JP7258686B2 - Information processing system, information processing method, and program - Google Patents

Description

The present invention relates to an information processing system, an information processing method, and a program.

A decision device is disclosed that decides whether or not to output sound from a speaker based on image information detected by an image sensor (Patent Document 1).

JP 2019-35897 A

Patent Literature 1 discloses a determination device that determines the timing of audio output from a speaker provided in a user's residence based on image information. Further, the determination device described in Patent Document 1 causes the speaker to output audio at the timing when the audio information is interrupted. According to the determination device of Patent Document 1, it is possible to cause the speaker to output sound according to the situation in the residence. However, the decision device described in Patent Document 1 cannot actively output voice from the speaker to the user.

SUMMARY OF THE INVENTION An object of the present invention is to provide a system for actively outputting sound based on user information of a user using a speaker.

An information processing system according to an aspect of the present invention includes a user information acquisition unit that acquires user information about a user using a speaker device that includes a microphone and a speaker, and based on the user information acquired by the user information acquisition unit: a response content identifying unit that identifies predetermined response content; and audio information based on the predetermined response content identified by the identifying unit so as to cause the speaker device to output voice along with the predetermined response content, and a transmission unit that transmits to the speaker device.

An information processing method according to an aspect of the present invention includes a user information acquisition step in which a computer acquires user information about a user who uses a speaker device including a microphone and a speaker; a response content specifying step of specifying predetermined response content based on the information; and a transmission step of transmitting the audio information based on the above to the speaker device.

A program according to an aspect of the present invention causes a computer to acquire user information about a user who uses a speaker device including a microphone and a speaker, and to specify predetermined response content based on the user information. and causing the speaker device to transmit voice information based on the specified predetermined response content so as to cause the speaker device to output voice along with the predetermined response content.

According to the present invention, it is possible to encourage the user to speak by actively outputting voice to the user based on the user information.

It is a figure which shows an example of a structure of a voice notification system. FIG. 4 is a diagram showing an overview of processing in the voice notification system; It is a figure which shows an example of the functional structure of a response server apparatus. It is a figure which shows an example of a speaker information table. It is a figure which shows an example of a user information table. It is a figure which shows an example of a minutes information table. It is a figure which shows an example of an image information table. It is a figure which shows an example of a response content table. It is a figure which shows an example of the method of acquiring user information. FIG. 10 is a diagram showing another example of a method of acquiring user information; It is a figure which shows an example of the functional structure of a speaker apparatus. It is a figure which shows an example of a functional structure of a user terminal device. It is a flowchart which shows an example of a process of a response server apparatus. It is a figure which shows an example of the hardware constitutions of a computer. FIG. 11 is a flowchart showing another example of processing of the response server device;

A voice notification system 1 according to an embodiment of the present invention will be described in detail below with reference to the drawings. However, the embodiments described below are merely examples, and are not intended to exclude various modifications and application of techniques not explicitly described below. That is, the present invention can be practiced by variously modifying or combining each embodiment without departing from the scope of the invention. In addition, in the following description of the drawings, the same or similar parts are denoted by the same or similar reference numerals.
==Configuration==

FIG. 1 is a diagram showing an example of the configuration of a voice notification system 1. As shown in FIG. As shown in FIG. 1, the voice notification system 1 includes, for example, a response server device 10, a speaker device 20, and a user terminal device 30. FIG. Note that the functions of the response server device 10 and the speaker device 20 may be implemented in one system. Also, the respective functions of the response server device 10 and the speaker device 20 may be realized by a plurality of other devices. Each component of the voice notification system 1 will be described below.

The response server device 10 is a device that causes the user to actively speak from the speaker device 20 by transmitting predetermined audio information to the speaker device 20 . The response server device 10 is composed of an information processing device such as a server computer, for example, and is connected to the speaker device 20 and the user terminal device 30 via the network 200 . Transmission and reception of various data between the response server device 10 and other devices will be described later.

Note that the voice notification system 1 may include a voice recognition server device (not shown). In this case, the response server device 10 functions as a back end when the voice recognition server device recognizes the user's voice using various conventional techniques, analyzes the user's voice, and executes a predetermined response. . That is, the speaker device 20, which will be described later, may use the functions of the response server device 10 by calling the functions provided by the response server device 10 using an API (Application Programming Interface). In the following description, the functions of the speech recognition server device will be omitted as appropriate.

The speaker device 20 is a device that acquires voice from the user, converts the voice into voice information, and transmits the voice information to the response server device 10 . Also, it speaks based on the audio information acquired from the speaker device 20 . The speaker device 20 is a so-called smart speaker. Here, an example of the hardware configuration of the speaker device 20 will be described in order to facilitate understanding of the following description. The speaker device 20 includes, for example, a microphone that detects sound and converts it into an electric signal, a speaker that outputs sound information obtained from the response server device 10, a communication module that communicates with an external device, and a speaker device that can be used visually. 20, an operation button for giving various operation instructions, a support button for communicating with a support operator, and a control unit for controlling each component. The function of the support button will be described later. There are various types of the speaker device 20, for example, one having a plurality of microphones and a plurality of speakers, a device having microphones arranged at equal intervals on the outer circumference of the upper surface, and one having microphones arranged at equal intervals on the outer circumference of the side surface. There is a device in which a speaker is arranged in the device, and the specifications are not limited.

The user terminal device 30 is a terminal device of a user, such as a smart phone. The user terminal device 30 is connected to the response server device 10 via the network 200, and displays various information transmitted from the response server device 10 on the display device 107 shown in FIG. The user uses the user terminal device 30 to make various requests to the response server device 10 . Note that the user terminal device 30 may be connected to the speaker device 20 by short-range wireless communication.
==Overview of Voice Notification System 1==

FIG. 2 is a diagram showing an outline of processing in the voice notification system 1. As shown in FIG. An overview of the operation of the voice notification system 1 will be described with reference to FIG.

First, in S<b>1 , the speaker device 20 transmits speaker information for identifying the speaker device 20 to the response server device 10 . This allows the response server device 10 to grasp the installation location and functions of the speaker device 20 .

Next, in S<b>2 , the user terminal device 30 transmits user information for identifying the user terminal device 30 via the speaker device 20 or directly to the response server device 10 . As a result, which speaker device 20 the user terminal device 30 is associated with is specified in the response server.

Next, in S<b>3 , the response server device 10 transmits audio information specified under predetermined conditions to the speaker device 20 based on the speaker information and the user information. As a result, the speaker device 20 utters appropriate content of sound from the speaker device 20 to the user at an appropriate timing for the user before the user speaks to the speaker device 20 . The content and timing of the sound output from the speaker device 20 will be described later.

Next, in S<b>4 , the response server device 10 acquires the user's voice as voice information via the speaker device 20 and transmits voice information specified based on the voice information to the speaker device 20 . As a result, the user is provided with various information by voice through the speaker device 20 . The information provided will be described later.
== Configuration of voice notification system 1 ==

Functions of the response server device 10, the speaker device 20, and the user terminal device 30 will be described below. In the following description, for ease of understanding, as an example, it is assumed that the user uses the speaker device 20 installed in a predetermined conference room in a conference reserved by a reservation management system (not shown). do.
<<response server device 10>>

A functional configuration of the response server device 10 will be described with reference to FIG. FIG. 3 is a diagram showing an example of the functional configuration of the response server device 10. As shown in FIG. As shown in FIG. 3, the response server device 10 includes a storage unit 11, a speaker information acquisition unit 12a, a user information acquisition unit 12b, a reservation information acquisition unit 12c, a recognition unit 13, a minutes identification unit 14, an image identification unit 15, a response It has the functions of a content identification unit 16 , an analysis unit 17 and a transmission unit 18 . The functions of response server device 10 are implemented by processor 101 shown in FIG.

The storage unit 11 has, for example, a speaker information table 11a, a user information table 11b, a minutes information table 11c, an image information table 11d, and a response content table 11e. Each table shows an example, and its contents are not particularly limited.

The speaker information table 11a is a table storing speaker information. As shown in FIG. 4, the data structure of the speaker information table 11a is a collection of records consisting of data such as installation location and specifications, with appropriate items such as speaker IDs as primary keys. Here, the speaker ID is an identification code for identifying the speaker. The identification code may be any unique number. The installation location is the location where the speaker device 20 is installed, such as a conference room number. The specifications are functional specifications of the speaker device 20 . The contents of the speaker information table 11a are appropriately updated by the administrator of the response server device 10, for example. The response server device 10 can identify the speaker device 20 by referring to the speaker information table 11a.

The user information table 11b is a table that stores user information. As shown in FIG. 5, the data structure of the user information table 11b is a collection of records consisting of data such as names and positions, with appropriate items such as user IDs as primary keys. Here, the user ID is an identification code that identifies a user, and includes, for example, a unique arbitrary number, mobile phone number, MAC (Media Access Control) address, BD (Bluetooth (registered trademark) Device) address, and the like. The name indicates the name of the user. The job title indicates the job title of the user. The contents of the user information table 11b are appropriately updated by the administrator of the response server device 10, for example. The response server device 10 can identify the user who uses the speaker device 20 by referring to the user information table 11b.

The minutes information table 11c is a table that stores minutes information indicating past minutes. As shown in FIG. 6, the data structure of the minutes information table 11c is a set of records composed of data such as minutes content and meeting ID, with appropriate items such as minutes ID as a primary key. Here, the minutes ID is an identification code for identifying the minutes. The contents of minutes are data recording the contents of the minutes of past meetings. The conference ID is an identification code that identifies the conference corresponding to the minutes. The contents of the minutes information table 11c are automatically updated at the end of the conference. By referring to the minutes information table 11c, the response server device 10 can present the minutes of the past conference corresponding to the conference to the user, so that smooth conference management can be realized.

The image information table 11d is a table storing images required for smooth conference management, for example. As shown in FIG. 7, the data structure of the image information table 11d is a collection of records composed of data such as images (including moving images), with appropriate items such as image IDs as primary keys. Here, an image is a still image, a moving image, or the like. The images may include presentation materials and the like used in meetings. The contents of the image information table 11d are appropriately updated by the administrator of the response server device 10, for example. The response server device 10 can present images corresponding to the conference to the user by referring to the image information table 11d, so that smooth conference management can be realized.

The response content table 11e is a table storing response content corresponding to, for example, user information and voice information. As shown in FIG. 8, the data structure of the response content table 11e includes data such as speaker IDs, user IDs, image IDs, minutes IDs, keywords, and response content, with appropriate items such as response content IDs as primary keys. is a set of records consisting of Specifically, the response content ID is associated with an image ID, minutes ID, and the like. For example, the response server device 10 identifies the speaker ID of the speaker device 20 used in a given conference, the user ID of the user terminal device 30 identified in the conference room, and the like, and identifies the corresponding response content ID. Thereby, the response content corresponding to the response content ID is specified. Here, the response content is a simple sentence or a compound sentence corresponding to the meeting, voice information, and user information. The content of the response indicates the voice, image, minutes, etc., and indicates the content of the response to be transmitted to the speaker device 20 . A keyword is a word or the like in text information obtained by converting voice information. The response server device 10 can also specify the contents of the response based on the keyword. The content of the response content table 11e is appropriately updated by the administrator of the response server device 10, for example. By referring to the response content table 11e, the response server device 10 can cause the speaker device 20 to output voices corresponding to the conference or the user, thereby realizing smooth conference management.

The speaker information acquisition unit 12 a acquires speaker information transmitted from the speaker device 20 . The acquired speaker information is stored in the speaker information table 11a.

The user information acquisition unit 12b acquires user information transmitted from the user terminal device 30 using the predetermined speaker device 20. FIG. User information is associated with, for example, speaker information of the speaker device 20 used by the user. Here, the user information acquisition unit 12b may acquire the user information directly from the user terminal device 30 or through the speaker device 20 .

Specifically, as shown in FIG. 9A, when the response server device 10 acquires the user information directly from the user terminal device 30, for example, the QR code (registered trademark) displayed in the conference room or the display device 300 By reading the displayed QR code with the reading function of the user terminal device 30 , the speaker information included in the QR code is added to the user information, and the user information is transmitted to the response server device 10 .

9B, when the response server device 10 acquires user information via the speaker device 20, for example, the user terminal device 30 transmits its own MAC address or BD address to the speaker device 20 as user information. By doing so, the user information and the speaker information are associated, and the information is transmitted to the response server device 10 .

The reservation information acquisition unit 12c acquires reservation information indicating the reservation status of the conference room from a reservation management system (not shown). The reservation information includes, for example, information on date and time, users, conference rooms, and purpose of use. As a result, the response server device 10 can specify, for example, which user uses which meeting room for what purpose at what time.

The recognition unit 13 refers to the speaker information table 11a based on the user information acquired by the user information acquisition unit 12b, and associates and recognizes the user terminal device 30 and the speaker device 20 used by the user. As a result, the response server device 10 can identify which user is using which speaker in which conference room. Here, the response server device 10 may output the user corresponding to the user information recognized by the recognition unit 13 to the display device 300 connected to the speaker device 20 . This makes it possible to grasp the attendance status of the participants in the conference.

The minutes identification unit 14 refers to the minutes information table 11c according to the response content of the response content identification unit when the response content identification unit 16, which will be described later, identifies that the minutes will be used. Identify the prescribed minutes that have been created. The minutes identifying unit 14 may output predetermined minutes identified via the transmitting unit 18 to the display device 300 connected to the speaker device 20 . As a result, the user can check the minutes of the previous meeting output to the display device 300, so that the meeting can proceed smoothly.

When the response content specifying unit 16 (to be described later) specifies that an image is to be used, the image specifying unit 15 refers to the image information table 11d and specifies a predetermined image according to the response content of the response content specifying unit. The image identification unit 15 may output the predetermined image identified via the transmission unit 18 to the display device 300 connected to the speaker device 20 . As a result, the discussion in the meeting can proceed smoothly.

The response content specifying unit 16 refers to the response content table 11e and specifies the response content based on the user information associated with the speaker information. Specifically, a user present in the conference room is identified based on the user information, and appropriate response content for the user is identified. For example, when a user scheduled to participate in a conference specified based on the reservation information enters the conference room, the response content table 11e is referenced based on the user information acquired by the user information acquisition unit 12b, For example, the content of the response confirming the name of the user is specified. The audio information generated based on the identified response content is transmitted to the speaker device 20 via the transmission section 18 . Thereby, the voice can be actively output to the user through the speaker device 20 .

After that, when it is specified that all the users scheduled to participate in the conference are present, for example, based on the acquired user information and reservation information, the response content specifying unit 16 refers to the response content table 11e, and determines whether to participate. Identifies the content of the response confirming the name of the person. Further, for example, when it is specified that the end time of the conference is approaching, the response content table 11e is referenced to specify the content of the response to inquire whether to extend the usage time of the conference room. Audio information generated based on the identified response content is transmitted to the speaker device 20 .

Further, the response content specifying unit 16 determines whether or not to use minutes information indicating past meeting minutes or an image corresponding to the meeting based on the specified response content.

The analysis unit 17 analyzes voice information related to voices uttered by users in the conference. Specifically, for example, the analysis unit 17 analyzes the emotions used by the conference participants based on the voice information. The analysis unit 17 trains a classifier based on, for example, a corpus with tags indicating emotions. The analysis unit 17 converts the user's voice information into text information, and decomposes it into words (morphemes) using, for example, a predetermined natural language analysis technique. Inputting the word into a classifier analyzes the emotion contained in the speech information.

The analysis unit 17 may have a function of giving points to the conference based on the result of analyzing the emotions, for example. For example, if the ratio of positive emotions such as "joy", "enjoyment", and "expectation" is relatively high in the whole meeting, the score will be evaluated high, and emotions such as "disgust", "despair", and "disappointment" If the ratio of Processing is executed so as to transmit information indicating the evaluation result to the speaker device 20 . This gives the user motivation to improve the content of the conference. In other words, the response server device 10 can actively participate in the conference via the speaker device 20, thereby improving the efficiency of the conference.

Also, the analysis unit 17 outputs music suitable for the atmosphere of the conference, for example, based on the result of analyzing the emotions. For example, if negative emotions such as ``disgust'', ``despair'', and ``disappointment'' are present in a relatively large proportion of the whole meeting, information about jazz music that brightens the mind is transmitted to the speaker device 20, for example, If the ratio of emotions such as "anger" is relatively high, processing is executed so as to transmit information about calming classical music to the speaker device 20.例文帳に追加This gives the user motivation to improve the content of the conference. In other words, the response server device 10 functions to actively improve the atmosphere of the conference through the speaker device 20, and the efficiency of the conference can be improved.

For example, the analysis unit 17 refers to the user information table 11b and analyzes the voice information of the user. In the unit 16 , processing is executed so as to specify the content of a response that refrains from speaking from a user with a higher position, and to transmit voice information generated based on the content of the response to the speaker device 20 . This makes it possible to revitalize the meeting and extract diverse opinions.

The transmission unit 18 transmits various information such as voice information to the speaker device 20 .
<<speaker device 20>>

Next, referring to FIG. 10, the functional configuration of the speaker device 20 will be described. FIG. 10 is a diagram showing an example of the functional configuration of the speaker device 20. As shown in FIG. As shown in FIG. 10 , the speaker device 20 has functions of a transmission/reception section 21 , a display control section 22 and a support section 23 . The function of the speaker device 20 is that the control unit (processor 101) of the speaker device 20 shown in FIG. etc.

The transmission/reception unit 21 controls transmission/reception of data in the speaker device 20 . For example, the transmitting/receiving unit 21 transmits voice information related to the voice input to the microphone described above to an external device such as the response server device 10 . Also, the transmission/reception unit 21 receives various information from an external device such as the response server device 10 .

The display control unit 22 controls the display of the display device 107 (display device 300 ) provided in the speaker device 20 or connected to the speaker device 20 . For example, the display control unit 22 generates various screens (user interfaces) necessary for the administrator's setting operation, and controls display on the display device 107 .

The support unit 23 generates support information indicating that a problem has occurred in the speaker device 20 when the above-described support button is pressed. The support unit 23 transmits support information to a support center (not shown) via the transmission/reception unit 21 . As a result, when a problem occurs in the speaker device 20, the administrator can quickly deal with the problem.
<<User terminal device 30>>

Next, referring to FIG. 11, the functional configuration of the user terminal device 30 will be described. FIG. 11 is a diagram showing an example of the functional configuration of the user terminal device 30. As shown in FIG. As shown in FIG. 11 , the user terminal device 30 has the functions of an input section 31 , a transmission/reception section 32 and a display control section 33 . 13, the control unit (processor 101) of the user terminal device 30 reads and executes a computer program stored in the storage device 103, and each component of the user terminal device 30 is configured. It is realized by controlling.

The input unit 31 receives various types of information according to the user's operation on the user terminal device 30 . For example, the input unit 31 receives an input for accessing the response server device 10 according to the user's operation.

The transmission/reception unit 32 controls transmission/reception of data in the user terminal device 30 . For example, the transmission/reception unit 32 transmits information input by the input unit 31 to an external device such as the response server device 10 . The transmission/reception unit 32 also receives notifications and various information from external devices such as the response server device 10 .

The display control unit 33 controls the display of the display device 107 provided in the user terminal device 30 or connected to the user terminal device 30 . For example, the display control unit 33 generates various screens (user interfaces) required for various operations by the administrator and controls display on the display device 107 .
== Operation flow ==

FIG. 12 is a flowchart showing an example of processing of the response server device 10. As shown in FIG. An example of processing executed by the response server device 10 will be described with reference to FIG.

First, in S<b>100 , the response server device 10 acquires speaker information from the speaker device 20 .

Next, in S<b>101 , the response server device 10 acquires user information from the user terminal device 30 or the speaker device 20 . As a result, the response server device 10 can recognize which conference room the user is in.

Next, in S102, the response server device 10 acquires reservation information from the reservation management system based on the user information. Thereby, the response server device 10 can recognize the reservation status of the conference room where the user is present.

Next, in S103, the response server device 10 specifies response content according to the purpose of the conference based on the reservation information. Based on the content of the specified response, the minutes information table 11c or the image information table 11d is referenced to specify minutes information or image information according to the purpose of the meeting.

Next, in S104, the response server device 10 refers to the response content table 11e and specifies response content based on the user information.

Next, in S<b>105 , the response server device 10 transmits audio information regarding the identified response content to the speaker device 20 . For example, through the speaker device 20, at the beginning of the conference, the name of the participant is read aloud to confirm attendance, or the purpose of the conference is notified by voice. As a result, since the speaker device 20 actively speaks to the user, the conference can proceed smoothly.

Next, in S<b>106 , the response server device 10 transmits the minutes information and the image information to the speaker device 20 . The speaker device 20 outputs the acquired minutes information and image information to the display device 300 . For example, the minutes of the previous meeting are displayed on the display device 300 via the speaker device 20, and photographs, graphs, and the like are displayed according to the purpose of the meeting. As a result, the response server device 10 can provide the user with the minutes of past meetings and images required for the meeting in order to facilitate the meeting.

Next, in S107, the response server device 10 determines whether or not the conference has ended. Specifically, the response server device 10 transmits to the speaker device 20 voice information asking whether the conference has ended at a predetermined time. For example, the speaker device 20 outputs a voice saying, "The meeting time is over. Do you want to extend it?" Audio information indicating a response from the user in accordance with the audio output from the speaker device 20 is acquired via the speaker device 20 . For example, when voice information "please extend 30 minutes" is obtained from the user via the speaker device 20, the response server device 10 sends the reservation management system via the transmission unit 18 to the reservation time of the conference room of 30 minutes. Send extension information to extend by minutes. After that, the response server device 10 refers to the response content table 11e based on the voice information of the user and determines whether or not the conference has ended.

If it is determined that the conference has ended (S107: NO), the process is repeated from S104. Thereby, the content of the response corresponding to the user's voice information is specified.

If it is determined that the conference has ended (S107: YES), the content of the conference is analyzed (S108). The analysis result is transmitted to the speaker device 20 . This allows each user to grasp points to be improved in the conference. For example, it outputs voices such as "Today's meeting is 70 points" or "Manager B talks too much".
==Hardware Configuration of Voice Notification System 1==

An example of a hardware configuration when the response server device 10, the speaker device 20 and the user terminal device 30 are implemented by the computer 100 will be described with reference to FIG. The function of each device can also be implemented by being divided into a plurality of devices. Part of the hardware configuration of the speaker device 20 is as described above.

FIG. 13 is a diagram illustrating an example of the hardware configuration of a computer; As shown in FIG. 13, the computer 100 includes a processor 101, a memory 102, a storage device 103, an input I/F section 104, a data I/F section 105, a communication I/F section 106, and a display device. 107.

The processor 101 is a control unit that controls various processes in the computer 100 by executing programs stored in the memory 102 .

The memory 102 is a storage medium such as a RAM (Random Access Memory). The memory 102 temporarily stores program codes of programs executed by the processor 101 and data necessary for executing the programs.

The storage device 103 is a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 103 stores an operating system and various programs for realizing each configuration described above.

The input I/F unit 104 is a device for receiving input from the user. Specific examples of the input I/F unit 104 include a keyboard, mouse, touch panel, various sensors, wearable devices, and the like. The input I/F unit 104 may be connected to the computer 100 via an interface such as USB (Universal Serial Bus).

A data I/F unit 105 is a device for inputting data from outside the computer 100 . A specific example of the data I/F unit 105 is a drive device for reading data stored in various storage media. Data I/F unit 105 may be provided outside computer 100 . In that case, the data I/F unit 105 is connected to the computer 100 via an interface such as USB.

The communication I/F unit 106 is a device for performing data communication with a device external to the computer 100 via the Internet N by wire or wirelessly. Communication I/F section 106 may be provided outside computer 100 . In that case, the communication I/F unit 106 is connected to the computer 100 via an interface such as USB.

The display device 107 is a device for displaying various information. Specific examples of the display device 107 include a liquid crystal display, an organic EL (Electro-Luminescence) display, and a wearable device display. The display device 107 may be provided outside the computer 100 . In that case, the display device 107 is connected to the computer 100 via, for example, a display cable. Further, when a touch panel is adopted as the input I/F section 104 , the display device 107 can be integrated with the input I/F section 104 .
==Other Embodiments==

The response content specifying unit 16 may perform reservation management of conference rooms, for example. For example, the response content specifying unit 16 refers to the response content table 11e based on the reservation information, and specifies the response content asking whether the user is present in the conference room via the speaker device 20. FIG. Specifically, referring to FIG. 14, the response server device 10 first acquires reservation information from the reservation management system (S200). Next, the response server device 10 determines whether or not the conference room is currently reserved (S201). If it is determined that the conference room is reserved (S201: YES), it is determined whether or not there is a person in the conference room by acquiring voice information from the speaker device 20 (S202). If it is determined that there is a person in the conference room (S202: YES), the response content identification unit 16 refers to the response content table 11e based on the reservation information, and asks for the name of the person who reserved the conference room. ("Who are you?", etc.), and transmits voice information regarding the content of the response to the speaker device 20 via the transmission unit 18 (S203). On the other hand, if it is determined that there is no one in the conference room (S202: NO), the response content specifying unit 16 specifies the content of the response asking whether someone is present (such as "Is there anyone?" Audio information about the contents of the response is transmitted to the speaker device 20 . Here, if there is no response to the question from the speaker device 20, the reservation of the reservation management system is canceled (S204). Also, if the conference room is not reserved (S201: NO), it is determined whether or not there is a person in the conference room by acquiring voice information from the speaker device 20 (S205). If it is determined that there are people in the conference room (S205: YES), the response content specifying unit 16 specifies the content of the response asking whether or not to make a reservation (such as "Do you want to make a reservation?" Then, the voice information regarding the content of the response is transmitted to the speaker device 20 (S206). As a result, the response server device 10 actively functions according to the reservation status of the conference room, so that the effective use of the conference room can be achieved.

The response server device 10 may further have the function of a presentation specific execution unit (not shown). The presentation identification execution unit refers to, for example, a presentation material database (not shown) that is open to the public on the cloud, and identifies the presentation material based on the response content identified by the response content identification unit 16 based on the user information. For example, a predetermined keyword in the response content is specified, and the presentation materials related to the keyword are specified. The presentation identification execution unit transmits information about the identified presentation material to the speaker device 20 via the transmission unit 18, converts the text information described in the presentation material into voice information, and transmits the voice information to the speaker. Send to device 20 . As a result, the response server device 10 can actively provide the presentation material to the user via the speaker device 20, and can also provide voice guidance regarding the contents of the presentation material, thereby improving the efficiency of the conference.

Also, the presentation identification execution unit (not shown) may identify a keyword for the purpose of using the conference room based on the reservation information, and identify the presentation materials related to the keyword. The presentation identification execution unit transmits information about the identified presentation material to the speaker device 20 via the transmission unit 18 . Then, the text information described in the presentation material is converted into voice information, and the voice information is transmitted to the speaker device 20 via the transmission unit 18 . As a result, presentation materials suitable for the purpose of the conference are automatically specified in the response server device 10, so that the conference can proceed smoothly.

The response content specifying unit 16 may have a function of specifying the response content to the user's question during the presentation through the speaker device 20, for example. First, the response content identification unit 16 converts the voice information regarding the question into text information. Next, the response content specifying unit 16 acquires the response content corresponding to the text information from the response content table 11e. Specifically, for example, text information is analyzed to extract keywords. Based on the extracted keyword, the response content table 11e is searched, and the type of question (person's name, place name, quantity, etc.) is specified. An answer is specified by specifying words corresponding to the specified question type from among the response contents extracted from the response content table 11e by searching. As a result, the response server device 10 actively executes the presentation and also answers the user's questions, so that the conference can proceed smoothly.

The response server device 10 may further have a function of a minutes creation unit (not shown) that creates minutes of a conference, for example. The minutes creation unit converts, for example, the user's voice information acquired via the speaker device 20 into text information, and inputs the text information as minutes in a predetermined format. Processing is executed so as to transmit to the user terminal device 30 information indicating a predetermined format in which text information is input. As a result, it is possible to reduce the work required for the user to create the minutes.

For example, instead of acquiring user information from the user terminal device 30, the response server device 10 may acquire the user's voice acquired by the speaker device 20 as user information. In this case, the response server device 10 has a voiceprint information database (not shown) that stores voiceprint information relating to the voiceprint of each user, and identifies the user by comparing the acquired voice information and the voiceprint information. As a result, it is possible to recognize a user who does not have the user terminal device 30, so that the sound notification system 1 can be reliably operated.

For example, instead of acquiring user information from the user terminal device 30, the response server device 10 may acquire face information about the user's face from a camera device (not shown) as user information. In this case, the response server device 10 has a face information database (not shown) that stores face information for each user, and identifies the user by comparing the acquired face information with the face information stored in the face information database. . As a result, it is possible to recognize a user who does not have the user terminal device 30, so that the sound notification system 1 can be reliably operated.

The response server device 10 may further include, for example, a timer (not shown) that measures the timing of executing various functions. The response server device 10 can execute a predetermined function at a predetermined time and execute a predetermined function after the predetermined time has elapsed by measuring a predetermined time and the passage of the predetermined time in the timer unit. As a result, the response server device 10 can actively perform its function at an appropriate timing, so that the conference can proceed smoothly.

In the above description, the speaker device 20 has been described as being installed in the conference room, but the present invention is not limited to this. The speaker device 20 can be installed in a place used by an unspecified number of users. Thereby, the voice notification system 1 actively speaks to the user at various places such as a private house, an entrance of a collective housing, a shop, a meeting place, and the like. By actively outputting voice to the user at various places, it is possible to encourage the user to speak.

It should be noted that the above-described embodiment is for facilitating understanding of the present invention, and is not for limiting interpretation of the present invention. The present invention may be modified and improved without departing from its spirit, and the present invention also includes equivalents thereof.

DESCRIPTION OF SYMBOLS 1... Voice notification system 10... Response server apparatus 11... Storage part 12a... Speaker information acquisition part 12b... User information acquisition part 12c... Reservation information acquisition part 13... Recognition part 14... Minutes identification part 15... Image identification unit 16... Response content identification unit 17... Analysis unit 18... Transmission unit 20... Speaker device 30... User terminal device

Claims (9)

User information that can identify a user who has accessed the speaker device is acquired from a speaker device having a microphone and a speaker when the user enters a conference room, and the conference room is reserved based on the user information. an acquisition unit that acquires reservation information regarding the reservation status of the conference room from a reservation management system that manages the
based on the user information and the reservation information acquired by the acquisition unit, specifying that users scheduled to participate in the conference in the conference room have gathered, and when it is specified that the users have gathered, the conference will be held; a response content identification unit that identifies the content of the response indicating that the name of the participant is to be confirmed ;
a transmitting unit configured to transmit audio information based on the response content specified by the response content specifying unit to the speaker device so as to cause the speaker device to output voice along with the response content;
An information processing system comprising The response content identifying unit is configured to inquire whether or not to extend the usage time of the conference room at a time when it is identified that the meeting ends at a predetermined time before the end time of the conference room. identify the
The information processing system according to claim 1 . The acquisition unit acquires the user information related to the user's voice from the speaker device,
The information processing system is
Analysis for analyzing emotions included in speeches of users participating in the conference in the conference room based on user information about the user's voice, and giving points to the conference in the conference room based on the analyzed emotions. further comprising the
The transmission unit transmits analysis information indicating a score, which is the result of analysis by the analysis unit, to the speaker device.
3. The information processing system according to claim 1 , wherein: The response content identification unit identifies image response content, which is response content indicating that a predetermined image is to be used, based on the reservation information,
The information processing system is
further comprising an image specifying unit that specifies the predetermined image based on the image response content specified by the response content specifying unit;
The transmitting unit transmits image information regarding the predetermined image to the speaker device so as to output the predetermined image to a display device connected to the speaker device.
4. The information processing system according to any one of claims 1 to 3 , characterized by: The response content identification unit identifies, based on the reservation information, minutes response content, which is response content indicating use of past minutes,
The information processing system is
Further comprising a minutes identification unit that identifies predetermined minutes information from a past database holding minutes information related to the past minutes based on the response content identified by the response content identification unit,
The transmission unit transmits the minutes information to the speaker device so as to output the minutes to a display device connected to the speaker device.
5. The information processing system according to any one of claims 1 to 4 , characterized by: The response content specifying unit specifies presentation response content, which is response content indicating that a predetermined presentation material is to be used, based on the reservation information,
a presentation identification execution unit that identifies presentation material information indicating presentation materials from a predetermined database based on the content of the presentation response;
further comprising
The transmission unit transmits the presentation material information so that the speaker device outputs the presentation material to a display device connected to the speaker device.
6. The information processing system according to any one of claims 1 to 5 , characterized by: The information processing system according to any one of claims 1 to 6 , further comprising the speaker device. the computer
User information that can identify a user who has accessed the speaker device is acquired from a speaker device having a microphone and a speaker when the user enters a conference room, and the conference room is reserved based on the user information. an acquisition step of acquiring reservation information regarding the reservation status of the conference room from a reservation management system that manages the
Based on the user information and the reservation information acquired in the acquiring step, it is specified that users scheduled to participate in the conference in the conference room have gathered, and when it is specified that the users have gathered, the conference is held. a response content identification step of identifying response content indicating confirmation of the name of the participant ;
a transmission step of transmitting audio information based on the response content specified in the response content specifying step to the speaker device so as to cause the speaker device to output voice along with the response content;
Information processing method that performs to the computer,
User information that can identify a user who has accessed the speaker device is acquired from a speaker device having a microphone and a speaker when the user enters a conference room, and the conference room is reserved based on the user information. Acquiring reservation information regarding the reservation status of the conference room from a reservation management system that manages the
Based on the user information and the reservation information, it is specified that the users scheduled to participate in the conference in the conference room are present, and when it is specified that the users are present, the names of the participants of the conference are confirmed. specifying the content of the response indicating that
causing the speaker device to transmit audio information based on the identified response content in order to cause the speaker device to output audio along with the response content;
program to run.

Images