Server device, server device control method and program

Abstract

Provided is a server device for providing more satisfying support to a hotel guest or the like. This server device comprises an acquisition means and a response control means. The acquisition means acquires an inquiry item from a guest having the inquiry item among a plurality of guests staying at a hotel. The response control means performs control in accordance with the acquired inquiry item so as to respond to the inquiry item using information outputted by an artificial intelligence (AI) model or enable a person in charge who is in charge of support for the guest to respond to the inquiry item.

Description

Server device, server device control method and storage medium

[0001] The present invention relates to a server device, a control method for a server device, and a storage medium.

[0002] Technology exists to provide information to hotel guests.

[0003] For example, Patent Document 1 describes providing a program or the like that responds according to user attributes. The program in Patent Document 1 acquires a request based on voice data acquired from a user interface installed in a guest room of an accommodation facility, and a user interface identifier that identifies the user interface. The program acquires guest information about a guest staying in the guest room based on the acquired user interface identifier. The program causes a computer to execute a process of outputting product / service information, which is information about a product or service, based on the acquired guest information and request.

[0004] International Publication No. 2019 / 244365

[0005] Patent Literature 1 discloses a system that responds to guest requests using a learning model obtained by machine learning. However, guests' requests and demands for hotels are diverse, and responses output by a pre-prepared learning model may be insufficient. In other words, if a system attempts to respond to guest requests using only the responses output by the learning model as disclosed in Patent Literature 1, the support provided to the guest may be insufficient.

[0006] The main object of the present invention is to provide a server device, a method for controlling a server device, and a storage medium that contribute to providing hotel guests with support that provides a higher level of satisfaction.

[0007] According to a first aspect of the present invention, there is provided a server device including: an acquisition means for acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at a hotel; and a response control means for, depending on the acquired inquiry, answering the inquiry using information output by an AI (Artificial Intelligence) model, or controlling so that a person in charge of supporting the guest can answer the inquiry.

[0008] According to a second aspect of the present invention, there is provided a method for controlling a server device, including: an acquisition step in a server device of acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at a hotel; and a response control step of, depending on the acquired inquiry, either answering the inquiry using information output by an AI (Artificial Intelligence) model, or performing control so that a person in charge of supporting guests can answer the inquiry.

[0009] According to a third aspect of the present invention, there is provided a computer-readable storage medium that stores a program for causing a computer mounted on a server device to execute an acquisition process for acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at a hotel, and an answer control process for either answering the inquiry using information output by an AI (Artificial Intelligence) model according to the acquired inquiry, or performing control so that a person in charge of supporting the guest can answer the inquiry.

[0010] According to each aspect of the present invention, a server device, a control method for a server device, and a storage medium are provided that contribute to providing more satisfying support to hotel guests and the like. Note that the effects of the present invention are not limited to those described above. The present invention may achieve other effects instead of or in addition to the effects described above.

[0011] FIG. 1 is a diagram illustrating an overview of an embodiment. FIG. 2 is a flowchart illustrating an overview of the operation of the embodiment. FIG. 3 is a diagram illustrating an example of a schematic configuration of an information processing system according to a first embodiment. FIG. 4 is a diagram illustrating installation of a guide terminal according to the first embodiment. FIG. 5 is a diagram illustrating the operation of the information processing system according to the first embodiment. FIG. 6 is a diagram summarizing classifications of inquiry types according to the first embodiment. FIG. 7 is a diagram illustrating an example of a processing configuration of a server device according to the first embodiment. FIG. 8 is a diagram illustrating an example of a guest management database according to the first embodiment. FIG. 9 is a flowchart illustrating an example of the operation of an inquiry response control unit according to the first embodiment. FIG. 10 is a flowchart illustrating an example of the operation of an inquiry response control unit according to the first embodiment. FIG. 11 is a diagram illustrating an example of a processing configuration of a guide terminal according to the first embodiment. FIG. 12 is a diagram illustrating an example of a display of the guide terminal according to the first embodiment. FIG. 13 is a sequence diagram illustrating an example of the operation of the information processing system according to the first embodiment. FIG. 14 is a sequence diagram illustrating an example of the operation of the information processing system according to the first embodiment. FIG. 15 is a diagram illustrating an example of a hardware configuration of a server device according to the present disclosure.

[0012] First, an overview of one embodiment will be described. Note that the reference numerals in the drawings are added to each element for convenience as an example to facilitate understanding, and the description of this overview is not intended to be limiting in any way. Furthermore, unless otherwise specified, the blocks shown in each drawing represent functional units, not hardware units. Connection lines between blocks in each drawing include both bidirectional and unidirectional lines. Unidirectional arrows are used to schematically indicate the flow of the main signal (data) and do not exclude bidirectionality. Note that in this specification and drawings, elements that can be similarly described may be assigned the same reference numerals to avoid redundant explanation.

[0013] A server device 100 according to one embodiment includes an acquisition unit 101 and a response control unit 102 (see FIG. 1 ). The acquisition unit 101 acquires an inquiry from a guest who has an inquiry among a plurality of guests staying at a hotel (step S1 in FIG. 2 ). The response control unit 102 responds to the inquiry using information output by an AI (artificial intelligence) model, depending on the acquired inquiry, or controls the response so that a person in charge of supporting the guest can respond to the inquiry (executes response control; step S2).

[0014] The server device 100 responds to inquiries from guests using answers (proposals) output by the AI ​​model based on the content of the inquiries, or controls the process so that hotel employees can respond to the inquiries. For example, if the reliability of the output results from the AI ​​model is low or if the request is difficult to handle using the AI ​​model, the server device 100 entrusts the handling to hotel employees. In other words, appropriate information is provided in response to the guest's inquiry, and the hotel employees can take appropriate action. As a result, support with a higher level of satisfaction is provided to guests.

[0015] Specific embodiments will be described in more detail below with reference to the drawings.

[0016] First Embodiment The first embodiment will be described in more detail with reference to the drawings.

[0017] [System Configuration] Fig. 3 is a diagram showing an example of the schematic configuration of the information processing system according to the first embodiment. As shown in Fig. 3, the information processing system includes a hotel headquarters and multiple hotels A to C. The same operator manages hotels A to C. Alternatively, hotels A to C may be managed by operators in a partnership.

[0018] The hotel headquarters is equipped with a server device 10 and an employee terminal 20. Each hotel is equipped with a guide terminal 30.

[0019] The server device 10 performs the main business of the hotel. Specifically, the server device 10 stores reservation information of guests staying at each hotel (e.g., name, gender, address, date of birth, biometric information, name of the hotel where the guest will be staying, dates of stay (length of stay: check-in date, check-out date), room type, etc.). The server device 10 uses the reservation information to perform check-in procedures, check-out procedures, etc. for the guests.

[0020] Examples of biometric information include data (features) calculated from physical characteristics unique to an individual, such as a face, fingerprint, voiceprint, veins, retina, or iris pattern. Alternatively, the biometric information may be image data such as a face image or fingerprint image. The biometric information may be any information that includes the user's physical characteristics. In the embodiment disclosed herein, a case where biometric information related to a person's "face" (a face image or features generated from a face image) is used will be described.

[0021] The server device 10 also has a function for supporting guests, specifically, a function for responding to questions and requests from guests.

[0022] The employee terminal 20 is a terminal used by hotel employees, particularly employees who provide support to guests.

[0023] As shown in Fig. 4, the guide terminal 30 is installed in the lobby of each hotel. The guide terminal 30 is, for example, a signage-type or tablet-type terminal. The guide terminal 30 is equipped with a camera for photographing the user, a display for displaying various information, a speaker for outputting audio, a microphone for acquiring audio, etc. Alternatively, the guide terminal 30 may be a smart speaker equipped with a speaker and a microphone.

[0024] The guide terminal 30 is a terminal that serves as an interface for guests who need support. Guests who have problems or other issues input questions, requests, etc. into the guide terminal 30. The guests receive answers to their questions or other issues via the guide terminal 30.

[0025] 3, a user (guest) carries a terminal 40. The user makes hotel reservations and the like using the terminal 40. Examples of the terminal 40 include mobile terminals such as smartphones and tablets.

[0026] The devices shown in Fig. 3 are interconnected. Specifically, the server device 10, the employee terminal 20, and the information terminal 30 are connected by wired or wireless communication means and are configured to be able to communicate with each other.

[0027] The configuration of the information processing system shown in Figure 3 is an example and is not intended to be limiting. For example, the system may include multiple server devices 10. Alternatively, each hotel may be equipped with multiple information terminals 30.

[0028] [Overall Operation] Next, an overall operation of the information processing system according to the first embodiment will be described.

[0029] <Room Reservation> A user operates the terminal 40 to access an accommodation reservation site provided by the server device 10. When the user operates the terminal 40 to apply for a reservation, the server device 10 acquires reservation information (e.g., the name, sex, address, date of birth, biometric information, name of the hotel where the reservation is made, date of stay (length of stay), room type, etc.).

[0030] The server device 10 stores the acquired reservation information in the guest management database. As described above, the reservation information is used for the check-in procedure of the guest. The guest management database will be described in detail later.

[0031] <Guest support> Guests will visit the hotel on the day of their stay and complete the check-in procedures.

[0032] A guest who has a problem or request regarding the use of the hotel, etc., inputs the inquiry into the information terminal 30 (see FIG. 5). For example, the guest inputs the question, request, etc. into the information terminal 30 by voice.

[0033] The guide terminal 30 photographs the guest who inputs the inquiry and acquires biometric information (e.g., a facial image). The guide terminal 30 notifies the server device 10 of the acquired biometric information and inquiry. Specifically, the guide terminal 30 transmits an "inquiry response request" including the biometric information, the inquiry, and the hotel ID to the server device 10.

[0034] The hotel ID is an ID for identifying the hotel where the information terminal 30 is installed. The hotel ID may be the name of the hotel or a predetermined code. Alternatively, the MAC (Media Access Control) address or IP (Internet Protocol) address of the information terminal 30 may be used as the hotel ID.

[0035] The server device 10 processes the inquiry response request received from the guide terminal 30. The server device 10 processes the inquiry response request using an AI (Artificial Intelligence) model obtained by machine learning.

[0036] The server device 10 inputs the inquiry item into a classification AI model, thereby classifying the inquiry item into five types.

[0037] The first inquiry type is an inquiry that does not require personal data of the guest who made the inquiry (e.g., all or part of the reservation information) when generating an answer, and does not require a predetermined level of accuracy (high accuracy) in the answer. For example, an inquiry about traffic congestion forecasts around a hotel is an example of the first inquiry type.

[0038] The second inquiry type is an inquiry that requires personal data of the guest who made the inquiry when generating an answer, but does not require a certain level of accuracy in the answer, such as an inquiry about recommended tourist spots around the hotel.

[0039] The third inquiry type is an inquiry that does not require personal data of the inquiring guest when generating an answer, and requires a certain level of accuracy in the answer, such as an inquiry about the opening hours of a restaurant or the like in a hotel.

[0040] The fourth inquiry type is an inquiry that requires personal data of the guest who made the inquiry when generating an answer and that requires a certain level of accuracy in the answer, such as an inquiry about the accommodation fee to be paid at check-out or the check-out time.

[0041] The first to fourth inquiry types can be summarized as shown in FIG.

[0042] The fifth inquiry type is an inquiry that does not fall into any of the first to fourth inquiry types. For example, an inquiry about a guest room defect or a hotel facility defect is exemplified as the fifth inquiry type.

[0043] The server device 10 inputs the inquiries received from the guests into an AI model (classification AI model) to classify the inquiries into one of the first to fifth inquiry types.

[0044] The server device 10 generates answers to inquiries for the first to fourth inquiry types using an AI model (an AI model different from the classification AI model) for the inquiry items. The server device 10 is equipped with first to fourth answering AI models corresponding to the first to fourth inquiry types, respectively.

[0045] The server device 10 inputs the inquiry classified by the classification AI model into one of the corresponding first to fourth answer AI models, and obtains information (suggested answers) from the answer AI model.

[0046] At this time, if a response is required for the second or fourth inquiry type, the server device 10 performs a matching process using the biometric information of the guest acquired from the guide terminal 30 and the biometric information stored in the guest management database. The server device 10 acquires personal data (e.g., gender, age, date of stay, room type, etc.) of the guest identified by the matching process.

[0047] For example, the server device 10 inputs an inquiry classified as the first inquiry type into an AI model (first answering AI model) prepared specifically for the first type and obtains an answer (proposed answer). Alternatively, the server device 10 inputs an inquiry classified as the second inquiry type into an AI model (second answering AI model) prepared in advance together with the guest's personal data read from the guest management database and obtains a proposed answer.

[0048] Here, for the first and second inquiry types, the server device 10 transmits information output by the AI ​​model as a response to the inquiry to the guide terminal 30. That is, for the first and second inquiry types, the server device 10 automatically responds without human intervention, such as by a hotel employee. Such automatic responses are permissible because high accuracy is not required for the responses to the first and second inquiry types.

[0049] On the other hand, for the third and fourth inquiry types, the server device 10 determines the method of response based on the "certainty" of the information (proposed answer) output by the AI ​​model. Specifically, the server device 10 determines, based on the confidence output by the AI ​​model, whether to send the answer acquired from the AI ​​model to the guide terminal 30 or leave the response to the inquiry to a hotel employee (customer support staff, support representative), etc.

[0050] If the confidence level is equal to or greater than a predetermined value (if the answer of the AI ​​model is reliable), the server device 10 notifies the guidance terminal 30 of the proposed answer output by the answering AI model. Specifically, the server device 10 transmits an "answer notification" including the proposed answer output by the answering AI model to the guidance terminal 30 (see FIG. 5).

[0051] When the answer notification is received, the guide terminal 30 presents the answer included in the answer notification to the guest. The guide terminal 30 outputs the answer by voice or displays it on a display.

[0052] If the confidence level is smaller than a predetermined value (if the AI ​​model's response is unreliable), the server device 10 requests a hotel employee to process the guest's inquiry. Specifically, the server device 10 instructs the guide terminal 30 to connect to the employee terminal 20. The server device 10 transmits a "connection instruction" to the guide terminal 30, including the IP address of the employee terminal 20 to be connected to, etc.

[0053] Upon receiving the connection instruction, the guide terminal 30 accesses the employee terminal 20 and sets it up so that the guest and the employee can converse with each other. The hotel employee converses with the guest via the employee terminal 20 and the guide terminal 30 and handles the guest's inquiries.

[0054] For the fifth inquiry type, the server device 10 does not use an AI model to provide a response. The server device 10 initially leaves the response (problem resolution) to the inquiry item of the fifth inquiry type to the hotel staff. For the fifth inquiry type, the server device 10 sends a connection instruction to the guide terminal 30.

[0055] Next, details of each device included in the information processing system according to the first embodiment will be described.

[0056] 7 is a diagram showing an example of a processing configuration (processing module) of the server device 10 according to the first embodiment. Referring to FIG. 7, the server device 10 includes a communication control unit 201, a hotel business control unit 202, an inquiry response control unit 203, and a storage unit 204.

[0057] The communication control unit 201 is a means for controlling communication with other devices. For example, the communication control unit 201 receives data (packets) from the guide terminal 30. The communication control unit 201 also transmits data to the guide terminal 30. The communication control unit 201 passes data received from other devices to other processing modules. The communication control unit 201 transmits data acquired from other processing modules to other devices. In this way, other processing modules transmit and receive data to and from other devices via the communication control unit 201. The communication control unit 201 has a function as a receiving unit that receives data from other devices and a function as a transmitting unit that transmits data to other devices.

[0058] The hotel business control unit 202 is a means for controlling the business of each hotel, and controls the room reservation, check-in procedure, check-out procedure, and the like.

[0059] Specifically, the hotel business control unit 202 realizes an accommodation reservation site for users to reserve rooms. The hotel business control unit 202 acquires information about the hotel reserved by the user (e.g., hotel name; hotel ID), room information (e.g., stay date, room type), and reservation person information (e.g., name, gender, etc.) from the accommodation reservation site.

[0060] The hotel business control unit 202 displays a GUI (Graphical User Interface) for acquiring the user's name, etc. on the terminal 40. The hotel business control unit 202 acquires reservation information from the user (name, gender, address, date of birth, biometric information, name of the hotel where the user will be staying, date of stay, room type, etc.).

[0061] When a facial image is acquired as biometric information, the hotel business control unit 202 generates feature quantities from the acquired facial image. Since existing technology can be used for the feature quantity generation process, a detailed description thereof will be omitted. For example, the hotel business control unit 202 extracts the eyes, nose, mouth, etc. from the facial image as feature quantities. The hotel business control unit 202 then calculates the positions of each feature quantity and the distances between each feature quantity as feature quantities (generating a feature vector consisting of multiple feature quantities).

[0062] Furthermore, when the hotel business control unit 202 acquires reservation information, it generates a user ID for identifying the user (guest). The user ID may be any information that can uniquely identify the guest. For example, the hotel business control unit 202 may assign a unique value each time reservation information is acquired and use this as the user ID.

[0063] The hotel business control unit 202 associates the generated user ID, name, biometric information, etc. and registers them in the guest management database (see FIG. 8). Note that the guest management database shown in FIG. 8 is an example and is not intended to limit the items to be stored. For example, a "facial image" may be registered in the guest management database as biometric information. Also, in FIG. 8, for ease of understanding, the hotel ID uses the name of the hotel shown in FIG. 3.

[0064] Furthermore, the hotel business control unit 202 controls check-in procedures, check-out procedures, etc. Check-in procedures may be performed using biometric authentication or by a hotel employee waiting at the reception counter. When the check-in procedures are performed, the guest room number in which the guest will be staying is stored in the guest management database.

[0065] Hotel room reservations and check-in procedures are not within the scope of this disclosure, and therefore further explanation will be omitted.

[0066] The inquiry response control unit 203 is a means for controlling the response to the inquiry received from the guest, and processes the inquiry response request received from the guide terminal 30.

[0067] The inquiry response control unit 203 has a function as an acquisition unit that acquires an inquiry from a guest who has an inquiry among multiple guests staying at the hotel. Furthermore, the inquiry response control unit 203 has a function as an answer control unit that answers the inquiry using information output by the AI ​​model according to the acquired inquiry, or controls so that the person in charge of supporting the guest can answer the inquiry.

[0068] The operation of the inquiry response control unit 203 will be described with reference to FIGS.

[0069] When an inquiry response request is received from the information terminal 30, the inquiry response control unit 203 determines the inquiry type of the inquiry item included in the request (step S101). Specifically, the inquiry response control unit 203 inputs the inquiry item into a classification AI model to obtain the type of the obtained inquiry item.

[0070] The inquiry response control unit 203 classifies the inquiry into one of several predetermined types, and, depending on the classified type, determines whether to respond to the inquiry using information output by the AI ​​model or whether the person in charge will respond to the inquiry.

[0071] The classification AI model (learning model) is obtained by machine learning using a large amount of training data in which labels (query item types) are assigned to query items. Any algorithm, such as a support vector machine, boosting, or neural network, can be used to generate the AI ​​model. Since well-known techniques can be used for the algorithms, such as the support vector machine, a description thereof will be omitted.

[0072] The inquiry response control unit 203 determines whether the inquiry item is a type that requires the application of an AI model or a type that does not require the application of an AI model (determining whether the application of an AI model is necessary; step S102). Specifically, the inquiry response control unit 203 determines that the application of an AI model is necessary if the inquiry type is any of types 1 to 4. The inquiry response control unit 203 determines that the application of an AI model is not necessary if the inquiry type is type 5.

[0073] If application of the AI ​​model is not necessary (step S103, No branch), the inquiry response control unit 203 executes the processing from step S113 onwards shown in FIG.

[0074] If it is necessary to apply an AI model (step S103, Yes branch), the inquiry response control unit 203 determines whether or not it is necessary to obtain personal data of the guest (guest who has requests, etc.) (determining whether personal data is necessary; step S104).

[0075] Specifically, the inquiry response control unit 203 determines that it is not necessary to acquire personal data of the guest if the inquiry type is the first or third type, and determines that it is necessary to acquire personal data of the guest if the inquiry type is the second or fourth type.

[0076] If it is not necessary to acquire the guest's personal data (step S105, No branch), the inquiry response control unit 203 executes the processes from step S109 onwards.

[0077] If it is necessary to obtain the guest's personal data (step S105, Yes branch), the inquiry response control unit 203 performs a matching process using the biometric information included in the inquiry response request and the biometric information stored in the guest management database (step S106).

[0078] Specifically, the inquiry response control unit 203 generates features from biometric information (face image) included in the inquiry response request. The inquiry response control unit 203 executes a matching process using the generated features and features registered in the guest management database. The inquiry response control unit 203 sets the generated features as the matching target and performs a matching process (one-to-N matching; N is a positive integer, the same applies below) between the generated features and the features registered in the guest management database.

[0079] The inquiry response control unit 203 calculates the similarity between the feature to be matched and each of the multiple feature values ​​on the registration side. The similarity can be calculated using chi-square distance, Euclidean distance, or the like. Note that the greater the distance, the lower the similarity, and the closer the distance, the higher the similarity.

[0080] The inquiry response control unit 203 determines that the matching process (authentication process) has failed if there is no feature among the multiple features registered in the guest management database that has a similarity with the feature to be matched that is greater than a predetermined value.

[0081] The inquiry response control unit 203 determines that the matching process is successful if, among the multiple feature quantities registered in the guest management database, there is a feature quantity whose similarity with the feature quantity to be matched is equal to or greater than a predetermined value. If the matching process is successful, the inquiry response control unit 203 identifies the guest (entry in the guest management database) corresponding to the feature quantity with the highest similarity as the inquirer.

[0082] If the matching process fails (step S107, No branch), the inquiry response control unit 203 determines that an error has occurred and terminates the process. In this case, the inquiry response control unit 203 may consider the possibility that a person other than a hotel guest is using the information terminal 30 and notify a security guard or the like to that effect.

[0083] If the matching process is successful (step S107, Yes branch), the inquiry response control unit 203 reads the personal data of the guest identified by the matching process from the guest management database (acquire personal data; step S108).

[0084] The inquiry response control unit 203 applies an AI model according to the type of inquiry to the inquiry (application of AI model; step S109). The server device 10 has first to fourth answering AI models corresponding to the first to fourth inquiry types, respectively.

[0085] The inquiry response control unit 203 obtains information (proposed responses) for the inquiry by inputting the inquiry into an AI model for response according to the inquiry type.

[0086] The first and third types of answering AI models are obtained by machine learning using a large amount of training data consisting of combinations of inquiries and corresponding answer ideas. The second and fourth types of answering AI models are obtained by machine learning using a large amount of training data consisting of combinations of inquiries, personal data, and corresponding answer ideas. Furthermore, at least the third and fourth types of answering AI models output a confidence level.

[0087] When a proposed answer is obtained from the answering AI model, the inquiry response control unit 203 determines whether or not a human response (guidance by a hotel employee) is required for the inquiry from the guest (step S110 in FIG. 10 ). Specifically, if the inquiry type is the first or second type, the inquiry response control unit 203 determines that a human response is not required.

[0088] If the inquiry type is the third or fourth type, the inquiry response control unit 203 determines whether or not a human response is required based on the result of threshold processing on the confidence level output by the AI ​​model.

[0089] If the confidence level is equal to or greater than a predetermined threshold, the inquiry response control unit 203 determines that manned response is unnecessary. If the confidence level is smaller than the predetermined threshold, the inquiry response control unit 203 determines that manned response is necessary.

[0090] If no human response is required (step S111, No branch), the inquiry response control unit 203 generates an answer using the information output by the answering AI model, and transmits an "answer notification" including the generated answer to the guidance terminal 30 (step S112). At this time, the inquiry response control unit 203 may adopt the information (proposed answer) output by the answering AI model as the answer as is, or may process the information output by the answering AI model to generate the answer.

[0091] If manned assistance is required (step S111, Yes branch), the inquiry response control unit 203 sends a "connection instruction" to the guidance terminal 30 (step S113). The inquiry response control unit 203 sends the connection instruction including the IP address of the employee terminal 20 and the like to the guidance terminal 30.

[0092] In this way, if the confidence level of the information output by the AI ​​model is equal to or greater than a predetermined value, the inquiry response control unit 203 uses the information output by the AI ​​model to respond to the inquiry. If the confidence level is lower than a predetermined value, the inquiry response control unit 203 performs control so that the person in charge can respond to the inquiry. More specifically, if the confidence level is lower than a predetermined value, the inquiry response control unit 203 instructs the first terminal (guide terminal 30) that has accepted the inquiry of the guest with the inquiry to connect to the second terminal (employee terminal 20) used by the person in charge.

[0093] The storage unit 204 is a means for storing information necessary for the operation of the server device 10. The storage unit 204 stores biometric information and personal data (e.g., gender, date of birth, date of stay, room type, etc.) for each of a plurality of guests in association with each other.

[0094] 11 is a diagram showing an example of a processing configuration (processing module) of guide terminal 30. Referring to FIG. 11, guide terminal 30 includes a communication control unit 301, a query control unit 302, and a storage unit 303.

[0095] The communication control unit 301 is a means for controlling communication with other devices. For example, the communication control unit 301 receives data (packets) from the server device 10. The communication control unit 301 also transmits data to the server device 10. The communication control unit 301 passes data received from other devices to other processing modules. The communication control unit 301 transmits data acquired from other processing modules to other devices. In this way, other processing modules transmit and receive data to and from other devices via the communication control unit 301. The communication control unit 301 has a function as a receiving unit that receives data from other devices and a function as a transmitting unit that transmits data to other devices.

[0096] The inquiry control unit 302 is a means for controlling inquiries made by guests. For example, the inquiry control unit 302 detects a user in front of the guest based on an output signal from a motion sensor or the like. When a user (guest) is detected, the inquiry control unit 302 controls a microphone or the like to acquire the inquiry from the user. Alternatively, when the user utters a predetermined phrase, the inquiry control unit 302 detects the user as a guest with an inquiry.

[0097] The inquiry control unit 302 converts the voice into text information using voice recognition technology or the like, and acquires the inquiry.

[0098] When the inquiry item is acquired, the inquiry control unit 302 controls the camera device (the camera device provided in the guidance terminal 30) to acquire biometric information (e.g., a facial image) of the user in front of the server device 10. The inquiry control unit 302 transmits an inquiry response request including the acquired biometric information, the inquiry item, and the hotel ID to the server device 10.

[0099] The inquiry control unit 302 acquires a response notice or a connection instruction from the server device 10 as a response to the inquiry response request.

[0100] When receiving the answer notification, the inquiry control unit 302 displays the answer included in the notification on a display etc. In this case, the inquiry control unit 302 may display the inquiry of the guest and the answer acquired from the server device 10 in an interactive format, as shown in Fig. 12. Alternatively, the inquiry control unit 302 may convert the acquired answer into audio data and output it from a speaker.

[0101] When a connection instruction is received, the inquiry control unit 302 accesses the employee terminal 20 having the IP address included in the instruction. When a connection is made with the employee terminal 20 (when a session is established), the inquiry control unit 302 transmits the inquiry (questions, requests, etc. from the guest) to the employee terminal 20.

[0102] The inquiry control unit 302 then transmits the voice data of the guest collected via the microphone to the employee terminal 20, and outputs voice data from the hotel employee from the speaker. The inquiry control unit 302 also transmits and receives image data of the guest and hotel employee to and from the employee terminal 20. The inquiry control unit 302 provides an interface for conversations between the hotel employee and the guest, such as an online conference.

[0103] The storage unit 303 is a means for storing information necessary for the operation of the guide terminal 30 .

[0104] [Employee Terminal] Examples of the employee terminal 20 include mobile terminal devices such as smartphones, mobile phones, game consoles, and tablets, as well as computers (personal computers, laptop computers). The employee terminal 20 can be any equipment or device that can accept operations from hotel employees and communicate with the server device 10. The configuration of the employee terminal 20 is clear to those skilled in the art, so a detailed description will be omitted.

[0105] When the employee terminal 20 starts connection with the information terminal 30, it presents the inquiry acquired from the information terminal 30 to the hotel employee, and sets up a situation in which the guest and the hotel employee can converse with each other.

[0106] [Terminal] Examples of the terminal 40 include a smartphone, a mobile phone, a game console, a mobile terminal device such as a tablet, a computer (personal computer, laptop computer), etc. The terminal 40 can be any equipment or device that can accept user operations and communicate with the server device 10, etc. Furthermore, the configuration of the terminal 40 is clear to those skilled in the art, so a detailed description thereof will be omitted.

[0107] [System Operation] Next, the operation of the information processing system according to the first embodiment will be described.

[0108] Referring to Figure 13, the operation of the information processing system when an answer based on the AI ​​model is provided to a guest will be described.

[0109] The guide terminal 30 transmits an inquiry response request including the biometric information of the guest and the inquiry to the server device 10 (step S01).

[0110] The server device 10 generates a response to the inquiry using the response AI model (step S02).

[0111] Server device 10 transmits a response notification including the generated response to guide terminal 30 (step S03).

[0112] The guide terminal 30 presents the answer contained in the received answer notice to the guest (step S04).

[0113] Next, with reference to FIG. 14, the operation of the information processing system when a hotel employee responds to questions and requests from a guest will be described.

[0114] The guide terminal 30 transmits an inquiry response request including the biometric information of the guest and the inquiry to the server device 10 (step S11).

[0115] The server device 10 determines whether human response is required based on the inquiry type and the confidence level output by the AI ​​model (step S12).

[0116] The server device 10 transmits a connection instruction to the guide terminal 30 (step S13).

[0117] Upon receiving the instruction, the guide terminal 30 connects to the employee terminal 20 (step S14).

[0118] The guide terminal 30 and the employee terminal 20 transmit and receive voice data and image data (step S15). The employee listens to the guest's concerns and solves them via the employee terminal 20 and the guide terminal 30.

[0119] In this way, when the inquiry is of the second or fourth type, the server device 10 acquires the biometric information of the guest who has the inquiry along with the inquiry. The server device 10 identifies the personal data of the guest who has the inquiry by performing a matching process using the acquired biometric information and multiple pieces of biometric information stored in the guest management database. Furthermore, when the confidence level output by the third or fourth AI model is equal to or greater than a predetermined value, the server device 10 responds to the inquiry using the information output by the third or fourth AI model. On the other hand, when the confidence level is less than the predetermined value, the server device 10 controls the process so that a person in charge can respond to the inquiry.

[0120] <Specific Examples> Specific examples of the above first to fifth types of inquiries and their answers will be given below.

[0121] The first inquiry type is an inquiry that does not require personal data of the guest (questioner, requester) and does not require a high level of accuracy in the answer. For example, a question about traffic congestion predictions around a hotel, such as "Will the roads be congested tomorrow?", is an example of this first inquiry type. Traffic congestion can occur regardless of the attributes of the guest (e.g., age or gender). Furthermore, since it is commonly recognized among users that predictions can be wrong due to accidents or other factors, a high level of accuracy is not required in the answer to this type of question. The server device 10 generates an answer using a learning model generated using the congestion level for each day of the week, and presents it to the guest.

[0122] In this way, when the inquiry is of the first type, which does not require the guest's personal data and does not require a certain level of accuracy in the answer, the server device 10 obtains an answer (proposed answer) to the inquiry by inputting the inquiry into the first AI model prepared for the first type.

[0123] The second inquiry type is an inquiry that requires personal data of the guest but does not require a high level of accuracy in the response. For example, an inquiry such as "Please tell me about some recommended tourist spots" is an example of the second inquiry type. Evaluations of tourist spots can vary significantly depending on age and gender. Therefore, by inputting the guest's attribute information (e.g., gender and age) into an AI model trained using information on tourist spots that are highly rated by age and gender, the server device 10 provides information on tourist spots that the guest is likely to like. On the other hand, since people's preferences often vary from person to person, the questioner himself or herself often does not require a high level of accuracy in the response to the question.

[0124] In this way, when the inquiry is of the second type, in which the inquiry requires the guest's personal data and the answer does not require a certain level of accuracy, the server device 10 inputs the inquiry and the personal data into a second AI model prepared for the second type, and obtains an answer to the inquiry.

[0125] The third inquiry type is an inquiry that does not require the guest's personal data and requires a highly accurate answer. For example, a question such as "What are the restaurant's business hours?" is an example of the third inquiry type. The business hours of restaurants operating in the hotel are not affected by the guest's personal data. Furthermore, the server device 10 cannot provide incorrect information about the business hours of restaurants operating in the hotel. The server device 10 generates an answer using a learning model generated using the business hours of restaurants operating in the hotel, and presents the answer to the guest.

[0126] In this way, when the inquiry is of the third type, which does not require the guest's personal data but requires a certain level of accuracy in the response, the server device 10 obtains the response to the inquiry by inputting the inquiry into a third AI model prepared for the third type.

[0127] The fourth inquiry type requires the guest's personal data and a high level of accuracy in the answer. For example, questions such as "What is the accommodation fee?" and "What is the check-out time?" are examples of the fourth inquiry type. The accommodation fee varies for each guest depending on the type (grade) of the room and the length of their stay. Alternatively, the check-out time varies depending on whether a guest uses late check-out. Therefore, in order to answer such questions, the guest's personal data (part of the reservation information, such as the length of stay and room type) is required. Furthermore, the server device 10 cannot provide incorrect information in response to this type of question. The server device 10 generates an answer using a learning model generated using the accommodation fee for each room type and length of stay, and presents the answer to the guest.

[0128] In this way, when the inquiry is of the fourth type, which requires the guest's personal data and a certain level of accuracy in the response, the server device 10 inputs the inquiry and the personal data into a fourth AI model prepared for the fourth type, and obtains the response to the inquiry.

[0129] The fifth inquiry type includes questions that do not fall into any of the first to fourth inquiry types, as well as requests that cannot be resolved without the physical or personal support of a hotel employee or other person. The fifth inquiry type also includes requests that require careful handling, such as complaints about room defects. For example, the fifth inquiry type includes requests such as "I'd like to borrow an iron," "Please call a taxi with my destination as the airport," and "The air conditioner isn't working." When a hotel employee receives such a request, they will instruct a staff member at the hotel where the guest is staying to bring the iron to the guest's room or arrange for a taxi.

[0130] It goes without saying that the specific examples for each inquiry type are merely illustrative. Furthermore, even inquiries of the same content may be classified into different types depending on the hotel's philosophy or policy. For example, if a response to an inquiry such as "What tourist spots do you recommend?" is made without using the guest's personal data (attribute information, such as gender and age), the inquiry may be classified as the first inquiry type.

[0131] Next, a modification of the first embodiment will be described.

[0132] <Variation 1> In the above embodiment, the guide terminal 30 is installed in the lobby. The guide terminal 30 may be installed in each guest room. In this case, the guest room number in which the guide terminal 30 is installed or the terminal ID of the guide terminal 30 may be used instead of biometric information (biometric authentication) to identify the guest asking a question or making a request. When transmitting an inquiry response request to the server device 10, the guide terminal 30 transmits the guest room number in which the terminal 30 is installed or the terminal ID of the terminal 30 instead of the biometric information of the questioner. The server device 10 may search the guest management database using the acquired guest room number as a key to identify the guest (questioner) with the inquiry. Alternatively, the server device 10 may identify the guest room number in which the guide terminal 30 is installed from the terminal ID to identify the questioner.

[0133] <Modification 2> In the above embodiment, the case where support for guests is provided using an AI model has been described. The server device 10 may provide support for guests using a means other than the AI ​​model instead of or in addition to the AI ​​model.

[0134] For example, the server device 10 may support guests using information obtained from the Internet (an external server on a network). For example, the server device 10 may obtain weather forecasts, evacuation information in the event of a disaster, and the like from an external server. For example, to answer a question such as "What will the weather be like tomorrow?", the server device 10 may obtain a weather forecast from an external server. In this case, a sixth type of inquiry, which queries an external server, may be added to the above five inquiry types. The server device 10 may obtain answers to inquiries classified as the sixth inquiry type from an external server. In this case, the server device 10 may store information on the external server to which inquiries should be made for each question, or may use an AI model that outputs the external server to which inquiries should be made when an inquiry is input.

[0135] <Variation 3> The server device 10 may determine whether to send a person to respond to a request from a guest based on other information, rather than the confidence level output by the AI ​​model. For example, the inquiry response control unit 203 of the server device 10 may determine whether to send a person to respond to a request based on the number of hotel employees on duty or the number of guests who have checked in. For example, when the number of guests is small or when there are many hotel employees, the server device 10 may control the hotel employees to respond to the inquiries of the guests.

[0136] <Variation 4> Depending on the content of the guest's inquiry, the question-and-answer exchange between the guest and the AI ​​model may continue several times. That is, the server device 10 may respond to the guest's questions in a chatbot-like format. In this case, the confidence level of the AI ​​model's output may decrease during the exchange, and the guest may switch from the AI ​​model to a hotel employee. When this switch occurs, the inquiry response control unit 203 of the server device 10 may present the hotel employee with the conversation history between the guest and the AI ​​model to ensure a smooth handover of the conversation. Specifically, the inquiry response control unit 203 sends a connection instruction including the conversation history to the guide terminal 30. After starting communication with the employee terminal 20, the guide terminal 30 sends the conversation history to the employee terminal 20.

[0137] As described above, the server device 10 according to the first embodiment classifies the types of inquiries from hotel guests and responds using answers (proposed answers) output by the AI ​​model based on the classified type, or controls the hotel staff to respond to the inquiries. For example, the server device 10 responds to inquiries using information output by the AI ​​model regarding information such as facility guides for the hotel. In contrast, for inquiries where the information obtained from the AI ​​model is unreliable and the answer requires accuracy (precision, precision), the server device 10 entrusts the response to the inquiry to hotel staff who are familiar with hotel operations. As a result, hotel guests are provided with support that provides a higher level of satisfaction.

[0138] Furthermore, hotels face the problem of a shortage of on-site employees to support guests. The information processing system disclosed herein solves this problem by centralizing guest support for multiple hotels at a headquarters or other location. Specifically, hotel front desk staff (those working at the front desk) are required to respond to questions and requests from guests. However, there is a problem of a shortage of hotel staff to respond to questions and requests, especially during the night. To address this problem, the information processing system disclosed herein is configured so that an AI model handles basic Q&A, and hotel staff on standby in remote locations respond only when in-person assistance is required. Even when hotel staff are not present at the hotels, multiple hotels are managed remotely from a single location, reducing the workload of on-site staff and reducing the number of staff required. In other words, the information processing system disclosed herein enables remote control of hotel front desks.

[0139] In this way, the information processing system disclosed herein supports guests who have problems via information terminals 30 installed in the hotel lobby or guest rooms. The information processing system also provides more appropriate information by using personal data of guests (information on the guest's gender, age, guest room, etc.) held by the hotel management system (PMS; Property Management System) and information obtained from the Internet. In other words, by linking with various systems including the hotel management system, hospitality for guests can be improved.

[0140] Next, the hardware of each device constituting the information processing system will be described. Fig. 15 is a diagram showing an example of the hardware configuration of the server device 10.

[0141] The server device 10 can be configured by an information processing device (so-called computer), and has the configuration shown in Fig. 15. For example, the server device 10 includes a processor 311, a memory 312, an input / output interface 313, and a communication interface 314. The components such as the processor 311 are connected by an internal bus or the like, and are configured to be able to communicate with each other.

[0142] However, the configuration shown in Fig. 15 is not intended to limit the hardware configuration of the server device 10. The server device 10 may include hardware not shown, and may not include the input / output interface 313 as necessary. Furthermore, the number of processors 311 and the like included in the server device 10 is not intended to be limited to the example shown in Fig. 15, and for example, the server device 10 may include multiple processors 311.

[0143] The processor 311 is a programmable device such as a central processing unit (CPU), a micro processing unit (MPU), or a digital signal processor (DSP). Alternatively, the processor 311 may be a device such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). The processor 311 executes various programs including an operating system (OS).

[0144] The memory 312 is a random access memory (RAM), a read only memory (ROM), a hard disk drive (HDD), a solid state drive (SSD), etc. The memory 312 stores an OS program, application programs, and various data.

[0145] The input / output interface 313 is an interface for a display device and an input device (not shown). The display device is, for example, a liquid crystal display. The input device is, for example, a keyboard, a mouse, a touch panel, or the like that accepts user operations.

[0146] The communication interface 314 is a circuit, module, etc. that communicates with other devices. For example, the communication interface 314 includes a network interface card (NIC).

[0147] The functions of the server device 10 are realized by various processing modules. The processing modules are realized, for example, by the processor 311 executing a program stored in the memory 312. The program can be recorded on a computer-readable storage medium. The storage medium can be a non-transitory medium such as a semiconductor memory, a hard disk, a magnetic recording medium, or an optical recording medium. That is, the present invention can also be embodied as a computer program product. The program can be downloaded via a network or updated using a storage medium storing the program. Furthermore, the processing modules can be realized by semiconductor chips.

[0148] The guide terminal 30 and the like can also be configured by an information processing device similar to the server device 10, and the basic hardware configuration is the same as that of the server device 10, so a description thereof will be omitted.

[0149] The server device 10 is equipped with a computer, and the computer executes a program to realize the functions of the server device 10. The server device 10 also executes a control method for the server device 10 by the program.

[0150] [Modification] The configuration, operation, etc. of the information processing system described in the above embodiment are merely examples, and are not intended to limit the configuration, etc. of the system.

[0151] In the above embodiment, a case has been described in which a guest inputs an inquiry to the server device 10 via the guide terminal 30. The guest may also transmit the inquiry to the server device 10 via the terminal 40 that the guest carries. In this case, the guest is given a two-dimensional barcode containing a URL (Uniform Resource Locator) or the like for accessing the server device 10. The guest operates the terminal 40 to access the server device 10 according to the two-dimensional barcode. Upon receiving the access, the server device 10 acquires the inquiry via the terminal 40 and presents a response.

[0152] In the above embodiment, a case has been described in which multiple AI models (a classification AI model and a response AI model) are linked together to generate a response to an inquiry. The server device 10 may use a single AI model that integrates the classification AI model and the response AI model to generate a response to an inquiry or determine whether a human response is required for the inquiry.

[0153] In the above embodiment, the server device 10 has been described as transmitting a connection instruction to the guide terminal 30. The server device 10 may also transmit a connection instruction to the employee terminal 20. Furthermore, if the system includes multiple employee terminals 20, the server device 10 may also assign the guest's inquiry to the employee terminal 20 of a hotel employee who is not involved in the guest's inquiry (an employee who is available). The server device 10 may also transmit a connection instruction to the employee terminal 20.

[0154] The server device 10 may transmit a response including information (e.g., name) of the guest who made the inquiry to the information terminal 30. The information terminal 30 that receives the response may respond to the inquiry while outputting a message such as "Thank you for your inquiry, Mr. Yamada Taro." In this case, the server device 10 may execute a matching process using biometric information to acquire information about the guest even in the case of the first or third inquiry type that does not require personal data of the guest.

[0155] In the above embodiment, it has been described that inquiry items for which an AI model is used are classified into four types. However, the number of inquiry items for which an AI model is used is not limited to four. The inquiry items may be classified into any number of inquiry types according to the hotel's policies, etc. For example, the first and second inquiry types may be combined.

[0156] In the above embodiment, the case where support is provided to hotel guests has been described. However, the support is not limited to hotel guests, and support may also be provided to day-use users.

[0157] In the above embodiment, the guest management database is configured inside the server device 10, but the database may be configured on an external database server or the like. That is, some of the functions of the server device 10 may be implemented in another device. More specifically, the above-described "enquiry response control unit (enquiry response control means)" and the like may be implemented in any of the devices included in the system.

[0158] The form of data transmission between the devices (server device 10, guide terminal 30) is not particularly limited, but the data transmitted between these devices may be encrypted. Biometric information of guests and other information is transmitted between these devices, and in order to appropriately protect this information, it is desirable to transmit and receive encrypted data.

[0159] In the flow charts (flowcharts, sequence diagrams) used in the above explanation, multiple steps (processes) are described in order, but the order of execution of the steps executed in the embodiments is not limited to the order described. In the embodiments, the order of the steps shown in the drawings can be changed to the extent that the content is not affected, such as by executing each process in parallel.

[0160] The above-described embodiments have been described in detail to facilitate understanding of the present disclosure, and it is not intended that all of the above-described configurations are required. Furthermore, when multiple embodiments are described, each embodiment may be used alone or in combination. For example, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of one embodiment with another configuration.

[0161] From the above explanation, it is clear that the present invention has industrial applicability, and the present invention is suitably applicable to information processing systems for supporting hotel guests, etc.

[0162] Some or all of the above embodiments may be described as, but are not limited to, the following supplementary notes. [Supplementary Note 1] A server device comprising: an acquisition means for acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at a hotel; and a response control means for, depending on the acquired inquiry, answering the inquiry using information output by an AI (Artificial Intelligence) model, or performing control so that a staff member in charge of supporting the guest can answer the inquiry. [Supplementary Note 2] The server device according to Supplementary Note 1, wherein the response control means answers the inquiry using the information output by the AI ​​model if the confidence level of the information output by the AI ​​model is equal to or greater than a predetermined value, and performs control so that the staff member can answer the inquiry if the confidence level is less than the predetermined value. [Supplementary Note 3] The server device according to Supplementary Note 2, wherein the response control means instructs a first terminal that has received the inquiry from the guest to connect to a second terminal used by the staff member if the confidence level is less than the predetermined value. [Supplementary Note 4] The server device according to Supplementary Note 1, wherein the response control means classifies the inquiry item into one of a plurality of predetermined types and, depending on the classified type, determines whether to respond to the inquiry item using information output by the AI ​​model or whether the person in charge will respond to the inquiry item. [Supplementary Note 5] The server device according to Supplementary Note 4, wherein the response control means, if the inquiry item is of a first type that does not require personal data of a guest who has the inquiry item and does not require a predetermined level of accuracy in the response, acquires the response to the inquiry item by inputting the inquiry item into a first AI model prepared for the first type, and if the inquiry item is of a second type that requires personal data of a guest who has the inquiry item and does not require a predetermined level of accuracy in the response, acquires the response to the inquiry item by inputting the inquiry item and the personal data of the guest who has the inquiry item into a second AI model prepared for the second type.[Supplementary Note 6] The server device according to Supplementary Note 5, wherein the response control means, if the inquiry item is a third type that does not require personal data of the guest who has the inquiry item and requires a predetermined level of accuracy in the response, inputs the inquiry item into a third AI model prepared for the third type to obtain a response to the inquiry item, and, if the inquiry item is a fourth type that requires personal data of the guest who has the inquiry item and requires a predetermined level of accuracy in the response, inputs the inquiry item and the personal data of the guest who has the inquiry item into a fourth AI model prepared for the fourth type to obtain a response to the inquiry item. [Supplementary Note 7] The server device according to Supplementary Note 6, further comprising storage means for storing biometric information and personal data for each of the plurality of guests in association with each other, wherein the acquisition means acquires the biometric information of the guest who has the inquiry item along with the inquiry item, and the response control means identifies the personal data of the guest who has the inquiry item by a matching process using the acquired biometric information and the stored plurality of pieces of biometric information. [Supplementary Note 8] The server device according to Supplementary Note 7, wherein the answer control means answers the inquiry using information output by the third or fourth AI model if the confidence level output by the third or fourth AI model is equal to or greater than a predetermined value, and performs control so that the person in charge can answer the inquiry if the confidence level is smaller than the predetermined value. [Supplementary Note 9] A control method for a server device, comprising: an acquisition step of acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at a hotel, and an answer control step of answering the inquiry using information output by an AI (Artificial Intelligence) model according to the acquired inquiry, or performing control so that the person in charge of supporting the guest can answer the inquiry. [Supplementary Note 10] The control method for a server device according to Supplementary Note 9, wherein the response control step: responds to the inquiry using the information output by the AI ​​model when the confidence level of the information output by the AI ​​model is equal to or greater than a predetermined value; and, when the confidence level is less than the predetermined value, performs control so that the person in charge can respond to the inquiry.[Supplementary Note 11] The control method for a server device according to Supplementary Note 10, wherein the response control step, if the certainty factor is smaller than the predetermined value, instructs a first terminal that has accepted the inquiry of the guest having the inquiry to connect to a second terminal used by the person in charge. [Supplementary Note 12] The control method for a server device according to Supplementary Note 9, wherein the response control step classifies the inquiry into one of a plurality of predetermined types, and determines whether to respond to the inquiry using information output by the AI ​​model or whether the person in charge will respond to the inquiry depending on the classified type. [Supplementary Note 13] The control method for a server device described in Supplementary Note 12, wherein the response control step acquires a response to the inquiry item by inputting the inquiry item into a first AI model prepared for the first type, if the inquiry item is of a first type that does not require personal data of the guest who has the inquiry item and does not require a specified level of accuracy in the response, and acquires a response to the inquiry item by inputting the inquiry item and the personal data of the guest who has the inquiry item into a second AI model prepared for the second type, if the inquiry item is of a second type that requires personal data of the guest who has the inquiry item and does not require a specified level of accuracy in the response. [Supplementary Note 14] The control method for a server device described in Supplementary Note 13, wherein the response control step acquires a response to the inquiry item by inputting the inquiry item into a third AI model prepared for the third type if the inquiry item is of a third type that does not require personal data of the guest who has the inquiry item and requires a predetermined level of accuracy in the response, and acquires a response to the inquiry item by inputting the inquiry item and the personal data of the guest who has the inquiry item into a fourth AI model prepared for the fourth type if the inquiry item is of a fourth type that requires personal data of the guest who has the inquiry item and requires a predetermined level of accuracy in the response.[Supplementary Note 15] The control method for a server device according to Supplementary Note 14, further comprising a storage step of storing biometric information and personal data for each of the plurality of guests in association with each other, wherein the acquisition step acquires the biometric information of the guest who has the inquiry along with the inquiry, and the response control step identifies the personal data of the guest who has the inquiry by a matching process using the acquired biometric information and the stored plurality of pieces of biometric information. [Supplementary Note 16] The control method for a server device according to Supplementary Note 15, wherein the response control step answers the inquiry using information output by the third or fourth AI model if the certainty level output by the third or fourth AI model is equal to or greater than a predetermined value, and performs control so that the person in charge can answer the inquiry if the certainty level is less than the predetermined value. [Supplementary Note 17] A computer-readable storage medium storing a program for causing a computer mounted on a server device to execute the following: an acquisition process for acquiring an inquiry from a guest who has an inquiry among multiple guests staying at a hotel; and an answer control process for, depending on the acquired inquiry, either answering the inquiry using information output by an AI (Artificial Intelligence) model, or controlling so that a staff member in charge of supporting the guest can answer the inquiry. [Supplementary Note 18] The storage medium of Supplementary Note 17, in which the answer control process: answers the inquiry using information output by the AI ​​model if the confidence level of the information output by the AI ​​model is equal to or greater than a predetermined value; and controls so that the staff member can answer the inquiry if the confidence level is less than the predetermined value. [Supplementary Note 19] The storage medium of Supplementary Note 18, in which the answer control process: instructs a first terminal that has received the inquiry from the guest to connect to a second terminal used by the staff member if the confidence level is less than the predetermined value. [Supplementary Note 20] The storage medium according to Supplementary Note 17, wherein the response control process classifies the inquiry into one of a plurality of predetermined types, and determines whether to respond to the inquiry using information output by the AI ​​model or whether the person in charge will respond to the inquiry, depending on the classified type.[Appendix 21] The storage medium described in Appendix 20, wherein the response control process obtains an answer to the inquiry by inputting the inquiry into a first AI model prepared for the first type when the inquiry is of a first type that does not require personal data of the guest who has the inquiry and does not require a specified level of accuracy in the response, and obtains an answer to the inquiry by inputting the inquiry and the personal data of the guest who has the inquiry into a second AI model prepared for the second type when the inquiry is of a second type that requires personal data of the guest who has the inquiry and does not require a specified level of accuracy in the response. [Supplementary Note 22] The storage medium of Supplementary Note 21, wherein the response control process: if the inquiry item is a third type that does not require personal data of the guest who has the inquiry item and requires a predetermined level of accuracy in the response, inputs the inquiry item into a third AI model prepared for the third type to obtain a response to the inquiry item; and if the inquiry item is a fourth type that requires personal data of the guest who has the inquiry item and requires a predetermined level of accuracy in the response, inputs the inquiry item and the personal data of the guest who has the inquiry item into a fourth AI model prepared for the fourth type to obtain a response to the inquiry item. [Supplementary Note 23] The storage medium of Supplementary Note 22, further executes a storage process that associates biometric information and personal data for each of the multiple guests and stores them, wherein the acquisition process acquires the biometric information of the guest who has the inquiry item along with the inquiry item, and the response control process identifies the personal data of the guest who has the inquiry item by a matching process using the acquired biometric information and the stored multiple pieces of biometric information. [Appendix 24] The storage medium described in Appendix 23, wherein the answer control process: answers the inquiry using information output by the third or fourth AI model when the confidence level output by the third or fourth AI model is equal to or greater than a predetermined value; and controls so that the person in charge can answer the inquiry when the confidence level is less than the predetermined value.

[0163] The disclosures of the above-cited prior art documents are incorporated herein by reference. Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments. Those skilled in the art will understand that these embodiments are merely illustrative and that various modifications are possible without departing from the scope and spirit of the present invention. In other words, the present invention naturally includes various modifications and alterations that may be made by those skilled in the art in accordance with the entire disclosure, including the claims, and the technical concepts thereof.

[0164] REFERENCE SIGNS LIST 10 Server device 20 Employee terminal 30 Guide terminal 40 Terminal 100 Server device 101 Acquisition means 102 Response control means 201 Communication control unit 202 Hotel business control unit 203 Inquiry response control unit 204 Storage unit 301 Communication control unit 302 Inquiry control unit 303 Storage unit 311 Processor 312 Memory 313 Input / output interface 314 Communication interface

Claims

1. an acquisition means for acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at the hotel; a response control means for responding to the inquiry using information output by an AI (Artificial Intelligence) model according to the acquired inquiry, or for controlling the person in charge of supporting the guest to respond to the inquiry; A server device comprising:

2. The answer control means If the confidence level of the information output by the AI ​​model is equal to or greater than a predetermined value, the information output by the AI ​​model is used to respond to the inquiry; 2. The server device according to claim 1, wherein when the certainty factor is smaller than the predetermined value, control is performed so that the person in charge can answer the inquiry.

3. The answer control means 3. The server device according to claim 2, wherein if the certainty factor is smaller than the predetermined value, the server device instructs a first terminal that has received the inquiry of the guest having the inquiry to connect to a second terminal used by the person in charge.

4. 2. The server device according to claim 1, wherein the response control means classifies the inquiry into one of a plurality of predetermined types, and determines, depending on the classified type, whether to respond to the inquiry using information output by the AI ​​model or to have the person in charge respond to the inquiry.

5. The answer control means If the inquiry is of a first type that does not require personal data of the guest having the inquiry and does not require a predetermined accuracy in the answer, the inquiry is input into a first AI model prepared for the first type, thereby obtaining an answer to the inquiry; 5. The server device of claim 4, wherein, when the inquiry is of a second type that requires personal data of the guest who has the inquiry and does not require a predetermined level of accuracy in the answer, the inquiry and the personal data of the guest who has the inquiry are input into a second AI model prepared for the second type, thereby obtaining an answer to the inquiry.

6. The answer control means If the inquiry is of a third type that does not require personal data of the guest who has the inquiry but requires a predetermined level of accuracy in the response, the inquiry is input into a third AI model prepared for the third type, thereby obtaining a response to the inquiry; 6. The server device according to claim 5, wherein, when the inquiry is of a fourth type that requires personal data of a guest who has the inquiry and that requires a predetermined level of accuracy in the answer, the inquiry and the personal data of the guest who has the inquiry are input into a fourth AI model prepared for the fourth type, thereby obtaining an answer to the inquiry.

7. Further comprising a storage means for storing biometric information and personal data for each of the plurality of guests in association with each other; the acquisition means acquires the inquiry item together with biometric information of the guest who has the inquiry item, 7. The server device according to claim 6, wherein the response control means identifies personal data of the guest who has the inquiry by performing a matching process using the acquired biometric information and the stored plurality of pieces of biometric information.

8. The answer control means If the confidence level output by the third or fourth AI model is equal to or greater than a predetermined value, the inquiry is answered using the information output by the third or fourth AI model; 8. The server device according to claim 7, wherein when the certainty factor is smaller than the predetermined value, control is performed so that the person in charge can answer the inquiry.

9. In the server device, an acquisition step of acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at the hotel; a response control step of responding to the inquiry using information output by an AI (Artificial Intelligence) model according to the acquired inquiry, or controlling the system so that a person in charge of supporting guests can respond to the inquiry; A method for controlling a server device, comprising:

10. The computer installed in the server device an acquisition process for acquiring an inquiry from a guest who has an inquiry among a plurality of guests staying at the hotel; An answer control process that answers the inquiry using information output by an AI (Artificial Intelligence) model according to the acquired inquiry, or controls the person in charge of supporting the guest to answer the inquiry; A program to execute.