a context that is current status information and executes a user utterance selection process in which the information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates using the context analysis result.

(2) The data processing unit
Determine the context type, which is the type of context that is the current status information,
The information processing device selects a context type that is similar to or highly relevant to the determined context type, and the information processing device transmits a user utterance having a slot that is the same as or similar to the slot registered in the database in association with the selected context type. The information processing device according to (1), which is selected as one corresponding user utterance.

(3) The data processing unit
The information processing apparatus according to (2), wherein the user speech selection process is executed with reference to a context information database in which a plurality of different context types are associated with and recorded main slots corresponding to each context type.

(4) The data processing unit
Refer to the inter-context distance table, which records distance values calculated based on similarities and relationships between multiple context types.
The information processing apparatus according to (2) or (3), which selects a context type having a high degree of similarity or relevance to the determined context type.

(5) The information processing device is
It has a voice analysis unit that executes the voice analysis process of the user's utterance.
The voice analysis unit generates a plurality of user utterance candidates when the user utterance contains an unclear part.
The data processing unit
The information processing device according to any one of (1) to (4), wherein the information processing device selects one user utterance corresponding to the plurality of user utterance candidates generated by the voice analysis unit.

(6) The context is
The information processing apparatus according to any one of (1) to (5), which is status information based on detection information of any one of a camera, a microphone, and a sensor, or at least one of information related to processing being executed in the information processing apparatus. ..

(7) The data processing unit
Described in any of (1) to (6), wherein the user who has made the user utterance is identified, a user-specific process is executed according to the user identification result, and the information processing apparatus selects one corresponding user utterance. Information processing equipment.

(8) The data processing unit
The place where the user utterance was made is identified, a place-specific process is executed according to the place identification result, and the information processing apparatus selects one corresponding user utterance (1) to (7). The information processing device described.

(9) The data processing unit further
The information processing apparatus according to any one of (1) to (8), which executes a response process corresponding to one user utterance selected in the user utterance selection process.

(10) The information processing apparatus has a data processing unit that determines a next processing candidate that is a candidate for the next processing to be executed.
The data processing unit
An information processing device that analyzes a context that is current status information and uses the context analysis result to determine the next processing candidate.

(11) The data processing unit is
Determine the context type, which is the type of context that is the current status information,
The information processing apparatus according to (10), wherein a context type having a high similarity or relevance to the determined context type is selected, and a process corresponding to the selected context type is determined as the next processing candidate.

(12) The data processing unit is
Refer to the inter-context distance table, which records distance values calculated based on similarities and relationships between multiple context types.
The information processing apparatus according to (11), which selects a context type having a high degree of similarity or relevance to the determined context type.

(13) The data processing unit further
The information processing apparatus according to any one of (10) to (12), which executes preparatory processing for the determined next processing candidate.

(14) This is an information processing method executed in an information processing device.
The information processing device has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of the user utterance.
The data processing unit
An information processing method that analyzes a context that is current status information and executes a user utterance selection process in which an information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates using the context analysis result.

(15) An information processing method executed in an information processing device.
The information processing device
The information processing apparatus has a data processing unit that determines a next processing candidate that is a candidate for processing to be executed next.
The data processing unit
An information processing method that analyzes a context that is current status information and uses the context analysis result to determine the next processing candidate.

(16) A program that executes information processing in an information processing device.
The information processing device has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of the user utterance.
The program is installed in the data processing unit.
A program that analyzes a context that is current status information and executes a user utterance selection process in which an information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates using the context analysis result.

(17) A program that executes information processing in an information processing device.
The information processing device
The information processing apparatus has a data processing unit that determines a next processing candidate that is a candidate for processing to be executed next.
The program is installed in the data processing unit.
A program that analyzes the context, which is the current status information, and determines the next processing candidate using the context analysis result.

In addition, the series of processes described in the specification can be executed by hardware, software, or a composite configuration of both. When executing processing by software, install the program that records the processing sequence in the memory in the computer built in the dedicated hardware and execute it, or execute the program on a general-purpose computer that can execute various processing. It can be installed and run. For example, the program can be pre-recorded on a recording medium. In addition to installing on a computer from a recording medium, the program can be received via a network such as LAN (Local Area Network) or the Internet and installed on a recording medium such as a built-in hard disk.

The various processes described in the specification are not only executed in chronological order according to the description, but may also be executed in parallel or individually as required by the processing capacity of the device that executes the processes. Further, in the present specification, the system is a logical set configuration of a plurality of devices, and the devices having each configuration are not limited to those in the same housing.

As described above, according to the configuration of one embodiment of the present disclosure, a device and a method capable of selecting one user utterance corresponding to the information processing device from a plurality of user utterance candidates are realized. NS.
Specifically, for example, it has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of user utterances. The data processing unit determines the context type, which is the type of context that is the current status information, selects a context type that is similar to or highly related to the determined context type, and associates it with the selected context type in the database. A user utterance having a slot that is the same as or similar to the slot registered in is selected as one corresponding user utterance by the information processing apparatus.
With this configuration, a device and a method that enable the information processing device to select one corresponding user utterance from a plurality of user utterance candidates are realized.

10 Agent device 11 Camera 12 Microphone 13 Display unit 14 Speaker 15 Sensor 18 Context information database 19 Context distance table 50 Data processing server 110 Input unit 111 Audio input unit 112 Image input unit 113 Sensor 120 Output unit 121 Audio output unit 122 Image output Unit 130 Data processing unit 140 Input data analysis unit 141 Voice analysis unit 142 Image analysis unit 143 Sensor information analysis unit 150 Data processing execution unit 151 User identification unit 152 Context analysis unit 153 Processing execution unit 160 Output information generation unit 161 Output audio generation unit 162 Display information generation unit 170 Storage unit 171 User information DB (database)
172 Context information database 173 Distance table between contexts 301 CPU
302 ROM
303 RAM
304 Bus 305 Input / output interface 306 Input unit 307 Output unit 308 Storage unit 309 Communication unit 310 Drive 311 Removable media

Claims (17)

It has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a voice analysis result of the user utterance.
The data processing unit
An information processing device that analyzes a context that is current status information and executes a user utterance selection process in which the information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates using the context analysis result. The data processing unit
Determine the context type, which is the type of context that is the current status information,
The information processing device selects a context type that is similar to or highly relevant to the determined context type, and the information processing device sends a user utterance having a slot that is the same as or similar to the slot registered in the database in association with the selected context type. The information processing device according to claim 1, which is selected as one corresponding user utterance. The data processing unit
The information processing apparatus according to claim 2, wherein the user speech selection process is executed with reference to a context information database in which a plurality of different context types are associated with and recorded main slots corresponding to each context type. The data processing unit
Refer to the inter-context distance table, which records distance values calculated based on similarities and relationships between multiple context types.
The information processing apparatus according to claim 2, wherein a context type having a high degree of similarity or relevance to the determined context type is selected. The information processing device
It has a voice analysis unit that executes the voice analysis process of the user's utterance.
The voice analysis unit generates a plurality of user utterance candidates when the user utterance contains an unclear part.
The data processing unit
The information processing device according to claim 1, wherein the information processing device selects one user utterance corresponding to the plurality of user utterance candidates generated by the voice analysis unit. The context is
The information processing apparatus according to claim 1, which is status information based on detection information of any one of a camera, a microphone, and a sensor, or at least one of information related to processing being executed in the information processing apparatus. The data processing unit
The information processing device according to claim 1, wherein the user who has made the user utterance is identified, a user-specific process according to the user identification result is executed, and the information processing device selects the corresponding user utterance. The data processing unit
The information processing device according to claim 1, wherein the information processing device identifies a place where the user utterance is made, executes a place-specific process according to the place identification result, and selects one user utterance corresponding to the information processing device. The data processing unit further
The information processing device according to claim 1, which executes a response process corresponding to one user utterance selected in the user utterance selection process. It has a data processing unit that determines the next processing candidate, which is the next processing candidate to be executed by the information processing device.
The data processing unit
An information processing device that analyzes a context that is current status information and uses the context analysis result to determine the next processing candidate. The data processing unit
Determine the context type, which is the type of context that is the current status information,
The information processing apparatus according to claim 10, wherein a context type having a high similarity or relevance to the determined context type is selected, and a process corresponding to the selected context type is determined as the next processing candidate. The data processing unit
Refer to the inter-context distance table, which records distance values calculated based on similarities and relationships between multiple context types.
The information processing apparatus according to claim 11, wherein a context type having a high degree of similarity or relevance to the determined context type is selected. The data processing unit further
The information processing apparatus according to claim 10, wherein the preparatory processing for the determined next processing candidate is executed. It is an information processing method executed in an information processing device.
The information processing device has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of the user utterance.
The data processing unit
An information processing method that analyzes a context that is current status information and executes a user utterance selection process in which an information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates using the context analysis result. It is an information processing method executed in an information processing device.
The information processing device
The information processing apparatus has a data processing unit that determines a next processing candidate that is a candidate for processing to be executed next.
The data processing unit
An information processing method that analyzes a context that is current status information and uses the context analysis result to determine the next processing candidate. A program that executes information processing in an information processing device.
The information processing device has a data processing unit that selects one user utterance corresponding to the information processing device from a plurality of user utterance candidates generated as a result of voice analysis of the user utterance.
The program is installed in the data processing unit.
A program that analyzes a context that is current status information and executes a user utterance selection process in which an information processing device selects one user utterance corresponding to the plurality of user utterance candidates from the plurality of user utterance candidates using the context analysis result. A program that executes information processing in an information processing device.
The information processing device
The information processing apparatus has a data processing unit that determines a next processing candidate that is a candidate for processing to be executed next.
The program is installed in the data processing unit.
A program that analyzes the context, which is the current status information, and determines the next processing candidate using the context analysis result.

Images