JP2022089968A - Information provision method, information provision system, information provision device, and computer program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information provision method capable of providing information by using audio and text input and output as appropriate, an information provision system, an information provision device, and a computer program.

SOLUTION: An information provision system has an information provision device that includes: a user interface placed in a hotel; a request acquisition unit that acquires a request based on a voice input to a user interface; a response information acquisition unit that acquires a piece of response information to the request acquired by the request acquisition unit from a database; an audio output processing unit that performs a series of processing to output a piece of response information acquired by the response information acquisition unit to the user interface via voice; and a processing unit that is configured so as to, when the response information cannot be acquired from the database, perform a series of processing to switch to an automatic response by means of text input/output.

SELECTED DRAWING: Figure 2

COPYRIGHT: (C)2022,JPO&INPIT

Description

Application for application of Article 30, Paragraph 2 of the Patent Act is available: HOTEL EMIT SHIBUYA (Hotel Emit Shibuya) on October 1, 2018, MIMARU Tokyo Akasaka on November 9, 2018, MIMARU Kyoto on November 9, 2018. Published at Shinmachi Sanjo and 4 other locations International Hotel Ryokan on November 20, 2018 International Hotel Ryokan November 20, 2018 No. 440, 2nd page, March 5, 2019, International Hotel Ryokan 2019 Published on page 2 of No. 447 on March 5, 2018 Published on page 4 of Nikkei MJ October 29, 2018 on October 29, 2018 Weekly building management on October 22, 2018 Published on page 20 of No. 1075 on October 22, 2018 Published on the Nikkei Cross Trend website on March 27, 2019 (https://xtrend.nikkei.com/atcl/entents/18) / 00130/00003 /? P = 1) (https://xtrend.nikkei.com/atcl/contents/18/00130/00003/?P=2) HOTELES (Weekly Hotel Restaurant) on March 8, 2019 ) Published on page 53 of Vol. 54, No. 10 Published on the Nikkei electronic version website on June 3, 1991 (https://www.nikkei.com/article/DGXMZO43221200S9A400C100000/?fbclid= IwAR)

Application for application of Article 30, Paragraph 2 of the Patent Law is available. Published on the PR TIMES website on September 28, 2018 (html: //prtimes.jp/main/html/rd/p/000000003.000033116.html) (Httpss: //prtimes.jp/main/html/rd/p/000000006.000003116.html) (https://prtimes.jp/main/html/rd/p/000000012.000033116.html) (html: //prtimes.jp/main/html/rd/p/000000012.000033116.html) //Prtimes.jp/main/html/rd/p/000000014.000003116.html) (https://prtimes.jp/main/html/rd/p/000000015.000033116.html) (https: // html. jp / main / html / rd / p / 0000000018.000003116.html) (https://prtimes.jp/main/html/rd/p/0000200020000000003116.html) On March 18, 2019, N- ＬＩＯのウェブサイトにて公開 （ｈｔｔｐｓ：／／ｎ－ｌｉｏ．ｃｏｍ／ｔｒａｄｆｉｔ－１／？ｆｂｃｌｉｄ＝ＩｗＡＲ１ｇｓＹｂｗＫｐＸ８ｓＰＪＩＡＮｈｗｆＱｕｙ＿Ｑｃ３ＴｇＢｂＤＤＪＷＶｇＩＬ＿ａｋＭｂＩＤＷｆｉｙｅｃｕ５ｃｔＮＭ） （ｈｔｔｐｓ：／／ｎ－ｌｉｏ．ｃｏｍ／ｔｒａｄｆｉｔ－２／？ｆｂｃｌｉｄ＝ＩｗＡＲ０Ｆｓｄ５ＨＤＴ３ＶＹｓｚｇＩｋＢＳＷＰ８ＸＱＳｎｅＶＫＮＷｌＢＷＲｎＢＮＷ５ｅ９ｇｕＯｘＰｊ４ｚｙｌｆｇＫｂｅ８）

Application for application of Article 30, Paragraph 2 of the Patent Act is available. Published on the website of HotelBank on January 18, 2019 (https://hotelbank.jp/ai-chatbot-speaker-tradfit-hitocommunics /) (https: ／／ｈｏｔｅｌｂａｎｋ．ｊｐ／ｔｒａｄｆｉｔ－ｉｎｔｅｒｖｉｅｗ－２０１９／？ｆｂｃｌｉｄ＝ＩｗＡＲ３Ｕｂ－ｗＱＡｋＧｘｉｋＣａＱｘｖ０８ｏａ６ＵＨｇＦＺＥＹＡａｖ７ｑＩｄ２ＭＲＢＺＬＭＨＥＰ０ｄ２－ｋＯｍＤｏ＿Ｅ） （ｈｔｔｐｓ：／／ｈｏｔｅｌｂａｎｋ．ｊｐ／ｈｙａｔｔ－ｒｅｇｅｎｃｙ－ｔｏｋｙｏ－ｔｒａｄｆｉｔ／） 平成３１年 １月 ７日に、Ｔｅｃｈ ｉｎ Published on the Asia website (https://www.techinasia.com/tech-southeast-asia-surging-tourist-arrivals) Published on the CANVAS8 website on January 10, 2019 (https: / /Livery.canvas8.com/signals/2019/01/10/tradfit-tourism.html) Published on the website of HOTELIER on November 12, 2018 (https://www.hotelier.jp) ／ｉｎｂｏｕｎｄｎｅｗｓ／ｓｅｒｖｉｃｅ／ｐｏｓｔ－９７４３．ｈｔｍｌ？ｆｂｃｌｉｄ＝ＩｗＡＲ１－ｎＥ２７３ＭＰＵｓ９ＱｉＬａＺｗ５ＯＱｄｐａ＿１ｔｓＯｂｘｔｍＦＸｅ３ＣＵ３ｓｄＡｋｃｋＺＷＮｃｏｒＶＮｔｖｏ） （ｈｔｔｐｓ：／／ｗｗｗ．ｈｏｔｅｌｉｅｒ．ｊｐ／ｉｎｂｏｕｎｄｎｅｗｓ／ｓｅｒｖｉｃｅ／２０１９０１２９－００３．ｈｔｍｌ？ｆｂｃｌｉｄ＝ＩｗＡＲ２ｈｎＫ９０ｗ１ｊＺＡＳｙｆｙＬｖｕＲｒＺ１ＩＸＤｑｗＯＭＥ－ＷＺＨＫＧｒＣｐｒＳＡｃｙｏｓｅＰＬｄｘＢｍＯＪｇＵ） 平成３０年１０月１０ Published on the Digital Daily Website on January (https://mainichi.jp/articles/20181011/k00/00m/020/043000c)

Application for application of Article 30, Paragraph 2 of the Patent Act is available. Published on the AMP website on September 29, 2018 (https://amp.review/2018/09/29/hotel_ai/) October 2018 Published on the website of the Shunkan Travel Newspaper on the 2nd (http://www.ryoko-net.co.jp/?p=42827) On the website of the Tourism Economic Newspaper on January 28, 2019. Published (https://www.kankokeisai.com/%E5%B0%8F%E7%94%B0%E6%80%A5%E3%83%9B%E3%83%86%E3%83%AB%E3 % 82% BB% E3% 83% B3% E3% 83% 81% E3% 83% A5% E3% 83% AA% E3% 83% BC% E3% 82% B5% E3% 82% B6% E3% 83 % B3% E3% 82% BF% E3% 83% AF% E3% 83% BC% E3% 80% 81ai-% E3% 82% B9% E3% 83% 94 /) On January 14, 2019, Published on the website of dietnambiz (https://bytenambiz.vn/loa-thong-minh-chatbot-dich-ngon-ngu-se-len-ngoi-trong-thoi-dai-du-lic-bun- 117501.htm) Published on the OK SKY website on February 13, 2019 (https://mag.ok-sky.jp/%E3%83%9B%E3%83%86%E3%83) % AB% E3% 81% AB% E3% 82% 82% E5% B0% 8E% E5% 85% A5% E3% 81% 95% E3% 82% 8C% E3% 82% 8B% E3% 82% B9 % E3% 83% 9E% E3% 83% BC% E3% 83% 88% E3% 82% B9% E3% 83% 94% E3% 83% BC% E3% 82% AB% E3% 83% BC% E3 % 81% A8% E3% 83% 81% E3% 83% A3 /) Published on the DIGITAL X website on October 30, 2018 (https://dcross.impress.co.jp/docs/) usse / 00735.html)

Application for application of Article 30, Paragraph 2 of the Patent Act has been submitted. Published on the SankeiBiz website on September 28, 2018 (https://www.sankeibiz.jp/busines/news/180928/prl1809281313120-n1.hmm). Published on the Sankei News website on September 29, 2018 (https://www.sankei.com/economy/news/180929/prl1809290029-n1.html) On January 18, 2019, TradFit Published on the website of NEWSLEREEASE operated by Co., Ltd. (http://file.swcms.net/file/hitocom/ja/tekiji/auto_201901118460795/pdfFile.pdf) CNET Japan website on October 11, 2018. Published on the site (https://japan.cnet.com/article/351267787/) Published on the website of the electronic version of the Nikkan Kogyo Shimbun on January 7, 2019 (https://www.nikkan.co) .Jp / releases / view / 90314) Published on the MIMARU Hotel website on November 9, 2018 (https://mimaruhotels.com/ja-jp/news-topics/news2018109.pdf) 2019 Published on the website of Odakyu Hotel Century Southern Tower on January 18, 2019 (https://www.outhertourter.co.jp/Portals/0/newsrelease/2018/aispeeker_chatbot.pdf) On January 18, 2019 , TV Tokyo released on a program called "WBS (World Business Satellite)" AbemaTV released on a program called "Keyaki Hills" on October 12, 2018

The present disclosure relates to an information providing method, an information providing system, an information providing device, and a computer program for providing various information to a user who uses an accommodation facility.

Systems that allow users to input voice to devices are becoming widespread. As such a system, a device called, for example, a smart speaker or an AI (Artificial Intelligence) speaker has begun to be installed in a home. The user can obtain various information by voice output from the smart speaker by asking a question by voice to the smart speaker. The user can also control the operation of home appliances by issuing voice commands to the smart speaker.

Patent Document 1 proposes a communication system that establishes a dialogue in natural language between a user and a robot. The robot has a microphone and a speaker, transmits the user's utterance acquired by the microphone to the server, receives a response from the server, and outputs the response by voice from the speaker. The server has a conversation database of questions and answers used for conversation, and refers to this conversation database to generate a response to a user's utterance and send it to a robot.

Japanese Unexamined Patent Publication No. 2017-191531

Although devices capable of voice input are becoming widespread, current devices cannot accurately respond to all of the various requests made by users. Further, voice input has a problem that the accuracy is lower than that of text input.

The present disclosure has been made in view of such circumstances, and its purpose is to provide information by appropriately using input / output of voice and text, an information providing method, an information providing system, and information provision. To provide equipment and computer programs.

The information providing method according to the present disclosure acquires a request based on the voice input to the user interface installed in the accommodation facility, acquires the response information corresponding to the acquired request from the database, and uses the acquired response information as the user. It is output by voice to the interface, and when the response information cannot be obtained from the database, it is switched to an automatic response by input / output of text.

In the present disclosure, a request based on voice input from the user is acquired by the user interface installed in the accommodation facility, and the response information to the acquired request is output by voice in the user interface. If it is not possible to output the response information for the acquired request, switch to automatic response by input / output of text. This allows the user to easily switch from audio input / output to text input / output.

In the case of the present disclosure, information can be provided to the user by appropriately using the input / output of voice and text.

It is a schematic diagram for demonstrating the outline of the information provision system which concerns on this embodiment. It is a schematic diagram for demonstrating the outline of the information provision system which concerns on this embodiment. It is a schematic diagram which shows an example of the access information displayed on a smart speaker. It is a schematic diagram which shows an example of a chat screen displayed on a smartphone. It is a schematic diagram which shows an example of a chat screen displayed on a smartphone. It is a block diagram which shows the structure of the smart speaker which concerns on this embodiment. It is a block diagram which shows the structure of the management server which concerns on this embodiment. It is a schematic diagram which shows one configuration example of an intention identification model. It is a schematic diagram which shows one configuration example of a response information DB. It is a schematic diagram which shows one configuration example of an operator DB. It is a block diagram which shows the structure of the smartphone which concerns on this embodiment. It is a flowchart which shows the procedure of the process performed by the smart speaker which concerns on this embodiment. It is a flowchart which shows the procedure of the switching control processing performed by the management server which concerns on this embodiment. It is a flowchart which shows the procedure of the chat start processing performed by the smartphone which concerns on this embodiment. It is a flowchart which shows the procedure of the chat processing performed by the smartphone which concerns on this embodiment. It is a flowchart which shows the procedure of the switching control processing performed by the management server which concerns on this embodiment. It is a flowchart which shows the procedure of the switching process to the manned response performed by the management server which concerns on this embodiment. It is a flowchart which shows the procedure of the learning process of the intention identification model performed by the management server which concerns on this embodiment. It is a schematic diagram for demonstrating the information provision before accommodation by the information provision system which concerns on this embodiment. It is a schematic diagram which shows an example of the access information displayed on the smart speaker which concerns on Embodiment 2. FIG. It is a flowchart which shows the procedure of the process performed by the smart speaker which concerns on Embodiment 2. FIG. It is a flowchart which shows the procedure of the voice communication start processing performed by the smartphone which concerns on Embodiment 2. FIG.

A specific example of the information providing system according to the embodiment of the present disclosure will be described below with reference to the drawings. It should be noted that the present disclosure is not limited to these examples, but is shown by the scope of claims and is intended to include all changes in the meaning and scope equivalent to the scope of claims.

<System overview>
1 and 2 are schematic views for explaining an outline of the information providing system according to the present embodiment. The information providing system 10 according to the present embodiment can provide information to a user by using a smart speaker 20 installed as a user interface in an accommodation facility such as a hotel guest room, a common area, or a private house used for a private lodging. The smart speaker 20 shown in FIG. 1 has a configuration in which a touch panel 25, a microphone 26, a speaker 27, a camera 28, and the like are appropriately arranged in a substantially hemispherical housing. However, the shape of the smart speaker 20 is an example and is not limited to this, and various shapes such as a columnar shape or a rectangular parallelepiped shape can be adopted. The user interface installed in the guest room is not limited to the smart speaker 20, and may be any device as long as it is an information processing device capable of input / output by voice.

A user (guest) staying in a guest room can activate the smart speaker 20 by speaking a specific keyword (for example, "start service"). The user can give various requests to the smart speaker 20 by voice input by utterance, and various information such as information about this accommodation facility can be obtained from the voice response information output from the smart speaker 20. .. In the illustrated example, the user gives an utterance request to the smart speaker 20 "tell me the check-out time". In the present embodiment, various requests or questions that the user inputs to the smart speaker 20 or the like are referred to as requests.

The voice request input by the user to the smart speaker 20 is input to the voice processing server 50 via a network such as the Internet. The voice processing server 50 converts the input voice information into text (character string) information by performing voice recognition processing on the voice input. The voice processing server 50 inputs the converted text to the management server 30.

The management server 30 performs a process of generating response information to a user's request based on the text information input from the voice processing server 50. For this process, the management server 30 uses the intention identification model 81 and the response information DB (database) 82. The intention identification model 81 is a trained model that has been trained in advance so as to accept text information related to a request as input and output an identification result that identifies the user's intention related to this request. The response information DB 82 is a database in which the intention related to the request and the text of the response message to the intention are stored in association with each other. In this example, the management server 30 includes the intention identification model 81 and the response information DB 82, but the present invention is not limited to this, and the intention identification model 81 or the response information DB 82 may be provided by another server.

The management server 30 inputs the text information obtained from the voice processing server 50 into the intention identification model 81, and acquires the information output by the intention identification model 81 to acquire the intention of the user's request. In the example shown in FIG. 1, the intention identification model 81 identifies the user's intention to inquire about the checkout time for the text information of "tell me the checkout time". Next, the management server 30 acquires the text information of the response message to the intention of the request by referring to the response information DB 82 based on the intention of the identified user. The management server 30 outputs the text information acquired from the response information DB 82 to the voice processing server 50. In the example shown in FIG. 1, text information such as "Please check out by 10 am" is stored in the response information DB 82 as response information in response to the intention of inquiring about the checkout time.

The voice processing server 50 to which the text output of the response information is given from the management server 30 converts the given text information into voice information. The voice processing server 50 outputs the converted voice information to the smart speaker 20. The smart speaker 20 acquires voice information output from the voice processing server 50, and outputs voice based on this voice information on the speaker 27. In the example shown in FIG. 1, the smart speaker 20 outputs the voice "Please check out by 10 am".

The management server 30 can also respond to a request from the user to the smart speaker 20 other than the voice output. For example, the management server 30 can display an image on the touch panel 25 of the smart speaker 20. In this case, the management server 30 outputs the information of the image for display to the voice processing server 50, and the voice processing server 50 gives this image information to the smart speaker 20.

Further, in the above-mentioned information provision to the user by voice input / output, for example, when the language spoken by the user is not included in the language supported by the voice processing of the voice processing server 50, for example, the content of the user's speech is described by the voice processing server 50. When it is not possible to properly convert to text information, it may not be possible to provide appropriate information to the user. In the information providing system according to the present embodiment, when it is not possible to appropriately provide information by voice input / output, it switches to information provision by text input / output. A system that automatically responds by inputting / receiving text is a so-called chatbot, and the information providing system according to the present embodiment provides information using the smart speaker 20 and information providing using the chatbot. It is a system that switches between and appropriately.

The management server 30 is notified, for example, that the voice processing server 50 cannot convert the voice into text, or, for example, when the intention identification model 81 cannot identify the intention of the user's request. A message prompting the user to switch to the chatbot is output to the smart speaker 20. The message can be, for example, "The voice request could not be recognized. Do you want to use a chatbot?" This message may be output by the smart speaker 20 as voice, or may be displayed as text on the touch panel 25. When the user indicates the intention to affirm the use of the chatbot in response to this message, the management server 30 provides access information for accessing the chatbot using a terminal device such as a smartphone 40. Output to the smart speaker 20. The user's will to decide whether or not to use the chatbot may be accepted, for example, as a voice input, or may be accepted, for example, by a touch operation on the touch panel 25 of the smart speaker 20.

FIG. 3 is a schematic diagram showing an example of access information displayed on the smart speaker 20. In the information providing system according to the present embodiment, the smart speaker 20 displays the access information 20a on the touch panel 25. The illustrated access information 20a is a two-dimensional code (for example, a barcode or a QR code (registered trademark)), and is a code of information such as a URL (Uniform Resource Locator) for accessing a chatbot, for example. Further, in the present embodiment, the access information 20a includes identification information for identifying an accommodation facility, a guest room, or the like. As a result, the chatbot can acquire the identification information included in the access information 20a and perform an automatic response suitable for the accommodation facility, the guest room, and the like. However, the access information 20a may be configured to include only information such as a URL and not to include identification information such as accommodation facilities and guest rooms. In this case, for example, the user may input information about accommodation facilities, guest rooms, and the like.

The user can acquire information such as a URL for accessing the chatbot by photographing the access information 20a displayed on the smart speaker 20 with the camera of his / her smartphone 40. The user who has acquired the access information 20a can start using the chatbot by accessing the server that provides the chatbot service using an application such as a browser installed on the smartphone 40. In this embodiment, the management server 30 provides the chatbot service. A chat screen is displayed on the display unit of the smartphone 40, and the user can input the request as text on the chat screen by using the text input function of the smartphone 40.

4 and 5 are schematic views showing an example of a chat screen displayed on the smartphone 40. FIG. 4 shows an example of displaying a selection box that prompts the user to select a language prior to using the chatbot. In this embodiment, English, Japanese, Chinese, Korean, and the like can be used as chat languages, and selectable languages are listed in the selection box in the notation of the language. The user can select any one language by performing a touch (tap) operation on the language displayed in the selection box.

The language selection box shown in FIG. 4 is not only displayed prior to the start of chat, but also when the user touches the language selection icon provided on the lower left side of the chat screen shown in FIG. May also be displayed. The language selection icon is labeled to indicate which language is currently selected. Further, on the chat screen of FIG. 5, a switching icon for switching to a manned response is displayed next to the language selection icon.

In the present embodiment, the user selects a language using the selection box shown in FIG. 4, but the present embodiment is not limited to this. For example, information such as the nationality of the user may be acquired from a server device that stores information about the guest of the accommodation facility, and a language suitable for the user may be automatically selected.

Further, FIG. 5 shows an example of a request and response by chat. In the illustrated example, English is selected as the chat language. In the illustrated chat screen, for example, title character strings such as "hotel information service", "Example hotel", and "inquiry" are displayed at the top, and this chat screen is a chat screen for making inquiries to the hotel. It is shown. Below the title string, the text of the request entered by the user and the text of the response to it are displayed in chronological order from top to bottom. In addition, the text entered by the user is displayed on the right side of the chat screen, and the text of the response by the chatbot is displayed on the left side. In this example, the text "How many waters would you like to order?" Is output as the response information to the text of the request "I want a water." By the user.

The text information input by the smartphone 40 is input to the translation server 60 via a network such as the Internet. The translation server 60 translates the input text information as needed. When a text in a language other than the language supported by the management server 30 is input, the translation server 60 translates the text into a language supported by the management server 30. For example, when the management server 30 can handle Japanese and English and a Chinese request is input, the translation server 60 translates the request from Chinese to Japanese or English and inputs the translated text information. Input to the management server 30. When the text information that does not need to be translated is input to the translation server 60, the text information may be input to the management server 30 without translation.

The management server 30 performs a process of generating response information to a user's request based on the text information input from the translation server 60. The processing of the management server 30 performed at this time is the same as the processing of generating response information to the user's request by voice input, and is performed using the above-mentioned intention identification model 81 and response information DB 82. The management server 30 outputs the response information of the generated text to the translation server 60. The translation server 60 appropriately translates the response information given by the management server 30 as necessary, and outputs the response information to the smartphone 40. The smartphone 40 automatically responds to the request input by the user by displaying the response information given as text from the translation server 60 on the chat screen as text. The management server 30 includes an intention identification model 81 and a response information DB 82 for acquiring response information for a voice input request, and an intention identification model 81 and a response information DB 82 for acquiring response information for a text input request. You may prepare separately.

Information is provided to the user by the chat bot, for example, when the request input by the user in text cannot identify the intention by the intention identification model 81, or when the response information corresponding to the response information DB 82 is not stored, for example. It may not be possible to provide appropriate information to the user. In the information providing system according to the present embodiment, when the information cannot be appropriately provided by the text input / output of the chatbot, the operator switches to the manned response. In the information providing system according to the present embodiment, there is an operator who responds to the request from the user in place of the management server 30 when the request from the user cannot be responded to by the automatic response. The operator can use the operator terminal 70 to exchange textual information with the user's smartphone 40, that is, to chat. The user can chat with the operator using the same chat screen as the chatbot's auto-answer.

When the management server 30 determines that the automatic response by text input / output cannot be performed, the management server 30 causes the smartphone 40 to output a message prompting the switching to the manned response. The message can be, for example, "We cannot answer your request. If you want to switch to a manned response, please touch the switch icon below." When the user performs a touch operation of the switching icon in response to this message and the user indicates the intention to affirm the switching to the manned response, the management server 30 notifies the operator terminal 70 to request the manned response. To switch from the chatbot's automatic response to the operator's manned response.

It should be noted that switching to a manned response by touching the switching icon provided on the chat screen may be accepted only when the management server 30 outputs a message prompting the switching to the smartphone 40, and whether or not this message is output may be accepted. Regardless, it may be accepted at all times. When the management server 30 accepts the switch only when the message prompting the switch is output to the smartphone 40, the switch icon may not be displayed on the chat screen when it is not needed.

After switching to the manned response by the operator, the management server 30 inputs the information of the text input by the user on the smartphone 40 and translated by the translation server 60 as necessary, and transmits the information of the text to the operator terminal 70. The operator terminal 70 displays a chat screen similar to that in FIG. 5 on the display unit based on the text information from the management server 30. The operator inputs the information of the response to the user's request displayed on the operator terminal 70 to the operator terminal 70 by using an input device such as a keyboard. In the present embodiment, the operator inputs text to the operator terminal 70, but the present invention is not limited to this, and a configuration such as voice input may be performed. The operator terminal 70 accepts the text input of the response by the operator and transmits the accepted text information to the management server 30. The management server 30 gives the text information from the operator terminal 70 to the translation server 60, and the text information translated by the translation server 60 is given to the user's smartphone 40 as needed. The smartphone 40 displays the given text information on the chat screen. As a result, communication by the user and the operator via text is established, and the operator can respond to the user's request.

In the present embodiment, switching from information provision by voice input / output using the smart speaker 20 to information provision by text input / output using the smartphone 40 is performed via the access information displayed on the smart speaker 20. Although it is configured, it is not limited to this. For example, when a device capable of using both audio input / output and text input / output is installed in a guest room or the like, the management server 30 outputs an instruction to switch from audio input / output to text input / output to the device. Based on the output, the device may switch from audio input / output to text input / output.

<Device configuration>
FIG. 6 is a block diagram showing the configuration of the smart speaker 20 according to the present embodiment. The smart speaker 20 according to the present embodiment includes a processing unit (processor) 21, a storage unit (storage) 22, a communication unit (transceiver) 23, a touch panel 25, a microphone 26, a speaker 27, a camera 28, and the like. There is. The processing unit 21 is configured by using an arithmetic processing unit such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit). Further, the processing unit 21 may employ a plurality of CPUs, a multi-core CPU, or the like. The processing unit 21 reads and executes the program 22a stored in the storage unit 22 to perform various processes such as reception of voice input, voice output, and image display.

The storage unit 22 is configured by using, for example, a non-volatile memory element such as a flash memory, a magnetic storage device such as a hard disk, or the like. The storage unit 22 stores various programs executed by the processing unit 21 and various data required for processing by the processing unit 21. In the present embodiment, the storage unit 22 stores the program 22a executed by the processing unit 21 and the identification information 22b for identifying the smart speaker 20.

The program 22a may be written to the storage unit 22 at the manufacturing stage of the smart speaker 20, for example. For example, in the program 22a, the smart speaker 20 may acquire what is distributed by a remote server device or the like by communication. For example, in the program 22a, the smart speaker 20 may read the program 22a recorded on the recording medium 99 such as a memory card or an optical disk and store it in the storage unit 22. For example, in the program 22a, the writing device may read out what has been recorded on the recording medium 99 and write it in the storage unit 22 of the smart speaker 20. The program 22a may be provided in the form of distribution via the network, or may be provided in the form recorded on the recording medium 99.

The identification information 22b is information in which characters, numerical values, and the like are appropriately combined, and may be any information as long as it can identify the smart speaker 20. In the present embodiment, the identification information 22b is information in which information for identifying the accommodation facility in which the smart speaker 20 is installed and information for identifying the guest room are combined. For example, the identification information 22b can be information indicating room 301 of the Example hotel. The identification information 22b is set by the system administrator, the accommodation facility administrator, or the like when the smart speaker 20 is installed in the guest room of the accommodation facility.

The communication unit 23 can communicate with various devices via a network N including the Internet, a wireless LAN (Local Area Network), a mobile phone communication network, and the like. In the present embodiment, the communication unit 23 communicates with the voice processing server 50 via the network N. The communication unit 23 transmits the data given from the processing unit 21 to the voice processing server 50, and gives the data received from the voice processing server 50 to the processing unit 21.

The touch panel 25 is one of the user interfaces included in the smart speaker 20, and has a display unit 25a and an input unit 25b. The display unit 25a is configured by using a liquid crystal display or the like, and displays various images, characters, and the like. The display unit 25a displays various images based on the processing of the processing unit 21. The input unit 25b is provided with a sensor for detecting contact by the user on the surface of the display unit 25a, and receives and accepts a touch (tap) operation or the like for an image or the like displayed on the display unit 25a as an input. Is notified to the processing unit 21.

The microphone 26 and the speaker 27 are one of the user interfaces included in the smart speaker 20, and realize a user interface by voice input / output. The microphone 26 acquires peripheral voice, converts it into digital voice information, and gives the voice information to the processing unit 21. The speaker 27 outputs audio based on the audio information given by the processing unit 21. Further, the camera 28 takes an image of, for example, a user or a guest room, and gives the captured image information to the processing unit 21.

The smart speaker 20 according to the present embodiment acquires a request uttered by the user by the speaker 27, and transmits the voice information related to the acquired request to the voice processing server 50 by the communication unit 23. At this time, the smart speaker 20 attaches the identification information 22b stored in the storage unit 22 and transmits the voice information. This voice information is converted into text information by the voice processing server 50 and given to the management server 30, and the management server 30 transmits the response to the request as text information to the voice processing server 50. The voice processing server 50 converts the text information from the management server 30 into voice information and transmits it to the smart speaker 20. The smart speaker 20 outputs the voice information given by the voice processing server 50 from the speaker 27.

If the management server 30 cannot respond to the user's request based on the text information given by the voice processing server 50, the management server 30 notifies that fact and transmits access information for accessing the chatbot. This notification and access information is given to the smart speaker 20 via the voice processing server 50. In response to this notification, the smart speaker 20 asks the user whether or not to switch to the chatbot, and when the switch to the chatbot is affirmed, as shown in FIG. 3, for accessing the two-dimensional code. Information is displayed on the display unit 25a of the touch panel 25.

FIG. 7 is a block diagram showing a configuration of the management server 30 according to the present embodiment. The management server 30 according to the present embodiment is configured to include a processing unit (processor) 31, a storage unit (storage) 32, a communication unit (transceiver) 33, and the like. The processing unit 31 is configured by using an arithmetic processing unit such as a CPU, MPU, or GPU (Graphics Processing Unit). The processing unit 31 reads and executes the server program 32a stored in the storage unit 32 to respond to a user's request, switch from voice input / output to a chatbot, and change from a chatbot to a manned response. Performs various processes such as switching process.

The storage unit 32 is configured by using a large-capacity storage device such as a hard disk. The storage unit 32 stores various programs executed by the processing unit 31 and various data required for processing by the processing unit 31. In the present embodiment, the storage unit 32 stores the server program 32a executed by the processing unit 31 and the intention identification model 81 as a learned model (discriminator). Further, the storage unit 32 is provided with two databases, a response information DB 82 in which a response to a user's request is stored, and an operator DB 83 in which information about an operator performing a manned response is stored.

The communication unit 33 can communicate with various devices via a network N including the Internet, a wireless LAN, a mobile phone communication network, and the like. In the present embodiment, the communication unit 33 communicates with the voice processing server 50, the translation server 60, the operator terminal 70, and the like via the network N. The communication unit 33 transmits the data given from the processing unit 31 to another device, and gives the data received from the other device to the processing unit 31.

The storage unit 32 may be an external storage device connected to the management server 30. Further, the management server 30 may be a multi-computer including a plurality of computers, or may be a virtual machine virtually constructed by software. Further, the management server 30 is not limited to the above configuration, and may include, for example, a reading unit for reading information stored in a portable storage medium, an input unit for receiving operation input, a display unit for displaying an image, and the like. ..

The server program 32a may be written to the storage unit 32, for example, at the manufacturing stage of the management server 30. For example, the management server 30 may acquire the server program 32a distributed by another remote server device or the like by communication. For example, in the server program 32a, the management server 30 may read the server program 32a recorded on the recording medium 98 such as a memory card or an optical disk and store it in the storage unit 32. For example, in the server program 32a, the writing device may read what was recorded on the recording medium 98 and write it in the storage unit 32 of the management server 30. The server program 32a may be provided in a mode of distribution via a network, or may be provided in a mode recorded on a recording medium 98.

The intention identification model 81 is a trained model in which machine learning or deep learning using teacher data has been performed in advance. The trained model performs a predetermined operation on the input value and outputs the operation result, and the storage unit 32 stores data such as coefficients and thresholds of the function defining this operation as the intention identification model 81. Will be done. The intention identification model 81 is a learned model learned to identify the user's intention with respect to the text information input by the user as voice or text. The processing unit 31 that executes the server program 32a reads the data stored as the intention identification model 81, so that the processing unit 31 can execute an operation for identifying the intention of the user's request.

FIG. 8 is a schematic diagram showing a configuration example of the intention identification model 81. In the present embodiment, the intention identification model 81 has an input layer that accepts input of text information related to a user's request, an intermediate layer that performs a predetermined operation on the input information, and an identification result of the intention of the user's request. It is configured as a neural network having an output layer that outputs information indicating the above. In the present embodiment, the intention identification model 81 may adopt, for example, a configuration of RNN (Recurrent Neural Network) as the neural network, but is not limited to this, and a model other than RNN may be adopted. The management server 30 generates an intention identification model 81 by learning the RNN model using the text information related to the request and the teacher data associated with the intention.

In the present embodiment, the management server 30 is provided with the intention identification model 81, but the present invention is not limited to this. For example, another server device includes an intention identification model 81, text information related to a user's request acquired by the management server 30 is transmitted to another server device, and the identification result by the intention identification model 81 possessed by the other server device is managed. The server 30 may acquire it.

Further, in the present embodiment, the management server 30 performs the learning process of the intention identification model 81. However, the learning process may be performed by another server device. The intention identification model 81 learned in this case may be transmitted from another server device to the management server 30 and stored in the storage unit 32, or may be held by another server device. The trained intention identification model 81 may be provided in a mode of distribution via a network or may be provided in a mode recorded on a recording medium 98, similarly to the server program 32a.

FIG. 9 is a schematic diagram showing a configuration example of the response information DB 82. The response information DB 82 is a database in which the intention of the user's request and the response information such as a response message to the request are stored in association with each other. Each item of the intention of the request of the response information DB 82 corresponds to the identification result of the intention identification model 81. Further, the response information of the response information DB 82 is text information of a message that responds to the intention of the request as a voice output of the smart speaker 20 or a text output by a chatbot. Since the response to the request differs depending on the accommodation facility, the response information DB 82 is provided for each accommodation facility. Further, although the response information DB 82 shown in FIG. 9 is in Japanese, a response information DB 82 corresponding to another language such as English or Chinese may be provided as needed.

The example shown in FIG. 9 is an example of the intention and response information of the request of the response information DB 82 of the “Example hotel” as an accommodation facility. The request given from the smart speaker 20 to the management server 30 via the voice processing server 50 and the request given from the smartphone 40 to the management server 30 via the translation server 60 are used to identify accommodation facilities, guest rooms, and the like. Identification information is attached as, for example, header information. The management server 30 has the response information DB 82 for a plurality of accommodation facilities, and can use the response information DB 82 suitable for the accommodation facility according to the identification information attached to the request.

In the example shown in the figure, the response information "It is 14:00. Early check-in from 12:00 is also possible for a fee." Is stored in association with the intention of the request "What time is check-in?" ing. In addition, the response information "Credit card payment is also possible" is stored in association with the intention of the request "Do you need cash at check-in?". In addition, the response information "It is the first floor" is stored in association with the intention of the request "Where is the front desk?". The intent and response information of the requested request shown in the figure are merely examples, and are not limited thereto.

FIG. 10 is a schematic diagram showing a configuration example of the operator DB 83. The operator DB 83 is a database in which conditions relating to the date and time and information relating to the operator to be switched to the manned response are stored in association with each other. The operator DB 83 is provided for each accommodation facility. In the illustrated example, it is set that the operator of the operator center makes a manned response to the date and time from 8:00 am to 8:00 pm on weekdays and from 6:00 am to 10:00 pm on holidays. Also, for dates and times on weekdays from midnight to 8 am and from 8 pm to 12 pm and on holidays from midnight to 6 am and from 10 pm to 12 pm The front operator is set to provide a manned response. When switching to the manned response, the management server 30 refers to the operator DB 83 based on the date and time information and determines the operator to perform the manned response. The management server 30 transmits a request for a manned response to the operator terminal 70 used by the determined operator. In the illustrated example, the operator center, the hotel front, and the like are set as operators, but in reality, the identification information and the like of the operator terminal 70 provided in these may be set.

Further, the operator DB 83 may store information about a language that the operator can handle. As a result, the management server 30 can make a manned response to an operator who can respond in the language used by the user. The management server 30 may allow the user to select a language for the language used by the user, for example, when switching to a manned response, or determines the user's language from information such as a guest list of accommodation facilities. May be good.

Further, in the management server 30 according to the present embodiment, the processing unit 31 reads and executes the server program 32a stored in the storage unit 32, so that the request acquisition unit 31a, the response processing unit 31b, the switching processing unit 31c, and the learning unit 31c are executed. The processing unit 31d and the like are realized as software-like functional blocks. The request acquisition unit 31a is a process in which the communication unit 33 communicates with the voice processing server 50 so that the user inputs voice to the smart speaker 20 and the voice processing server 50 acquires a request converted into text information. I do. Further, the request acquisition unit 31a is a process in which the user inputs to the smartphone 40 by communicating with the translation server 60 in the communication unit 33, and the translation server 60 acquires a request translated into an appropriate language. I do. The request information acquired by the request acquisition unit 31a is all text information.

The response processing unit 31b responds to the request acquired by the request acquisition unit 31a by using the intention identification model 81 and the response information DB 82 stored in the storage unit 32. The response processing unit 31b inputs the text information of the request acquired by the request acquisition unit 31a into the intention identification model 81, and acquires the intention identification result output by the intention identification model 81. The response processing unit 31b refers to the response information DB 82 based on the intention of the acquired request, and acquires the response information corresponding to the intention. The response processing unit 31b transmits the acquired response information to the voice processing server 50 or the translation server 60, and makes a response by the voice output of the smart speaker 20 or a response by the text output of the smartphone 40.

The switching processing unit 31c switches from a voice response using the smart speaker 20 to a chatbot using the smartphone 40 when an appropriate response cannot be made to the user's request acquired by the request acquisition unit 31a. Or, switch from a chatbot to a manned response. In the switching processing unit 31c, for example, when the intention identification model 81 cannot identify the intention with respect to the text information of the request acquired by the request acquisition unit 31a, or the response information corresponding to the identified intention is transmitted from the response information DB 82. If it cannot be obtained, switch it.

When the switching processing unit 31c cannot respond to the request given by the voice processing server 50, the switching processing unit 31c transmits an instruction prompting the switching to the chatbot to the smart speaker 20 that is the transmission source of this request. do. At this time, the instruction given from the management server 30 to the smart speaker 20 via the voice processing server 50 includes an image of the access information 20a necessary for accessing the chatbot. The access information 20a is information in which, for example, a URL for accessing a chatbot and identification information of an accommodation facility and a guest room in which the smart speaker 20 is installed are two-dimensionally coded. Upon receiving this instruction, the smart speaker 20 asks the user whether or not to switch to the chatbot, and displays the access information 20a when a reply to the effect of switching is obtained.

When the switching processing unit 31c cannot respond to the request given by the translation server 60, the switching processing unit 31c transmits an instruction for urging the smartphone 40, which is the transmission source of the request, to switch to the manned response. Upon receiving this instruction, the smartphone 40 inquires the user whether or not to switch from the chatbot to the manned response, and when a reply to the effect of switching is obtained, sends a switching request to the management server 30. Upon receiving this request, the switching processing unit 31c of the management server 30 acquires information regarding the date and time at that time, refers to the operator DB 83 stored in the storage unit 32, and determines the operator to be switched to. Further, at this time, the management server 30 may determine the operator to be switched to in consideration of the language that the operator can handle. The switching processing unit 31c transmits an instruction to perform a manned response to the operator terminal 70 used by the determined operator. After that, the management server 30 relays the text information related to the user's request and the operator's response between the smartphone 40 and the operator terminal 70.

The learning processing unit 31d performs a process of learning (re-learning) the intention identification model 81. The learning processing unit 31d, for example, performs the above-mentioned switching by the switching processing unit 31c, and finally asks the operator to input the teacher data after the manned response by the operator is completed. At this time, the learning processing unit 31d displays the text information related to the user's request that the response processing unit 31b could not respond to on the operator terminal 70, and the request actually determined by the operator with respect to this text information. Ask for intent input. The learning processing unit 31d acquires information from the operator terminal 70 as teacher data, which is a combination of the text information requested by the user and the intention input by the operator, and stores the information in the storage unit 32. The learning processing unit 31d relearns the intention identification model 81 stored in the storage unit 32 using the newly stored teacher data when a predetermined amount of teacher data is accumulated or each time the teacher data is acquired. do. The re-learning of the intention identification model 81 may be performed by another server device, and the management server 30 may only store the teacher data.

FIG. 11 is a block diagram showing the configuration of the smartphone 40 according to the present embodiment. The smartphone 40 according to the present embodiment includes a processing unit (processor) 41, a storage unit (storage) 42, a communication unit (transceiver) 43, a touch panel 44, a camera 45, and the like. The processing unit 41 is configured by using an arithmetic processing device such as a CPU or an MPU. The processing unit 41 reads and executes the program 42a stored in the storage unit 42 to perform various processing such as a processing for accessing the management server 30 and a processing for realizing a chat.

The storage unit 32 is configured by using a non-volatile memory element such as a flash memory. The storage unit 42 stores various programs executed by the processing unit 41 and various data required for processing by the processing unit 41. In the present embodiment, the storage unit 42 stores the program 42a executed by the processing unit 41. The program 42a may be written in the storage unit 42, for example, at the manufacturing stage of the smartphone 40. For example, in the program 42a, the smartphone 40 may acquire what is distributed by a remote server device or the like by communication. For example, in the program 42a, the smartphone 40 may read the program 42a recorded on a recording medium such as a memory card or an optical disk and store it in the storage unit 42. For example, in the program 42a, the writing device may read out what is recorded on the recording medium and write it in the storage unit 42 of the smartphone 40. The program 42a may be provided in a mode of distribution via a network, or may be provided in a mode recorded on a recording medium.

The communication unit 43 can communicate with various devices via a network N including the Internet, a wireless LAN, a mobile phone communication network, and the like. In the present embodiment, the communication unit 43 communicates with the translation server 60 via the network N. The communication unit 43 transmits the data given from the processing unit 41 to the translation server 60, and gives the data received from the translation server 60 to the processing unit 41.

The touch panel 44 is one of the user interfaces included in the smartphone 40, and has a display unit and an input unit. The display unit of the touch panel 44 is configured by using a liquid crystal display or the like, and displays various images, characters, and the like based on the processing of the processing unit 41. The input unit of the touch panel 44 is provided with a sensor for detecting contact by the user on the surface of the display unit, and receives and accepts a touch (tap) operation or the like for an image or the like displayed on the display unit as an input. Is notified to the processing unit 41.

The camera 45 captures an image of the surrounding area and gives the captured image information to the processing unit 41. In the present embodiment, the camera 45 of the smartphone 40 is used for capturing the access information 20a displayed on the touch panel 25 of the smart speaker 20.

Further, in the smartphone 40 according to the present embodiment, the processing unit 41 reads out and executes the program 42a stored in the storage unit 42, so that the access information acquisition unit 41a, the chat processing unit 41b, and the like are software-like functional blocks. Is realized as. The access information acquisition unit 41a performs a process of acquiring the access information 20a of the two-dimensional code displayed on the touch panel 25 by the smart speaker 20. The access information acquisition unit 41a displays, for example, a message prompting the image capture of the access information 20a displayed on the smart speaker 20 on the touch panel 44, and acquires an image of the access information 20a imaged by the camera 45. Based on the acquired image, the access information acquisition unit 41a acquires the URL for accessing the chatbot included in the access information 20a, and the identification information of the accommodation facility and the guest room in which the smart speaker 20 is installed. do.

The chat processing unit 41b accesses the management server 30 that provides the chatbot (via the translation server 60) based on the access information acquired by the access information acquisition unit 41a. The chat processing unit 41b displays the language selection box shown in FIG. 4 and accepts the selection of the language used for chat, and then displays the chat screen shown in FIG. The chat processing unit 41b acquires the text information of the request input by the user, and transmits the acquired text information to the management server 30 via the translation server 60. Further, the chat processing unit 41b receives the text information of the response transmitted from the management server 30 via the translation server 60, and displays the received text information on the chat screen. The chat processing unit 41b can proceed with the chat by the same processing regardless of whether the chat partner is an automatic response by the chatbot or a manned response of the operator.

<Response switching process>
In the information providing system according to the present embodiment, three types of information providing methods are provided: voice response using the smart speaker 20, automatic response by a chatbot using the smartphone 40, and manned response by the operator using the smartphone 40. It is provided to users. Further, in the information providing system according to the present embodiment, the management server 30 determines the determination of switching from the voice response of the smart speaker 20 to the automatic response of the chat bot and switching from the automatic response of the chat bot to the manned response of the operator. By doing this and encouraging the user to switch the information provision method, smooth switching of the information provision method is realized.

(1) Switching from the voice response of the smart speaker 20 to the automatic response of the chatbot For example, a user staying at an accommodation facility asks a question or request about the accommodation facility by using the smart speaker 20 installed in the guest room. Request by input. The smart speaker 20 transmits the voice information related to the input request to the voice processing server 50, and the voice processing server 50 converts the voice information into text information and sends it to the management server 30.

If the input voice information is Japanese, the voice processing server 50 transmits Japanese text information to the management server 30, and if it is English, the voice processing server 50 transmits English text information to the management server 30. When voice information in a language not supported by the voice processing server 50 is input, the voice processing server 50 sends a notification to the management server 30 that the voice information cannot be converted into text information.

The management server 30 acquires response information to a user's request using the intention identification model 81 and the response information DB 82 based on the text information received from the voice processing server 50. The management server 30 transmits this response information as text information to the voice processing server 50, and the voice processing server 50 converts the text information into voice information and transmits it to the smart speaker 20. The smart speaker 20 receives voice information from the voice processing server 50, and outputs the received voice information from the speaker 27 as a response to a user's request.

Further, when the management server 30 cannot acquire the response information even by using the intention identification model 81 and the response information DB 82 based on the text information received from the voice processing server 50, the management server 30 changes from the voice response to the automatic response of the chat bot. The switching instruction prompting the switching is transmitted to the smart speaker 20 via the voice processing server 50. At this time, the management server 30 generates the access information 20a of the two-dimensional code including the information such as the URL for accessing the chatbot and the identification information of the accommodation facility and the guest room where the smart speaker 20 is installed. Send along with the switching instruction.

There may be a plurality of factors that prevent the management server 30 from acquiring response information. For example, the reason is that the voice processing server 50 cannot convert the voice information into the text information because the voice input to the smart speaker 20 is unclear. The same applies when the input voice information is in a language that is not supported by the voice processing server 50. In these cases, the voice processing server 50 gives a notification to the management server 30 that the voice processing was not possible, and it can be determined that the management server 30 cannot acquire the response information by this notification.

Further, for example, the fact that the intention identification model 81 cannot identify the intention of the request can be mentioned as a factor. When the intention identification model 81 is configured to output the intention of the identified request and the certainty of the identification result for the input request, when the output certainty does not exceed a predetermined threshold value. The management server 30 can determine that the intention identification model 81 cannot identify the intention and can determine that the response information cannot be acquired.

Further, for example, the reason is that the intention of the request identified by the intention identification model 81 and the response information corresponding thereto are not registered in the response information DB 82. The management server 30 can search the response information DB 82 based on the intention of the request output by the intention identification model 81, and can determine that the response information cannot be acquired when the corresponding item does not exist in the response information DB 82.

The method for determining that the management server 30 cannot acquire the response information corresponding to the request is not limited to the above method, and various methods can be adopted.

The smart speaker 20 that receives the switching instruction from the management server 30 via the voice processing server 50 outputs a message or the like inquiring whether to switch to the automatic response of the chatbot from the speaker 27 or the touch panel 25. Is displayed in, and the user inquires whether or not switching is possible. When a response affirming the switching is obtained from the user by voice input or an operation on the touch panel, the smart speaker 20 displays the two-dimensional code of the access information 20a attached to the switching instruction on the touch panel 25.

When the access information 20a is displayed on the touch panel 25 of the smart speaker 20, the user reads the access information 20a on his / her smartphone 40 and accesses the chat bot realized by the management server 30 on the smartphone 40. be able to. The smartphone 40 displays the language selection box shown in FIG. 4 and allows the user to select the language used in the chat. The smartphone 40 displays a chat screen in the selected language. In this chat screen, the smartphone 40 accepts the text input of the request by the user and outputs the text of the response by the management server 30. In the present embodiment, the smartphone 40 reads the access information 20a by an application program or the like that reads a two-dimensional code, and accesses the URL included in the read access information 20a by a program such as a browser. It shall be. The chat screen is displayed on the browser, and the process for displaying the chat screen is performed by the cooperation of the management server 30 and the smartphone 40.

In the present embodiment, the user selects the language used for chat, but the present invention is not limited to this. The management server 30 may automatically select a language based on, for example, the identification information of the accommodation facility and the guest room included in the access information 20a. For example, the management server 30 acquires the identification information of the accommodation facility and the guest room from the smartphone 40, and stays in the guest room of the accommodation facility identified by the identification information from another server device or the like that manages the guests of the accommodation facility. By acquiring information such as the nationality of the user, the language used for chat can be selected.

FIG. 12 is a flowchart showing a procedure of processing performed by the smart speaker 20 according to the present embodiment. The processing unit 21 of the smart speaker 20 according to the present embodiment determines whether or not the voice input of the request by the user to the microphone 26 has been made (step S1). When no voice input is made (S1: NO), the processing unit 21 waits until the request voice input is made. When voice input is made (S1: YES), the processing unit 21 acquires the voice input by the microphone 26 as voice information of digital data (step S2). The processing unit 21 transmits the acquired voice information to the voice processing server 50 by the communication unit 23 (step S3).

After that, the processing unit 21 determines whether or not a response to the transmitted request has been received (step S4). If no response has been received (S4: NO), the processing unit 21 waits until the response is received. Here, the response received by the smart speaker 20 is voice response information to the request or an instruction to switch to the chatbot. When the response is received (S4: YES), the processing unit 21 determines whether or not the received response is an instruction to switch to the chatbot (step S5). If it is not a switching instruction (S5: NO), the processing unit 21 outputs the voice information of the received response from the speaker 27 (step S6), and ends the processing.

When the received response is a switching instruction (S5: YES), the processing unit 21 inquires the user whether or not the switching is possible by outputting a voice from the speaker 27 or displaying a message or the like inquiring whether or not the switching is possible on the touch panel 25. (Step S7). The processing unit 21 determines whether or not an answer affirming the switching has been obtained in response to this inquiry (step S8). When an answer affirming the switching is obtained (S8: YES), the processing unit 21 displays the two-dimensional code access information 20a given from the management server 30 together with the switching instruction on the touch panel 25 (step S9), and processes the information. To finish. When an answer affirming the switching is not obtained (S8: NO), the processing unit 21 ends the processing without displaying the access information 20a.

FIG. 13 is a flowchart showing a procedure of switching control processing performed by the management server 30 according to the present embodiment. The request acquisition unit 31a of the processing unit 31 of the management server 30 according to the present embodiment determines whether or not the communication unit 33 has received the request by the text information from the voice processing server 50 (step S21). If the request has not been received (S21: NO), the request acquisition unit 31a waits until the request is received.

When the request is received (S21: YES), the response processing unit 31b of the processing unit 31 inputs the text information of the received request into the intention identification model 81 stored in the storage unit 32 (step S22). Next, the response processing unit 31b acquires the identification result of the intention of the request output by the intention identification model 81 (step S23). Based on the acquired identification result, the response processing unit 31b determines whether or not the intention of the request can be identified (step S24). When the intention of the request is identifiable (S24: YES), the response processing unit 31b refers to the response information DB 82 stored in the storage unit 32 based on the identified intention (step S25). The response processing unit 31b refers to the response information DB 82 and determines whether or not the response information has been obtained (step S26). When the response information is obtained (S26: YES), the response processing unit 31b transmits the response information acquired from the response information DB 82 to the smart speaker 20 of the request transmission source via the voice processing server 50 (step S27). , End the process.

When the intention of the request cannot be identified by the intention identification model 81 (S24: NO), or when the response information for the intention of the request cannot be obtained from the response information DB 82 (S26: NO), the processing unit 31 The switching processing unit 31c of the above generates access information 20a for accessing the chatbot (step S28). The switching processing unit 31c transmits a switching instruction including the generated access information 20a to the smart speaker 20 of the request transmission source via the voice processing server 50 (step S29), and ends the processing.

FIG. 14 is a flowchart showing a procedure of chat start processing performed by the smartphone 40 according to the present embodiment. The processing unit 41 of the smartphone 40 according to the present embodiment starts an application program in response to, for example, a user operation, and shifts to a mode for reading a two-dimensional code (step S41). In this mode, the access information acquisition unit 41a of the processing unit 41 acquires the access information 20a by capturing the access information 20a with the camera 45 (step S42). The access information acquisition unit 41a acquires the URL and the identification information included in the acquired access information 20a (step S43).

Next, the chat processing unit 41b of the processing unit 41 accesses the management server 30 based on the acquired URL and the identification information (step S44). At this time, by transmitting the identification information acquired by the smartphone 40 from the access information 20a to the management server 30, the management server 30 can determine which accommodation facility or guest room the user is accessing from. can. The chat processing unit 41b displays a language selection box and accepts the selection of the language used for chat (step S45). The chat processing unit 41b starts chat processing with the chatbot provided by the management server 30 in the selected language (step S46), and ends the processing.

(2) Switching from the automatic response of the chatbot to the manned response of the operator The user who has started the chat using the smartphone 40 can input the request by text input. The text information of the input request is transmitted from the smartphone 40 to the translation server 60, and the text information is translated by the translation server 60 as necessary. The translation server 60 transmits the translated text information or the text information that does not need to be translated to the management server 30. If the translation of the text information is not necessary, the text information may be directly transmitted from the smartphone 40 to the management server 30.

The management server 30 acquires response information to a user's request using the intention identification model 81 and the response information DB 82 based on the text information received from the translation server 60. The management server 30 transmits this response information as text information to the translation server 60, and the translation server 60 translates the text information as needed. The translation server 60 transmits the translated text information or the text information that does not need to be translated to the smartphone 40. The smartphone 40 receives the text information from the translation server 60 and displays the received text information on the chat screen as a response to the user's request.

Further, when the management server 30 cannot acquire the response information even by using the intention identification model 81 and the response information DB 82 based on the text information received from the translation server 60, the operator's manned response is obtained from the automatic response of the chat bot. A switching instruction prompting the user to switch to is transmitted to the smartphone 40 via the translation server 60.

There may be a plurality of factors that prevent the management server 30 from acquiring response information. For example, the fact that the intention identification model 81 cannot identify the intention of the request can be mentioned as a factor. Further, for example, the reason is that the intention of the request identified by the intention identification model 81 and the response information corresponding thereto are not registered in the response information DB 82. Various methods can be adopted as a method for determining that the management server 30 cannot acquire the response information corresponding to the request.

The smartphone 40, which receives the switching instruction from the management server 30 via the translation server 60, displays a message or the like inquiring whether or not to switch to the manned response of the operator on the chat screen, and inquires whether or not the user can switch. .. In response to this inquiry, the user can switch to a manned response by, for example, touching the switching icon provided on the chat screen. When the user gives an affirmative answer, the smartphone 40 sends a request for switching to the manned response to the management server 30 via the translation server 60.

The management server 30 that has received the switching request from the smartphone 40 acquires the date and time information at that time, and refers to the operator DB 83 stored in the storage unit 32 based on the acquired date and time information. The management server 30 determines an operator requesting a manned response based on the date and time information and the operator DB 83, and transmits an instruction to perform the manned response to the operator terminal 70 used by the determined operator. Further, at this time, the management server 30 may determine the operator to be switched to in consideration of the language that the operator can handle.

Further, the management server 30 transmits information such as the history and the user so far and displays it on the operator terminal 70 before the operator starts to respond to the manned response. The history so far may include, for example, text information indicating the content of the voice input / output by the smart speaker 20, text information input / output by the automatic response of the chatbot, and the like. The management server 30 stores these information as history information in the storage unit 32. Further, the information about the user can be, for example, information such as the gender, age, and nationality of the user, and is acquired from another server device or the like that stores information about the guest of the accommodation facility. By displaying this information on the operator terminal 70 in advance, the operator who makes a manned response can smoothly start chatting with the user.

After that, the management server 30 relays the transmission / reception of text information between the smartphone 40 and the operator terminal 70 to establish a chat using the text information of the user and the operator.

Further, in the present embodiment, after the manned response by the operator is completed, the management server 30 requests the operator who has performed the manned response to create teacher data for re-learning the intention identification model 81. The management server 30 inquires, for example, the operator terminal 70 that has completed the manned response to the user what the intention of the user's request was. At this time, the management server 30 may transmit the text information input by the user in the voice response or the automatic response of the chatbot before the manned response to the operator terminal 70, and display the text information on the operator terminal 70. .. Based on the message or the like displayed on the operator terminal 70, the operator inputs what the intention of the request of the user who made the manned response was. The operator terminal 70 transmits the information input by the operator to the management server 30. The management server 30 receives the information from the operator terminal 70, creates teacher data in which the text information of the request related to the user's input and the intention of the request input by the operator are associated with each other, and stores the teacher data in the storage unit 32. Remember. The information input by the operator at the operator terminal 70 can be used not only for learning the intention identification model 81, but also for adding or modifying the response information to the response information DB 82.

FIG. 15 is a flowchart showing a procedure of chat processing performed by the smartphone 40 according to the present embodiment. The chat processing unit 41b of the processing unit 41 of the smartphone 40 according to the present embodiment accepts the input of the request by the user based on the operation on the touch panel 44 (step S51). The chat processing unit 41b transmits the text information of the received request to the translation server 60 by the communication unit 43 (step S52).

After that, the chat processing unit 41b determines whether or not a response to the transmitted request has been received (step S53). If no response has been received (S53: NO), the chat processing unit 41b waits until the response is received. Here, the response received by the smartphone 40 is text information of the response to the request or an instruction to switch to the manned response by the operator. When the response is received (S53: YES), the chat processing unit 41b determines whether or not the received response is an instruction to switch to a manned response (step S54). If it is not a switching instruction (S54: NO), the chat processing unit 41b displays the text information of the received response on the chat screen (step S55), and ends the processing.

When the received response is a switching instruction (S54: YES), the chat processing unit 41b inquires the user whether or not the switching is possible by displaying a message inquiring whether or not the switching is possible (step S56). The chat processing unit 41b determines whether or not an answer affirming the switching has been obtained for this inquiry (step S57). When an answer affirming the switching is obtained (S57: YES), the chat processing unit 41b sends a request for switching to the manned response to the management server 30 via the translation server 60 (step S58), and performs processing. finish. If no answer affirming the switch is obtained (S57: NO), the chat processing unit 41b ends the process without transmitting the switch request.

FIG. 16 is a flowchart showing a procedure of switching control processing performed by the management server 30 according to the present embodiment. The request acquisition unit 31a of the processing unit 31 of the management server 30 according to the present embodiment determines whether or not the communication unit 33 has received the request by the text information from the translation server 60 (step S71). If the request has not been received (S71: NO), the request acquisition unit 31a waits until the request is received.

When the request is received (S71: YES), the response processing unit 31b of the processing unit 31 inputs the text information of the received request into the intention identification model 81 stored in the storage unit 32 (step S72). Next, the response processing unit 31b acquires the identification result of the intention of the request output by the intention identification model 81 (step S73). Based on the acquired identification result, the response processing unit 31b determines whether or not the intention of the request can be identified (step S74). When the intention of the request is identifiable (S74: YES), the response processing unit 31b refers to the response information DB 82 stored in the storage unit 32 based on the identified intention (step S75). The response processing unit 31b refers to the response information DB 82 and determines whether or not the response information has been obtained (step S76). When the response information is obtained (S76: YES), the response processing unit 31b transmits the response information acquired from the response information DB 82 to the request transmission source smartphone 40 via the translation server 60 (step S77), and processes the response information. To finish.

When the intention of the request cannot be identified by the intention identification model 81 (S74: NO), or when the response information for the intention of the request cannot be obtained from the response information DB 82 (S76: NO), the processing unit 31 The switching processing unit 31c of the above transmits a switching instruction from the automatic response of the chatbot to the manned response by the operator to the smartphone 40 of the request transmission source via the voice processing server 50 (step S78), and ends the processing.

FIG. 17 is a flowchart showing a procedure of switching processing to a manned response performed by the management server 30 according to the present embodiment. The switching processing unit 31c of the processing unit 31 of the management server 30 according to the present embodiment determines whether or not a request for switching to a manned response from the smartphone 40 has been received via the translation server 60 (step S91). When the request for switching to the manned response has not been received (S91: NO), the switching processing unit 31c waits until the request is received.

When the request for switching to the manned response is received (S91: YES), the switching processing unit 31c acquires the date and time information at that time (step S92). The date and time information can be obtained from, for example, an operating system operating on the management server 30. The switching processing unit 31c refers to the operator DB 83 stored in the storage unit 32 based on the acquired date and time information (step S93). The switching processing unit 31c determines an operator to perform a manned response based on the date and time information and the operator DB 83 (step S94). The switching processing unit 31c gives an instruction to give a response to the operator terminal 70 used by the determined operator (step S95).

After that, the processing unit 41 transmits the user's request from the smartphone 40 to the operator terminal 70, and the operator's response from the operator terminal 70 is transmitted to the smartphone 40 to relay the request and the response (step S96). .. The processing unit 41 determines whether or not the manned response is completed (step S97). When the manned response is not completed (S97: NO), the processing unit 41 returns the processing to step S96 and continuously relays the request and the response.

When the manned response is completed (S97: YES), the processing unit 41 inquires of the operator terminal 70 that has performed the manned response the intention of the user's request (step S98). Based on the operator's response to this inquiry, the processing unit 41 generates teacher data in which the text information of the request and the intention of the request are associated with each other and stores it in the storage unit 32 (step S99), and ends the processing.

<Re-learning of intention discriminative model>
In the information providing system according to the present embodiment, the learning (re-learning) process of the intention identification model 81 of the management server 30 is performed using the teacher data created as a result of the manned response by the operator. The re-learning of the intention identification model 81 is performed at a periodic timing such as once a month, or at a timing when the accumulated amount of teacher data exceeds a predetermined amount.

FIG. 18 is a flowchart showing a procedure of learning processing of the intention identification model 81 performed by the management server 30 according to the present embodiment. The learning processing unit 31d of the processing unit 31 of the management server 30 according to the present embodiment determines whether or not the timing for re-learning the intention identification model 81 has been reached (step S111). If the timing for re-learning has not been reached (S111: NO), the learning processing unit 31d waits until the timing for re-learning is reached.

When the timing for re-learning is reached (S111: YES), the learning processing unit 31d reads out the learning data stored in the storage unit 32 (step S112). Further, the learning processing unit 31d reads out the intention identification model 81 stored in the storage unit 32. The learning processing unit 31d performs a process of learning the intention identification model 81 using the read learning data (step S114). The learning processing unit 31d stores the learned intention identification model 81 that has completed the learning processing in the storage unit 32 (step S115), and ends the processing.

<Use before staying>
In the information providing system according to the present embodiment, information is provided not only to the user (guest) staying at the accommodation facility but also to the user (for example, a reservation guest) before staying in the accommodation facility by the same method. Is possible. FIG. 19 is a schematic diagram for explaining information provision before accommodation by the information provision system according to the present embodiment. For example, the user can make a reservation for accommodation in the accommodation facility to the reservation server 80. After the reservation of the accommodation by the user is completed, the reservation server 80 transmits the access information for accessing the information providing system that provides the information of the accommodation facility to the reserved user.

The information for access from the reservation server 80 to the user can be transmitted, for example, by sending an e-mail to an e-mail address registered as information related to the user. For example, a URL for accessing the information providing system or the management server 30, identification information of the reserved accommodation facility, and the like may be attached to the e-mail to the user as access information. The e-mail transmitted by the reservation server 80 is received by, for example, the user's smartphone 40, and the user accesses the information providing system on the smartphone 40 based on the access information attached to the e-mail. In this case, the user can use the information provision by the automatic response of the chatbot provided by the management server 30. Further, for example, an image of a two-dimensional code of access information may be attached to the e-mail. The user displays the two-dimensional code on the smartphone 40, reads the two-dimensional code using the camera 28 with his / her own smart speaker 20 installed at home, and accesses the information providing system with the smart speaker 20. You may. In this case, the user can use the information provision by the voice response provided by the management server 30 on the smart speaker 20.

Further, for example, the transmission of the access information from the reservation server 80 to the user may be by mail. A letter or card printed with a two-dimensional code for access information is enclosed in the accommodation facility information mailed to the user. The user can read the two-dimensional code with his / her own smartphone 40 or smart speaker 20 and use the information providing system with his / her own smartphone 40 or smart speaker 20.

The management server 30 of the information providing system can make a similar response to a request from a user regardless of whether the guest is a guest or a reservation guest. However, the management server 30 may set a limit on the information given as a response to the reserved guest user. Further, the information providing system may provide information to users other than the guest and the reserved guest, for example, a user who is considering staying. In this case, the user can use the information providing system by accessing the website of the accommodation facility or the like using his / her smartphone 40 or the smart speaker 20 and issuing a request such as an inquiry.

<Summary>
In the information providing system according to the present embodiment having the above configuration, the smart speaker 20 installed in the guest room of the accommodation facility acquires a request based on the voice input from the user, and the response information to the acquired request is obtained by the smart speaker 20. Output audio with. When the response information for the acquired request cannot be output, the management server 30 switches to the automatic response by text input / output.

When the response information cannot be output to the request, when the response information corresponding to the user's request cannot be obtained from the response information DB 82 and an appropriate response cannot be made to the request, the request is made. This is the case when it is not possible to make a unique response for each. Specifically, for example, when the language spoken by the user is not included in the language supported by the voice processing server 50, or when the content spoken by the user cannot be appropriately converted into text information by the voice processing server 50, the user's request. Includes the case where the intention cannot be identified by the intention identification model 81, or the case where the response information corresponding to the response information DB 82 is not stored.

It should be noted that a predetermined message such as "cannot respond to the request" may be uniformly responded to the user's request, for example, when the intention of the request cannot be identified. Such a response is not a unique response for each request and is not an appropriate response to the request. Even when such a response is performed, in the present embodiment, it is included in the case where the response information for the request cannot be output.

When switching from the voice input / output to the text input / output, the management server 30 causes the touch panel 25 of the smart speaker 20 to display the access information 20a for accessing the automatic response by the text input / output. As a result, the user can easily switch from the voice input to the text input / output by using the access information 20a displayed on the smart speaker 20.

Further, the management server 30 according to the present embodiment receives access from the smartphone 40 based on the access information 20a displayed by the smart speaker 20, acquires a request based on the text input to the smartphone 40, and responds to the acquired request. The response information is output to the smartphone 40 as a text. As a result, the user can input text using the smartphone 40 that he / she is accustomed to and obtain a response to the request.

Further, the management server 30 according to the present embodiment switches to a manned response by the operator when the response information cannot be output in response to the request based on the input of the text information. As a result, the operator can reliably respond to the user's request, which cannot be handled by the automatic response.

Further, the management server 30 according to the present embodiment stores the operator's response according to the date and time in the operator DB 83, refers to the operator DB 83 based on the date and time information for switching, and is the operator to which the manned response is switched. To determine. As a result, the management server 30 can appropriately determine the switching destination of the manned response according to, for example, the working time of the operator center, and can reliably perform the manned response to the request from the user.

Further, the management server 30 according to the present embodiment uses an intention identification model 81 learned to receive information related to a user's request as input, and to identify and output the intention of the request. The management server 30 acquires the information related to the user's request and inputs it to the intention identification model 81, acquires the intention of the request output by the intention identification model 81, and inputs the response information to the acquired request intention to the smart speaker 20 or Output to the smartphone 40. When the response information cannot be output in response to the user's request and the operator switches to the manned response, the management server 30 relearns the intention identification model 81 based on the result of the manned response. As a result, the discriminative ability of the intention discrimination model 81 can be improved, and the accuracy of the automatic response to the user's request can be improved.

Further, the management server 30 according to the present embodiment stores the response information for the request in the response information DB 82, and the response information DB 82 is provided for each accommodation facility. The smart speaker 20 and the smartphone 40 transmit identification information for identifying the accommodation facility and the guest room together with the request input by the user. The management server 30 uses the response information DB 82 corresponding to the accommodation facility based on the identification information received together with the request from the user, and acquires the response information to the request. The management server 30 outputs the acquired response information from the smart speaker 20 or the smartphone 40. As a result, the management server 30 can provide the user with response information suitable for the accommodation facility.

The information providing system according to the present embodiment also provides information to the user before staying. For example, the reservation server 80 transmits access information to the smartphone 40 of the user who has reserved accommodation at the accommodation facility. The user accesses the information providing system with the smartphone 40 based on the access information, and the management server 30 accepts the access from the user's smartphone 40 based on the access information. As a result, the information providing system can provide information not only to the user staying at the accommodation facility but also to the user before staying at the accommodation facility. The user can acquire various information about the accommodation facility before staying and prepare for a trip or the like.

In the present embodiment, the user interface installed in the accommodation facility is the smart speaker 20, but the present invention is not limited to this. The user interface may be any device as long as it can perform audio input / output by a microphone and a speaker. For example, a personal computer connected to a microphone and a speaker can be used as a user interface. Further, in the present embodiment, the terminal device used by the user is the smartphone 40, but the present invention is not limited to this. The terminal device may be any device capable of input / output text, such as a personal computer, a tablet terminal device, a mobile phone, or the like.

Further, in the present embodiment, before switching from the voice response to the chatbot automatic response and switching from the chatbot automatic response to the operator's manned response, the user is inquired about whether or not the switch is possible. However, it is not limited to this. The management server 30 may automatically perform these switching without making an inquiry to the user. Further, in the present embodiment, the smart speaker 20 is configured to display the access information 20a as a two-dimensional code, but the present invention is not limited to this. For example, the access information 20a may be displayed by the smart speaker 20 as character information including information such as a URL, a login ID, and a password. Any method may be used to output the access information 20a.

Further, in the present embodiment, a plurality of server devices of the management server 30, the voice processing server 50, the translation server 60, and the reservation server 80 share the processing to realize the information providing system. Not limited to the above. For example, these plurality of server devices may be realized as one server device, or may be shared by, for example, five or more server devices. For example, the management server 30 may perform processing of the voice processing server 50 or the translation server 60. Further, for example, the management server 30 may perform the processing of the reservation server 80. Further, the server device that holds and learns the intention identification model 81 may be a device different from the management server 30.

Further, in the present embodiment, the management server 30 is configured to respond to the request by using the intention identification model 81 and the response information DB 82, but the present invention is not limited to this. For example, the management server 30 may use a trained model that accepts input of text information of a request and outputs response information to the request. Further, for example, the management server 30 may use a database in which the text information of the request and the response information are associated with each other without using the trained model. Any method may be used for the management server 30 to respond to the request.

<Embodiment 2>
In the information providing system according to the above-described embodiment, the smart speaker 20 first makes a voice response to the user's request, and when it is determined that an appropriate voice response cannot be made, the chatbot switches to the response. If the chatbot further determines that an appropriate response cannot be made, the operator switches to a manned response. On the other hand, in the information providing system according to the second embodiment, when it is determined that the smart speaker 20 cannot perform an appropriate voice response, the user switches between a chatbot response and an operator manned response. Can be selected.

In the information providing system according to the second embodiment, the user staying at the accommodation facility makes a request by utterance to the smart speaker 20 provided in the guest room, and the information of the response to the request is transmitted by the voice of the smart speaker 20. It can be obtained from the output. In this case, the processing of the voice response performed by the smart speaker 20, the management server 30, the voice processing server 50, etc. of the information providing system may be the same as that described in the first embodiment.

When it is determined that the information cannot be provided by an appropriate voice response, for example, when the language spoken by the user is not included in the supported language of the voice response, the management server 30 according to the second embodiment is a chatbot. Prompts the user to switch to a response by or a manned response by the operator. At this time, the management server 30 displays the information for switching to the response by the chatbot and the information for switching to the manned response on the display unit 25a of the smart speaker 20, and allows the user to select which response to switch to. ..

FIG. 20 is a schematic diagram showing an example of access information displayed on the smart speaker 20 according to the second embodiment. In the information providing system according to the second embodiment, the smart speaker 20 displays on the touch panel 25 the access information 20a for switching to the response by the chatbot and the access information 20b for switching to the manned response of the call center. ..

In the illustrated example, the smart speaker 20 displays the message "Please read the code of the desired response method" at the top of the substantially circular touch panel 25, and below this message is for access for the chatbot. The information 20a and the access information 20b for the call center are displayed side by side.

The display method of the access information 20a and 20b shown in FIG. 20 is an example, and is not limited to this. For example, the smart speaker 20 displays an option such as a button or an icon for accepting a selection of either a chatbot or a call center on the touch panel 25, accepts a user to select a response method based on a touch operation for this option, and selects and responds. Only the access information 20a and 20b corresponding to the method may be displayed on the touch panel 25. Further, for example, the smart speaker 20 may display information such as a telephone number for accessing the call center instead of the access information 20b.

The user can select the response method by reading one of the two access information 20a and 20b displayed on the smart speaker 20 with the camera of the smartphone 40. When the access information 20a for the response by the chatbot is read, the smartphone 40 acquires information such as a URL from the access information 20a, accesses the chatbot, and provides the user with the response service by the chatbot. .. Since the response by the chatbot is the same as that of the above-described embodiment, detailed description thereof will be omitted.

When the access information 20b for a manned response by the call center is read, the smartphone 40 acquires information such as a telephone number or a URL from the access information 20b and accesses the call center (that is, makes a call to the call center). ). In the second embodiment, by accessing the call center with the smartphone 40, the operator and the user of the call center can perform voice communication (call) via the smartphone 40. However, the operator and the user may not perform voice communication, but may chat with the operator via the operator terminal 70, the management server 30, and the like described in the above-described embodiment.

In the call center of the information providing system according to the second embodiment, a plurality of operators corresponding to each language are resident in order to support a plurality of languages. The smart speaker 20 determines a language used by the user, and displays access information 20b capable of performing voice communication with an operator corresponding to this language. The language used by the user may be determined by the smart speaker 20, the management server 30, the voice processing server 50, or any other device.

Several methods can be adopted as a method for determining the language used by the user. Although a plurality of language determination methods will be described below, the information providing system may perform language determination using one or more of these plurality of methods.

(1) Judgment from the user's utterance The language used by the user is determined based on the content of words, words, sentences, etc. that the user utters to the smart speaker 20. The voice information related to the user's utterance is transmitted from the smart speaker 20 to the voice processing server 50, and the voice processing server 50 can convert the voice information into text information for the language to be processed. Therefore, the voice processing server 50 can determine whether or not the given voice information is in the language to be processed, and if the voice information corresponds to a plurality of languages, whether or not the voice information is in the language to be processed. can. When the voice information is not the language to be processed, for example, the voice processing server 50 may only determine the language without converting it into text information, and for example, the voice information that the voice processing server 50 cannot process may be processed by the management server 30. The management server 30 may determine the language from the voice information, or the smart speaker 20 may determine the language from the voice information, for example.

In order to determine the language from the voice information, for example, a learning model in which machine learning is performed using the teacher data in which the voice information and the language type are associated with each other can be used. This learning model learns more languages than the language to be processed by the speech processing server 50, accepts speech information as input, and outputs information regarding the language type of the speech information. The voice processing server 50, the management server 30, or the smart speaker 20 stores this learning model in advance, and can determine a language based on voice information for a language that is not a processing target of the voice processing server 50.

(2) Judgment from guest information When the management server 30 or the computer of the accommodation facility has a database or the like for managing information about the guest, the language used by the user is determined based on the information stored in this database. be able to. For example, when information about a country or place such as a user's address or hometown is stored in a database as a user's guest information, it is determined that the language corresponding to this country or place is the language used by the user. Can be done.

A hotel management system called PMS (Property Management System) can be used to manage guest information. The smart speaker 20 or the management server 30 can communicate with the PMS server, acquire information about the staying user, and determine the language used by this user.

(3) Judgment from smartphone information Information on the language set in the smartphone 40 possessed by the user can be acquired, and the language used by the user can be determined based on the acquired information. For example, the smart speaker 20 can exchange information with and from the smartphone 40 by using wireless communication such as NFC (Near Field Communication), Bluetooth (registered trademark), or wireless LAN. The smartphone 40 is set in advance regarding the language used by the user, and the smart speaker 20 acquires the information of the language setting from the smartphone 40 by wireless communication and determines the language used by the user.

When using the setting information of the smartphone 40, the smartphone 40 may make the determination instead of the smart speaker 20 determining the language. That is, the smartphone 40 that has read the access information 20b displayed on the smart speaker 20 determines the access destination according to the language set for itself when accessing the call center based on the access information 20b. You may.

(4) Selection by User The smart speaker 20 can receive a language selection operation from the user and determine the language used by the user. For example, the smart speaker 20 displays the same language selection box of the smartphone 40 shown in FIG. 4 on the touch panel 25, and accepts the language selection by the user on the touch panel 25. The smart speaker 20 may accept the language selection at an appropriate timing. The smart speaker 20 may accept language selection at the timing when the user visits the accommodation facility and first uses the smart speaker 20, for example, immediately before displaying the access information 20b for accessing the call center. The language selection may be accepted at the timing of.

As the device such as the smart speaker 20, the management server 30, the smartphone 40, or the voice processing server 50 according to the second embodiment, any one of the above (1) to (4) may be adopted or a plurality thereof may be appropriately combined. To determine the language used by the user. The smart speaker 20 displays the access information 20b according to the determination result of the language used on the touch panel 25. A user who has read the access information 20b with the smartphone 40 can perform voice communication with the operator in the language used by himself / herself by accessing the call center using the access information 20b.

In the information providing system according to the second embodiment, the device such as the smart speaker 20, the management server 30, the smartphone 40, or the voice processing server 50 determines the language used by the user before displaying the access information 20b. It is a configuration, but it is not limited to this. For example, even if the access information 20b displayed by the smart speaker 20 is read by the smartphone 40, the user accesses the call center with the smartphone 40 using the access information 20b, and then the language used by the user is determined. good. In this case, for example, a device such as a server that manages a call center determines the language used by the user by adopting any one of (1) to (4) above or by appropriately combining a plurality of them, and the determination result is obtained. Voice communication is performed between the operator and the user according to the above.

Further, the access information 20b displayed by the smart speaker 20 may display different information depending on, for example, each accommodation facility, each room of the accommodation facility, each location of the accommodation facility, and the like. As a result, the call center can determine which accommodation facility or the like is inquiring according to the telephone number dialed by the smartphone 40. Further, the access information 20b may display different information depending on, for example, time or day of the week, and different information depending on, for example, whether or not the call center is open or whether or not the operator is present. May be displayed.

FIG. 21 is a flowchart showing a procedure of processing performed by the smart speaker 20 according to the second embodiment. The processing unit 21 of the smart speaker 20 according to the second embodiment transmits voice information related to a request from a user to the voice processing server 50, and outputs voice information received from the voice processing server 50 from the speaker 27. (Step S201).

The processing unit 21 determines whether or not a switching instruction for instructing switching from the voice response to the response by the chatbot or the response by the call center is given from the voice processing server 50 during the voice response processing (step). S202). When the switching instruction is not given (S202: NO), the processing unit 21 returns the processing to step S201 and continues the voice response processing.

When a switching instruction is given (S202: YES), the user is inquired about whether or not switching is possible by outputting a voice message or the like inquiring about whether or not switching is possible from the speaker 27 or displaying it on the touch panel 25 (step S203). The processing unit 21 determines whether or not an answer affirming the switching has been obtained for this inquiry (step S204). If no answer affirming the switch is obtained (S204: NO), the processing unit 21 returns the processing to step S201 and continues the voice response processing.

When an answer affirming the switching is obtained (S204: YES), the processing unit 21 determines the language used by the user (step S205). The language determination may be performed at a timing earlier than this. Further, the language determination may be performed by a device other than the smart speaker 20, and in this case, the processing unit 21 of the smart speaker 20 directly or indirectly acquires the determination result from the device that has performed the language determination.

Next, as shown in FIG. 11, the processing unit 21 uses the touch panel 25 to provide access information 20a for switching to a response by a chatbot and access information 20b for switching to a manned response by a call center. Is displayed (step S206), and the process is terminated.

FIG. 22 is a flowchart showing a procedure of voice communication start processing performed by the smartphone 40 according to the second embodiment. The processing unit 41 of the smartphone 40 according to the second embodiment starts an application program in response to, for example, a user operation, and shifts to a mode for reading a two-dimensional code (step S211). In this mode, the access information acquisition unit 41a of the processing unit 41 captures the access information 20b displayed by the smart speaker 20 with the camera 45, so that the access information 20b for switching to the manned response by the call center is performed. (Step S212). The access information acquisition unit 41a acquires information such as a telephone number included in the acquired access information 20b (step S213).

Next, the processing unit 41 accesses the call center based on the acquired information such as the telephone number (step S214). The processing unit 41 starts voice communication between the user and the call center (step S215), and ends the processing.

In the information providing system according to the second embodiment of the above configuration, the smart speaker 20 installed in the guest room of the accommodation facility acquires a request based on the voice input from the user, and the response information to the acquired request is obtained by the smart speaker 20. Output audio with. When the response information for the acquired request cannot be output, the management server 30 and the smart speaker 20 switch to either an automatic response by text input / output or a manned response by the operator.

At this time, the smart speaker 20 displays the access information 20a for switching to the automatic response by text input / output and the access information 20b for switching to the manned response by the operator, and tells the user which switching is to be performed. Let me choose. The user can select which response method to switch to by reading any of the access information 20a or 20b with his / her smartphone 40.

As a result, the user can select and switch between the response by the chatbot and the manned response by the operator when the desired result cannot be obtained by the voice response using the smart speaker 20. Since the user can switch to the response method according to his / her preference, it can be expected that information suitable for the user will be provided.

Further, the information providing system according to the second embodiment determines the type of language used by the user, and switches to a manned response by an operator who can handle the determined language. As a result, the user can smoothly perform voice communication with the operator.

The information providing system according to the second embodiment has a configuration in which the access information 20b displayed by the smart speaker 20 is read by the smartphone 40, and the user performs voice communication with the operator of the call center using the smartphone 40. , Not limited to this. For example, when the switch to the manned response by the call center operator is selected by the user, the smart speaker 20 may access the call center, and the smart speaker 20 may perform voice communication by the user and the operator.

Further, the information providing system according to the second embodiment does not have to be provided with yesterday's manned response of the operator by chat using the operator terminal 70.

Further, since the other configurations of the information providing system according to the second embodiment are the same as those of the information providing system according to the previous embodiment, the same reference numerals are given to the same parts, and detailed description thereof will be omitted. ..

<Embodiment 3>
The information providing system according to the second embodiment described above switches to either an automatic response by text input / output or a manned response by an operator when it is not possible to output response information to a request by voice. ing. On the other hand, when the information providing system according to the third embodiment cannot output the response information to the request by voice, first, it switches to the automatic response by text input / output. This can be performed by the same procedure as the information providing system according to the first embodiment.

The information providing system according to the first embodiment described above switches to a manned response of the operator by text input / output when the automatic response by text input / output cannot respond to the user's request. On the other hand, when the information providing system according to the third embodiment cannot respond to the user's request by the automatic response by the text input / output, the information providing system according to the first embodiment has the same manned response by the text input / output. Allows the user to choose between switching to or switching to a voice manned response by the call center operator.

The management server 30 of the information providing system according to the third embodiment automatically responds to the chatbot when the intention of the request from the user cannot be identified or when the response information to the intention of the request cannot be obtained. Sends the operator's instruction to switch to the manned response to the user's smartphone 40. This corresponds to, for example, the process shown in step S78 of the flowchart shown in FIG.

The smartphone 40 of the information providing system according to the third embodiment determines whether or not a switching instruction has been received from the management server 30 while performing an automatic response of the chatbot by text input / output. This corresponds to, for example, the process shown in step S54 of the flowchart shown in FIG.

When the switching instruction is received from the management server 30, the smartphone 40 according to the third embodiment selects whether to switch to a manned response by the operator's text input / output or to switch to the manned response by the call center operator's voice input / output. Accept. At this time, the smartphone 40 displays a message on the touch panel 44 to switch to a manned response, for example, a button labeled "chat (text input / output)", and a label "call center (voice input / output)". The buttons marked with are displayed side by side. By accepting a touch operation for any of the buttons, the smartphone 40 accepts the selection of a manned response by text input / output or a manned response by voice input / output.

When switching to the manned response by text input / output is selected, the smartphone 40 transmits a request for switching to the manned response by text input / output to the management server 30. This corresponds to, for example, the process shown in step S58 of the flowchart shown in FIG. The management server 30 that has received the request from the smartphone 40 performs a manned response by text input / output, for example, by processing the flowchart shown in FIG.

When switching to the manned response by voice input / output is selected, the smartphone 40 according to the third embodiment transmits a request for switching to the manned response by voice input / output to the management server 30. Upon receiving this request, the management server 30 performs, for example, a process of determining the language used by the user to determine a call center, an operator, or the like suitable for the user. The management server 30 transmits information such as a telephone number for making a call with the determined operator to the smartphone 40, or performs a process of establishing a call connection between the operator and the smartphone 40. When the smartphone 40 receives information such as a telephone number from the management server 30, the smartphone 40 accesses the call center based on the received information and starts voice communication with the operator.

The information providing system according to the third embodiment of the above configuration selects to switch to a manned response by text input / output or a manned response by voice input / output when the automatic response by text input / output cannot respond to the user's request. Accepts from the user and switches to the selected manned response.

As a result, the user can switch to a manned response by the operator when the desired result cannot be obtained by the automatic response by the chatbot, and can switch to either text input / output or voice input / output. You can choose whether to do it. Since the user can switch to the response method according to his / her preference, it can be expected that information suitable for the user will be provided.

Since the other configurations of the information providing system according to the third embodiment are the same as those of the information providing system according to the previous embodiment, the same reference numerals are given to the same parts, and detailed description thereof will be omitted.

The embodiments disclosed this time should be considered to be exemplary in all respects and not restrictive. The scope of the present disclosure is expressed by the scope of claims, not the above-mentioned meaning, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

10 Information provision system 20 Smart speaker (user interface)
20a Access information 21 Processing unit 22 Storage unit 22a Program 22b Identification information 23 Communication unit 25 Touch panel 25a Display unit 25b Input unit 26 Microphone 27 Speaker 28 Camera 30 Management server (information providing device)
31 Processing unit 31a Request acquisition unit 31b Response processing unit 31c Switching processing unit 31d Learning processing unit 32 Storage unit 32a Server program 33 Communication unit 40 Smartphone (terminal device)
41 Processing unit 41a Access information acquisition unit 41b Chat processing unit 42 Storage unit 42a Program 43 Communication unit 44 Touch panel 45 Camera 50 Voice processing server 60 Translation server 70 Operator terminal 80 Reservation server 81 Intention identification model (identifier)
82 Response information DB
83 Operator DB
99 Recording medium

The information providing method according to the present disclosure can acquire the voice input to the voice input / output device installed in the accommodation facility, perform voice recognition processing on the acquired voice, and can use the language related to the acquired voice. When it is included in the corresponding language, the voice input / output device can output the response information to the voice by voice, and the voice recognition process for the acquired voice cannot be performed, or the language related to the acquired voice is the corresponding language. If it is not included in, a response by input / output of text using a text input / output device different from the voice input / output device, or voice communication with an operator using a voice communication device different from the voice input / output device. Performs processing related to switching to the response by .

Claims (17)

Get a request based on the voice input to the user interface installed in the accommodation,
Obtain the response information corresponding to the obtained request from the database and
The acquired response information is output to the user interface by voice.
An information providing method for switching to an automatic response by input / output of text when the response information cannot be acquired from the database. The information providing method according to claim 1, wherein when the response information cannot be acquired from the database, access information for switching to an automatic response by input / output of text is output to the user interface. Accepting access from the terminal device based on the access information,
Acquire a request based on the text input to the terminal device,
The response information corresponding to the acquired request is acquired from the database, and the response information is acquired.
The acquired response information is output to the terminal device as a text.
The information providing method according to claim 2. The information providing method according to claim 3, wherein when the response information corresponding to the request based on the text cannot be obtained from the database, the response is switched to the manned response by the operator. Accepts the selection of manned response by text input / output or manned response by voice input / output,
The information providing method according to claim 4, wherein the response is switched to a manned response by an operator according to the accepted selection. The information providing method according to claim 4 or 5, wherein the switching destination to the manned response is determined based on the information of the date, time or language. Using a classifier learned to accept information related to a user's request as input and identify and output the intention of the user's request,
By inputting the information related to the user's request into the classifier, the intent of the request output by the classifier is acquired.
The response information corresponding to the intention of the acquired request is acquired from the database, and the response information is acquired.
Output the acquired response information
When the operator switches to the manned response, the classifier is relearned based on the result of the manned response.
The information providing method according to any one of claims 4 to 6. Acquire the identification information that identifies the accommodation facility,
Output the response information corresponding to the acquired request and identification information,
The information providing method according to any one of claims 2 to 7. The database stores response information for each accommodation facility, and stores the response information.
Based on the identification information, the response information corresponding to the accommodation facility is acquired from the database.
The information providing method according to claim 8. The access information is transmitted to the user before staying at the accommodation facility, and the access information is transmitted to the accommodation facility.
Accepting access from the user's terminal device based on the access information,
The information providing method according to any one of claims 2 to 9. When the response information cannot be obtained from the database, the information for switching to the automatic response by input / output of text and the information for switching to the manned response by the operator are selectively displayed.
The information providing method according to any one of claims 1 to 10. When information is selected to switch to any of the above manned responses,
Determine the language used by the user and
Switch to manned response by the operator corresponding to the determined language,
The information providing method according to claim 11. The user interface installed in the accommodation facility and
A request acquisition unit that acquires a request based on a voice input to the user interface, a response information acquisition unit that acquires response information corresponding to a request acquired by the request acquisition unit from a database, and a response acquired by the response information acquisition unit. It has a voice output processing unit that performs processing to output information to the user interface by voice, and a processing unit that performs processing related to switching to an automatic response by input / output of text when the response information cannot be acquired from the database. An information providing system equipped with an information providing device. A request acquisition unit that acquires requests based on voice input to the user interface installed in the accommodation facility,
The response information acquisition unit that acquires the response information corresponding to the request acquired by the request acquisition unit from the database, and the response information acquisition unit.
A voice output processing unit that performs processing to output the response information acquired by the response information acquisition unit to the user interface by voice, and a voice output processing unit.
An information providing device including a processing unit that performs processing related to switching to an automatic response by input / output of text when the response information cannot be acquired from the database. On the computer
Get a request based on the voice input to the user interface installed in the accommodation,
Obtain the response information corresponding to the obtained request from the database and
The acquired response information is output to the user interface by voice.
If the response information cannot be obtained from the database, switch to automatic response by input / output of text.
A computer program that executes processing. On the computer
Acquires access information output by the user interface installed in the accommodation facility,
Based on the acquired access information, access the information providing device that provides information related to the accommodation facility, and access it.
Get a request by text input and
The response information corresponding to the request is acquired from the information providing device and output as a text.
Based on the control from the information providing device, the operation related to the switching to the manned response is accepted.
A computer program that executes processing. The computer program according to claim 16, wherein the processing is selected by selecting a language related to the text input of the request and the text output of the response information.

Images