Systems, methods, and information processing devices.

Abstract

Improve AI chatbot technology that includes multiple conversational models. [Solution] System 1 comprises a communication device 10 and a server 20. The server 20 stores a first interactive model and a second interactive model. The communication device 10 displays a first screen 40 for interaction between the user and the first interactive model, and sends the question text entered by the user on the first screen 40 to the server. The server 20 determines whether the predicted time required for the first interactive model to generate an answer to the question text is long or long according to a predetermined standard. If the server 20 determines that the predicted time is long according to the predetermined standard, the server 20 performs interaction between the user and the second interactive model until the first interactive model has finished generating the answer.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , , ,

[0001] This disclosure relates to a system.

Background Art

[0002] Conventionally, a technology of an AI chatbot including a plurality of dialogue models has been known. For example, Patent Document 1 discloses a technology of an AI chatbot including a plurality of dialogue models, which selects a dialogue model according to the content of a user's question and conducts a dialogue with the user.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is room for improvement in the technology of an AI chatbot including a plurality of dialogue models.

[0005] In view of such circumstances, an object of the present disclosure is to improve the technology of an AI chatbot including a plurality of dialogue models.

Means for Solving the Problems

[0006] A system according to an embodiment of the present disclosure is a system including a communication device and a server, where the server stores a first dialogue model and a second dialogue model, and the communication device displays a first screen for conducting a dialogue between the user and the first dialogue model, sends a question sentence input by the user to the first screen to the server, and the server The system determines whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. If the predicted time is determined to be long in light of the predetermined criteria, the user and the second interactive model will perform a dialogue until the first interactive model completes generating the response.

[0007] A method according to one embodiment of this disclosure is: A method comprising a communication device and a server, The server stores a first interactive model and a second interactive model. The aforementioned communication device To display a first screen for interaction between the user and the first interactive model, The user enters the question text on the first screen and sends it to the server. The aforementioned server, The process involves determining whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. If the predicted time is determined to be long in light of the predetermined criteria, the system includes performing a dialogue between the user and the second dialogue model until the first dialogue model completes generating a response.

[0008] An information processing apparatus according to one embodiment of this disclosure is The server stores a first interactive model and a second interactive model. The aforementioned communication device is A first screen is displayed for interaction between the user and the first interactive model. The question entered by the user on the first screen is sent to the server. The aforementioned server, The system determines whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. When it is determined that the predicted time is long in light of the predetermined criterion, the conversation between the user and the second dialogue model is executed until the generation of the response by the first dialogue model is completed.

Effect of the Invention

[0009] According to one embodiment of the present disclosure, the technology of an AI chatbot including a plurality of dialogue models is improved.

Brief Description of the Drawings

[0010] [Figure 1] It is a block diagram showing a schematic configuration of a system according to an embodiment of the present disclosure. [Figure 2] It is a flowchart showing the operation of the server. [Figure 3] It is a flowchart showing the operation of the communication device. [Figure 4] It is a diagram showing an example of a dialogue screen with the first dialogue model. [Figure 5] It is a diagram showing an example in which a dialogue screen with the second dialogue model is superimposed on the dialogue screen with the first dialogue model. [Figure 6] It is a diagram showing an example in which the dialogue with the second dialogue model and the question content are displayed on the dialogue screen with the first dialogue model. [Figure 7] It is a diagram showing an example in which the dialogue with the first dialogue model and the dialogue with the second dialogue model are displayed so as to be distinguishable.

Mode for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present disclosure will be described.

[0012] (Overview of the Embodiment) Referring to FIG. 1, an overview of the system 1 according to an embodiment of the present disclosure will be described. The system 1 includes a communication device 10 and a server 20. A user can operate the communication device 10 to interact with an AI chatbot stored in the server. When the server 20 determines that it takes time to generate an answer to the user's question, during the period until the generation of the answer is completed, another AI chatbot different from the AI chatbot during answer generation is used to interact with the user. The communication device 10 and the server 20 are communicably connected to a network 30 including, for example, the Internet and a mobile communication network.

[0013] The communication device 10 is, for example, a computer, a smartphone, or a navigation device mounted on a vehicle, but is not limited thereto and may be any communication device. The number of communication devices 10 included in the system 1 may be arbitrarily determined.

[0014] The server 20 is one or a plurality of computers capable of communicating with each other and is communicable with the communication device 10 via the network 30.

[0015] First, an overview of this embodiment will be described, and details will be described later. The system 1 includes a communication device 10 and a server 20. The server 20 stores a first dialogue model and a second dialogue model. Further, the communication device 10 displays a first screen 40 for the user to interact with the first dialogue model, and transmits the question text input by the user to the first screen 40 to the server. The server 20 determines whether the prediction time required for the first dialogue model to generate an answer to the question content related to the question text is long in light of a predetermined criterion. Then, when it is determined by the server 20 that the prediction time is long in light of the predetermined criterion, the server 20 executes an interaction between the user and the second dialogue model until the generation of the answer by the first dialogue model is completed.

[0016] Thus, according to this embodiment, if the server 20 determines that the estimated time required to generate an answer to a user's question is long according to a predetermined standard, the server 20 will perform a dialogue between the user and the second dialogue model until the first dialogue model completes generating the answer. This shortens the user's perceived time spent waiting for the first dialogue model to generate an answer. In addition, by engaging in a dialogue with the second dialogue model, the user can recognize that system 1 is functioning correctly. Therefore, the technology of an AI chatbot including multiple dialogue models is improved in that it can shorten the user's perceived time and allow the user to recognize that system 1 is functioning correctly.

[0017] Next, we will describe each component of System 1 in detail.

[0018] (Configuration of communication device 10) As shown in Figure 1, the communication device 10 comprises a communication unit 11, an output unit 12, an input unit 13, a control unit 14, and a storage unit 15.

[0019] The communication unit 11 includes one or more communication interfaces connected to the network 30. These communication interfaces may, for example, support mobile communication standards such as 4G (4th Generation) or 5G (5th Generation), but are not limited to these. In this embodiment, the communication device 10 communicates with the server 20 via the communication unit 11 and the network 30.

[0020] The output unit 12 includes one or more output devices that output information. These output devices are, for example, a display or a speaker, but are not limited to these. Alternatively, the output unit 12 may include an interface for connecting an external output device.

[0021] The input unit 13 includes one or more input devices for detecting user input. These input devices are, but are not limited to, physical keys, capacitive keys, pointing devices such as mice, touchscreens integrated with the display of the output unit 12, or microphones that accept voice input. Alternatively, the input unit 13 may include an input interface for detecting user input via an external input device.

[0022] The control unit 14 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific process, but is not limited to these. The programmable circuit is an FPGA (Field-Programmable Gate Array), but is not limited to this. The dedicated circuit is an ASIC (Application Specific Integrated Circuit), but is not limited to this. The control unit 14 controls the operation of the entire communication device 10.

[0023] The storage unit 15 includes one or more memories. The memories are, for example, semiconductor memories, magnetic memories, or optical memories, but are not limited to these. Each memory included in the storage unit 15 may function as, for example, a main memory, an auxiliary memory, or a cache memory. The storage unit 15 stores any information used for the operation of the communication device 10. For example, the storage unit 15 may store system programs, application programs, and embedded software. The information stored in the storage unit 15 may be updateable with information obtained from the network 30 via, for example, the communication unit 11.

[0024] (Server 20 configuration) As shown in Figure 1, the server 20 includes a communication unit 21, an output unit 22, an input unit 23, a control unit 24, and a storage unit 25.

[0025] The communication unit 21 includes one or more communication interfaces connected to the network 30. These communication interfaces may, for example, support mobile communication standards such as 4G (4th Generation) or 5G (5th Generation), but are not limited to these. In this embodiment, the server 20 communicates with the communication device 10 via the communication unit 21 and the network 30.

[0026] The output unit 22 includes one or more output devices for outputting information. These output devices are, for example, a display or a speaker, but are not limited to these. Alternatively, the output unit 22 may include an interface for connecting an external output device.

[0027] The input unit 23 includes one or more input devices for detecting user input. These input devices are, but are not limited to, physical keys, capacitive keys, pointing devices such as mice, touchscreens integrated with the display of the output unit 22, or microphones that accept voice input. Alternatively, the input unit 23 may include an input interface for detecting user input via an external input device.

[0028] The control unit 24 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processors are, for example, general-purpose processors such as CPUs (Central Processing Units) or GPUs (Graphics Processing Units), or dedicated processors specialized for specific processing, but are not limited to these. The programmable circuits are, for example, FPGAs (Field-Programmable Gate Arrays), but are not limited to these. The dedicated circuits are, for example, ASICs (Application Specific Integrated Circuits), but are not limited to these. The control unit 24 controls the operation of the entire server 20.

[0029] The storage unit 25 includes one or more memories. The memories are, for example, semiconductor memory, magnetic memory, or optical memory, but are not limited to these. Each memory included in the storage unit 25 may function as, for example, main memory, auxiliary memory, or cache memory. The storage unit 25 stores any information used for the operation of the server 20. For example, the storage unit 25 may store system programs, application programs, and embedded software. The storage unit 25 may also store an AI chatbot including a first dialogue model and a second dialogue model. The first dialogue model is a model that generates and outputs answers to the user's questions. The second dialogue model is a model that engages in dialogue with the user until the first dialogue model has finished generating the answers. The second dialogue model is a model that requires less time to generate dialogue compared to the first dialogue model.

[0030] (Operation flow of Server 20) Referring to Figure 2, the operation of the server 20 according to this embodiment will be described.

[0031] S100: The control unit 24 starts interacting with the first interactive model stored in the memory unit 25.

[0032] Interaction with the first interactive model may begin when the server 20 receives information that the user has operated the communication device 10 and initiated interaction with the first interactive model, but is not limited to this, and any start condition may be defined.

[0033] S101: The input unit 23 receives the question text entered by the user into the input unit 13 via the network 30.

[0034] The question is a sentence entered by the user into the input unit 13. Any method can be used for input.

[0035] S102: The control unit 24 determines whether the predicted time required for the first interactive model to generate an answer to the question content related to the question statement is long or long according to a predetermined standard.

[0036] The question content is extracted from the question text entered by the user. Any method can be used to extract the information, such as query transformation including natural language processing. The predicted time may be determined to be short according to a predetermined criterion if, for example, the question content related to the question text entered by the user is included in the history information described later. Conversely, if the question content related to the question text entered by the user is not included in the history information, the predicted time may be determined to be long according to a predetermined criterion. If the predicted time is determined to be long according to the predetermined criterion, S103 is executed; if it is determined to be short, S104 is executed.

[0037] S103: The control unit 24 performs dialogue between the user and the second interactive model until the first interactive model has finished generating a response.

[0038] If the control unit 24 determines that the predicted time is long according to a predetermined criterion, it will communicate with the second interactive model via the network 30 using the communication device 10 operated by the user until the first interactive model completes generating the answer. This shortens the user's perceived time spent waiting for the first interactive model to generate the answer. In addition, by communicating with the second interactive model, the user can recognize that system 1 is operating normally.

[0039] S104: The control unit 24 transmits the response (sentence) generated by the first interactive model to the communication device 10 via the network 30.

[0040] The control unit 24 may, for example, send the response to the communication device 10. Alternatively, the control unit 24 may send information related to the response, and the communication device 10 may create the response.

[0041] S105: The control unit 24 stores the question and the answer to the question in the storage unit 25.

[0042] The memory unit 25 stores history information including one or more questions previously entered and one or more answers to those questions. The control unit 24, if the question content related to the question entered by the user is included in the history information of the memory unit 25, determines that the prediction time is short and may use the first interactive model to extract the answer content corresponding to the question content from the history information and generate an answer to the question content based on the extracted answer content. This reduces the user's waiting time until the answer generation by the first interactive model is completed.

[0043] (Operation flow of communication device 10) The operation of the communication device 10 according to this embodiment will be described with reference to Figure 3.

[0044] S200: The control unit 14 displays a first screen 40 on the output unit 12 for interaction between the user and the first interactive model.

[0045] The first screen 40 is a screen for the user and the first interactive model to interact. Figure 4 shows an example of the first screen 40. The first screen 40 includes a user question 41, the first interactive model's answer 42, and another user question 43. The user question 41 is, "The Proactive Driving Assist function is turned OFF, what kind of function is it?" The first interactive model's answer 42 is an explanation of the Proactive Driving Assist function and includes a video icon 44. Clicking the video icon 44 plays the video. The user question 43 is, "Only the same song is playing. I want to play other songs as well." The first screen 40 includes an input section for the user to enter a question and a display section to provide an answer to the user's question, but is not limited to this and can display any information.

[0046] S201: The control unit 14 sends the question entered by the user on the first screen 40 to the server 20.

[0047] The user enters a question into the input unit 13. The entered question is sent to the server 20 via the network 30. Any method can be used to input the question, such as text input or voice input.

[0048] S202: The control unit 14 determines whether or not interaction with the second interactive model has started.

[0049] The control unit 14 determines whether the server 20 has decided to initiate a dialogue between the user and the second interactive model. For example, the control unit 14 may receive information from the server 20 via the network 30 that a dialogue with the second interactive model has been initiated, but is not limited to this and can be determined by any method. If the server 20 has initiated a dialogue with the second interactive model, S203 is executed; if the dialogue with the second interactive model has not been initiated, S204 is executed.

[0050] S203: The control unit 14 overlays and displays a second screen 50 on the output unit 12, which allows the user to interact with the second interactive model.

[0051] The second screen 50 is a screen for the user and the second interactive model to interact. Figure 5 shows an example in which the second screen 50 is superimposed on the first screen 40. The second screen 50 includes an input section for the user to enter a question and a display section for providing an answer to the user's question, but is not limited to this and can display any information. Furthermore, the second screen 50 is not limited to superimposed display and can employ any display method. This allows the user to recognize that System 1 is functioning correctly. In the example in Figure 5, the second screen 50 shows a dialogue unrelated to the question the user asked the first interactive model, "Do you have any hobbies you like?", but is not limited to this and can display any dialogue.

[0052] S204: The control unit 14 receives the response (sentence) generated by the first interactive model from the server 20 via the network 30.

[0053] The response may be received, for example, as text from server 20. Alternatively, information related to the response may be received and text may be created using communication device 10.

[0054] S205: The control unit 14 displays the answer on the output unit 12.

[0055] For example, when the control unit 14 receives a response from the server 20, it displays the received response on the output unit 12. Alternatively, when the control unit 14 receives a response from the server 20, it may create a response based on the response and display it on the output unit 12. Any method can be used for output, such as text display or audio output.

[0056] As described above, System 1 comprises a communication device 10 and a server 20. The server 20 stores a first interactive model and a second interactive model. The communication device 10 displays a first screen 40 for interaction between the user and the first interactive model, and sends the question text entered by the user on the first screen 40 to the server. The server 20 determines whether the predicted time required for the first interactive model to generate an answer to the question text is long or long according to a predetermined standard. If the server 20 determines that the predicted time is long according to the predetermined standard, the server 20 performs interaction between the user and the second interactive model until the first interactive model has finished generating the answer.

[0057] In this configuration, if the server 20 determines that the estimated time required to generate an answer to a user's question is long according to a predetermined standard, the server 20 will perform a dialogue between the user and the second dialogue model until the first dialogue model has finished generating the answer. This shortens the user's perceived time spent waiting for the first dialogue model to generate the answer. In addition, the user can recognize that system 1 is functioning correctly by engaging in a dialogue with the second dialogue model. Therefore, the technology of an AI chatbot including multiple dialogue models is improved in that it can shorten the user's perceived time and allow the user to recognize that system 1 is functioning correctly.

[0058] While this disclosure has been described based on the drawings and embodiments, it should be noted that those skilled in the art may make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions, etc., included in each component or step can be rearranged in a logically consistent manner, and multiple components or steps can be combined into one or divided into two.

[0059] For example, in the embodiment described above, it is also possible to distribute the configuration and operation of the server 20 among multiple computers that can communicate with each other. For example, it is also possible to provide some or all of the components of the server 20 in the communication device 10.

[0060] For example, in the embodiment described above, it is also possible to distribute the configuration and operation of the server 20 to multiple computers that can communicate with each other. Alternatively, for example, it is also possible to provide some or all of the components of the server 20 in the communication device 10.

[0061] In the embodiment described above, the storage unit 25 may store a database containing information about vehicles. Alternatively, the first interactive model may be a RAG (Retrieval Augmented Generation) model that references the database containing information about vehicles when generating answers to user questions. When the control unit 24 determines whether the predicted time is long or long according to a predetermined criterion, it may determine this based on whether the first interactive model needs to reference the database containing information about vehicles stored in the storage unit 25 in order to generate an answer. Specifically, if the server 20 determines that the first interactive model does not need to reference the database, the control unit 24 determines that the predicted time is short. On the other hand, if the server 20 determines that the first interactive model needs to reference the database, the control unit 24 determines that the predicted time is long. This allows the user to interact with the second interactive model while the first interactive model using RAG is generating an answer, shortening the user's perceived time and allowing them to recognize that the system 1 is operating normally.

[0062] Furthermore, in the embodiment described above, the server 20 may transmit the question content related to the question statement to the communication device 10. The communication device 10 may also display the question content on the output unit 12 until it receives an answer to the question content from the server 20. Figure 6 is a diagram showing an example of a screen including a second screen 50 and a question list 60. The question list 60 includes user question 61 and user question 62. User question 61 is the question "What is Proactive Driving Assist?". User question 62 is the question "Only the same song is playing." Here, user questions 41 and 43 in Figure 4 correspond to user questions 61 and 62 in Figure 6, respectively. Also, user question 61 has been answered, and when user question 61 is selected, the answer 42 of the first interactive model in Figure 4 is displayed. On the second screen 50, a dialogue between the user and the second interactive model is taking place. This allows the user to immediately find the question statement. It also allows the user to recognize that system 1 is operating normally. In the example shown in Figure 6, the user's input question, "Only the same song is playing," and the question content of question list 60, "Only the same song is playing," which server 20 is currently generating an answer for, match. However, they do not necessarily have to match. For example, server 20 may perform query transformation including natural language processing and send only the information extracted from the question to communication device 10, and communication device 10 may display only the information extracted from the question on output unit 12. Alternatively, communication device 10 may display the question generated by server 20 based on the information extracted from the question on output unit 12. In this case, the user can confirm whether an answer to the question they intended has been generated, and can modify the question as needed. This allows the user to shorten the time it takes to obtain an answer to the question they intended.

[0063] Furthermore, in the embodiment described above, Figure 7 is an example of a screen showing the dialogue with the first interactive model and the dialogue with the second interactive model on the first screen 40 in a manner that allows the user to distinguish between them. In Figure 7, the dialogue with the second interactive model is displayed in a cloud-shaped message box, the dialogue with the first interactive model is displayed in a rectangular message box with comments appearing from the left, and the user's question is displayed in a rectangular message box with comments appearing from the right. Methods for displaying them in a distinguishable manner include, but are not limited to, changing the shape or color of the message boxes, changing the size, font, or color of the text, or changing the ending of sentences. Any method can be adopted. This allows the user to immediately understand whether they are interacting with the first interactive model or the second interactive model. In addition, the user can recognize that the operation of System 1 is normal.

[0064] Furthermore, in the embodiment described above, the server 20 may send a message to the communication device 10 indicating that the first interactive model's response will soon be completed or has been completed when the first interactive model finishes generating a response while the user is interacting with the second interactive model. The communication device 10 may also display the message received from the server 20 on the output unit 12. For example, in Figure 7, the message "It looks like the response is almost ready. I look forward to talking to you again!" is displayed using the message box of the second interactive model. The message may be displayed using the message box of the second interactive model, or any other method such as displaying a predefined phrase can be used. In addition, any method can be used to indicate that the first interactive model's response will soon be completed or has been completed, such as displaying a message, outputting sound, or vibrating. This allows, for example, a user who is driving a vehicle and cannot concentrate on the response to move to a safe location to check the response once it has been generated. Therefore, the user can spend the waiting time until the response is generated in a meaningful way.

[0065] Furthermore, in the embodiments described above, the server 20 may share the context of the interaction between the user and the first interactive model with the second interactive model. The method of sharing the context is not limited to this; for example, the control unit 24 may input information extracted from the user's question to the second interactive model, but any method can be employed. By sharing the context of the first interactive model, the second interactive model can provide topics of interest to the user. It can also provide information that is beneficial to the user. This makes it possible to shorten the user's perceived time. Additionally, because the user can engage in conversation about topics of interest, user satisfaction with System 1 can be improved.

[0066] Furthermore, it is also possible to use a general-purpose computer as the server 20 according to the above-described embodiment. Specifically, a program describing the processing content that realizes each function of the server 20 according to the above-described embodiment is stored in the memory of the general-purpose computer, and the processor reads and executes the program. Therefore, this disclosure can also be realized as a program that can be executed by a processor, or as a non-temporary computer-readable medium that stores said program.

[0067] Some embodiments of the present disclosure are described below. However, it should be noted that the embodiments of the present disclosure are not limited to these. [Note 1] A system comprising a communication device and a server, The server stores a first interactive model and a second interactive model. The aforementioned communication device is A first screen is displayed for interaction between the user and the first interactive model. The question entered by the user on the first screen is sent to the server. The aforementioned server, The system determines whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. A system that, if the predicted time is determined to be long in light of the predetermined criteria, performs a dialogue between the user and the second dialogue model until the first dialogue model completes generating a response. [Note 2] The system described in Appendix 1, The aforementioned server, The system stores historical information including one or more questions previously entered and one or more answers to those questions. If the question content related to the question sentence entered by the user is included in the history information, it is determined that the prediction time is short, and the first interactive model is used to extract the answer content corresponding to the question content from the history information, and an answer to the question content is generated based on the extracted answer content. A system that determines that the predicted time is long if the question content related to the question sentence entered by the user is not included in the history information, and generates an answer to the question content using the first interactive model. [Note 3] The system described in Appendix 1 or 2 The aforementioned server, It stores a database containing information about the vehicle, The system determines whether the first interactive model needs to refer to the database in order to generate an answer to the question content related to the question sentence entered by the user. If the first interactive model determines that it does not need to refer to the database, it determines that the prediction time is short, and uses the first interactive model to generate an answer corresponding to the question. A system that determines that the first interactive model needs to refer to the database, determines that the prediction time is long, and uses the first interactive model to refer to the database and generate an answer corresponding to the question. [Note 4] A system described in any one of the appendices 1 to 3, The communication device is a system that, when an interaction between the user and the second interactive model is performed, superimposes a second screen for the interaction with the second interactive model onto the first screen. [Note 5] A system described in any one of the appendices 1 to 4, The server transmits the question content related to the question sentence entered by the user to the communication device. The communication device is a system that displays the question content until it obtains an answer to the question content from the server. [Note 6] A system described in any one of the appendices 1 to 3 or 5, The communication device is a system that, when an interaction between the user and the second interactive model is performed, displays on the first screen the interaction with the first interactive model and the interaction with the second interactive model in a manner that allows the user to distinguish between them. [Note 7] A system described in any one of the appendices 1 to 6, While the server is performing an interaction between the user and the second interactive model, when the generation of a response by the first interactive model is complete, the server sends a message to the communication device indicating that the response by the first interactive model will soon be completed or has been completed. The communication device is a system that displays the received message. [Note 8] A method comprising a communication device and a server, The server stores a first interactive model and a second interactive model. The aforementioned communication device To display a first screen for interaction between the user and the first interactive model, The user enters the question text on the first screen and sends it to the server. The aforementioned server, The process involves determining whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. A method comprising: if the predicted time is determined to be long in light of the predetermined criteria, performing a dialogue between the user and the second dialogue model until the first dialogue model completes generating a response. [Note 9] The method described in Appendix 8, The aforementioned server, The system further includes storing historical information that includes one or more questions previously entered and one or more answers to those questions, If the question content related to the question sentence entered by the user is included in the history information, it is determined that the prediction time is short, and the first interactive model is used to extract the answer content corresponding to the question content from the history information, and an answer to the question content is generated based on the extracted answer content. A method comprising determining that the predicted time is long if the content of the question related to the question sentence entered by the user is not included in the history information, and generating an answer to the content of the question using the first interactive model. [Note 10] The method described in Appendix 8 or 9 The aforementioned server, To store a database containing information about the vehicle, The first interactive model further includes determining whether it needs to refer to the database in order to generate an answer to the question content relating to the question sentence entered by the user, If the first interactive model determines that it does not need to refer to the database, it determines that the prediction time is short, and uses the first interactive model to generate an answer corresponding to the question. A method comprising determining that the prediction time is long when the first interactive model determines that it needs to refer to the database, and using the first interactive model to refer to the database and generate an answer corresponding to the question content. [Note 11] The method described in any one of the appendices 8 to 10, A method further comprising the communication device superimposing a second screen for interacting with the second interactive model onto the first screen when an interaction between the user and the second interactive model is performed. [Note 12] The method described in any one of the appendices 8 to 11, The server transmits the question content related to the question sentence entered by the user to the communication device. A method further comprising the communication device displaying the content of the question until it obtains an answer to the content of the question from the server. [Note 13] The method described in any one of the appendices 8 to 10 or 12, A method for the communication device to display, on the first screen, the dialogue with the first interactive model and the dialogue with the second interactive model in a manner that allows the user to distinguish between them when an dialogue between the user and the second interactive model is performed. [Note 14] The method described in any one of the appendices 8 to 13, The server, while performing dialogue between the user and the second interactive model, sends a message to the communication device indicating that the first interactive model will soon complete or has completed generating a response when the first interactive model completes generating a response. A method further comprising the communication device displaying the received message. [Note 15] An information processing device comprising a communication device and a server, The server stores a first interactive model and a second interactive model. The aforementioned communication device is A first screen is displayed for interaction between the user and the first interactive model. The question entered by the user on the first screen is sent to the server. The aforementioned server, The system determines whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. An information processing device that, when it is determined that the predicted time is long in light of the predetermined criteria, performs a dialogue between the user and the second interactive model until the first interactive model completes generating a response. [Note 16] The information processing device described in Appendix 15, The aforementioned server, The system stores historical information including one or more questions previously entered and one or more answers to those questions. If the question content related to the question sentence entered by the user is included in the history information, it is determined that the prediction time is short, and the first interactive model is used to extract the answer content corresponding to the question content from the history information, and an answer to the question content is generated based on the extracted answer content. An information processing device that determines that the predicted time is long if the content of the question related to the question sentence entered by the user is not included in the history information, and generates an answer to the content of the question using the first interactive model. [Note 17] Information processing device as described in Appendix 15 or 16 The aforementioned server, It stores a database containing information about the vehicle, The system determines whether the first interactive model needs to refer to the database in order to generate an answer to the question content related to the question sentence entered by the user. If the first interactive model determines that it does not need to refer to the database, it determines that the prediction time is short, and uses the first interactive model to generate an answer corresponding to the question. An information processing device that determines that the first interactive model needs to refer to the database, determines that the prediction time is long, and uses the first interactive model to refer to the database and generate an answer corresponding to the question. [Note 18] An information processing device described in any one of the appendices 15 to 17, The communication device is an information processing device that, when an interaction between the user and the second interactive model is performed, superimposes a second screen for interacting with the second interactive model onto the first screen. [Note 19] An information processing device described in any one of the appendices 15 to 17, The server transmits the question content related to the question sentence entered by the user to the communication device. The communication device displays the question content until it obtains an answer to the question content from the server. When an interaction between the user and the second interactive model is performed, the information processing device displays the interaction with the first interactive model and the interaction with the second interactive model on the first screen in a manner that allows the user to distinguish between them. [Note 20] An information processing device described in any one of the appendices 15 to 19, While the server is performing an interaction between the user and the second interactive model, when the generation of a response by the first interactive model is complete, the server sends a message to the communication device indicating that the response by the first interactive model will soon be completed or has been completed. The communication device is an information processing device that displays the received message. [Explanation of Symbols]

[0068] 1 System, 10 Communication device, 11 Communication unit, 12 Output unit, 13 Input unit, 14 Control unit, 15 Storage unit, 20 Server, 21 Communication unit, 22 Output unit, 23 Input unit, 24 Control unit, 25 Storage unit, 30 Network, 40 First screen, 41 User question, 42 First interactive model's answer, 43 User question, 44 Video icon, 50 Second screen, 60 Question list, 61 User question, 62 User question

Claims

1. A system comprising a communication device and a server, The server stores a first interactive model and a second interactive model. The aforementioned communication device is A first screen is displayed for interaction between the user and the first interactive model. The question entered by the user on the first screen is sent to the server. The aforementioned server, The system determines whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. A system that, if the predicted time is determined to be long in light of the predetermined criteria, performs a dialogue between the user and the second interactive model until the first interactive model completes generating a response.

2. The system according to claim 1, The aforementioned server, The system stores historical information including one or more questions previously entered and one or more answers to those questions. If the question content related to the question sentence entered by the user is included in the history information, it is determined that the prediction time is short, and the first interactive model is used to extract the answer content corresponding to the question content from the history information, and an answer to the question content is generated based on the extracted answer content. A system that determines that the predicted time is long if the question content related to the question sentence entered by the user is not included in the history information, and generates an answer to the question content using the first interactive model.

3. The system according to claim 1 The aforementioned server, It stores a database containing information about the vehicle, The system determines whether the first interactive model needs to refer to the database in order to generate an answer to the question content related to the question sentence entered by the user. If the first interactive model determines that it does not need to refer to the database, it determines that the prediction time is short, and uses the first interactive model to generate an answer corresponding to the question. A system that, if the first interactive model determines that it needs to refer to the database, determines that the prediction time is long, and uses the first interactive model to refer to the database and generate an answer corresponding to the question.

4. The system according to claim 1, The communication device is a system that, when an interaction between the user and the second interactive model is performed, superimposes a second screen for the interaction with the second interactive model onto the first screen.

5. The system according to claim 1, The server transmits the question content related to the question sentence entered by the user to the communication device. The communication device is a system that displays the question content until it obtains an answer to the question content from the server.

6. The system according to claim 1, The communication device is a system that, when an interaction between the user and the second interactive model is performed, displays on the first screen the interaction with the first interactive model and the interaction with the second interactive model in a manner that allows the user to distinguish between them.

7. A system according to any one of claims 1 to 6, While the server is performing an interaction between the user and the second interactive model, when the generation of a response by the first interactive model is complete, the server sends a message to the communication device indicating that the response by the first interactive model will soon be completed or has been completed. The communication device is a system that displays the received message.

8. A method comprising a communication device and a server, The server stores a first interactive model and a second interactive model. The aforementioned communication device To display a first screen for interaction between the user and the first interactive model, The user enters the question text on the first screen and sends it to the server. The aforementioned server, The process involves determining whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. A method comprising: if the predicted time is determined to be long in light of the predetermined criteria, performing a dialogue between the user and the second dialogue model until the first dialogue model completes generating a response.

9. The method according to claim 8, The aforementioned server, The system further includes storing historical information that includes one or more questions previously entered and one or more answers to those questions, If the question content related to the question sentence entered by the user is included in the history information, it is determined that the prediction time is short, and the first interactive model is used to extract the answer content corresponding to the question content from the history information, and an answer to the question content is generated based on the extracted answer content. A method comprising determining that the predicted time is long if the content of the question related to the question sentence entered by the user is not included in the history information, and generating an answer to the content of the question using the first interactive model.

10. The method according to claim 8, The aforementioned server, To store a database containing information about the vehicle, The first interactive model further includes determining whether it needs to refer to the database in order to generate an answer to the question content relating to the question sentence entered by the user, If the first interactive model determines that it does not need to refer to the database, it determines that the prediction time is short, and uses the first interactive model to generate an answer corresponding to the question. A method comprising determining that the prediction time is long when the first interactive model determines that it needs to refer to the database, and using the first interactive model to refer to the database and generate an answer corresponding to the question content.

11. The method according to claim 8, A method further comprising the communication device superimposing a second screen for performing dialogue with the second interactive model onto the first screen when dialogue between the user and the second interactive model is performed.

12. The method according to claim 8, The server transmits the question content related to the question sentence entered by the user to the communication device. A method further comprising the communication device displaying the content of the question until it obtains an answer to the content of the question from the server.

13. The method according to claim 8, A method for the communication device to display, on the first screen, the dialogue with the first interactive model and the dialogue with the second interactive model in a manner that allows the user to distinguish between them when an dialogue between the user and the second interactive model is performed.

14. A method according to any one of claims 8 to 13, The server, while performing dialogue between the user and the second interactive model, sends a message to the communication device indicating that the first interactive model will soon complete or has completed generating a response when the first interactive model completes generating a response. A method further comprising the communication device displaying the received message.

15. An information processing device comprising a communication device and a server, The server stores a first interactive model and a second interactive model. The aforementioned communication device is A first screen is displayed for interaction between the user and the first interactive model. The question entered by the user on the first screen is sent to the server. The aforementioned server, The system determines whether the predicted time required for the first interactive model to generate an answer to the question related to the aforementioned question is long or long according to a predetermined standard. An information processing device that, when it is determined that the predicted time is long in light of the predetermined criteria, performs a dialogue between the user and the second interactive model until the first interactive model completes generating a response.

16. An information processing device according to claim 15, The aforementioned server, The system stores historical information including one or more questions previously entered and one or more answers to those questions. If the question content related to the question sentence entered by the user is included in the history information, it is determined that the prediction time is short, and the first interactive model is used to extract the answer content corresponding to the question content from the history information, and an answer to the question content is generated based on the extracted answer content. An information processing device that determines that the predicted time is long if the content of the question related to the question sentence entered by the user is not included in the history information, and generates an answer to the content of the question using the first interactive model.

17. The information processing apparatus according to claim 15 The aforementioned server, It stores a database containing information about the vehicle, The system determines whether the first interactive model needs to refer to the database in order to generate an answer to the question content related to the question sentence entered by the user. If the first interactive model determines that it does not need to refer to the database, it determines that the prediction time is short, and uses the first interactive model to generate an answer corresponding to the question. An information processing device that determines that the first interactive model needs to refer to the database, determines that the prediction time is long, and uses the first interactive model to refer to the database and generate an answer corresponding to the question.

18. An information processing device according to claim 15, The communication device is an information processing device that, when an interaction between the user and the second interactive model is performed, superimposes a second screen for the interaction with the second interactive model onto the first screen.

19. An information processing device according to claim 15, The server transmits the question content related to the question sentence entered by the user to the communication device. The communication device displays the question content until it obtains an answer to the question content from the server. When an interaction between the user and the second interactive model is performed, the information processing device displays the interaction with the first interactive model and the interaction with the second interactive model on the first screen in a manner that allows the user to distinguish between them.

20. An information processing apparatus according to any one of claims 15 to 19, While the server is performing an interaction between the user and the second interactive model, when the generation of a response by the first interactive model is complete, the server sends a message to the communication device indicating that the response by the first interactive model will soon be completed or has been completed. The communication device is an information processing device that displays the received message.

Images