Information processing system, information processing method, and computer program

Abstract

A technology is provided that can improve the convenience of interactions between a user and multiple artificial intelligences. [Solution] A generated sentence is obtained from each of the multiple artificial intelligences. The generated sentence obtained from each of the multiple artificial intelligences is displayed on a display device. An input sentence from a user is obtained through an input device and transmitted to at least one of the multiple artificial intelligences. The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence. When a first instruction is input from a user through the input device, the input sentence is transmitted to one of the multiple artificial intelligences that is designated by the user. When a second instruction is input from a user through the input device, the input sentence is transmitted to the multiple artificial intelligences.

Description

[Technical field]

[0001] The present disclosure relates to an information processing system and an information processing method. [Background technology]

[0002] Conventionally, a dialogue system that realizes a dialogue with a user is known (see, for example, Patent Document 1). The dialogue is carried out, for example, through text or voice. As a conventional system, a system using artificial intelligence is also known. The artificial intelligence is based on, for example, a large-scale language model. ChatGPT (registered trademark) is widely known as an artificial intelligence. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-8913 A Summary of the Invention [Problem to be solved by the invention]

[0004] In a conventional technique for realizing a dialogue using artificial intelligence, an information processing system that mediates between a user and the artificial intelligence transmits an input sentence by the user to the artificial intelligence. The artificial intelligence generates a response sentence based on the input sentence. The information processing system acquires the response sentence generated by the artificial intelligence and displays the response sentence to the user through a user interface.

[0005] The conventional system is a simple system that realizes one-to-one dialogue between a user and an artificial intelligence. Therefore, according to one aspect of the present disclosure, it is desirable to provide a highly convenient technology for interaction between a user and multiple artificial intelligences. [Means for solving the problem]

[0006] According to one aspect of the present disclosure, there is provided an information processing system including a generated sentence acquisition unit, a display control unit, and a transmission unit. The generated sentence acquisition unit is configured to acquire generated sentences from each of a plurality of artificial intelligences.

[0007] The display control unit is configured to cause the display device to display the generated sentences acquired from each of the plurality of artificial intelligences. The transmission unit is configured to acquire an input sentence from a user through the input device and transmit the input sentence to at least one of the plurality of artificial intelligences.

[0008] The generated sentence includes a response sentence to the input sentence, and is generated by a corresponding artificial intelligence. When a first instruction is input from a user through the input device, the transmission unit transmits the input sentence to one of the plurality of artificial intelligences designated by the user. When a second instruction is input from the user through the input device, the transmission unit transmits the input sentence to the plurality of artificial intelligences.

[0009] According to the information processing system configured in this manner, a user can send a common input sentence to multiple artificial intelligences. According to one aspect of the present disclosure, it is possible to provide an information processing system that is highly convenient for a user to use multiple artificial intelligences.

[0010] According to an aspect of the present disclosure, when a third instruction is input from the user through the input device, the transmission unit may be configured to transmit the input sentence and the generated sentence of the dialogue between the user and a first artificial intelligence among the plurality of artificial intelligences to a second artificial intelligence among the plurality of artificial intelligences, the second artificial intelligence being different from the first artificial intelligence. The generated sentence acquisition unit may be configured to acquire a response sentence to the dialogue content as the generated sentence from the second artificial intelligence.

[0011] According to the information processing system configured in this way, for example, a user can obtain a response to the content of a dialogue with an artificial intelligence from another artificial intelligence. For example, the user can obtain another idea that incorporates the idea of ​​a first artificial intelligence from a second artificial intelligence, and thus it is possible to make effective use of multiple artificial intelligences.

[0012] According to one aspect of the present disclosure, each of the first artificial intelligence and the second artificial intelligence may be an artificial intelligence designated by a user among a plurality of artificial intelligences. That is, each of the first artificial intelligence and the second artificial intelligence may be designated by a user. In this case, the user can meaningfully utilize the function realized by the third instruction by designating the artificial intelligence.

[0013] According to an aspect of the present disclosure, the transmission unit may be configured to selectively transmit a part of the dialogue between the user and the first AI to the second AI when the third instruction is input. By providing a part of the dialogue content, but not the whole of it, to the second AI, it is possible to obtain a reaction from the second AI that focuses on the part of the dialogue content.

[0014] According to one aspect of the present disclosure, when a fourth instruction is input by a user through an input device, the transmission unit may be configured to transmit a generated sentence obtained from a first artificial intelligence among the multiple artificial intelligences to a second artificial intelligence among the multiple artificial intelligences that is different from the first artificial intelligence, and to transmit the generated sentence obtained from the second artificial intelligence to the first artificial intelligence, thereby allowing the first artificial intelligence and the second artificial intelligence to interact with each other.

[0015] According to the information processing system configured in this way, the user can see the results of the discussion between the artificial intelligences on the theme or topic of interest. The results of such discussion can be useful for the user's deeper thinking on the theme or topic of interest, for example.

[0016] According to one aspect of the present disclosure, each of the first artificial intelligence and the second artificial intelligence may be an artificial intelligence designated by a user among a plurality of artificial intelligences. That is, each of the first artificial intelligence and the second artificial intelligence may be designated by a user. In this case, the user can meaningfully utilize the function realized by the fourth instruction by designating the artificial intelligence.

[0017] According to one aspect of the present disclosure, when a fifth instruction is input by a user through an input device, the transmission unit may be configured to transmit the generated sentence obtained from a first artificial intelligence among the multiple artificial intelligences to a second artificial intelligence among the multiple artificial intelligences that is different from the first artificial intelligence, and to transmit the generated sentence obtained from the second artificial intelligence to a third artificial intelligence among the multiple artificial intelligences that is different from the first artificial intelligence and the second artificial intelligence.

[0018] According to the information processing system configured in this manner, the user can obtain from a third artificial intelligence the results of the accumulated ideas of multiple artificial intelligences. According to an aspect of the present disclosure, the transmission unit may transmit the dialogue content between the user and each of the plurality of artificial intelligences to a specific artificial intelligence different from the plurality of artificial intelligences. When a sixth instruction is input from the user through the input device, the transmission unit may transmit the input sentence to the specific artificial intelligence.

[0019] The generated sentence acquisition unit may acquire, from the specific artificial intelligence, a generated sentence based on the input sentence transmitted to the specific artificial intelligence. The display control unit may be configured to display, on a display device, the generated sentence acquired from the specific artificial intelligence.

[0020] According to an information processing system configured in this manner, a user can obtain a response sentence from a specific artificial intelligence that comprehensively takes into consideration the interactions between the user and multiple artificial intelligences.

[0021] According to an aspect of the present disclosure, the plurality of artificial intelligences may include two or more artificial intelligences playing different roles. According to the information processing system configured in this manner, the user can receive meaningful information from the plurality of artificial intelligences.

[0022] According to an aspect of the present disclosure, the two or more artificial intelligences may include an artificial intelligence that plays a devil's advocate. According to the information processing system configured in this manner, the user can realize deep thinking on various themes through dialogue with the devil's advocate.

[0023] According to one aspect of the present disclosure, the display control unit may control the display device to display a display screen including a plurality of partitioned areas on the display device, and to display, in each of the plurality of areas on the display screen, a sentence generated by a corresponding one of the plurality of artificial intelligences. According to the information processing system configured in this manner, the content of the dialogue between the user and the plurality of artificial intelligences can be displayed on the display screen in a form that is easily understandable to the user.

[0024] According to an aspect of the present disclosure, the display control unit may be configured to receive a user operation for the multiple areas through an input device, and change the order of the multiple areas on the display screen according to the user operation. According to the information processing system configured in this manner, it is possible to display to the user a display screen that is easier for the user to understand regarding the content of the dialogue between the user and the multiple artificial intelligences.

[0025] According to one aspect of the present disclosure, each of the multiple areas may display an input field for writing an input sentence for a corresponding artificial intelligence.

[0026] According to one aspect of the present disclosure, the transmission unit may be configured to transmit, on condition that a generated sentence displayed in a first area of ​​the multiple areas is dragged and dropped into an input field of a second area of ​​the multiple areas, the dragged generated sentence to an artificial intelligence corresponding to the input field into which the generated sentence was dropped.

[0027] According to one aspect of the present disclosure, the generated sentence acquisition unit may be configured to acquire a response sentence to the dragged generated sentence from an artificial intelligence corresponding to the input field into which the generated sentence is dropped.

[0028] According to an information processing system configured in this manner, a user can obtain the reaction of another artificial intelligence to the output of an artificial intelligence, thereby making it possible to make meaningful use of multiple artificial intelligences.

[0029] According to one aspect of the present disclosure, each of the multiple areas may display the content of a dialogue between a user and a corresponding artificial intelligence by arranging a sentence input by the user and a sentence generated by the corresponding artificial intelligence.

[0030] According to one aspect of the present disclosure, the sending unit may be configured to send the dragged generated sentence, together with a portion of the dialogue content describing the context in which the dragged generated sentence was generated, to an artificial intelligence corresponding to the input field into which the generated sentence was dropped.

[0031] According to the information processing system configured in this manner, the user can obtain an appropriate response from the second artificial intelligence with a simple operation.

[0032] According to one aspect of the present disclosure, the display control unit may be configured to control the display device to display a plurality of display windows on the display device, and to display in each of the plurality of display windows a generated sentence generated by a corresponding one of the plurality of artificial intelligences.

[0033] The transmission unit may be configured to determine that a fourth instruction has been input when an operation of superimposing, among the multiple display windows, a display window associated with the first artificial intelligence on a display window associated with the second artificial intelligence is performed through the input device, and to cause the first artificial intelligence and the second artificial intelligence to interact with each other.

[0034] According to the information processing system configured in this manner, it is possible to improve the user's operability regarding the fourth instruction input.

[0035] According to one aspect of the present disclosure, for processing based on the fifth instruction, the transmission unit may be configured as follows. That is, the transmission unit may be configured to be able to receive additional instructions for at least one of the second AI and the third AI from a user through an input device. In this case, the transmission unit may be configured to input the additional instructions received for the second AI to the second AI when transmitting the generated sentence obtained from the first AI to the second AI. The transmission unit may be configured to input the additional instructions received for the third AI to the third AI when transmitting the generated sentence obtained from the second AI to the third AI.

[0036] With an information processing system configured in this manner, the user can obtain from a third artificial intelligence the results of the accumulated thoughts of multiple artificial intelligences while controlling the direction of thinking by inputting additional instructions.

[0037] According to one aspect of the present disclosure, for processing based on the fourth instruction, the transmission unit may be configured as follows: That is, when the fourth instruction is input, the transmission unit may be configured to cause the first artificial intelligence and the second artificial intelligence to interact with each other until at least one of the generated sentence obtained from the first artificial intelligence and the generated sentence obtained from the second artificial intelligence among the multiple artificial intelligences satisfies a predetermined condition, and to end the interaction between the first artificial intelligence and the second artificial intelligence when the predetermined condition is satisfied.

[0038] According to the information processing system configured in this way, the dialogue between the artificial intelligences can be terminated when a predetermined condition is satisfied without the user inputting an end command, thus improving the convenience for the user.

[0039] According to one aspect of the present disclosure, one of the first artificial intelligence and the second artificial intelligence may be configured to score a generated sentence input from the other of the first artificial intelligence and the second artificial intelligence. The transmission unit may be configured to determine that a predetermined condition is satisfied when a score given to the generated sentence by the scoring is equal to or greater than a threshold, and to terminate the dialogue between the first artificial intelligence and the second artificial intelligence.

[0040] According to one aspect of the present disclosure, a computer program for causing a computer to function as at least a part of the generated sentence acquisition unit, the display control unit, and the transmission unit included in the information processing system described above may be provided.

[0041] According to an aspect of the present disclosure, there may be provided an information processing method corresponding to the above-described information processing system. The information processing method may be executed by a computer.

[0042] According to an aspect of the present disclosure, an information processing method may include acquiring a generated sentence from each of a plurality of artificial intelligences. The information processing method may include displaying the generated sentence acquired from each of the plurality of artificial intelligences on a display device.

[0043] The information processing method may include receiving an input sentence from a user through an input device and transmitting the input sentence to at least one of a plurality of artificial intelligences. The generated sentence may include a response sentence to the input sentence and may be generated by the corresponding artificial intelligence.

[0044] The transmitting may include, when a first instruction is input from the user through the input device, transmitting the input sentence to one of the multiple artificial intelligences designated by the user, and, when a second instruction is input from the user through the input device, transmitting the input sentence to the multiple artificial intelligences.

[0045] According to the information processing method configured in this manner, the same effects as those of the information processing system described above can be achieved. [Brief description of the drawings]

[0046] [Figure 1] 1 is a block diagram illustrating a configuration of an information processing system according to a first embodiment. [Diagram 2] FIG. 1 is a diagram (part 1) for explaining the configuration of a service provision screen. [Diagram 3] FIG. 2 is a diagram (part 2) for explaining the configuration of the service provision screen. [Figure 4] FIG. 4A is an explanatory diagram regarding the transmission of an AI input sentence when the send button is pressed, and FIG. 4B is an explanatory diagram regarding the transmission of an AI input sentence when the broadcast button is pressed. [Diagram 5] FIG. 13 is an explanatory diagram regarding rearrangement of chat screens. [Figure 6] FIG. 11 is an explanatory diagram regarding a drag-and-drop operation of a message. [Figure 7] FIG. 13 is a diagram illustrating the transmission of a statement to another artificial intelligence. [Figure 8] FIG. 13 is an explanatory diagram regarding a superimposing operation. [Figure 9] FIG. 1 is a diagram explaining the sending and receiving of AI input sentences and AI output sentences in an AI-AI dialogue. [Figure 10] FIG. 11 is an explanatory diagram regarding a cascade function. [Figure 11] 11 is a flowchart (part 1) illustrating an operation reception process executed by a processor. [Figure 12] 13 is a second flowchart illustrating the operation reception process executed by the processor. [Figure 13] 1 is a flowchart showing an AI dialogue process executed by a processor. [Figure 14] 11 is a flowchart showing a cascade-related process executed by a processor. [Figure 15] 11 is a flowchart showing a master-related process executed by a processor. [Figure 16] FIG. 1 is an explanatory diagram regarding the generation of artificial intelligence having a scoring function. [Figure 17] FIG. 13 is a diagram illustrating an example of an AI output sentence with scoring. [Figure 18] 11 is a flowchart showing a termination control process executed by a processor. [Figure 19] FIG. 11 is an explanatory diagram regarding an additional instruction. [Figure 20] FIG. 13 is a diagram illustrating a user interface related to an additional instruction. [Figure 21] 11 is a flowchart showing a relay-related process executed by a processor. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0047] Exemplary embodiments of the present disclosure will now be described with reference to the drawings. [First embodiment] The information processing system 10 of this embodiment shown in Fig. 1 is configured to communicate with an information terminal 60 and an AI server 70, and provide a dialogue service with multiple artificial intelligences 71 to a user who operates the information terminal 60. The AI ​​server 70 functions as the multiple artificial intelligences 71.

[0048] The plurality of artificial intelligences 71 includes, for example, two or more artificial intelligences 71 each having a different virtual personality. In other words, the plurality of artificial intelligences 71 includes two or more artificial intelligences 71 each playing a different role.

[0049] The multiple artificial intelligences 71 may include two or more artificial intelligences 71 of the same configuration. The multiple artificial intelligences 71 may include a mixture of two or more artificial intelligences 71 of different configurations and two or more artificial intelligences 71 of the same configuration.

[0050] For example, the multiple artificial intelligences 71 may include two or more artificial intelligences 71 that play people having different age groups and genders. For example, the multiple artificial intelligences 71 may include two or more artificial intelligences 71 that play people having different occupations, qualifications, and / or expertise. For example, the multiple artificial intelligences 71 may include two or more artificial intelligences that function as writers.

[0051] The information processing system 10 can prepare multiple artificial intelligences 71 on the AI ​​server 70 by inputting an instruction to create the artificial intelligence 71, which includes information specifying the configuration of the artificial intelligence 71, to the AI ​​server 70.

[0052] The information specifying the configuration of the artificial intelligence 71 includes instructions for the artificial intelligence 71 and knowledge to be imparted to the artificial intelligence 71. These instructions specify how the artificial intelligence 71 should behave, in other words, what role it should play. By providing knowledge to the artificial intelligence 71, it is possible to cause the artificial intelligence 71 to execute a behavior based on specific knowledge.

[0053] 1, the information processing system 10 includes a processor 11, a memory 13, a storage 15, and a communication interface 19. The processor 11 is configured to execute processing according to a computer program. The memory 13 functions as a working memory when the processor 11 executes processing. The memory 13 is, for example, a RAM.

[0054] The storage 15 stores computer programs as well as various data to be used in the processes executed by the processor 11. An example of the storage 15 is a solid-state drive (SSD).

[0055] The communication interface 19 is configured to be able to communicate with the information terminal 60 and the AI ​​server 70 through a wide area network (e.g., the Internet). For simplicity, only one information terminal 60 is shown in Fig. 1. However, the information processing system 10 may be configured to be able to communicate with multiple information terminals 60 corresponding to multiple users.

[0056] The information terminal 60 is, for example, an information terminal owned by a user. Examples of the information terminal 60 include a personal computer, a smartphone, and a tablet terminal. The information terminal 60 includes a user interface 61. The user interface 61 includes a display device 61A and an input device 61B.

[0057] The display device 61A is configured to be able to display information for a user. An example of the display device 61A is a liquid crystal display. The input device 61B is configured to be able to receive an operation from a user. An example of the input device 61B is a keyboard, a pointing device, and a touch panel.

[0058] The information terminal 60 accesses the information processing system 10 in accordance with an operation from a user via the input device 61B, and performs communication regarding the interactive service with the information processing system 10. At this time, the information processing system 10 displays a service provision screen G0 on the display device 61A of the information terminal 60.

[0059] The information processing system 10 realizes a dialogue between the user and the multiple artificial intelligences 71 by accepting an operation from the user on the service provision screen G0 via the input device 61B.

[0060] The information processing system 10 accepts an input sentence for the artificial intelligence 71 through the input device 61B and the service provision screen G0. Hereinafter, the input sentence for the artificial intelligence 71 is referred to as an AI input sentence. The information terminal 60 transmits the AI ​​input sentence input to the service provision screen G0 through the input device 61B to the information processing system 10.

[0061] The information processing system 10 transmits the AI ​​input sentence received from the information terminal 60 to at least one of the multiple artificial intelligences 71. Among the multiple artificial intelligences 71, the artificial intelligence 71 that receives the AI ​​input sentence generates a response sentence to the AI ​​input sentence and returns it to the information processing system 10. Hereinafter, the generated sentence generated by the artificial intelligence 71, including the response sentence, is referred to as the AI ​​output sentence.

[0062] The information processing system 10 displays the received AI output sentence on the display device 61A of the information terminal 60, specifically on the service provision screen G0. This allows a dialogue between the user and multiple artificial intelligences 71 to be realized through the service provision screen G0.

[0063] The service provision screen G0, as shown in FIG. 2, is configured to be capable of displaying AI output statements of a plurality of artificial intelligences 71, and is further configured to be capable of receiving input operations of AI input statements for the plurality of artificial intelligences 71.

[0064] The service provision screen G0 includes a plurality of chat screens G1, G3 corresponding to a plurality of artificial intelligences 71. According to this embodiment, a plurality of artificial intelligences 71 are designated as conversation partners by the user through the input device 61B. The service provision screen G0 displays chat screens G1, G3 related to the plurality of artificial intelligences 71 designated as conversation partners.

[0065] In this embodiment, the plurality of artificial intelligences 71 that the user can designate as a conversation partner includes a specific artificial intelligence 71M (hereinafter, referred to as a master 71M) that is given a specific role.

[0066] The master 71M is an artificial intelligence that is given the role of overseeing the artificial intelligences 71 other than the master 71M among the multiple artificial intelligences 71. Hereinafter, each of the multiple artificial intelligences 71 other than the master 71M will be expressed as an artificial intelligence 71A using the symbol 71A. As described above, the multiple artificial intelligences 71A include two or more artificial intelligences 71A that play different roles.

[0067] 2 shows the configuration of the service provision screen G0 when three AIs 71A and one master 71M are specified as conversation partners by the user. The chat screen G3 shown in FIG. 2 is a chat screen associated with the master 71M. Each of the multiple chat screens G1 is a chat screen associated with an AI 71A other than the master 71M among the multiple AIs 71.

[0068] The chat screen G1 includes a profile image G11, a chat display screen G13, an input field G15, and a send button G18. The profile image G11 is an area on the chat screen G1 that displays an anthropomorphized image of the associated artificial intelligence 71 and a name given to the artificial intelligence 71A. For example, when the artificial intelligence 71A plays the role of a woman in her twenties, the profile image G11 displays an avatar image of the woman in her twenties and the name of the artificial intelligence 71A that allows the user to identify her as a woman in her twenties.

[0069] The chat display screen G13 is a vertical scroll screen. The chat display screen G13 displays the contents of the conversation between the user and the artificial intelligence 71A in a time series arranged from top to bottom using speech bubbles. The input field G15 is configured to be able to accept text input from the user through the input device 61B.

[0070] The send button G18 is an operation object for receiving an instruction to send the text entered in the input field G15 of the same chat screen G1 to the artificial intelligence 71A. When the send button G18 is pressed, the text written in the input field G15 of the same chat screen G1 is sent to the corresponding artificial intelligence 71A as an AI input sentence.

[0071] When a specific operation is performed through the input device 61B, the send button G18 temporarily changes to a broadcast button G19. Fig. 3 shows the configuration of the service provision screen G0 including the broadcast button G19. For example, the send button G18 changes to the broadcast button G19 only while a specific key (e.g., a shift key on a keyboard) on the input device 61B is being pressed.

[0072] The mass send button G19 is an operation object for accepting a mass send instruction to send the text entered in the input field G15 of the same chat screen G1 simultaneously as an AI input text to all of the multiple artificial intelligences 71A whose chat screens G1 are displayed on the service provision screen G0.

[0073] That is, by pressing the send button G18, the AI ​​input sentence is sent to one corresponding AI 71A as shown in Fig. 4A, whereas by pressing the broadcast button G19, the AI ​​input sentence is sent to multiple AIs 71A at once as shown in Fig. 4B. In this respect, the send button G18 and the broadcast button G19 are different.

[0074] Next, a configuration of the chat screen G3 associated with the master 71M will be described. The chat screen G3 includes a profile image G31, a chat display screen G33, an input field G35, and an operation button group G37, as shown in FIG.

[0075] The profile image G31 is an area on the chat screen G3 that displays a personified image of the associated master 71M and a name given to the master 71M. The chat display screen G33 is a vertically scrolling screen.

[0076] The chat display screen G33 displays the contents of conversations between the user and multiple artificial intelligences 71 including the master 71M, arranged in chronological order from top to bottom using speech bubbles. The chat display screen G33 displays the contents of conversations between the user and multiple artificial intelligences 71A together with information about the speaker.

[0077] The input field G35 is configured to be able to accept text input from the user via the input device 61 B. The operation button group G37 includes a send button G371, a call button G373, a memo pad button G375, and an output button G379.

[0078] The send button G371 is an operation object for receiving an instruction to send the text entered in the input field G35 to the master 71M. When the send button G371 is pressed, the text written in the input field G35 is sent as an AI input sentence to the master 71M associated with the chat screen G3.

[0079] The call button G373 is a button for the user to specify the conversation partner. When the call button G373 is pressed, a selection screen for the artificial intelligence 71 (not shown) is displayed. The user can specify one or more artificial intelligences 71A and one master 71M as conversation partners from among the multiple artificial intelligences 71 displayed on the selection screen through the input device 61B. By specifying a conversation partner through the call button G373, the chat screen G1 for each of the specified artificial intelligences 71A is displayed on the service provision screen G0.

[0080] The chat screen G3 is displayed on the service provision screen G0 even before the master 71M is designated as a conversation partner. According to one example, a standard master 71M is prepared in advance as a conversation partner without being designated by the user.

[0081] The memo pad button G375 is used when the user makes a note via the input device 61B. When the memo pad button G375 is pressed, an electronic memo pad is displayed on the display device 61A. Information written in the memo pad is recorded in the information processing system 10 without being transmitted to the artificial intelligence 71.

[0082] The output button G379 is an operation object for receiving an instruction to output the contents of the dialogue between the user and the artificial intelligence 71. For example, the information processing system 10 is configured to output the contents of the dialogue between the user and the multiple artificial intelligences 71 as text when the output button G379 is pressed. The information processing system 10 may be configured to output the contents of the dialogue between the user and the multiple artificial intelligences 71 as text, together as minutes. The minutes can be generated by the master 71M.

[0083] As shown in Fig. 5, each of the chat screens G1 and G3 in the service provision screen G0 functions as an individual display window. The service provision screen G0 is configured so that the user can change the left-right arrangement of each of the chat screens G1 and G3 (display windows) in the service provision screen G0 to an arbitrary arrangement by moving the chat screens G1 and G3 (display windows) via the input device 61B. The moving operation of the chat screens G1 and G3 (display windows) is realized, for example, by a drag operation.

[0084] The information processing system 10 is also configured to be able to transmit a statement selected by the user from the content of a dialogue between a first AI and the user to a second AI different from the first AI, and the service provision screen G0 has a graphical user interface for this purpose. Here, the first AI and the second AI are arbitrarily selected by the user from the multiple AIs 71A designated as conversation partners.

[0085] As shown in FIG. 6, the AI ​​input sentence and the AI ​​output sentence displayed in the form of speech bubbles on the chat screen G1 in the service provision screen G0 are each independently configured as an operational object OJ1 that can be dragged and dropped. Hereinafter, the term "statement" is used to refer to both the AI ​​input sentence and the AI ​​output sentence. For example, the AI ​​input sentence is a statement made by a user, and the AI ​​output sentence is a statement made by the artificial intelligence 71. However, as will be described later, the AI ​​input sentence may be a statement made by the artificial intelligence 71.

[0086] On the service provision screen G0, the user can perform a drag-and-drop operation by dragging the speech bubble (operation object OJ1) of the statement that the user wants to send to the second AI from the chat display screen G13 of the chat screen G1 corresponding to the first AI and dropping it into the input field G15 of the chat screen G1 corresponding to the second AI.

[0087] The information processing system 10 is configured to transmit, by this drag-and-drop operation (hereinafter referred to as the "transfer operation"), a statement corresponding to the speech bubble specified by the user (hereinafter referred to as the "transferred statement") to the second artificial intelligence.

[0088] According to this transfer operation, the transferred text is copied in an edited state to the input field G15 of the chat screen G1 corresponding to the second AI. The edited transferred text is a text to which the information of the sender corresponding to the transferred text is added to the end of the transferred text.

[0089] When the transferred text is an AI output text by the first AI, the identification information of the first AI is written as the speaker information at the end of the processed transferred text. When the speaker (for example, the first AI) is named "XX", the special character string ""[XX's opinion]" is written at the end of the processed transferred text.

[0090] When the send button G18 is pressed while the processed transfer sentence is input in the input field G15, the processed transfer sentence is sent to the second AI. As a modified example, the information processing system 10 may be configured to send the processed transfer sentence to the second AI when the transfer sentence is dropped into the input field G15, without waiting for the send button G18 to be pressed.

[0091] In detail, as shown in FIG. 7, the information processing system 10 not only generates the processed transfer sentence D1, but also adds a series of statement sentences D2 connected to the transfer sentence to the processed transfer sentence D1 to generate an AI input sentence (hereinafter referred to as a "dialogue input sentence") D3 for the second artificial intelligence, and transmits this dialogue input sentence D3 to the second artificial intelligence.

[0092] 7 illustrates how the information processing system 10 generates a dialogue input sentence D3 by attaching a series of statements D2 to a processed transfer sentence D1, and transmits the dialogue input sentence D3 to the second artificial intelligence. As can be seen from FIG. 7, in the dialogue input sentence D3, each of the statements D21 included in the series of statements D2 is accompanied by speaker information. The speaker information is information that enables the artificial intelligence 71 to identify the speaker corresponding to the statement D21.

[0093] The series of statements D2 is transmitted to the second AI to convey to the second AI the context (i.e., the circumstances) in which the statements corresponding to the transferred statements occurred. The series of statements D2 corresponds to a part of the dialogue between the user and the first AI. In other words, the series of statements D2 is a partial extraction of the dialogue related to the transferred statements from the dialogue between the user and the first AI. The series of statements D2 is configured by arranging a predetermined number of statements D21 included in the consecutive dialogues between the user and the first AI in chronological order up to the utterance of the transferred statement.

[0094] A characteristic feature of this embodiment is that the dialogue input sentence D3 also stores a series of utterances between the user and the second AI as related sentences D4. Each of the utterances D41 included in the related sentences D4 is accompanied by speaker information. The related sentences D4 are configured by arranging a series of utterances in chronological order, with the latest utterance in the dialogue between the user and the second AI as the end point. Specifically, the related sentences D41 are configured by arranging a predetermined number of past utterances D41, including the latest utterance, that occurred in the dialogue between the user and the second AI, in chronological order.

[0095] By inputting such a dialogue input sentence D3 into the second artificial intelligence, a meaningful response to the processed transferred sentence D1 from the second artificial intelligence is expected, taking into consideration the dialogue content between the first artificial intelligence and the user and the dialogue content between the second artificial intelligence and the user.

[0096] According to this embodiment, when the AI ​​input text contains the special character string "X's opinion," each AI 71A is instructed in advance to respond to the comment text (transfer text) associated with the special character string, taking into account the context up to the comment. Such an instruction in advance realizes a meaningful response from the second AI to the processed transfer text D1.

[0097] In addition, the information processing system 10 is configured to realize a dialogue between the artificial intelligences 71A (hereinafter referred to as "AI dialogue"). This AI dialogue is available when the chat screen G1 of two or more artificial intelligences 71A is displayed on the service provision screen G0.

[0098] In this state, the user can select a first artificial intelligence and a second artificial intelligence to be the subject of AI-to-AI dialogue from among two or more artificial intelligences 71A, and, as shown in Figure 8, move the chat screen G1 of the first artificial intelligence by dragging it so that it is superimposed on the chat screen G1 of the second artificial intelligence (hereinafter referred to as the "superimposition operation").

[0099] When this overlay operation causes the chat screen G1 of the first artificial intelligence and the chat screen G2 of the second artificial intelligence to be overlaid, the information processing system 10 determines that an instruction has been given to start an AI-to-AI dialogue between the first artificial intelligence and the second artificial intelligence.

[0100] Then, as shown in Figure 9, the information processing system 10 repeats the process of sending the AI ​​output sentence of the first AI to the second AI as an AI input sentence, and sending the AI ​​output sentence from the second AI as a response sentence to this AI input sentence to the first AI as an AI input sentence, until an instruction to end the AI ​​dialogue is input.

[0101] This AI-to-AI dialogue starts with the input text from the user being sent to the first AI or the second AI as an AI input sentence after the overlapping operation, resulting in an AI output sentence being output from the first AI or the second AI. This starting AI output sentence is referred to here as the starting output sentence. Furthermore, the input text from the user that triggers the generation of the starting output sentence is referred to as the starting input sentence. Moreover, the AI ​​to which the starting input sentence is input, of the first AI or the second AI, is referred to as the starting AI.

[0102] The instruction to end the AI ​​dialogue is the same as the instruction to start the AI ​​dialogue. In other words, the user can input the instruction to end the AI ​​dialogue through the information processing system 10 by performing the overlapping operation again while the AI ​​dialogue is being conducted.

[0103] A characteristic feature of this embodiment is that in the AI-AI dialogue, an AI input sentence with the same structure as the dialogue input sentence D3 described above is generated. Hereinafter, the AI ​​input sentence used in the AI-AI dialogue will be referred to as the "AI-AI input sentence."

[0104] That is, the origin output sentence is input to the non-origin AI as a first inter-AI input sentence together with the series of utterances between the user and the origin AI up to the time immediately before the origin output sentence, the speaker information of the series of utterances, and the speaker information of the origin output sentence. The series of utterances is a predetermined number of utterances. The non-origin AI is an AI between the first artificial intelligence and the second artificial intelligence that is not the origin AI, that is, an AI that interacts with the origin AI.

[0105] The starting output sentence included in the first AI-to-AI input sentence includes the above-mentioned "[XX's opinion]" as a special character string. Here, the name of the starting AI that output the starting output sentence is inserted in "XX". Furthermore, the first AI-to-AI input sentence includes a series of statements including the latest statements between the non-starting AI and the user, and speaker information for the series of statements, just like dialogue input sentence D3.

[0106] When sending an AI output sentence from a non-initiating AI that outputs a response sentence to a first AI-to-AI input sentence to an originating AI for AI-to-AI dialogue, the information processing system 10 inputs to the originating AI as a second AI-to-AI input sentence, together with the AI ​​output sentence from the non-initiating AI, the AI-to-AI input sentence including a series of statements between the user and the non-initiating AI up to immediately before the AI ​​output sentence, speaker information of the series of statements, and speaker information of the AI ​​output sentence.

[0107] When sending an AI output sentence from an origin AI that outputs an AI output sentence in response to a second AI-AI input sentence to a non-origin AI for AI-AI dialogue, the information processing system 10 inputs to the non-origin AI, as a third AI-AI input sentence, an AI-AI input sentence including the series of statement sentences up to the AI ​​output sentence, the speaker information of the series of statement sentences, and the speaker information of the AI ​​output sentence, together with the AI ​​output sentence from the origin AI. The fourth AI-AI input sentence is generated in the same manner as the third AI-AI input sentence.

[0108] According to this embodiment, such AI-to-AI dialogue makes it possible to obtain meaningful information from the first artificial intelligence and the second artificial intelligence.

[0109] In addition, the information processing system 10 of this embodiment has a cascade function for inputting AI output sentences in sequence to a plurality of artificial intelligences 71A. The cascade function is available when three or more artificial intelligences 71A are designated as conversation partners from among a plurality of artificial intelligences 71A dedicated to the cascade function prepared in advance, and three or more chat screens G1 are displayed on the service provision screen G0.

[0110] The cascade function is realized by preparing a dedicated artificial intelligence 71A for each step of an intellectual task that can be decomposed into multiple steps. That is, the cascade function realizes the intellectual task using multiple artificial intelligences 71A by utilizing the AI ​​output sentence from the artificial intelligence 71A of each step as an input to the artificial intelligence 71A of the next step. By obtaining a deliverable based on the intellectual task using multiple artificial intelligences 71A, a high-quality deliverable can be obtained efficiently. One example of the intellectual task is the task of writing an article.

[0111] As shown in Figure 10, the task of creating an article can be broken down into the following steps: deciding on the article plan, deciding on the article title, deciding on the article structure (chapter division), creating an outline for each chapter, and creating the article text for each chapter from the outline.

[0112] When using the cascade function, a dedicated AI 71A is placed at each step according to the user's designation of the person to talk to. After that, the information processing system 10 accepts input sentences from the user to the AI ​​71A located at the top of the intellectual work, and inputs the AI ​​output sentences from the AI ​​71A of each step to the AI ​​71A of the next step.

[0113] In Fig. 10, the AI ​​output sentences of the artificial intelligence 71A located at the starting point of each arrow are input to the artificial intelligence 71A located at the end point of the arrow. From this, the plan, article title, article structure, summary of each chapter, and article text of each chapter are created in the corresponding artificial intelligence 71A. The article text of each chapter is created by the artificial intelligence 71A prepared for each chapter. The created article texts of each chapter are finally compiled into one article by the master 71M.

[0114] The circle symbol in the center of the arrow in Figure 10 represents the procedure in which the user selects one of the multiple candidates presented, on the assumption that the AI ​​output statement from the upstream arrow presents multiple candidates for the input statement to the next step.

[0115] This procedure is realized by the user inputting an AI input sentence indicating the selection of one of multiple candidates through the input field G15 of the same chat screen G1, based on the AI ​​output sentence displayed on the chat screen G1.

[0116] The artificial intelligence 71A inputs an AI input sentence indicating one candidate selected by the user from among multiple candidates presented to the user, as an input to the artificial intelligence 71A in the next step. According to a first example, the AI ​​input sentence input to the artificial intelligence 71A in the next step is an input sentence including information on multiple candidates and information on the candidate selected by the user. According to a second example, the AI ​​input sentence is an input sentence including only information on the candidate selected by the user from among the multiple candidates.

[0117] When the first example AI input sentence is input to the next step AI 71A, the next step AI 71A can generate an AI output sentence by taking into account both the candidate selected by the user and the candidate not selected from among the multiple candidates. In this case, the AI ​​71A can be instructed in advance to generate an AI output sentence based on the selected candidate, taking into account the fact that the candidate not selected by the user was not selected.

[0118] The functions of the information processing system 10 described above are realized by the processor 11 executing processes in accordance with computer programs stored in the storage 15. Next, the details of the processes executed by the processor 11 will be described with reference to FIGS.

[0119] When the information processing system 10 is accessed from the information terminal 60, the processor 11 starts the processing shown in FIG. 11 after user authentication, and displays the service provision screen G0 on the display device 61A of the information terminal 60 through communication with the information terminal 60 (S110).

[0120] Thereafter, the processor 11 waits until an operation is performed on the service provision screen G0 via the input device 61B (S120), and when an operation is performed (Yes in S120), the processor 11 identifies the performed operation (S130).

[0121] If the operation identified in S130 is a text input operation into the input field G15, G35 (Yes in S140), the processor 11 accepts the text input operation into the input field G15, G35 and displays the input text in the corresponding input field G15, G35 (S145). After that, the processor 11 returns to the process of S120.

[0122] If the operation identified in S130 is the pressing of the send button G18, G371 (Yes in S150), the processor 11 determines that an instruction to send text has been input, and sends the text entered in the input field G15, G35 of the same chat screen G1, G3 as the pressed send button G18, G371 as shown in FIG. 4A to the artificial intelligence 71 associated with the same chat screen G1, G3 as the pressed send button G18, G371 (S160).

[0123] Processor 11 further displays the AI ​​input sentence transmitted in S160 and the AI ​​output sentence received from the AI ​​71 to which the AI ​​input sentence was transmitted as a response to the AI ​​input sentence in the form of speech bubbles on chat display screens G13, G33 of chat screens G1, G3 associated with the AI ​​71 to which the AI ​​input sentence was transmitted (S165). After that, processor 11 returns to the processing of S120.

[0124] In S160, if no text has been entered in the corresponding input field G15, G35, the processor 11 does not transmit the AI ​​input sentence to the artificial intelligence 71, and further does not execute the processing of S165, and returns to the processing of S120.

[0125] If the operation identified in S130 is the pressing of the simultaneous transmission button G19 (Yes in S170), the processor 11 determines that an instruction to transmit text simultaneously has been input, and transmits the text input in the input field G15 as an AI input sentence simultaneously to all of the multiple artificial intelligences 71A associated with the multiple chat screens G1 displayed on the service provision screen G0, as shown in Fig. 4B (S180). The text to be transmitted simultaneously is, for example, the text input in the input field G15 of the same chat screen G1 as the pressed simultaneous transmission button G19.

[0126] Processor 11 further displays the AI ​​input sentence transmitted in S180 and the AI ​​output sentence received from each AI 71A to which the AI ​​input sentence was transmitted as a response to the AI ​​input sentence in the form of a speech bubble on chat display screen G13 of chat screen G1 associated with each AI 71A (S185). After that, processor 11 returns to the process of S120.

[0127] If the operation identified in S130 is a transfer operation (Yes in S190), the processor 11 determines that a transfer instruction has been input, and displays an processed transfer sentence D1 in which the commenter's name has been added as the special character string "[XX's opinion]" to the end of the comment that was the target of the transfer operation (i.e., the transfer sentence), in the input field G15 into which the comment was dropped (S200).

[0128] Thereafter, when the send button G18 on the same chat screen G1 as the input field G15 is pressed, the processor 11 sends the processed transfer sentence D1, the series of comment sentences D2, the related sentences D4, and the dialogue input sentence D3 including the commenter information to the artificial intelligence 71A associated with the same chat screen G1 as the pressed send button G18 (S205).

[0129] As described above, and further as shown in Fig. 7, the series of messages D2 sent in S205 is a series of messages D2 indicating the contents of the dialogue between the user and the artificial intelligence 71A (i.e., the first artificial intelligence) associated with the chat screen G1 from which the dragged-and-dropped message (i.e., the message to be transferred) was dragged, and is a group of a predetermined number of past messages adjacent to the message to be transferred. The series of messages D2 explains the context of the dialogue leading up to the message to be transferred.

[0130] As described above, the related sentence D4 is a series of statements indicating the contents of the dialogue between the AI ​​71A (i.e., the second AI) associated with the chat screen G1 of the drop destination and the user, and is a group of a predetermined number of past statements from the latest statement. This related sentence D4 is transmitted to the second AI to generate an AI output sentence that takes into account the past dialogue between the second AI and the user.

[0131] Then, the processor 11 displays the processed transfer sentence D1 included in the dialogue input sentence D3 sent in S205, and the AI ​​output sentence received from the AI ​​71A (i.e., the second AI) to which the dialogue input sentence D3 was sent as a response to the dialogue input sentence D3, in the form of a speech bubble on the chat display screen G13 of the chat screen G1 associated with this AI 71A (i.e., the second AI) (S209). Then, the processor 11 returns to the process of S120.

[0132] If the operation identified in S130 is an overlay operation (Yes in S210), the processor 11 determines whether the two artificial intelligences 71A corresponding to the two chat screens G1 that were the subject of the overlay operation are engaged in an AI-to-AI dialogue with each other (S220).

[0133] If it is determined that the AIs are not currently engaged in dialogue (No in S220), the processor 11 determines that the overlapping operation is an instruction to start dialogue between the AIs, and starts dialogue processing between the AIs for these two AIs 71A (S230). After that, the processor 11 returns to the process of S120.

[0134] On the other hand, if it is determined in S220 that an AI-AI dialogue is in progress (Yes in S220), processor 11 determines that the overlapping operation is an instruction to end the AI-AI dialogue, and ends the AI-AI dialogue processing for the two AIs 71 in the AI-AI dialogue (S240). After that, processor 11 returns to the process of S120.

[0135] In S230, the processor 11 can execute the AI-to-AI dialogue processing shown in Fig. 13. When the AI-to-AI dialogue processing shown in Fig. 13 starts, the processor 11 accepts a text input from the input field G15 of the chat screen G1 of one of the two artificial intelligences 71A that are the subject of the AI-to-AI dialogue (S231).

[0136] Thereafter, when the send button G18 on the chat screen G1 is pressed, the processor 11 transmits the input text to the starting AI as a starting input sentence (S232). The starting AI is the AI ​​71A that has received the text input from the input field G15, among the two AIs 71A that are the targets of the AI-AI dialogue.

[0137] After transmission in S232, the processor 11 displays the starting input sentence transmitted in S232 and, as a response to the starting input sentence, the AI ​​output sentence (i.e., the starting output sentence) received from the artificial intelligence 71A (i.e., the starting AI) to which the starting input sentence was transmitted, in the form of a speech bubble on the chat display screen G13 of the chat screen G1 associated with this artificial intelligence 71A (S233).

[0138] Furthermore, processor 11 transmits the first AI-to-AI input sentence including the starting output sentence to the non-starting AI (S234). After transmission in S234, processor 11 displays the AI ​​output sentence received from the AI ​​71A (i.e., the non-starting AI) to which the first AI-to-AI input sentence was transmitted as a response to the starting output sentence transmitted in S234 and the first AI-to-AI input sentence in the form of a speech bubble on chat display screen G13 of chat screen G1 associated with this AI 71A (S235).

[0139] Furthermore, the processor 11 transmits to the origin AI the second AI-AI input sentence, which includes the AI ​​output sentence received in S235 (S236).

[0140] After transmission in S236, processor 11 realizes an AI-to-AI dialogue by repeatedly executing processes similar to S233, S234, and S235 related to the transmitted AI-to-AI input sentence until an instruction to end the AI-to-AI dialogue is input. Note that when understanding a process similar to S233, the origin input sentence should be read as an AI output sentence from a non-origin AI included in the AI-to-AI input sentence received immediately before.

[0141] In addition, if the operation identified in S130 is not any of the following: text input operation into the input field G15, G35, pressing the Send button G18, pressing the Send all button G19, forwarding operation, and overlay operation (No in S140, No in S150, No in S170, No in S190, No in S210), and further, if it is not an operation to close the service provision screen G0 (No in S260), the processor 11 executes processing corresponding to the other identified operation (S270).

[0142] Examples of other operations include the above-mentioned pressing operation of the call button G373, pressing operation of the memo pad button G375, pressing operation of the output button G379, and an operation related to rearrangement of the chat screen G1. The processor 11 can control the display of the display device 61A so as to change the left-right rearrangement order of the multiple chat screens G1 displayed on the service provision screen G0 in accordance with the rearrangement operation of the chat screen G1 (S270). After executing the process of S270, the processor 11 returns the process to S120. When an operation to close the service provision screen is performed (Yes in S260), the processor 11 ends the operation reception process shown in FIG. 11 and FIG. 12.

[0143] Next, the contents of the cascade-related process executed by the processor 11 to realize the cascade function will be described with reference to Fig. 14. When the cascade-related process shown in Fig. 14 is started, the processor 11 accepts an input statement from the user to the artificial intelligence 71A located at the upstream of the intellectual work realized by the cascade function, that is, the artificial intelligence 71A for realizing the first step of the intellectual work (S310).

[0144] Specifically, the processor 11 accepts text input from the user through the input field G15 of the chat screen G1 associated with the most upstream artificial intelligence 71A, that is, the first step artificial intelligence 71A (S310).

[0145] When text is input, processor 11 transmits the input text to first step artificial intelligence 71A as an AI input sentence (S320).

[0146] Then, the processor 11 displays this AI input sentence and, as a response to the AI ​​input sentence, the AI ​​output sentence received from the first-step artificial intelligence 71A in the form of a speech bubble on the chat display screen G13 of the chat screen G1 of the first-step artificial intelligence 71 (S330).

[0147] The AI ​​output sentence from the artificial intelligence 71A in the first step presents a plurality of candidates for the input sentence to the artificial intelligence 71A in the next step (i.e., the second step).

[0148] After the process of S330, processor 11 accepts a user's selection from among multiple candidates included in the AI ​​output sentence received in S330 through input field G15 (S340). Specifically, as the selection content, an input operation of text indicating the candidate selected by the user is accepted through input field G15 (S340). When the text indicating the selection content is input, processor 11 transmits the corresponding selection content to first-step artificial intelligence 71A (S350).

[0149] After the process of S350, the processor 11 receives the AI ​​output sentence output from the first-step artificial intelligence 71A, and transmits the AI ​​output sentence to the second-step artificial intelligence 71A as an AI input sentence (S360). The second-step artificial intelligence 71A is the artificial intelligence 71A for realizing the second step of the intellectual task.

[0150] The AI ​​output statement output from the first step artificial intelligence 71A, in other words, the AI ​​input statement to the second step artificial intelligence 71A, is the AI ​​input statement according to the first or second example described above with respect to the cascade function.

[0151] That is, according to the first example, the AI ​​input sentence is an input sentence that includes information on the multiple candidates and information on the candidate selected by the user. According to the second example, the AI ​​input sentence is an input sentence that includes only information on the candidate selected by the user from among the multiple candidates.

[0152] After processing S360, processor 11 receives the AI ​​output sentence output from second-step artificial intelligence 71 as a response sentence to this AI input sentence. Processor 11 displays the received AI output sentence in the form of a speech bubble on chat display screen G13 of chat screen G1 associated with second-step artificial intelligence 71 (S370). The AI ​​output sentence from second-step artificial intelligence 71A presents multiple candidates for input sentences to the next step (i.e., third step) artificial intelligence 71A.

[0153] In the next S380, the processor 11 accepts, via the input field G15, a user's selection from among multiple candidates for the input sentence to the next-step artificial intelligence 71A contained in the AI ​​output sentence received in S370. When text representing the selection is entered in the input field G15, the processor 11 transmits the corresponding selection to the second-step artificial intelligence 71A (S390).

[0154] After processing of S390, the processor 11 receives the AI ​​output sentence output from the second step artificial intelligence 71A, and transmits the AI ​​output sentence as a new AI input sentence to the third step artificial intelligence 71A (S400).

[0155] Thereafter, the processor 11 receives the AI ​​output statement output from the third step artificial intelligence 71, and repeatedly executes the same processes as S370, S380, S390, and S400 while updating the steps of the intellectual work.

[0156] However, if an AI output sentence that does not include a candidate is received in S370, the processor 11 does not accept the input of the selection in S380, and can send the AI ​​output sentence received in S370 to the artificial intelligence 71 in the next step (S400).

[0157] The cascade function is realized by the above-mentioned processing executed by the processor 11. In addition, according to the information processing system 10 of this embodiment, the processor 11 repeatedly executes the master-related process shown in FIG. 15 to provide the master 71M with the contents of the conversation between each artificial intelligence 71A and the user.

[0158] That is, when a new message is displayed on a plurality of chat screens G1 (Yes in S410), the processor 11 executes a process of additionally displaying this message in the form of a speech bubble on the chat display screen G33 of the chat screen G3 (S420). If the message is a message from the artificial intelligence 71A, the processor 11 processes the message by adding "[XX's opinion]" to the end of the message, and additionally displays the processed message on the chat display screen G33. The name of the speaker is inserted in place of "XX". The processor 11 further transmits the message (processed message) to the master 71M together with instructions to record the message as a log (S430). At this time, the processor 11 provides the inventor information to the master 71M.

[0159] The information processing system 10 of the present embodiment described above is configured to acquire a generated sentence (i.e., an AI output sentence) from each of the multiple artificial intelligences 71. The information processing system 10 is configured to acquire an input sentence from a user through the input device 61B, and transmit the input sentence to at least one of the multiple artificial intelligences 71 as an AI input sentence.

[0160] The information processing system 10 is configured to display an AI output sentence obtained from each of the multiple artificial intelligences 71 on the display device 61A through a service provision screen G0.

[0161] When a user inputs a send instruction by pressing the send button 18G via the input device 61B (Yes in S150), the information processing system 10 sends the input sentence to one of the multiple artificial intelligences 71 specified by the user, i.e., the artificial intelligence 71 corresponding to the pressed send button 18G (S160).

[0162] When a user inputs a mass transmission instruction by pressing the mass transmission button 19G via the input device 61B (Yes in S170), the information processing system 10 transmits the input text to all of the multiple artificial intelligences 71A except for the master 71M (S180).

[0163] According to the information processing system 10 configured in this way, the user can simultaneously transmit a common input sentence to the multiple artificial intelligences 71A. Therefore, according to this embodiment, it is possible to provide the information processing system 10 that is highly convenient when the user uses the multiple artificial intelligences 71.

[0164] According to this embodiment, when a transfer instruction is input by a transfer operation through the input device 61B (Yes in S190), the information processing system 10 transmits the dialogue contents between the user and a first AI (the drag source AI) among the multiple AIs 71A through the AI ​​input sentences and the AI ​​output sentences to a second AI (the drag destination AI) among the multiple AIs 71A that is different from the first AI (S205). The information processing system 10 acquires the AI ​​output sentences from the second AI and displays them on the display device 61A (S209).

[0165] The transfer operation is a drag-and-drop operation of a statement, and the first AI and the second AI correspond to the AI ​​of the drag source and the AI ​​of the drag destination, respectively. That is, according to this embodiment, the user can specify the first AI and the second AI by the drag-and-drop operation.

[0166] According to the information processing system 10 configured in this manner, the user can obtain a response to the content of the dialogue with the first artificial intelligence from another second artificial intelligence. For example, the user can obtain another thought from the second artificial intelligence that takes into account the thought of the first artificial intelligence.

[0167] For example, regarding a certain theme, it is possible to obtain from the second AI the thoughts of a woman, taking into account the thoughts of a man obtained from the first AI. Examples of combinations of virtual personalities for the combination of the first AI and the second AI here are not limited to combinations of men and women, but include various combinations of people, such as combinations of people from different residential areas, combinations of people from different generations, and combinations of people with different expertise. Therefore, according to this embodiment, it is possible to meaningfully utilize multiple AIs 71 with different virtual personalities, in other words, different roles, set.

[0168] In addition, the dialogue input sentence D3 sent to the second AI by the transfer operation includes the dialogue between the user and the first AI up to the utterance of the transferred sentence, but the dialogue content included in the dialogue input sentence D3 is not the entire dialogue between the user and the first AI, but a part related to the transferred sentence. In this way, by selectively providing a part of the dialogue content, rather than the entire content, to the second AI, it is possible to obtain an appropriate reaction from the second AI to a utterance that should be noticed.

[0169] In addition, the transferred sentence is often the latest sentence among the utterances generated in the dialogue between the user and the first AI. In this case, the dialogue input sentence D3 can store the latest part of the dialogue content exchanged between the user and the first AI. By providing the latest part of the dialogue content to the second AI, the user can obtain the second AI's reaction to the most recent dialogue content regarding the most recent dialogue between the user and the first AI.

[0170] In addition, in this embodiment, when a user inputs an instruction to start an AI dialogue through the input device 61B by a superimposition operation (Yes in S210), the information processing system 10 realizes a dialogue between the first AI and the second AI as the two AIs 71A corresponding to the two chat screens G1 that are the subject of the superimposition operation. The first AI and the second AI here correspond to the AI ​​71A designated by the user by the superimposition operation.

[0171] Specifically, by executing the AI-to-AI dialogue processing shown in Figure 13, the information processing system 10 transmits an AI output sentence obtained from a first AI to a second AI different from the first AI as an AI input sentence (S234), and transmits the AI ​​output sentence obtained from the second AI to the first AI as an AI input sentence (S236), thereby realizing dialogue between the first AI and the second AI.

[0172] According to the information processing system 10 configured in this way, the user can see the results of the discussion between the artificial intelligences on a theme or topic of interest. The results of such discussions can be useful for the user's deeper thinking on the theme or topic, for example.

[0173] In addition, in this embodiment, with regard to the cascade function, the information processing system 10, starting from a user instruction to send an AI input statement to the first step artificial intelligence 71A, sends the AI ​​output statement of the first step artificial intelligence 71A as an AI input statement to the second step artificial intelligence 71A (S360), and sends the AI ​​output statement of the second step artificial intelligence 71A as an AI input statement to the third step artificial intelligence 71A (S400).

[0174] According to this embodiment, each step of the intellectual work can be realized by using a different artificial intelligence 71A. According to such an intellectual work using a plurality of artificial intelligences 71A, compared to a case where an intellectual work such as article writing is performed by interaction using a single artificial intelligence 71A, a product that is the result of accumulating the ideas of a plurality of artificial intelligences 71 or a product based on multifaceted ideas can be obtained, and a high-quality product can be obtained efficiently.

[0175] In addition, according to this embodiment, the information processing system 10 transmits the contents of the dialogue between the user and the multiple artificial intelligences 71A to the master 71M, which is a specific artificial intelligence 71M different from the multiple artificial intelligences 71A (S430). When a transmission instruction to the master 71M is input by pressing the transmission button G371, the information processing system 10 transmits the text entered in the input field G35 to the master 71M as an AI input sentence (S160).

[0176] Therefore, the user can send an instruction to execute a process based on the content of the dialogue between the user and the multiple artificial intelligences 71A as an AI input sentence to the master 71M, and obtain the answer as an AI output sentence (S165). The answer (AI output sentence) from the master 71M is displayed on the display device 61A through the chat display screen G33 of the chat screen G3 (S165).

[0177] According to the information processing system 10 configured in this manner, the user can obtain a response sentence that comprehensively considers the exchange between the user and the multiple artificial intelligences 71A from the master 71M. For example, the user can cause the master 71M to generate a summary or minutes of the contents of the dialogue between the user and the multiple artificial intelligences 71.

[0178] In addition, according to the present embodiment, the plurality of artificial intelligences 71A includes two or more artificial intelligences 71 playing different roles. Therefore, the user can receive meaningful information from the plurality of artificial intelligences 71A.

[0179] In addition, the multiple artificial intelligences 71A may include an artificial intelligence that plays the role of "devil's advocate," and the information processing system 10 may be configured to allow a user to specify the artificial intelligence 71A that plays the role of "devil's advocate" as a conversation partner.

[0180] The artificial intelligence 71A playing the role of "devil's advocate" is an artificial intelligence 71A that is set to always speak in a critical or refuting position against statements made by the user or other artificial intelligences 71A. By preparing such an artificial intelligence 71A, the user can realize deep thoughts on various themes through dialogue with the artificial intelligence 71A by designating the artificial intelligence 71A playing the role of "devil's advocate" as a conversation partner.

[0181] In addition, in this embodiment, the service provision screen G0 displays a chat screen G1 for each artificial intelligence 71A. This causes the display screen of the display device 61A to be partitioned. That is, in each of a plurality of areas corresponding to a plurality of chat screens G1, the content of the dialogue between the corresponding one artificial intelligence 71A and the user is displayed. That is, the information processing system 10 controls the display device 61A via the service provision screen G0 so that the content of the dialogue between the corresponding one artificial intelligence 71A of the plurality of artificial intelligences 71A and the user is displayed in each of a plurality of areas on the display screen.

[0182] Therefore, according to this embodiment, the contents of the dialogue between the plurality of artificial intelligences 71A and the user can be displayed in an easily understandable manner for the user.

[0183] According to this embodiment, each chat screen G1, G3 is configured as a movable display window. That is, the information processing system 10 is configured to accept a rearrangement operation on the multiple chat screens G1, G3 from the user through the input device 61B, and change the order of the multiple chat screens G1, G3 on the service provision screen G0 according to the rearrangement operation. Therefore, according to this embodiment, it is possible to provide the information processing system 10 that can display to the user a display screen that allows the user to more easily understand the contents of the conversation between the user and the multiple artificial intelligences 71.

[0184] According to this embodiment, the chat display screen G13 of each chat screen G1 displays the contents of the conversation between the user and the corresponding AI 71A by arranging the input sentences by the user and the AI ​​output sentences by the corresponding AI 71A in chronological order. Each chat screen G1 further displays an input field G15 for writing an input sentence to the corresponding AI 71A.

[0185] The information processing system 10 is configured to determine that a transfer instruction has been input when a statement (including an AI output statement) displayed as dialogue content on the chat display screen G13 is dragged and dropped into an input field G15 by a transfer operation, and to transmit the dragged statement to the artificial intelligence 71A (the artificial intelligence at the drop destination) corresponding to the input field G15 into which the statement was dropped.

[0186] When the dragged statement is sent to the artificial intelligence 71A at the drop destination, the dragged statement (AI output statement) is sent to the artificial intelligence 71A at the drop destination together with a portion of the dialogue content of the drag source that explains the context in which the dragged statement (AI output statement) was generated.

[0187] According to the information processing system 10 configured in this manner, the operability for the user regarding the transfer operation can be improved, and the user can obtain an appropriate response sentence from the dropped artificial intelligence 71A with a simple operation.

[0188] In addition, according to the present embodiment, an instruction to start an AI dialogue can be given by superimposing the chat screen G1, which provides good user operability in inputting an instruction to start an AI dialogue.

[0189] [Second embodiment] Next, an information processing system 10 according to a second embodiment will be described. The information processing system 10 according to the second embodiment is obtained by adding a new function to the information processing system 10 according to the first embodiment. The hardware configuration of the information processing system 10 according to the second embodiment is the same as that of the first embodiment.

[0190] Therefore, in the following, as a description of the second embodiment, configurations related to functions added to the information processing system 10 of the second embodiment will be selectively described. Configurations in the information processing system 10 of the second embodiment that are similar to those in the first embodiment will be denoted by the same reference numerals and descriptions thereof will be omitted.

[0191] In this embodiment, one or more artificial intelligences 71B having a scoring function are provided as at least one of the above-mentioned plurality of artificial intelligences 71A. The artificial intelligence 71B is the artificial intelligence 71A having a scoring function.

[0192] The artificial intelligence 71B is configured to score the AI ​​input sentence and generate and output an AI output sentence including the scoring result when the user instructs the AI ​​to score the sentence. That is, the artificial intelligence 71B is configured to generate and output an AI output sentence including an evaluation score for the AI ​​input sentence.

[0193] The information processing system 10 can prepare one or more artificial intelligences 71B on the AI ​​server 70 by inputting an instruction to create an artificial intelligence 71B to the AI ​​server 70. As shown in Fig. 16, the information processing system 10 can prepare one or more artificial intelligences 71B on the AI ​​server 70 by inputting, to the AI ​​server 70, a creation instruction including an instruction to "score an AI input sentence, and generate and output an AI output sentence including the scoring result, when instructed by a user to score / evaluate," together with information on a virtual personality.

[0194] When the information processing system 10 of this embodiment instructs the AI ​​server 70 to generate an artificial intelligence 71B, it does not specify explicit scoring criteria to the AI ​​server 70. Each artificial intelligence 71B operates to score an AI input sentence based on its own ideas without specifying a scoring criteria. An individual virtual personality is set for each artificial intelligence 71B. The scoring of the artificial intelligence 71B is influenced by the virtual personality. In other words, the AI ​​input sentence is scored according to different criteria between artificial intelligences 71B set with different virtual personalities.

[0195] FIG. 17 illustrates an example of the content of a conversation between a user and the artificial intelligence 71B, which is displayed on the chat display screen G13. According to this embodiment, the user can input a message such as "Please evaluate the idea I will now explain" as an AI input sentence to the artificial intelligence 71B through the input field G15. A specific example of an idea is an idea. After that, the user can input an AI input sentence explaining the idea to the artificial intelligence 71B through the input field G15.

[0196] In response to this AI input sentence, the artificial intelligence 71B outputs a response sentence including an evaluation score for the user's thought and details of the evaluation as an AI output sentence. This scoring function allows the user to obtain an objective evaluation of his / her own thought, such as an idea, through a dialogue with the artificial intelligence 71B.

[0197] In addition, the scoring function can be used not only in the dialogue between the user and the artificial intelligence 71B, but also in the dialogue between the artificial intelligences 71A and 71B. According to this embodiment, the processor 11 starts the AI ​​dialogue process (FIG. 13) (S230) when an overlapping operation is performed (Yes in S210), as in the first embodiment (see FIG. 12).

[0198] When a user provides the artificial intelligence 71A with a topic for a conversation, such as generating ideas, by inputting text (S231) to the artificial intelligence 71A, the artificial intelligence 71A's response to the topic is generated as an AI output sentence and displayed on the screen (S232, S233), and this AI output sentence is input to the artificial intelligence 71B (S234).

[0199] The artificial intelligence 71B scores the answer of the artificial intelligence 71A contained in this AI output statement, and the AI ​​output statement including the evaluation score and details of the evaluation is displayed on the screen and input to the artificial intelligence 71A (S235, S236).

[0200] In the artificial intelligence 71A, an AI output sentence including a new answer to the above theme is generated based on the evaluation score, and this AI output sentence is input to the artificial intelligence 71B. In this manner, a dialogue between the artificial intelligences 71A and 71B is repeated, in which the utterances of the artificial intelligence 71A are scored by the artificial intelligence 71B.

[0201] During execution of the AI ​​dialogue processing, the processor 11 executes in parallel the end control processing shown in Fig. 18. In the end control processing, the processor 11 judges whether the evaluation score by the artificial intelligence 71B is equal to or greater than a threshold value (S520) each time the AI ​​output sentence of the artificial intelligence 71A is scored (Yes in S510). Here, it is considered that the higher the evaluation, the higher the evaluation score.

[0202] When the evaluation score is less than the threshold (No in S520), processor 11 decides to continue the AI-AI dialogue processing (S530) and returns to the processing of S510. On the other hand, when the score of artificial intelligence 71B is equal to or greater than the threshold (Yes in S520), processor 11 decides to end the AI-AI dialogue processing (S540). Processor 11 ends the AI-AI dialogue processing (FIG. 13) when the screen display of the evaluation score is completed. Thereafter, processor 11 ends the end control processing.

[0203] In this manner, in this embodiment, the processor 11 causes the artificial intelligences 71A and 71B to repeatedly execute a dialogue until an answer of a predetermined quality is obtained on the topic specified by the user, and when an answer of the predetermined quality is obtained, ends the dialogue between the artificial intelligences 71A and 71B without instructions from the user.

[0204] According to this embodiment, the user can obtain an appropriate answer on a desired topic from the artificial intelligence 71A by using the above-mentioned scoring function. Therefore, the user can conveniently use the dialogue function between the artificial intelligences 71A and 71B.

[0205] [Third embodiment] Next, an information processing system 10 according to a third embodiment will be described. The information processing system 10 according to the third embodiment is obtained by adding a new function to the information processing system 10 according to the first embodiment. The hardware configuration of the information processing system 10 according to the third embodiment is the same as that of the first embodiment.

[0206] Therefore, in the following, as an explanation of the third embodiment, configurations related to functions added to the information processing system 10 of the first embodiment will be selectively explained. The same components in the information processing system 10 of the third embodiment as those in the first embodiment will be denoted by the same reference numerals and explanations thereof will be omitted. The additional functions explained below may be provided in the information processing system 10 of the second embodiment instead of the first embodiment.

[0207] The information processing system 10 of this embodiment has an automatic relay function as one of the cascade functions described as the first embodiment. In the automatic relay function, unlike the first embodiment, the AI ​​output sentence from the AI ​​71A of the upstream step is input to the AI ​​71A of the adjacent next step downstream, without presenting candidates for input sentences to the next step to the user.

[0208] That is, in the automatic relay function, the AI ​​output sentences from each AI 71A from the first step AI 71A to the final step AI 71A are input to the downstream adjacent next step AI 71A without the user having to select a candidate. This allows the user to automatically execute an intellectual task that can be decomposed into multiple steps by multiple AIs 71A without the user having to select a candidate.

[0209] An example of intellectual work includes writing an article as mentioned above, and an example of a deliverable includes an article. Another example of intellectual work includes MVVSS as a framework that systematically organizes the five elements that constitute the foundation of an organization. MVVSS consists of five elements: mission (M), vision (V), values ​​(V), spirit (S), and slogan (S). The automatic relay function can be used to formulate this MVVSS.

[0210] According to this embodiment, the automatic relay function does not have a function to allow the user to select a candidate, but is configured to be able to accept additional instructions for the artificial intelligence 71A. The user can perform an additional operation of instructions for the artificial intelligence 71A_2 to a transmission path of an AI output statement between any two adjacent artificial intelligences 71A_1 and 71A_2 (see FIG. 19) among the multiple artificial intelligences 71A from the first step artificial intelligence 71A to the final step artificial intelligence 71A.

[0211] According to this embodiment, the information processing system 10 is configured to display the chat screen G1 as a virtual card and to be able to perform an effect of turning the card over in response to a user operation as shown in Fig. 20. For example, the user can turn the card over by clicking the upper left area of ​​the chat screen G1.

[0212] The back of the card is provided with an input field G16 for the user to input instructions (hereinafter referred to as "additional instructions") to the corresponding artificial intelligence 71A. By inputting additional instructions to the artificial intelligence 71A in the input field G16, the user can indirectly control the AI ​​output statements generated by the artificial intelligence 71A.

[0213] For example, when creating an MVVSS using the automatic relay function, the user can input an additional instruction to limit the directionality of the MVVSS in the input field G16, thereby causing the artificial intelligence 71A to generate an MVVSS in the direction desired by the user using the automatic relay function. In other words, it is possible to prevent the artificial intelligence 71A from generating an MVVSS in a direction not desired by the user.

[0214] When an instruction to execute the automatic relay function is input in a state in which two or more artificial intelligences 71A from the first step to the final step used in the automatic relay function have been called on the service provision screen G0, the processor 11 starts the relay-related process shown in Fig. 21. When the relay-related process starts, the processor 11 sets the variable M to the value "1" (S610).

[0215] The processor 11 further accepts an input operation of additional instructions for the artificial intelligence 71A from the first step to the final step through the service provision screen G0 (S620). The user can optionally input additional instructions through the input field G16 for one or more of the artificial intelligences 71A from the first step to the final step.

[0216] Thereafter, similarly to S310, the processor 11 accepts text input from the user through the input field G15 to the artificial intelligence 71A for implementing the first step of the intellectual task (S630).

[0217] When text is input, processor 11 determines whether additional instructions have been input to artificial intelligence 71A of the Mth step (S640). If it is determined that additional instructions have not been input (No in S640), processor 11 inputs the input text to artificial intelligence 71A of the Mth step as an AI input sentence (S650).

[0218] If it is determined that an additional instruction has been input (Yes in S640), processor 11 inputs the input text with the additional instruction attached to it as an AI input sentence to artificial intelligence 71A of the Mth step (S655). As a result, processor 11 causes artificial intelligence 71A to generate an AI output sentence with the additional instruction given to artificial intelligence 71A in addition to the instructions given when artificial intelligence 71A of the Mth step was generated.

[0219] Then, the processor 11 displays the AI ​​input sentence to the artificial intelligence 71A of the Mth step, and the AI ​​output sentence received from the artificial intelligence 71A of the Mth step as a response to the AI ​​input sentence, in the form of a speech bubble on the chat display screen G13 of the chat screen G1 of the artificial intelligence 71A of the Mth step (S660).

[0220] Processor 11 further increments variable M by 1, i.e., updates variable M to a value incremented by 1 (S670). Thereafter, processor 11 determines whether an additional instruction has been input to artificial intelligence 71A of the Mth step (S680) prior to inputting the AI ​​output statement from artificial intelligence 71A of the (M-1)th step, which was received immediately before, to artificial intelligence 71A of the next step, i.e., the Mth step.

[0221] If it is determined that no additional instructions have been input (No at S680), processor 11 inputs the AI ​​output statement received from artificial intelligence 71A in the (M-1)th step as an AI input statement to artificial intelligence 71A in the Mth step (S690).

[0222] If it is determined that an additional instruction has been input (Yes at S680), processor 11 inputs the AI ​​output statement received from artificial intelligence 71A of the (M-1)th step, with the additional instruction attached, as an AI input statement to artificial intelligence 71A of the Mth step (S695).

[0223] Then, the processor 11 displays this AI input sentence and the AI ​​output sentence received from the Mth step artificial intelligence 71A as a response to the AI ​​input sentence in the form of a speech bubble on the chat display screen G13 of the chat screen G1 of the Mth step artificial intelligence 71A (S700).

[0224] After the process of S700, processor 11 determines whether or not the Mth step is the final step (S710). If processor 11 determines that the Mth step is not the final step (No in S710), it repeats the process of S670 to S710, thereby repeating the operation of inputting the AI ​​output sentence from artificial intelligence 71A of each step to artificial intelligence 71A of the next step. Then, if it determines that it is the final step (Yes in S710), processor 11 ends the automatic relay-related process.

[0225] According to this embodiment, the user can use the automatic relay function to have multiple artificial intelligences 71A automatically execute an intellectual task that can be decomposed into multiple steps, and obtain a product related to the intellectual task.

[0226] Although an example of utilizing the additional instruction with the automatic relay function has been described above, the utilization of the additional instruction is not limited to the automatic relay function. For example, the information processing system 10 may be configured to receive an additional instruction for each artificial intelligence 71A through the service provision screen G0, not limited to the automatic relay function. The reception may be realized by the method shown in FIG. 20. When an additional instruction is set, the processor 11 can attach the additional instruction when transmitting an AI input sentence to the corresponding artificial intelligence 71A. By setting such an additional instruction, the user can indirectly control the behavior of each artificial intelligence 71A.

[0227] [Other embodiments] The present disclosure is not limited to the above-described embodiment, and can adopt various aspects. For example, in the above embodiment, the information processing system 10 provides an interactive service as a web service, but a computer program that realizes the functions of the information processing system 10 may be installed on the information terminal 60, and the information terminal 60 may be configured to communicate with the AI ​​server 70 without going through the information processing system 10.

[0228] The function of one component in the above embodiment may be distributed among multiple components. The functions of multiple components may be integrated into one component. Some of the configurations of the above embodiment may be omitted. All aspects included in the technical idea specified by the wording of the claims are embodiments of the present disclosure.

[0229] [Technical idea disclosed in this specification] It can be understood that the present specification discloses the following technical ideas. [Item 1] A generated sentence acquisition unit configured to acquire generated sentences from each of a plurality of artificial intelligences; A display control unit configured to display the generated sentences acquired from each of the plurality of artificial intelligences on a display device; A sending unit configured to receive an input sentence from a user through an input device and send the input sentence to at least one of the plurality of artificial intelligences; Equipped with The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmission unit is When a first instruction is input from the user through the input device, the input sentence is sent to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, the input sentence is transmitted to the plurality of artificial intelligences. An information processing system configured as follows. [Item 2] the transmission unit is configured, when a third instruction is input from the user through the input device, to transmit a dialogue content between the user and a first artificial intelligence among the plurality of artificial intelligences, through the input sentence and the generated sentence, to a second artificial intelligence among the plurality of artificial intelligences, which is different from the first artificial intelligence; The generated sentence acquisition unit is configured to acquire, as the generated sentence, a response sentence to the dialogue content from the second artificial intelligence. Item 1. The information processing system according to item 1. [Item 3] Each of the first artificial intelligence and the second artificial intelligence is an artificial intelligence designated by the user from among the plurality of artificial intelligences. Item 2. An information processing system according to item 2. [Item 4] The transmission unit is configured to selectively transmit a part of the dialogue content between the user and the first artificial intelligence to the second artificial intelligence when the third instruction is input. Item 2 or Item 3. The information processing system according to item 2 or 3. [Item 5] The part of the dialogue content includes the latest input sentence and the latest generated sentence exchanged between the user and the first artificial intelligence, Item 4. An information processing system according to item 4. [Item 6] The transmission unit is configured to transmit the generated sentence obtained from a first artificial intelligence among the plurality of artificial intelligences to a second artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence, and transmit the generated sentence obtained from the second artificial intelligence to the first artificial intelligence, thereby causing the first artificial intelligence and the second artificial intelligence to interact with each other. Item 1. The information processing system according to item 1. [Item 7] Each of the first artificial intelligence and the second artificial intelligence is an artificial intelligence designated by the user from among the plurality of artificial intelligences. Item 6. The information processing system according to item 6. [Item 8] The transmission unit is configured, when a fifth instruction is input from the user through the input device, to transmit the generated sentence obtained from a first artificial intelligence among the plurality of artificial intelligences to a second artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence, and to transmit the generated sentence obtained from the second artificial intelligence to a third artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence and the second artificial intelligence. Item 1. The information processing system according to item 1. [Item 9] The transmission unit is Transmitting the content of the dialogue between the user and each of the plurality of artificial intelligences to a specific artificial intelligence different from the plurality of artificial intelligences; When a sixth instruction is input from the user through the input device, the input sentence is transmitted to the specific artificial intelligence. It is configured as follows: the generated sentence acquisition unit acquires, from the specific artificial intelligence, a generated sentence based on the input sentence transmitted to the specific artificial intelligence; The display control unit is configured to display the generated sentence acquired from the specific artificial intelligence on the display device. An information processing system according to any one of items 1 to 8. [Item 10] The plurality of artificial intelligences includes two or more artificial intelligences playing different roles. An information processing system according to any one of items 1 to 9. [Item 11] The two or more artificial intelligences include an artificial intelligence that plays devil's advocate. Item 11. The information processing system according to item 10. [Item 12] The display control unit controls the display device to display a display screen including a plurality of partitioned areas on the display device, and to display, in each of the plurality of areas on the display screen, the sentence generated by a corresponding one of the plurality of artificial intelligences. An information processing system according to any one of items 1 to 11. [Item 13] The display control unit is configured to receive a user operation on the plurality of areas through the input device, and to change an order of the plurality of areas on the display screen in accordance with the user operation. Item 13. The information processing system according to item 12. [Item 14] the display control unit controls the display device to display a display screen including a plurality of partitioned areas on the display device, and to display, in each of the plurality of areas on the display screen, the sentence generated by a corresponding one of the plurality of artificial intelligences; Each of the plurality of areas further displays an input field for writing the input sentence for the corresponding one of the artificial intelligences; the transmission unit, on condition that the generated sentence displayed in a first area of ​​the plurality of areas is dragged and dropped into the input field of a second area of ​​the plurality of areas, transmits the dragged generated sentence to an artificial intelligence corresponding to the input field into which the generated sentence has been dropped; The generated sentence acquisition unit is configured to acquire a response sentence to the dragged generated sentence from an artificial intelligence corresponding to the input field into which the generated sentence is dropped. Item 1. The information processing system according to item 1. [Item 15] In each of the plurality of areas, the dialogue between the user and the corresponding one of the artificial intelligences is displayed by arranging the input sentence by the user and the generated sentence by the corresponding one of the artificial intelligences; Item 15. The information processing system according to item 14, wherein the transmission unit is configured to transmit the dragged generated sentence, together with a portion of the dialogue content explaining the context in which the dragged generated sentence was generated, to an artificial intelligence corresponding to the input field into which the generated sentence was dropped. [Item 16] the display control unit controls the display device to display a plurality of display windows on the display device and to display, in each of the plurality of display windows, the sentence generated by a corresponding one of the plurality of artificial intelligences; The transmission unit is configured to determine that the fourth instruction has been input on condition that an operation of superimposing a display window associated with the first artificial intelligence, among the plurality of display windows, on a display window associated with the second artificial intelligence has been performed through the input device, and to cause the first artificial intelligence and the second artificial intelligence to interact with each other. Item 6. The information processing system according to item 6. [Item 17] The transmission unit is configured to be able to receive additional instructions for at least one of the second artificial intelligence and the third artificial intelligence from the user through the input device, and is configured to input the additional instructions received for the second artificial intelligence to the second artificial intelligence when transmitting the generated sentence obtained from the first artificial intelligence to the second artificial intelligence, and to input the additional instructions received for the third artificial intelligence to the third artificial intelligence when transmitting the generated sentence obtained from the second artificial intelligence to the third artificial intelligence. Item 9. The information processing system according to item 8. [Item 18] The transmission unit is configured, when the fourth instruction is input, to cause the first artificial intelligence and the second artificial intelligence to interact with each other until at least one of the generated sentence acquired from a first artificial intelligence and the generated sentence acquired from the second artificial intelligence among the plurality of artificial intelligences satisfies a predetermined condition, and to end the interaction between the first artificial intelligence and the second artificial intelligence when the predetermined condition is satisfied. Item 6. The information processing system according to item 6. [Item 19] one of the first artificial intelligence and the second artificial intelligence is configured to score the generated sentence input from the other of the first artificial intelligence and the second artificial intelligence; The transmission unit is configured to determine that the predetermined condition is satisfied when the score given to the generated sentence by the scoring is equal to or greater than a threshold, and to terminate the dialogue between the first artificial intelligence and the second artificial intelligence. Item 19. The information processing system according to item 18. [Item 20] A computer program for causing a computer to function as the generated sentence acquisition unit, the display control unit, and the transmission unit included in the information processing system according to any one of items 1 to 19. [Item 21] 1. A computer-implemented information processing method, comprising: Obtaining generated sentences from each of a plurality of artificial intelligences; displaying the generated sentences obtained from each of the plurality of artificial intelligences on a display device; Acquiring an input sentence from a user through an input device, and transmitting the input sentence to at least one of the plurality of artificial intelligences; Including, The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmitting step includes: When a first instruction is input from the user through the input device, transmitting the input sentence to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, transmitting the input sentence to the plurality of artificial intelligences; An information processing method comprising: [Explanation of symbols]

[0230] 10...information processing system, 11...processor, 13...memory, 15...storage, 19...communication interface, 60...information terminal, 61...user interface, 61A...display device, 61B...input device, 70...AI server, 71, 71A, 71A_1, 71A_2, 71B...artificial intelligence, 71M...master, G0...service provision screen, G1...chat screen, G3...master screen, G11, G31...profile image, G13, G33...chat display screen, G15, G16, G35...input field, G18...send button, G19...mass send button, G37...operation button group, G371...send button, G373...call button, G375...memo pad button, G379...output button.

Claims

1. A generated sentence acquisition unit configured to acquire generated sentences from each of a plurality of artificial intelligences; A display control unit configured to display the generated sentences acquired from each of the plurality of artificial intelligences on a display device; A sending unit configured to receive an input sentence from a user through an input device and send the input sentence to at least one of the plurality of artificial intelligences; Equipped with The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmission unit is When a first instruction is input from the user through the input device, the input sentence is sent to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, the input sentence is transmitted to the plurality of artificial intelligences; When a third instruction is input from the user through the input device, the content of the dialogue between the user and a first artificial intelligence among the plurality of artificial intelligences through the input sentence and the generated sentence is transmitted to a second artificial intelligence among the plurality of artificial intelligences, the second artificial intelligence being different from the first artificial intelligence. It is configured as follows: The generated sentence acquisition unit is configured to acquire, as the generated sentence, a response sentence to the dialogue content from the second artificial intelligence. Information processing system.

2. Each of the first artificial intelligence and the second artificial intelligence is an artificial intelligence designated by the user from among the plurality of artificial intelligences.

2. The information processing system according to claim 1.

3. The transmission unit is configured to selectively transmit a part of the dialogue content between the user and the first artificial intelligence to the second artificial intelligence when the third instruction is input.

2. The information processing system according to claim 1.

4. A generated sentence acquisition unit configured to acquire generated sentences from each of a plurality of artificial intelligences; A display control unit configured to display the generated sentences acquired from each of the plurality of artificial intelligences on a display device; A sending unit configured to receive an input sentence from a user through an input device and send the input sentence to at least one of the plurality of artificial intelligences; Equipped with The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmission unit is When a first instruction is input from the user through the input device, the input sentence is sent to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, the input sentence is transmitted to the plurality of artificial intelligences. The system is further configured as follows: Transmitting the content of the dialogue between the user and each of the plurality of artificial intelligences to a specific artificial intelligence different from the plurality of artificial intelligences; When a third instruction is input from the user through the input device, the input sentence is transmitted to the specific artificial intelligence. It is configured as follows: the generated sentence acquisition unit acquires, from the specific artificial intelligence, a generated sentence based on the input sentence transmitted to the specific artificial intelligence; The display control unit is configured to display the generated sentence acquired from the specific artificial intelligence on the display device. Information processing system.

5. A generated sentence acquisition unit configured to acquire generated sentences from each of a plurality of artificial intelligences; A display control unit configured to display the generated sentences acquired from each of the plurality of artificial intelligences on a display device; A sending unit configured to receive an input sentence from a user through an input device and send the input sentence to at least one of the plurality of artificial intelligences; Equipped with The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmission unit is When a first instruction is input from the user through the input device, the input sentence is sent to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, the input sentence is transmitted to the plurality of artificial intelligences. It is configured as follows: the display control unit is configured to control the display device to display a display screen including a plurality of partitioned areas on the display device, to display in each of the plurality of areas the sentence generated by a corresponding one of the plurality of artificial intelligences, and to control the display device to display in each of the plurality of areas an input field for writing the input sentence for the corresponding one of the artificial intelligences; the transmission unit is configured to transmit, on condition that the generated sentence displayed in a first area of ​​the plurality of areas is dragged and dropped into the input field of a second area of ​​the plurality of areas, the dragged generated sentence to an artificial intelligence corresponding to the input field into which the generated sentence has been dropped; The generated sentence acquisition unit is configured to acquire a response sentence to the dragged generated sentence from an artificial intelligence corresponding to the input field into which the generated sentence is dropped. Information processing system.

6. In each of the plurality of areas, the dialogue between the user and the corresponding one of the artificial intelligences is displayed by arranging the input sentence by the user and the generated sentence by the corresponding one of the artificial intelligences; The information processing system of claim 5, wherein the transmission unit is configured to transmit the dragged generated sentence to an artificial intelligence corresponding to the input field into which the generated sentence was dropped, together with a portion of the dialogue content explaining the context in which the dragged generated sentence was generated.

7. A generated sentence acquisition unit configured to acquire generated sentences from each of a plurality of artificial intelligences; A display control unit configured to display the generated sentences acquired from each of the plurality of artificial intelligences on a display device; A sending unit configured to receive an input sentence from a user through an input device and send the input sentence to at least one of the plurality of artificial intelligences; Equipped with The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmission unit is When a first instruction is input from the user through the input device, the input sentence is sent to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, the input sentence is transmitted to the plurality of artificial intelligences; configured to, when a third instruction is input from the user through the input device, transmit the generated sentence obtained from a first artificial intelligence among the plurality of artificial intelligences to a second artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence, and transmit the generated sentence obtained from the second artificial intelligence to a third artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence and the second artificial intelligence; An additional instruction for at least one of the second artificial intelligence and the third artificial intelligence is received from the user through the input device, the additional instruction received for the second artificial intelligence is input to the second artificial intelligence when the generated sentence obtained from the first artificial intelligence is transmitted to the second artificial intelligence, and the additional instruction received for the third artificial intelligence is input to the third artificial intelligence when the generated sentence obtained from the second artificial intelligence is transmitted to the third artificial intelligence. It is configured as follows: Information processing system.

8. The plurality of artificial intelligences includes two or more artificial intelligences playing different roles. The information processing system according to any one of claims 1 to 7.

9. The two or more artificial intelligences include an artificial intelligence that plays devil's advocate.

9. The information processing system according to claim 8.

10. A computer program for causing a computer to function as the generated sentence acquisition unit, the display control unit, and the transmission unit provided in the information processing system according to any one of claims 1 to 7.

11. 1. A computer-implemented information processing method, comprising: Obtaining generated sentences from each of a plurality of artificial intelligences; displaying the generated sentences obtained from each of the plurality of artificial intelligences on a display device; Acquiring an input sentence from a user through an input device, and transmitting the input sentence to at least one of the plurality of artificial intelligences; Including, The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmitting step includes: When a first instruction is input from the user through the input device, transmitting the input sentence to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, transmitting the input sentence to the plurality of artificial intelligences; When a third instruction is input from the user through the input device, transmitting the dialogue content between the user and a first artificial intelligence among the plurality of artificial intelligences through the input sentence and the generated sentence to a second artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence; Including, The acquiring includes acquiring, from the second artificial intelligence, a response sentence to the dialogue content as the generated sentence. Information processing methods.

12. 1. A computer-implemented information processing method, comprising: Obtaining generated sentences from each of a plurality of artificial intelligences; displaying the generated sentences obtained from each of the plurality of artificial intelligences on a display device; Acquiring an input sentence from a user through an input device, and transmitting the input sentence to at least one of the plurality of artificial intelligences; Including, The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmitting step includes: When a first instruction is input from the user through the input device, transmitting the input sentence to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, transmitting the input sentence to the plurality of artificial intelligences; Transmitting dialogue content between the user and each of the plurality of artificial intelligences to a specific artificial intelligence different from the plurality of artificial intelligences; When a third instruction is input from the user through the input device, transmitting the input sentence to the specific artificial intelligence; Including, The acquiring step includes acquiring, from the specific artificial intelligence, a generated sentence based on the input sentence transmitted to the specific artificial intelligence; The displaying includes displaying the generated sentence obtained from the specific artificial intelligence on the display device. Information processing methods.

13. 1. A computer-implemented information processing method, comprising: Obtaining generated sentences from each of a plurality of artificial intelligences; displaying the generated sentences obtained from each of the plurality of artificial intelligences on a display device; Acquiring an input sentence from a user through an input device, and transmitting the input sentence to at least one of the plurality of artificial intelligences; Including, The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmitting step includes: When a first instruction is input from the user through the input device, transmitting the input sentence to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, transmitting the input sentence to the plurality of artificial intelligences; Including, The displaying includes controlling the display device to display a display screen including a plurality of partitioned areas on the display device, and to display the sentence generated by a corresponding one of the plurality of artificial intelligences in each of the plurality of areas on the display screen, and to control the display device to display an input field for writing the input sentence for the corresponding one of the plurality of artificial intelligences in each of the plurality of areas, said transmitting includes, on condition that the generated sentence displayed in a first area of ​​said plurality of areas is dragged and dropped into the input field of a second area of ​​said plurality of areas, transmitting the dragged generated sentence to an artificial intelligence corresponding to the input field into which the generated sentence has been dropped; The acquiring includes acquiring a response sentence to the dragged generated sentence from an artificial intelligence corresponding to the input field into which the generated sentence is dropped. Information processing methods.

14. 1. A computer-implemented information processing method, comprising: Obtaining generated sentences from each of a plurality of artificial intelligences; displaying the generated sentences obtained from each of the plurality of artificial intelligences on a display device; Acquiring an input sentence from a user through an input device, and transmitting the input sentence to at least one of the plurality of artificial intelligences; Including, The generated sentence includes a response sentence to the input sentence and is generated by a corresponding artificial intelligence; The transmitting step includes: When a first instruction is input from the user through the input device, transmitting the input sentence to one of the plurality of artificial intelligences designated by the user; When a second instruction is input from the user through the input device, transmitting the input sentence to the plurality of artificial intelligences; When a third instruction is input from the user through the input device, transmitting the generated sentence obtained from a first artificial intelligence among the plurality of artificial intelligences to a second artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence, and transmitting the generated sentence obtained from the second artificial intelligence to a third artificial intelligence among the plurality of artificial intelligences that is different from the first artificial intelligence and the second artificial intelligence; receiving additional instructions for at least one of the second artificial intelligence and the third artificial intelligence from the user through the input device, inputting the additional instructions received for the second artificial intelligence into the second artificial intelligence when transmitting the generated sentence obtained from the first artificial intelligence to the second artificial intelligence, and inputting the additional instructions received for the third artificial intelligence into the third artificial intelligence when transmitting the generated sentence obtained from the second artificial intelligence to the third artificial intelligence; An information processing method comprising:

Images