JP2020170239A - Output program, output device and output method - Google Patents

Abstract

To output appropriate information regardless of input to an interactive system by a user.SOLUTION: An output program causes a computer to execute: an acquisition procedure of acquiring reaction information which is character information generated as reaction for second information other than first information inputted to an interactive system by a user; and an output procedure of outputting the reaction information acquired by the acquisition procedure to the user. Moreover, the acquisition procedure acquires the reaction information for the second information other than the first information inputted to the interactive system which is a non-task-oriented type interactive system by the user.SELECTED DRAWING: Figure 1

Description

The present invention relates to an output program, an output device and an output method.

Conventionally, a technique related to a device that responds to a human conversation has been known. For example, a technology related to a device that interacts with a person by utterances that can be associated with scenery or landscape has been proposed.

JP-A-2018-147145

However, in the above-mentioned conventional technique, it is not always possible to output appropriate information without depending on the input by the user to the dialogue system. For example, in the above-mentioned conventional technology, only the utterance sentence that can be associated with the scenery or the landscape is selected from the utterance contents registered in advance, and appropriate information is output without depending on the input by the user to the dialogue system. It is not always possible to do so.

The present application has been made in view of the above, and an object of the present application is to provide an output program, an output device, and an output method capable of outputting appropriate information without depending on input by a user to an interactive system. ..

The output program according to the present application includes an acquisition procedure for acquiring reaction information, which is character information generated as a reaction to second information other than the first information input by the user to the dialogue system, and the acquisition procedure acquired by the acquisition procedure. It is characterized in that a computer executes an output procedure for outputting reaction information to the user.

According to one aspect of the embodiment, there is an effect that appropriate information can be output without depending on the input by the user to the dialogue system.

FIG. 1 is a diagram showing an example of output processing according to the embodiment. FIG. 2 is a diagram showing a configuration example of the output device according to the embodiment. FIG. 3 is a diagram showing an example of the sensor information storage unit according to the embodiment. FIG. 4 is a diagram showing an example of a content storage unit according to the embodiment. FIG. 5 is a diagram showing an example of the reaction information storage unit according to the embodiment. FIG. 6 is a diagram showing an example of a model information storage unit according to the embodiment. FIG. 7 is a diagram showing an example of a model according to the embodiment. FIG. 8 is a diagram showing an example of the learning data storage unit according to the embodiment. FIG. 9 is a flowchart showing an output processing procedure according to the embodiment. FIG. 10 is a diagram showing a configuration example of the content distribution device according to the embodiment. FIG. 11 is a diagram showing an example of a user information storage unit according to the embodiment. FIG. 12 is a diagram showing an example of a content storage unit according to the embodiment. FIG. 13 is a diagram showing an example of output processing according to a modified example. FIG. 14 is a diagram showing an example of output processing according to a modified example. FIG. 15 is a hardware configuration diagram showing an example of a computer that realizes the function of the output device.

Hereinafter, modes for implementing the output program, output device, and output method according to the present application (hereinafter, referred to as “embodiments”) will be described in detail with reference to the drawings. The output program, output device, and output method according to the present application are not limited by this embodiment. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. Example of output processing]
First, an example of output processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of output processing according to the embodiment. As illustrated in FIG. 1, the output processing system 1 includes a content distribution device 20 and an output device 100. These various devices are communicably connected by wire or wirelessly via a network N (for example, the Internet). The output processing system 1 shown in FIG. 2 may include an arbitrary number of content distribution devices 20 and an arbitrary number of output devices 100.

The content distribution device 20 is an information processing device that distributes content. In the example shown in FIG. 1, the content distribution device 20 distributes a news article, which is an example of the content displayed on the output device 100, in response to a distribution request from the output device 100.

The output device 100 is a non-task-oriented dialogue systems, which is a system for conducting non-task-oriented dialogues such as chats with users and conversations without love. The task-oriented dialogue system refers to a system that performs tasks such as search, news reading, and reservation agency in response to a user's request. The output device 100 is a type of chatbot, which is a program that automatically interacts with a user through text or voice. The output device 100 acquires reaction information which is character information generated as a reaction to a second information other than the first information input by the user to the dialogue system, and outputs the acquired reaction information to the user. It is a device.

Further, the output device 100 is an input / output device having an acquisition device such as a microphone for acquiring ambient sound and an input / output device having an output device such as a speaker capable of outputting an arbitrary sound. For example, a smart It is a device called a speaker. Further, the output device 100 is a device capable of outputting music and providing information by voice. Further, the output device 100 has a reception function for receiving sound input, and has an output function of outputting a sound according to the content of the acquired voice when the voice emitted by the user is acquired. The output device 100 may be various information processing devices such as smartphones and tablets, in addition to the smart speaker. FIG. 1 shows an example in which the output device 100 is a smartphone. Further, the output device 100 does not necessarily have to have an output device such as a speaker. For example, the output device 100 may output various information to the user by displaying information such as a character string instead of the voice.

Further, the output device 100 includes a physical sensor which is a sensor for detecting the physical state of the user who uses the output device 100. For example, the output device 100 includes an arbitrary physical sensor such as a gyro sensor, an image sensor, an acceleration sensor, a temperature sensor, a volume sensor, and a brightness sensor. The output device 100 detects the physical state of the user who uses the output device 100 by a physical sensor. Further, the output device 100 acquires sensor information which is information on the physical state of the user by the physical sensor. The output device 100 determines the timing of outputting the reaction information to the user based on the acquired sensor information. In the example shown in FIG. 1, the output device 100 determines whether or not it is the timing to output the reaction information to the user by voice based on the acquired sensor information.

From here, the flow of output processing will be described with reference to FIG. FIG. 1 is a diagram showing an example of output processing according to the embodiment. In the example shown in FIG. 1, the output device 100 acquires voice information regarding the user's voice indicating the utterance by the user by the volume sensor (step S11). When the output device 100 acquires the voice information, the output device 100 determines whether or not it is the timing to output the reaction information to the user based on the acquired voice information (step S12). Specifically, the output device 100 determines whether or not a predetermined period has elapsed from the user's utterance to the dialogue system. For example, when the output device 100 determines that a predetermined period (for example, 30 seconds) has elapsed from the user's utterance to the dialogue system based on the acquired voice information, the output device 100 outputs reaction information to the user. Judge that it is time to do. Subsequently, when the output device 100 determines that it is time to output the reaction information to the user, the output device 100 transmits a content distribution request to the content distribution device 20 (step S13).

The content distribution device 20 receives a content distribution request from the output device 100. When the content distribution device 20 receives the content distribution request, the content distribution device 20 identifies a user who uses the output device 100 of the request source. Subsequently, when the content distribution device 20 identifies the user, the content distribution device 20 selects the content according to the user (step S14). When the content distribution device 20 selects the content, the content distribution device 20 distributes the selected content to the output device 100. Specifically, the content distribution device 20 distributes the content # 1, which is a news article about the formation of a labor union by the online shopping company A, to the output device 100.

The output device 100 acquires the content # 1 from the content distribution device 20 (step S15). When the output device 100 acquires the content # 1, the acquired content # 1 is input to the model M1 to generate reaction information # 1 which is character information indicating a reaction to the content # 1 (step S16). Specifically, the output device 100 generates summary information R11 that is text information corresponding to the summary of the content # 1, "It seems that a labor union was formed by company A." Further, the output device 100 generates the trigger information R12 which is the character information that triggers the dialogue related to the content # 1 with the user. More specifically, the output device 100 generates the trigger information R12, which is character information requesting the user for an opinion on the content # 1, "Does a strike occur?". The output device 100 generates reaction information # 1 including summary information R11 and trigger information R12. When the output device 100 generates the reaction information # 1, the output device 100 acquires the generated reaction information # 1. Although FIG. 1 has described an example in which the reaction information # 1 is character information including both the summary information R11 and the trigger information R12, the reaction information # 1 may not include the summary information R11. That is, the reaction information # 1 may be the trigger information R12.

When the output device 100 acquires the reaction information # 1, the output device 100 outputs the reaction information # 1 by voice (step S17). Specifically, the output device 100 outputs the summary information R11 by voice and then outputs the trigger information R12 by voice.

As described above, the output device 100 acquires reaction information which is character information generated as a reaction to the second information other than the first information input by the user to the dialogue system. Further, the output device 100 outputs the acquired reaction information to the user. As a result, the output device 100 can spontaneously output the character information that triggers the dialogue related to the news article or the like, even if the user does not act on the dialogue system. That is, the output device 100 can spontaneously and appropriately talk to a person from the device. Therefore, the output device 100 can output appropriate information without depending on the input by the user to the dialogue system.

[2. Output device configuration]
Next, the configuration of the output device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the output device 100 according to the embodiment. As shown in FIG. 2, the output device 100 includes a communication unit 110, a storage unit 120, an input unit 130, a display unit 140, a physical sensor 150, and a control unit 160.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the content distribution device 20.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The storage unit 14 stores, for example, an output program or the like. Further, as shown in FIG. 2, the storage unit 14 includes a sensor information storage unit 121, a content storage unit 122, a reaction information storage unit 123, a model information storage unit 124, and a learning data storage unit 125.

(Sensor information storage unit 121)
The sensor information storage unit 121 stores various information related to detection by the physical sensor. For example, the sensor information storage unit 121 stores the sensor information detected by the physical sensor. An example of the sensor information storage unit according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing an example of the sensor information storage unit according to the embodiment. In the example shown in FIG. 3, the sensor information storage unit 121 has items such as "log ID", "type", "sensor information", "date and time", and "position".

The "log ID" indicates identification information for identifying the acquired sensor information. “Type” indicates information regarding the type of detected sensor information. “Sensor information” indicates the detected sensor information. In FIG. 3, an example in which conceptual information such as “SN11” is stored in “sensor information” is shown, but in reality, specifically detected information (sensor data) or a file indicating the storage location thereof is shown. The path name and the like may be stored.

For example, in the case of the type of sensor information "image", the "sensor information" stores a still image or a moving image that captures the user's appearance, or a file path name indicating the storage location thereof. Further, for example, in the case of the sensor information type "utterance", the "sensor information" includes voice data indicating the user's utterance, character information after converting the voice data, or a file path name indicating the storage location thereof. Etc. are stored.

“Date and time” indicates the date and time when the sensor information was detected. In FIG. 3, the “date and time” is abstractly illustrated as “dt11” or the like, but a specific date and time such as “March 23, 2019 22:31:52” may be stored. The "date and time" is not limited to the time point, and may be a predetermined period such as "March 23, 2019 22:31" or "March 23, 2019 22:30-31". Further, the "position" indicates the position where the corresponding action was performed. Although the "position" is illustrated by an abstract code such as "LC11" in FIG. 3, information indicating latitude and longitude and information indicating an address such as "B intersection in Z town, Y city, X prefecture" are stored. You may.

(Content storage unit 122)
The content storage unit 122 stores various information related to the content. For example, the content storage unit 122 stores information about the content acquired from the content distribution device 20. For example, the content storage unit 122 stores information related to news articles, posted information in SNS (Social Networking Service), advertisements, reviews of movies, and the like. For example, the content storage unit 122 stores an HTML file forming the content, character information displayed on the content, a still image, and a moving image. An example of the content storage unit according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing an example of a content storage unit according to the embodiment. In the example shown in FIG. 4, the content storage unit 122 has items such as "content ID", "content", and "acquisition date and time".

The "content ID" indicates identification information for identifying the content. "Content" indicates text information included in content such as news articles, posted information on SNS, advertisements, and movie reviews. In FIG. 4, an example in which conceptual information such as "content # 11" is stored in "content" is shown, but in reality, specific content (HTML file forming) or its storage location is shown. The file path name and the like may be stored. Further, the "content" may store a still image or a moving image displayed in a news article, posted information on an SNS, an advertisement, a movie review, or the like. Alternatively, the "content" may store character information extracted from these image information as a result of analyzing image information displayed in news articles, posted information in SNS, and reviews of advertisements, movies, and the like. "Acquisition date and time" indicates the date and time when the content was acquired.

(Reaction information storage unit 123)
The reaction information storage unit 123 stores various information related to the reaction information. For example, the reaction information storage unit 123 stores the reaction information generated by the output device 100. An example of the reaction information storage unit according to the embodiment will be described with reference to FIG. FIG. 5 is a diagram showing an example of the reaction information storage unit according to the embodiment. In the example shown in FIG. 5, the reaction information storage unit 123 has items such as "reaction ID", "reaction information", "response by user", "generation date and time", and "content ID".

The "reaction ID" indicates identification information for identifying the reaction information. The "reaction information" indicates character information indicating a reaction to the content identified by the content ID. The "content ID" indicates identification information for identifying the content to be reacted. "Response by the user" indicates whether or not the user responds to the reaction information. Specifically, "1" is stored when there is a response from the user to the reaction information, and "0" is stored when there is no response from the user to the reaction information. "Generation date and time" indicates the date and time when the reaction information was generated.

(Model information storage unit 124)
The model information storage unit 124 stores various information related to the model that generates reaction information, which is character information indicating a reaction to the second information other than the first information input by the user to the dialogue system. For example, the model information storage unit 124 stores a model that outputs reaction information, which is character information indicating a reaction to the second information, when the second information other than the first information input by the user is input to the dialogue system. An example of the model information storage unit according to the embodiment will be described with reference to FIG. FIG. 6 is a diagram showing an example of a model information storage unit according to the embodiment. In the example shown in FIG. 6, the model information storage unit 124 has items such as "model ID" and "model data".

The "model ID" indicates identification information for identifying a model that generates reaction information. "Model data" indicates model data of a model. For example, the "model data" stores data for generating reaction information, which is character information indicating a reaction to the second information from the second information other than the first information input by the user to the dialogue system.

Here, an example of the model according to the embodiment will be described with reference to FIG. 7. FIG. 7 shows an example of the model according to the embodiment. In FIG. 7, an example in which the model M1 that generates reaction information, which is character information indicating a reaction to the second information from the second information other than the first information input by the user to the dialogue system, is a Seq2Seq (Sequence to Sequence Model). Will be described. Seq2Seq is a model for learning a rule for inputting a sequence of words (character string) and outputting another sequence of words (character string). Specifically, Seq2Seq is an Encoder-Decoder model whose component is LSTM (Long Short Term Memory), which is a kind of RNN (Recurrent Neural Network).

In the example shown in FIG. 7, an example in which the character string "ABC" is input and the character string "WXYZ" is output is shown. Applying the example shown in Fig. 1, "ABC" is appealing for the abolition of "arbitrary personnel evaluation", "a labor union was formed by a major online shopping company A." This is the character information of the content # 1 which is a news article. In addition, "WXYZ" is textual information that indicates the reaction to content # 1 such as "It seems that a labor union was formed at company A. Will a strike occur?" When there is such a pair of "ABC" (content # 1 which is a news article) and "WXYZ" (reaction information # 1 indicating a response to the content # 1), the model M1 which is Seq2Seq is the model M1 of FIG. The RNN is trained so that the "ABC" is vectorized on the Encoder side where "ABC" is input and the "WXYZ" is generated on the Decoder side where the "WXYZ" in FIG. 7 is output.

The model data MDT1 includes an input layer into which the second information is input, an output layer, a first element which is any layer from the input layer to the output layer and belongs to a layer other than the output layer, and the first element. Reaction information that includes a second element whose value is calculated based on the weight of the first element, and indicates a reaction to the second information input to the input layer according to the second information input to the input layer. The output device 100 may be made to function so as to output from the output layer.

Here, it is assumed that the model data MDT1 is realized by the regression model represented by "y = a1 * x1 + a2 * x2 + ... + ai * xi". In this case, the first element included in the model data MDT1 corresponds to input data (xi) such as x1 and x2. Further, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element corresponds to any node of the input layer, and the second element can be regarded as the node of the output layer.

Further, it is assumed that the model data MDT1 is realized by a neural network having one or a plurality of intermediate layers such as DNN (Deep Neural Network). In this case, the first element included in the model data MDT1 corresponds to either the node of the input layer or the intermediate layer. Further, the second element corresponds to a node in the next stage, which is a node to which a value is transmitted from a node corresponding to the first element. Further, the weight of the first element corresponds to a connection coefficient which is a weight considered for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

The output device 100 outputs reaction information using a model having an arbitrary structure such as the regression model and the neural network described above. Specifically, the model data MDT1 is set with a coefficient so as to output reaction information indicating a reaction to the second information when the second information is input. The output device 100 uses such model data MDT1 to output reaction information indicating a reaction to the second information.

In the above example, the model data MDT1 is a model (hereinafter referred to as model X) that outputs reaction information indicating a reaction to the second information when the second information is input. However, the model data MDT1 according to the embodiment may be a model generated based on the result obtained by repeating the input / output of data to the model X. For example, the model data MDT1 is a model (hereinafter referred to as model Y) learned by inputting reaction information indicating a reaction to the second information output by the model X when the second information is input. May be good. Alternatively, the model data MDT1 may be a model trained to input the second information and output the output value of the model Y.

Further, when the output device 100 performs the estimation process using GAN (Generative Adversarial Networks), the model data MDT1 may be a model forming a part of GAN.

(Learning data storage unit 125)
The learning data storage unit 125 stores various information related to the learning data (correct answer data) of the model. For example, the learning data storage unit 125 stores the content and the reaction information which is the character information indicating the reaction to the content. An example of the learning data storage unit according to the embodiment will be described with reference to FIG. FIG. 8 is a diagram showing an example of the learning data storage unit according to the embodiment. In the example shown in FIG. 8, the learning data storage unit 125 has items such as “learning data ID”, “content”, “reaction information”, and “date and time”.

The "learning data ID" indicates identification information for identifying the learning data. “Content” indicates text information included in content such as news articles, posted information on SNS (Social Networking Service), advertisements, and movie reviews. In FIG. 8, an example in which conceptual information such as “content # 1-1” is stored in “content” is shown, but in reality, specific content (HTML file forming) or its storage location is shown. A file path name indicating the above may be stored. Further, the "content" may store a still image or a moving image displayed in a news article, posted information on an SNS, an advertisement, a movie review, or the like. Alternatively, the "content" may store character information extracted from these image information as a result of analyzing image information displayed in news articles, posted information in SNS, and reviews of advertisements, movies, and the like. "Reaction information" indicates character information indicating a reaction to the content. "Date and time" indicates the date and time when the model learned the training data.

(Input unit 130)
The input unit 130 is an input device that receives various operations from the user. For example, the input unit 130 is realized by a keyboard, a mouse, operation keys, or the like.

(Display unit 140)
The display unit 140 is a display device for displaying various information, that is, a screen. For example, the display unit 140 is realized by a liquid crystal display or the like. When a touch panel is adopted for the output device 100, the input unit 130 and the display unit 140 are integrated. Further, in the following description, the display unit 140 may be described as a screen.

(Physical sensor 150)
The physical sensor 150 is a sensor that detects the physical state of the user who uses the output device 100. For example, as the physical sensor 150, any sensor such as a gyro sensor, an image sensor, an acceleration sensor, a temperature sensor, a volume sensor, and a brightness sensor that measures the inclination of the output device 100 in the three axial directions can be applied.

The physical sensor 150 acquires sensor information that is information about the physical state of the user who uses the output device 100. When the physical sensor 150 acquires the sensor information, the physical sensor 150 stores the acquired sensor information in the sensor information storage unit 121. Specifically, the physical sensor 150, which is a volume sensor, acquires voice information regarding the user's voice indicating an utterance by the user. When the physical sensor 150, which is a volume sensor, acquires voice information, the acquired voice information is stored in the sensor information storage unit 121. Further, the physical sensor 150, which is an image sensor, acquires image information related to the user's image. When the physical sensor 150, which is an image sensor, acquires image information, the acquired image information is stored in the sensor information storage unit 121. Further, the physical sensor 150, which is an acceleration sensor, acquires acceleration information regarding acceleration accompanying the movement of the user. When the physical sensor 150, which is an acceleration sensor, acquires acceleration information, the acquired acceleration information is stored in the sensor information storage unit 121.

(Control unit 160)
In the control unit 160, various programs (corresponding to an example of the output program) stored in the storage device inside the output device 100 are executed by the CPU (Central Processing Unit), MPU (Micro Processing Unit), etc. using the RAM as a work area. It is realized by being done. For example, these various programs correspond to application programs called web browsers. Further, the control unit 160 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 160 includes a determination unit 161, a request unit 162, a generation unit 163, an acquisition unit 164, and an output unit 165, and functions and operations of information processing described below. To realize or execute. The internal configuration of the control unit 160 is not limited to the configuration shown in FIG. 2, and may be another configuration as long as it is a configuration for performing information processing described later.

(Judgment unit 161)
The determination unit 161 determines whether or not it is time to output reaction information to the user. Specifically, the determination unit 161 refers to the sensor information storage unit 121 to acquire sensor information which is information on the physical state of the user who uses the output device 100. Subsequently, when the sensor information is acquired, the determination unit 161 determines whether or not it is the timing to output the reaction information to the user based on the acquired sensor information.

Further, the determination unit 161 determines whether or not the timing is other than the request of the second information by the user to the dialogue system. More specifically, the output unit 165 determines whether or not the timing is based on the user's context. In the example shown in FIG. 1, the output unit 165 determines whether or not it is the timing when a predetermined period has elapsed from the user's utterance to the dialogue system. In the example shown in FIG. 1, the determination unit 161 refers to the sensor information storage unit 121 to acquire voice information such as the log LG1. Subsequently, when the determination unit 161 acquires the voice information, it determines whether or not a predetermined period (for example, 30 seconds) has elapsed from the user's utterance to the dialogue system based on the acquired voice information. .. When the determination unit 161 determines that a predetermined period (for example, 30 seconds) has elapsed from the user's utterance to the dialogue system, it determines that it is the timing to output the reaction information to the user.

The determination unit 161 may determine whether or not it is the timing to output the reaction information to the user based on the user's position information. For example, the determination unit 161 refers to the position information stored in the “position” of the sensor information storage unit 121, and acquires the position information of the user who uses the output device 100. Subsequently, the determination unit 161 determines whether the user is indoors or outdoors based on the acquired position information. For example, when the determination unit 161 determines that the user is at the user's home, it may determine that it is the timing to output the reaction information to the user. Further, when the determination unit 161 determines that the user is in the park, it may determine that it is the timing to output the reaction information to the user.

(Request unit 162)
The request unit 162 requests the distribution of the content. Specifically, the request unit 162 transmits a content distribution request to the content distribution device 20 when the determination unit 161 determines that it is time to output the reaction information to the user. In addition, the request unit 162 receives the content from the content distribution device 20. When the request unit 162 receives the content, the request unit 162 stores the received content in the content storage unit 122.

(Generator 163)
The generation unit 163 generates reaction information from the second information. Specifically, the generation unit 163 acquires the second information other than the first information input by the user to the dialogue system. More specifically, the generation unit 163 acquires the second information other than the first information input by the user to the dialogue system which is a non-task-oriented dialogue system. In addition, the generation unit 163 acquires the second information selected according to the user. For example, the generation unit 163 acquires the second information which is a predetermined content. In the example shown in FIG. 1, the generation unit 163 acquires the second information which is a news article. More specifically, the generation unit 163 refers to the content storage unit 122 to acquire the content # 1 which is a news article.

Subsequently, when the generation unit 163 acquires the second information, the generation unit 163 generates reaction information by inputting the acquired second information into a predetermined model. When the generation unit 163 generates the reaction information, the generated reaction information is stored in the reaction information storage unit 123. More specifically, when the generation unit 163 acquires the second information, it refers to the model information storage unit 124 and acquires the model M1. For example, when the generation unit 163 inputs the second information other than the first information input by the user into the dialogue system, the generation unit 163 acquires the model M1 that outputs the reaction information which is the character information indicating the reaction to the second information. For example, when the generation unit 163 inputs the second information other than the first information input by the user into the dialogue system, the generation unit 163 acquires the model M1 which is the Seq2Seq which outputs the reaction information which is the character information indicating the reaction to the second information. To do. Subsequently, when the generation unit 163 acquires the model M1, the generation unit 163 inputs the second information to the acquired model M1. The generation unit 163 acquires the output information of the model M1 as reaction information. In this way, the generation unit 163 generates reaction information which is character information indicating a reaction to the second information other than the first information input by the user to the dialogue system. More specifically, the generation unit 163 generates reaction information for the second information other than the first information input by the user to the dialogue system which is a non-task-oriented dialogue system. In addition, the generation unit 163 generates reaction information for the second information selected according to the user. For example, the generation unit 163 generates reaction information for the second information which is a predetermined content. In the example shown in FIG. 1, the generation unit 163 generates reaction information for the second information which is a news article. More specifically, the generation unit 163 generates reaction information indicating a reaction to the content # 1, which is a news article selected according to the user by the content distribution device 20.

In addition, the generation unit 163 generates summary information which is a summary of the second information. In the example shown in FIG. 1, the generation unit 163 generates summary information R11, which is text information corresponding to a summary of content # 1 which is a news article, "It seems that a labor union was formed at company A." In addition, the generation unit 163 generates reaction information that triggers a dialogue related to the second information with the user. For example, the generation unit 163 acquires reaction information that requests the user to give an opinion on the second information. In the example shown in FIG. 1, the generation unit 163 generates the trigger information R12, which is character information requesting the user for an opinion on the content # 1 which is a news article, "Does a strike occur?". The generation unit 163 generates reaction information # 1 including summary information R11 and trigger information R12. Note that, in FIG. 1, an example in which the generation unit 163 generates reaction information # 1 including both summary information R11 and trigger information R12 has been described, but even if reaction information # 1 not including summary information R11 is generated, Good. That is, the generation unit 163 may generate the reaction information # 1 which is the trigger information R12.

(Acquisition unit 164)
The acquisition unit 164 acquires the reaction information generated by the generation unit 163. Specifically, the acquisition unit 164 acquires reaction information, which is character information generated as a reaction to second information other than the first information input by the user to the dialogue system. More specifically, the acquisition unit 164 acquires reaction information to the second information other than the first information input by the user to the dialogue system, which is a non-task-oriented dialogue system. To do. For example, the acquisition unit 164 acquires reaction information with respect to the second information which is a predetermined content. In addition, the acquisition unit 164 acquires reaction information for the second information selected according to the user. In the example shown in FIG. 1, the acquisition unit 164 acquires reaction information to the second information which is a news article. More specifically, the acquisition unit 164 acquires reaction information indicating a reaction to the content # 1, which is a news article selected according to the user by the content distribution device 20.

In addition, the acquisition unit 164 acquires summary information which is a summary of the second information. In the example shown in FIG. 1, the acquisition unit 164 acquires the summary information R11 that is the text information corresponding to the summary of the content # 1 which is a news article, "It seems that a labor union was formed at company A." In addition, the acquisition unit 164 acquires reaction information that triggers a dialogue related to the second information with the user. For example, the acquisition unit 164 acquires reaction information that requests the user to give an opinion on the second information. In the example shown in FIG. 1, the acquisition unit 164 acquires the trigger information R12, which is character information requesting the user for an opinion on the content # 1 which is a news article, "Does a strike occur?". The acquisition unit 164 acquires reaction information # 1 including summary information R11 and trigger information R12. In addition, in FIG. 1, an example in which the acquisition unit 164 acquires the reaction information # 1 including both the summary information R11 and the trigger information R12 has been described, but even if the reaction information # 1 not including the summary information R11 is acquired, Good. That is, the acquisition unit 164 may acquire the reaction information # 1 which is the trigger information R12.

(Output unit 165)
The output unit 165 outputs the reaction information acquired by the acquisition unit 164 to the user. Specifically, the output unit 165 outputs the reaction information acquired by the acquisition unit 164 to the user when the determination unit 161 determines that it is the timing to output the reaction information to the user. More specifically, the output unit 165 outputs reaction information at a timing other than the user's request for the second information to the dialogue system. For example, the output unit 165 outputs reaction information at a timing based on the user's context. In the example shown in FIG. 1, the output unit 165 outputs reaction information at a timing when a predetermined period has elapsed from the user's utterance to the dialogue system.

Further, the output unit 165 outputs summary information and reaction information. More specifically, the output unit 165 outputs the reaction information after outputting the summary information. Further, the output unit 165 outputs the reaction information by voice. In the example shown in FIG. 1, the output unit 165 outputs the summary information R11 by voice and then outputs the trigger information R12 by voice.

[3. Output processing flow]
Next, the procedure of output processing according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an output processing procedure according to the first embodiment. In the example shown in FIG. 9, the output device 100 determines whether or not it is the timing to output the reaction information based on the sensor information (step S101). When the output device 100 determines that it is not the timing to output the reaction information (step S101; No), the output device 100 ends the process.

On the other hand, when the output device 100 determines that it is the timing to output the reaction information (step S101; Yes), the output device 100 acquires the predetermined content from the content distribution device 20 (step S102). Subsequently, when the output device 100 acquires the predetermined content, the output device 100 generates reaction information for the predetermined content (step S103). Subsequently, when the output device 100 generates the reaction information, the output device 100 outputs the generated reaction information (step S104).

[4. Configuration of content distribution device]
Next, the configuration of the content distribution device 20 according to the embodiment will be described with reference to FIG. FIG. 10 is a diagram showing a configuration example of the content distribution device 20 according to the embodiment. As shown in FIG. 10, the content distribution device 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

(Communication unit 21)
The communication unit 21 is realized by, for example, a NIC or the like. Then, the communication unit 21 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the output device 100.

(Memory unit 22)
The storage unit 22 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. Further, as shown in FIG. 10, the storage unit 14 has a user information storage unit 221 and a content storage unit 222.

(User information storage unit 221)
The user information storage unit 221 stores various information about the user. An example of the user information storage unit according to the embodiment will be described with reference to FIG. FIG. 11 is a diagram showing an example of a user information storage unit according to the embodiment. In the example shown in FIG. 11, the user information storage unit 221 has items such as "user ID" and "user information".

The "user ID" indicates identification information for identifying the user. "User information" indicates information about the user. For example, "user information" is a keyword related to a genre or topic, hobby or preference that the user is interested in. The "user information" may include user demographic information such as the user's age, gender, place of residence, family life cycle, income, and occupation. Further, the "user information" may include psychographic information such as a user's sense of values, lifestyle, personality, and preference.

(Content storage unit 222)
The content storage unit 222 stores various information related to the content. For example, the content storage unit 222 stores information related to content that is a review of news articles, posted information on SNS, advertisements, movies, and the like. For example, the content storage unit 222 stores an HTML file forming the content, and a still image or a moving image displayed on the content. An example of the content storage unit according to the embodiment will be described with reference to FIG. FIG. 12 is a diagram showing an example of a content storage unit according to the embodiment. In the example shown in FIG. 12, the content storage unit 222 has items such as "content ID", "content", and "type".

The "content ID" indicates identification information for identifying the content. "Content" indicates text information included in content such as news articles, posted information on SNS, advertisements, and movie reviews. In FIG. 12, an example in which conceptual information such as "content # 1" is stored in "content" is shown, but in reality, specific content (HTML file forming) or its storage location is shown. The file path name and the like may be stored. Further, the "content" may store a still image or a moving image displayed in a news article, posted information on an SNS, an advertisement, a movie review, or the like. Alternatively, the "content" may store character information extracted from these image information as a result of analyzing image information displayed in news articles, posted information in SNS, and reviews of advertisements, movies, and the like. "Type" indicates the type of content. For example, the "type" indicates a type such as whether the content is a news article, posted information on SNS, an advertisement, or a movie review.

(Control unit 23)
The control unit 23 is realized by, for example, the CPU, MPU, or the like executing various programs stored in the storage device inside the content distribution device 20 using the RAM as a work area. Further, the control unit 23 is realized by, for example, an integrated circuit such as an ASIC or FPGA.

As shown in FIG. 10, the control unit 23 includes a reception unit 231, a selection unit 232, and a distribution unit 233, and realizes or executes an information processing function or operation described below. The internal configuration of the control unit 23 is not limited to the configuration shown in FIG. 10, and may be another configuration as long as it is a configuration for performing information processing described later.

(Reception Department 231)
The reception unit 231 receives the content distribution request. The reception unit 231 receives the content distribution request. Specifically, the reception unit 231 receives the content distribution request from the output device 100.

(Selection unit 232)
The selection unit 232 selects the content according to the user. Specifically, the selection unit 232 identifies the user who uses the output device 100 of the request source when the content distribution request is received by the reception unit 231. For example, the selection unit 232 refers to the user information storage unit 221 to identify a user who uses the request source output device 100. Subsequently, when the selection unit 232 identifies the user, the selection unit 232 refers to the user information storage unit 221 and acquires the user information associated with the specified user. When the selection unit 232 acquires the user information, the selection unit 232 selects the content according to the user based on the acquired user information. For example, the selection unit 232 acquires keywords related to genres, topics, hobbies, and tastes that the user is interested in, based on the user information. Subsequently, the selection unit 232 refers to the content storage unit 222 and selects the content in which the acquired keyword is set as the content according to the user.

In the example shown in FIG. 1, when the user U1 is specified, the selection unit 232 refers to the user information storage unit 221 and acquires the user information # 1 associated with the specified user U1. Subsequently, when the user information # 1 is acquired, the selection unit 232 acquires keywords related to the genre, topic, hobby, or preference that the user U1 is interested in, based on the acquired user information # 1. Subsequently, the selection unit 232 refers to the content storage unit 222 and selects the content # 1, which is a news article in which the acquired keyword is set, as the content according to the user U1.

(Distribution Department 233)
The distribution unit 233 distributes the content selected by the selection unit 232. Specifically, the distribution unit 233 distributes the content selected by the selection unit 232 to the output device 100. In the example shown in FIG. 1, the distribution unit 233 distributes the content # 1 selected by the selection unit 232 to the output device 100.

[5. Modification example]
The output processing system 1 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. Therefore, another embodiment of the output processing system 1 will be described below. The same parts as those in the embodiment are designated by the same reference numerals, and the description thereof will be omitted.

[5-1. Output processing of reaction information showing the impression of the dialogue system]
FIG. 1 has described an example in which the output device 100 outputs the trigger information R12, which is character information requesting the user for an opinion on the content # 1, "Does a strike occur?", But the reaction information gives an opinion on the content. It is not limited to the character information requested from the user. FIG. 13 describes an example in which the output device 100 outputs reaction information indicating an impression of the second information of the dialogue system. In the example shown in FIG. 13, the acquisition unit 164 acquires reaction information indicating an impression of the second information of the dialogue system.

From here, an example of output processing according to a modified example will be described with reference to FIG. FIG. 13 is a diagram showing an example of output processing according to a modified example. In the example shown in FIG. 13, the determination unit 161 refers to the sensor information storage unit 121 to acquire image information regarding the user's image (step S21). When the image information is acquired, the determination unit 161 determines whether or not it is the timing to output the reaction information to the user based on the acquired image information (step S22). Specifically, when the determination unit 161 determines that the user is in a stationary state for a predetermined time or longer (for example, 5 minutes or longer) based on the acquired image information, the determination unit 161 outputs the reaction information to the user at the timing. Judge that there is. Subsequently, the request unit 162 transmits a content distribution request to the content distribution device 20 when the determination unit 161 determines that it is time to output the reaction information to the user (step S23).

The content distribution device 20 acquires a content distribution request from the output device 100. When the content distribution device 20 acquires a content distribution request, the content distribution device 20 identifies a user who uses the output device 100 of the request source. Subsequently, when the content distribution device 20 identifies the user, the content distribution device 20 selects the content according to the user (step S24). When the content distribution device 20 selects the content, the content distribution device 20 distributes the selected content to the output device 100. Specifically, the content distribution device 20 distributes the content # 2, which is a news article about the government distributing tablet terminals to all evacuation centers in the disaster area, to the output device 100.

The generation unit 163 acquires the content # 2 from the content distribution device 20 (step S25). When the content # 2 is acquired, the generation unit 163 inputs the acquired content # 2 into the model M1 to generate reaction information # 2, which is character information indicating a reaction to the content # 2 (step S26). Specifically, the generation unit 163 generates summary information R21, which is text information corresponding to the summary of content # 2, "The government seems to distribute tablet terminals to all evacuation centers." In addition, the generation unit 163 generates the trigger information R22, which is the character information that triggers the dialogue related to the content # 2 with the user. More specifically, the generation unit 163 generates the trigger information R22, which is character information indicating the impression of the content # 2 of the dialogue system, "I want it to be usable even if there is a power failure." The generation unit 163 generates reaction information # 2 including summary information R21 and trigger information R22. The acquisition unit 164 acquires the reaction information # 2 generated by the generation unit 163. Note that, in FIG. 13, an example in which the generation unit 163 generates reaction information # 2 including both summary information R21 and trigger information R22 has been described, but even if reaction information # 2 not including summary information R21 is generated, Good. That is, the generation unit 163 may generate the reaction information # 2, which is the trigger information R22.

The output unit 165 outputs the reaction information # 2 acquired by the acquisition unit 164 as voice (step S27). Specifically, the output device 100 outputs the summary information R21 by voice and then outputs the trigger information R22 by voice.

[5-2. Output processing of reaction information that encourages user actions]
FIG. 1 has described an example in which the output device 100 outputs reaction information # 1 including the trigger information R12, which is character information requesting the user for an opinion on the content # 1, "Does a strike occur?". The information is not limited to textual information that requires the user to give an opinion on the content. FIG. 14 describes an example in which the output device 100 outputs reaction information that prompts the user to take an action related to the second information. In the example shown in FIG. 14, the acquisition unit 164 acquires reaction information that prompts the user to take an action related to the second information. Specifically, the acquisition unit 164 acquires reaction information that urges the user to take an action other than responding to the reaction information.

Further, in FIG. 1, an example in which the output device 100 acquires the reaction information # 2 for the content # 1 which is a news article has been described, but the output device 100 may acquire the reaction information for the second information which is an advertisement. .. In the example shown in FIG. 14, the acquisition unit 164 acquires reaction information with respect to the second information which is an advertisement.

From here, an example of output processing according to a modified example will be described with reference to FIG. FIG. 14 is a diagram showing an example of output processing according to a modified example. In the example shown in FIG. 14, the determination unit 161 refers to the sensor information storage unit 121 and acquires acceleration information regarding acceleration accompanying the movement of the user (step S31). When the determination unit 161 acquires the acceleration information, it determines whether or not it is the timing to output the reaction information to the user based on the acquired acceleration information (step S32). Specifically, when the determination unit 161 determines that the user is in a stationary state for a predetermined time or longer (for example, 5 minutes or longer) based on the acquired acceleration information, the determination unit 161 outputs the reaction information to the user at the timing. Judge that there is. Subsequently, the request unit 162 transmits a content distribution request to the content distribution device 20 when the determination unit 161 determines that it is time to output the reaction information to the user (step S33).

The content distribution device 20 acquires a content distribution request from the output device 100. When the content distribution device 20 acquires a content distribution request, the content distribution device 20 identifies a user who uses the output device 100 of the request source. Subsequently, when the content distribution device 20 identifies the user, the content distribution device 20 selects the content according to the user (step S34). When the content distribution device 20 selects the content, the content distribution device 20 distributes the selected content to the output device 100. Specifically, the content distribution device 20 distributes the content # 3, which is an advertisement regarding the newly released product C, to the output device 100.

The generation unit 163 acquires the content # 3 from the content distribution device 20 (step S35). When the content # 3 is acquired, the generation unit 163 inputs the acquired content # 3 into the model M1 to generate reaction information # 3, which is character information indicating a reaction to the content # 3 (step S36). Specifically, the generation unit 163 generates summary information R31 that is character information corresponding to the summary of the content # 3, "It seems that the product C has been released." In addition, the generation unit 163 generates the trigger information R32, which is the character information that triggers the dialogue related to the content # 3 with the user. More specifically, the generation unit 163 generates the trigger information R32, which is character information for urging the user to perform an action related to the content # 3. For example, the generation unit 163 generates the trigger information R32, which is character information prompting the user to take an action other than the response to the reaction information # 3, "Why don't you go buy it together next time?". The generation unit 163 generates reaction information # 2 including summary information R31 and trigger information R32. The acquisition unit 164 acquires the reaction information # 3 generated by the generation unit 163. In FIG. 14, an example in which the generation unit 163 generates reaction information # 3 including both summary information R31 and trigger information R32 has been described, but even if reaction information # 3 not including summary information R31 is generated, Good. That is, the generation unit 163 may generate the reaction information # 3, which is the trigger information R32.

The output unit 165 outputs the reaction information # 3 acquired by the acquisition unit 164 as voice (step S37). Specifically, the output device 100 outputs the summary information R31 by voice and then outputs the trigger information R32 by voice.

Although FIG. 14 has described an example in which the output device 100 acquires reaction information # 2 for content # 2, which is an advertisement, as content other than news articles, the content other than news articles is not limited to advertisements. Specifically, the acquisition unit 164 acquires reaction information with respect to the second information which is the posted information in a predetermined SNS (Social Networking Service).

[5-3. Output at the timing related to push notification]
The output unit 165 outputs reaction information at the timing related to the push notification in the dialogue system. Specifically, the determination unit 161 acquires information regarding push notifications in the dialogue system. For example, the determination unit 161 acquires information on performing push notifications at predetermined period programmed in advance as information on push notifications in the dialogue system. Subsequently, when the determination unit 161 acquires the information related to the push notification, it determines whether or not it is the timing related to the push notification in the dialogue system based on the acquired information related to the push notification. The output unit 165 outputs reaction information when the determination unit 161 determines that the timing is related to the push notification in the dialogue system.

[5-4. Output at the timing of the search]
The output unit 165 outputs reaction information at the timing when the user's action related to the second information is performed, which is the user's action other than the action for the dialogue system. Specifically, the output unit 165 outputs reaction information at the timing when the user performs a search related to the second information. More specifically, the determination unit 161 acquires search information regarding the user's search behavior from the search server (not shown). Subsequently, when the search information is acquired, the determination unit 161 determines whether or not it is the timing when the user performs a search related to the second information based on the acquired search information. The output unit 165 outputs reaction information when it is determined by the determination unit 161 that it is the timing when the user performs a search related to the second information.

[5-5. Timing judgment after content acquisition]
FIG. 1 has described an example in which the request unit 162 transmits a content distribution request to the content distribution device 20 after the determination unit 161 determines whether or not it is the timing to output the reaction information to the user. Not limited to this. Specifically, the output unit 165 outputs reaction information at predetermined time (for example, 60 minutes). In addition, the request unit 162 transmits a content distribution request to the content distribution device 20 at predetermined time (for example, 30 minutes). For example, the request unit 162 transmits a content distribution request to the content distribution device 20 at a certain time t1. When the content distribution device 20 receives the distribution request, the content distribution device 20 distributes the first content to the output device 100. Subsequently, the request unit 162 acquires the first content from the content distribution device 20. When the request unit 162 acquires the first content, the request unit 162 stores the acquired first content in the content storage unit 122. Subsequently, the generation unit 163 acquires the first content with reference to the content storage unit 122. When the generation unit 163 acquires the first content, the generation unit 163 generates the first reaction information by inputting the acquired first content into a predetermined model. When the generation unit 163 generates the first reaction information, the generated first reaction information is stored in the reaction information storage unit 123.

Subsequently, the request unit 162 transmits a content distribution request to the content distribution device 20 at time t2, which is 30 minutes after the time t1. When the content distribution device 20 receives the distribution request, the content distribution device 20 distributes the second content to the output device 100. Subsequently, the request unit 162 acquires the second content from the content distribution device 20. When the request unit 162 acquires the second content, the request unit 162 stores the acquired second content in the content storage unit 122. Subsequently, the generation unit 163 generates the second reaction information by inputting the second content into the predetermined model. When the generation unit 163 generates the second reaction information, the generated second reaction information is stored in the reaction information storage unit 123. Subsequently, when the generation unit 163 generates the second reaction information, the generation unit 163 refers to the content storage unit 122 and acquires the first content requested to be delivered at time t1 and the second content requested to be delivered at time t2. .. Subsequently, when the generation unit 163 acquires the first content and the second content, the generation unit 163 determines the degree of similarity between the first content and the second content. When the similarity between the first content and the second content exceeds a predetermined threshold value, the generation unit 163 considers that the first content is old and has been updated to the new second content, and the content storage unit 122 to the first 1 Delete the content. Subsequently, the determination unit 161 determines whether or not it is the timing to output the reaction information to the user. The output unit 165 outputs the second reaction information when the determination unit 161 determines that it is the timing to output the reaction information to the user.

[5-6. Response information to the review]
The generation unit 163 generates reaction information, which is character information described by the dialogue system from the standpoint of the writer of the review, as reaction information for the content which is a movie review. For example, the generation unit 163, as reaction information to the content that is a movie review of a horror movie, is a character stated from the standpoint of the review writer, such as "XX (movie title) was scary! I can't sleep tonight." Generate reaction information, which is information.

[5-7. Model update]
The generation unit 163 feeds back the response from the user and generates reaction information using the updated model. Specifically, the generation unit 163 generates reaction information using a model updated according to the presence or absence of a response by the user by referring to the item of "presence or absence of response by the user" of the reaction information storage unit 123. .. For example, the generation unit 163 learns by making the weight of learning for the set data of the reaction information and the content that the user has responded to be larger than the weight of learning for the set data of the reaction information and the content that has not been responded by the user. Reaction information is generated using the model.

[5-8. Summary generative model and reaction generative model]
In the example shown in FIG. 1, an example in which the generation unit 163 inputs the content # 1 into one model M1 to generate the reaction information # 1 including the summary information R11 and the trigger information R12 has been described, but the summary information R11 has been described. And the trigger information R12 may be generated by another model. Specifically, the generation unit 163 generates summary information by using the model M11 that outputs summary information that is a summary of the second information when the second information is input. Further, the generation unit 163 generates the reaction information by using the model M12 that outputs the reaction information indicating the reaction to the second information when the second information is input. In the example shown in FIG. 1, when the content # 1 is input, the generation unit 163 generates the summary information R11 by using the model M11 that outputs the summary information R11 which is a summary of the content # 1. Further, the generation unit 163 generates the trigger information R12 by using the model M12 that outputs the trigger information R12 indicating the reaction to the content # 1 when the content # 1 is input.

In this case, the output processing system 1 may include a plurality of output devices 100 called a summary output device 100 and a reaction output device 100. For example, the output device 100 serving as a summary outputs the summary information R11, which is a summary of the content # 1, by voice. Subsequently, the output device 100 of the reaction combination outputs the trigger information R12 indicating the reaction to the content # 1 by voice different from that of the output device 100 of the summary combination. The output processing system 1 includes an output device 100 that serves as a summary, an output device 100 that serves as a reaction, an output device 100 that promotes dialogue, and an output device 100 that assists the progress of dialogue. A plurality of output devices 100 may be included.

[5-9. Output to screen]
The output unit 165 may output the reaction information to the user by displaying the character information on the screen instead of the voice. Further, the output unit 165 may output image information instead of the sound. In this case, the output unit 165 displays an image in which the user can understand the reaction information at a glance. The image information may be either a moving image or a still image. Further, when the output device 100 is a humanoid robot, the output unit 165 may output reaction information by gesturing or gesturing the robot.

[6. effect〕
As described above, the output device 100 according to the embodiment includes an acquisition unit 164 and an output unit 165. The acquisition unit 164 acquires reaction information, which is character information generated as a reaction to second information other than the first information input by the user to the dialogue system. The output unit 165 outputs the reaction information acquired by the acquisition unit 164 to the user.

As a result, the output device 100 can spontaneously output the character information that triggers the dialogue related to the news article or the like, even if the user does not act on the dialogue system. That is, the output device 100 can spontaneously and appropriately talk to a person from the device. Therefore, the output device 100 can output appropriate information without depending on the input by the user to the dialogue system.

In addition, the acquisition unit 164 acquires reaction information for second information other than the first information input by the user to the dialogue system, which is a non-task-oriented dialogue system.

As a result, the output device 100 can spontaneously output the character information that triggers the dialogue related to the news article or the like, even if the user does not act on the non-task-oriented dialogue system.

In addition, the acquisition unit 164 acquires reaction information with respect to the second information which is a predetermined content.

As a result, the output device 100 can spontaneously output the character information that triggers the dialogue related to the predetermined content.

In addition, the acquisition unit 164 acquires reaction information to the second information which is a news article.

As a result, the output device 100 can spontaneously output the character information that triggers the dialogue related to the news article.

In addition, the acquisition unit 164 acquires reaction information with respect to the second information which is the posted information in the predetermined SNS (Social Networking Service).

As a result, the output device 100 can voluntarily output the character information that triggers the dialogue related to the posted information in the SNS.

In addition, the acquisition unit 164 acquires reaction information with respect to the second information which is an advertisement.

As a result, the output device 100 can spontaneously output the character information that triggers the dialogue related to the advertisement.

In addition, the acquisition unit 164 acquires reaction information that triggers a dialogue related to the second information with the user.

As a result, the output device 100 can spontaneously output the character information that triggers the dialogue related to the news article or the like, even if the user does not act on the dialogue system.

In addition, the acquisition unit 164 acquires reaction information indicating an impression of the second information of the dialogue system.

As a result, the output device 100 can voluntarily start an appropriate dialogue with the impression of the second information as a trigger for the dialogue, even if the user does not act on the dialogue system.

In addition, the acquisition unit 164 acquires reaction information that requests the user to give an opinion on the second information.

As a result, the output device 100 can voluntarily start an appropriate dialogue by requesting the user for an opinion on the second information even if the user does not act on the dialogue system.

In addition, the acquisition unit 164 acquires reaction information that prompts the user to take an action related to the second information. For example, the acquisition unit 164 acquires reaction information that urges the user to take an action other than responding to the reaction information.

As a result, the output device 100 can voluntarily start an appropriate dialogue by encouraging the second information-related action without any action from the user to the dialogue system.

Further, the output unit 165 outputs reaction information at a timing other than the user's request for the second information to the dialogue system.

As a result, the output device 100 can voluntarily start an appropriate dialogue without any action from the user to the dialogue system.

Further, the output unit 165 outputs reaction information at the timing related to the push notification in the dialogue system.

As a result, the output device 100 can voluntarily start an appropriate dialogue at the timing related to the push notification in the dialogue system.

Further, the output unit 165 outputs reaction information at a timing based on the user's context.

As a result, the output device 100 can spontaneously start an appropriate dialogue according to the context of the user.

Further, the output unit 165 outputs reaction information at a timing when a predetermined period has elapsed from the user's utterance to the dialogue system.

As a result, the output device 100 can voluntarily start an appropriate dialogue at the timing when the dialogue with the user is interrupted.

Further, the output unit 165 outputs reaction information at the timing when the user's action other than the action for the dialogue system and the user's action related to the second information is performed. For example, the output unit 165 outputs reaction information at the timing when the user performs a search related to the second information.

As a result, the output device 100 can spontaneously start an appropriate dialogue at the timing when the search is performed by the user.

Further, the output device 100 according to the embodiment further includes a generation unit 163. The generation unit 163 generates reaction information from the second information. The acquisition unit 164 acquires the reaction information generated by the generation unit 163. Specifically, the generation unit 163 generates reaction information by inputting the second information into a predetermined model.

As a result, the output device 100 can spontaneously and appropriately output reaction information other than the reaction information registered in advance.

In addition, the acquisition unit 164 acquires reaction information for the second information selected according to the user.

As a result, the output device 100 can voluntarily and appropriately start a dialogue of contents according to the user.

Further, the output unit 165 outputs the reaction information by voice. Further, the output unit 165 may output image information instead of the sound. In this case, the output unit 165 displays an image in which the user can understand the reaction information at a glance. The image information may be either a moving image or a still image.

As a result, the output device 100 can spontaneously and appropriately output the reaction information in a timely manner.

In addition, the acquisition unit 164 acquires summary information which is a summary of the second information. Further, the output unit 165 outputs summary information and reaction information. Further, the output unit 165 outputs the reaction information after outputting the summary information.

As a result, the output device 100 makes it possible to share a common topic with the user by outputting the summary information. Further, the output device 100 can create an opportunity to elicit a user's response to the summary information by outputting the reaction information.

[7. Hardware configuration]
Further, the output device 100 and the content distribution device 20 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 15 is a hardware configuration diagram showing an example of a computer that realizes the functions of the output device 100 and the content distribution device 20. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via a predetermined communication network and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the predetermined communication network.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the output device 100 and the content distribution device 20, the CPU 1100 of the computer 1000 realizes the functions of the control unit 160 or the control unit 23 by executing the program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via a predetermined communication network.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

[8. Others]
Further, among the processes described in the above-described embodiments and modifications, all or part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed. It is also possible to automatically perform all or part of the processed processing by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

In addition, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the output unit can be read as an output means or an output circuit.

1 Output processing system 100 Output device 110 Communication unit 120 Storage unit 121 Sensor information storage unit 122 Content storage unit 123 Reaction information storage unit 124 Model information storage unit 125 Learning data storage unit 130 Input unit 140 Display unit 150 Physical sensor 160 Control unit 161 Judgment unit 162 Request unit 163 Generation unit 164 Acquisition unit 165 Output unit

Claims (25)

An acquisition procedure for acquiring reaction information, which is character information generated as a reaction to second information other than the first information input by the user to the dialogue system, and
An output procedure for outputting the reaction information acquired by the acquisition procedure to the user,
An output program characterized by having a computer execute. The acquisition procedure is
The output program according to claim 1, wherein the reaction information to the second information other than the first information input by the user to the dialogue system, which is a non-task-oriented dialogue system, is acquired. The acquisition procedure is
The output program according to claim 1 or 2, wherein the reaction information with respect to the second information, which is a predetermined content, is acquired. The acquisition procedure is
The output program according to claim 3, wherein the reaction information to the second information, which is a news article, is acquired. The acquisition procedure is
The output program according to claim 3, wherein the reaction information to the second information, which is the posted information in a predetermined SNS (Social Networking Service), is acquired. The acquisition procedure is
The output program according to claim 3, wherein the reaction information to the second information, which is an advertisement, is acquired. The acquisition procedure is
The output program according to any one of claims 1 to 6, wherein the reaction information that triggers a dialogue related to the second information with the user is acquired. The acquisition procedure is
The output program according to any one of claims 1 to 7, wherein the reaction information indicating an impression of the second information of the dialogue system is acquired. The acquisition procedure is
The output program according to any one of claims 1 to 7, wherein the reaction information for requesting an opinion on the second information from the user is acquired. The acquisition procedure is
The output program according to any one of claims 1 to 7, wherein the reaction information for urging the user to take an action related to the second information is acquired. The acquisition procedure is
The output program according to claim 10, further comprising acquiring the reaction information that prompts the user to perform an action other than the response to the reaction information. The output procedure is
The output program according to any one of claims 1 to 11, wherein the reaction information is output at a timing other than the request of the second information by the user to the dialogue system. The output procedure is
The output program according to any one of claims 1 to 12, characterized in that the reaction information is output at the timing related to the push notification in the dialogue system. The output procedure is
The output program according to any one of claims 1 to 13, wherein the reaction information is output at a timing based on the context of the user. The output procedure is
The output program according to claim 14, wherein the reaction information is output at a timing when a predetermined period has elapsed from the user's utterance to the dialogue system. The output procedure is
14. Claim 14 or claim, wherein the reaction information is output at the timing when the user's action related to the second information is performed, which is an action of the user other than the action for the dialogue system. The output program according to 15. The output procedure is
The output program according to claim 16, wherein the reaction information is output at the timing when the user performs a search related to the second information. A generation procedure for generating the reaction information from the second information,
Let the computer run
The acquisition procedure is
The output program according to any one of claims 1 to 17, wherein the reaction information generated by the generation procedure is acquired. The generation procedure is
The output program according to claim 18, wherein the reaction information is generated by inputting the second information into a predetermined model. The acquisition procedure is
The output program according to any one of claims 1 to 19, wherein the reaction information to the second information selected according to the user is acquired. The output procedure is
The output program according to any one of claims 1 to 20, wherein the reaction information is output by voice. The acquisition procedure is
Obtain summary information that is a summary of the second information,
The output procedure is
The output program according to any one of claims 1 to 20, wherein the summary information and the reaction information are output. The output procedure is
The output program according to claim 22, wherein the reaction information is output after the summary information is output. An acquisition unit that acquires reaction information, which is character information generated as a reaction to second information other than the first information input by the user to the dialogue system.
An output unit that outputs the reaction information acquired by the acquisition unit to the user,
An output device characterized by comprising. A computer-executed output method
An acquisition process for acquiring reaction information, which is character information generated as a reaction to second information other than the first information input by the user to the dialogue system, and
An output step of outputting the reaction information acquired by the acquisition step to the user,
An output method characterized by including.

Images