Artificial intelligence system and program of artificial intelligence system

Abstract

To provide an artificial intelligence system which allows a user to transmit instruction command information to pre-trained artificial intelligence means to communicate with each other, while checking a content of a page of an uploaded document file or a page in predetermined information based on URL information.SOLUTION: An artificial intelligence system 100 includes a user terminal 110 and servers 120, 130. A browser 111 of a user terminal displays a talk screen 112 which can communicate with pre-trained artificial intelligence means 131 of the server 130. When operation to designate a document file DF or operation to designate URL information, which is location information on predetermined information, is performed on the browser, the user terminal uploads the document file or the URL information to the server 120. The server generates talk screen data including a page of the document file or a page of the predetermined information, as a content to be displayed, based on the document file or the URL information, and transmits the talk screen data to the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an artificial intelligence system that includes a user terminal and a server, in which the user terminal displays or outputs audio based on the server, and a program for the system. [Background technology]

[0002] 2. Description of the Related Art Conventionally, server systems that provide functions such as saving and displaying files uploaded by users are known (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-66473 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional server system described above, files uploaded to cloud storage could only be viewed, downloaded, and edited by users other than the user who uploaded the file, depending on the permissions granted to them. In order to know the contents of the file, however, the user had to open the file and read it himself / herself. If the file contained a large amount of information, such as many pages, this took time, making it difficult to grasp the contents to a certain extent in a short period of time.

[0005] Therefore, the present invention solves the problems of the prior art as described above, and the object of the present invention is to provide an artificial intelligence system and a program therefor in which a user can view the contents of an uploaded document file page or a page of specified information based on URL information and interact with a pre-trained artificial intelligence means by sending instruction and command information such as creating a summary, pointing out problems, pointing out areas for improvement, and asking questions about the information. [Means for solving the problem]

[0006] The invention according to claim 1 is an artificial intelligence system comprising a user terminal and a server, the user terminal displaying or outputting audio based on the server, the browser of the user terminal displaying a talk screen that can freely communicate with the pre-trained artificial intelligence means of the server, when an operation to specify a document file or an operation to specify URL information that is location information for specific information is performed in the browser of the user terminal, the user terminal uploads the document file or URL information to the server, the server creates talk screen data including a page of the document file or a page of the specific information in the display content based on the received document file or URL information and transmits it to the user terminal, the user terminal displays the received talk screen data in the browser, when an operation to input / send instruction command information is performed in the browser of the user terminal, the user terminal transmits the instruction command information to the server, the server uses the pre-trained artificial intelligence means to generate text data for the content information specified by the loaded document file or URL information based on the received instruction command information, and transmits the generated text data obtained by the execution to the user terminal, the user terminal displays the received generated text data in the browser or outputs it as audio.

[0007] The invention of claim 2 further solves the above-mentioned problem by being configured in such a way that, in addition to the configuration of the artificial intelligence system described in claim 1, when the pre-trained artificial intelligence means generates text data based on instruction command information, the pre-trained artificial intelligence means generates basis information regarding which page or part of the content information identified by the loaded document file or URL information the text data is based on, the server transmits the generated text data and basis information to a user terminal, and the user terminal displays the generated text data and basis information in a browser.

[0008] The invention of claim 3 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 2, linking a text portion of the basis information received in the browser from the server to a portion corresponding to the basis information on the page of the document file or the page of specified information displayed on the talk screen, and when an operation is performed on the text portion of the basis information in the browser, the browser displays a portion corresponding to the basis information on the page of the document file or the page of specified information on the talk screen.

[0009] The invention of claim 4 further solves the above-mentioned problem by being configured in such a way that, in addition to the configuration of the artificial intelligence system described in any one of claims 1 to 3, when a first predetermined operation is performed on the talk screen of the browser, the user terminal sends instruction command information to a server to create a table of contents, and the server uses a pre-trained artificial intelligence means based on the received instruction command information to create a table of contents to generate table of contents information for the content information identified by the loaded document file or URL information, and sends the generated table of contents information obtained by the execution to the user terminal, and the user terminal displays the received generated table of contents information on the browser.

[0010] The invention of claim 5 further solves the above-mentioned problem by being configured in such a way that, in addition to the configuration of the artificial intelligence system described in claim 4, when a second specified operation is performed on the talk screen of the browser, the user terminal sends instruction command information to the server to create a page-by-page summary, and the server, based on the received instruction command information to create a page-by-page summary, uses a pre-trained artificial intelligence means to generate page-by-page summary information for the content information identified by the loaded document file or URL information, and transmits the generated page-by-page summary information obtained by the execution to the user terminal, and the user terminal displays the received generated page-by-page summary information on the browser.

[0011] The invention of claim 6 further solves the above-mentioned problem by being configured in such a way that, in addition to the configuration of the artificial intelligence system described in claim 5, when a third specified operation is performed on the talk screen of the browser, the server adds generated table of contents information, generated page-by-page summary information, instruction command information on the talk screen, and generated text data to the page of the document file or the page of specified information displayed in the browser of the user terminal, and downloads them to the user terminal.

[0012] The invention according to claim 7 further comprises, in addition to the configuration of the artificial intelligence system according to claim 6, when the user terminal uploads a document file or URL information to a server, the browser opens a sharing setting window in which other user identification information can be freely input, and the user terminal transmits the other user identification information to the server based on the input / setting operation of the other user identification information; The above-mentioned problem is further solved by being configured such that the server allows sharing of talk screen data between the user and other users based on the received other user identification information, the talk screen data including in its display content a page of a document file or a page of specified information based on the received document file or URL information.

[0013] The invention of claim 8 further solves the above-mentioned problem by being configured in such a way that, in addition to the configuration of the artificial intelligence system described in claim 7, when the server creates talk screen data, the pre-trained artificial intelligence means reads a page of a document file or a page of specified information based on a document file or URL information, generates multiple pieces of related question information in which information related to the content information identified by the read document file or URL information serves as answer information, and the server transmits the generated question information to a user terminal; or, when the pre-trained artificial intelligence means generates text data based on instruction command information, the pre-trained artificial intelligence means generates multiple pieces of related question information in which information related to the content information identified by the read document file or URL information serves as answer information, and the server transmits the generated text data and the generated question information in that order to the user terminal.

[0014] The invention according to claim 9 is a program for an artificial intelligence system including a user terminal and a server, the user terminal displaying or outputting audio based on the server, the program including a talk screen display step in which the browser of the user terminal displays a talk screen that can freely communicate with the pre-trained artificial intelligence means of the server, a designation operation determination step in which it is determined whether or not an operation for designating a document file or an operation for designating URL information that is location information for predetermined information has been performed in the browser of the user terminal, an upload step in which the user terminal uploads the document file or the URL information to the server when the designation operation has been performed, a talk screen data transmission step in which the server creates talk screen data including a page of the document file or a page of the predetermined information in the display content based on the received document file or URL information, and transmits the talk screen data to the user terminal, and The above-mentioned problem is solved by having a talk screen data display step in which a user terminal displays the received talk screen data on a browser; a command input / transmission operation determination step in which a command input / transmission operation is determined in the browser of the user terminal; a command transmission step in which the user terminal transmits command information to a server when the input / transmission operation is performed; a text data generation step in which the server uses a pre-trained artificial intelligence means based on the received command information to generate text data about the content information specified by the loaded document file or URL information; a generated data transmission step in which the server transmits the generated text data obtained by the execution to the user terminal; and a generated data display / audio output step in which the user terminal displays the received generated text data on a browser or outputs it as audio. Effect of the Invention

[0015] The artificial intelligence system of the present invention is equipped with a user terminal and a server, which not only enables the user terminal to display or output audio based on the server, but also provides the following unique effects.

[0016] According to the artificial intelligence system of the invention of claim 1, the contents of the page of the uploaded document file or the page of specified information based on the URL information are displayed on the talk screen, so that the user can view the contents and send instruction and command information to the pre-trained artificial intelligence means, such as creating a summary, pointing out problems, pointing out areas for improvement, and asking questions about the information, to interact with the pre-trained artificial intelligence means.

[0017] According to the artificial intelligence system of the invention of claim 2, in addition to the effect achieved by the invention of claim 1, not only the generated text data but also the basis information is displayed in the browser, so that the user can easily check the accuracy and reliability (veracity) of the generated text data by referring to the content information identified by the original document file or URL information based on the basis information. In other words, the user can easily confirm which part and what the text data was generated based on, without simply looking at the generated text data and accepting the contents of the generated text data.

[0018] According to the artificial intelligence system of the invention of claim 3, in addition to the effect achieved by the invention of claim 2, the part that the user wants to check is displayed with just a click, so that the user can easily check the part that he or she wants to check in the content information (specified information) identified by the original document file or URL information.

[0019] According to the artificial intelligence system of the invention of claim 4, in addition to the effect of any one of the inventions of claims 1 to 3, table of contents information is generated and displayed in the browser, so that the user can easily understand what is written and in what order.

[0020] According to the artificial intelligence system of the invention of claim 5, in addition to the effect of the invention of claim 4, summary information for each page is generated and displayed in the browser, so that the user can easily understand what is written on each page.

[0021] According to the artificial intelligence system of the invention of claim 6, in addition to the effect achieved by the invention of claim 5, not only the pages of the document file or the pages of the specified information but also the table of contents information, summary information for each page, and the interaction between the pre-trained artificial intelligence means and the user are downloaded as a set, so that the user can save a complete record of the pages of the document file or the pages of the specified information.

[0022] According to the artificial intelligence system of the invention of claim 7, in addition to the effects achieved by the invention of claim 6, the content uploaded by a user is shared with other users, allowing documents to be shared with other users and allowing other users to interact with the pre-trained artificial intelligence means regarding the contents of the document.

[0023] According to the artificial intelligence system of the invention of claim 8, in addition to the effect achieved by the invention of claim 7, multiple anticipated question information regarding content information identified by a document file or URL information is generated and displayed in a browser, so that a user can first select one of the multiple question information and interact with the pre-trained artificial intelligence means to easily deepen his / her understanding of the content information identified by the document file or URL information loaded by the pre-trained artificial intelligence means without having to read all of it himself / herself.

[0024] According to the program of the artificial intelligence system of the invention of claim 9, similar to the effect achieved by the invention of claim 1, the contents of the page of the uploaded document file or the page of specified information based on the URL information are displayed on the talk screen, so that the user can view the contents and send instruction and command information to the pre-trained artificial intelligence means, such as creating a summary, pointing out problems, pointing out areas for improvement, and asking questions about the information, to interact with the pre-trained artificial intelligence means. [Brief description of the drawings]

[0025] [Figure 1] FIG. 1 is a diagram showing the concept of an artificial intelligence system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a chart showing an example of the operation of the artificial intelligence system according to the embodiment of the present invention. [Diagram 3] A figure showing an example of an AI document screen as a talk screen of a browser on a user terminal of an artificial intelligence system according to an embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing an example of a document registration window of a browser on a user terminal of an artificial intelligence system according to an embodiment of the present invention. [Diagram 5] FIG. 2 is a diagram showing an example of a document file displayed on an AI document screen of an artificial intelligence system according to an embodiment of the present invention. [Figure 6] A figure showing an example of interaction between a user and a pre-trained artificial intelligence means on the AI ​​document screen of the artificial intelligence system according to an embodiment of the present invention. [Figure 7] A figure showing the portion of a document file corresponding to basis information displayed on the AI ​​document screen of an artificial intelligence system according to an embodiment of the present invention. [Figure 8] FIG. 13 shows an example of an exchange when a question with little relevance to a document file is asked on the AI ​​document screen of the artificial intelligence system according to an embodiment of the present invention. [Figure 9] FIG. 13 is a diagram showing the state when the table of contents generation button is operated on the AI ​​document screen of the artificial intelligence system according to an embodiment of the present invention. [Figure 10] FIG. 13 is a diagram showing the state when the page-by-page summary generation button is operated on the AI ​​document screen of the artificial intelligence system according to an embodiment of the present invention. [Figure 11] A figure showing an example of a download file when the document download button is operated on the AI ​​document screen of the artificial intelligence system according to an embodiment of the present invention. [Figure 12] A figure showing an example of a sharing settings window of a browser on a user terminal of an artificial intelligence system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0026] The artificial intelligence system of the present invention includes a user terminal and a server, and the browser of the user terminal displays a talk screen that can freely communicate with the pre-trained artificial intelligence means of the server. When an operation to specify a document file or an operation to specify URL information that is location information for predetermined information is performed in the browser of the user terminal, the user terminal uploads the document file or the URL information to the server, and the server creates talk screen data including a page of the document file or a page of the predetermined information in the display content based on the received document file or URL information and transmits the created talk screen data to the user terminal. The user terminal displays the received talk screen data in the browser, and the browser of the user terminal displays instruction command information. The specific implementation may be any as long as, when information is input / transmitted, the user terminal transmits instruction and command information to the server, the server uses the pre-trained artificial intelligence means based on the received instruction and command information to generate text data for the content information specified by the loaded document file or URL information, and transmits the generated text data obtained through execution to the user terminal, and the user terminal displays the received generated text data in a browser or outputs it as audio, thereby allowing the user to view the content and send instruction and command information to the pre-trained artificial intelligence means to create a summary, point out problems, point out areas for improvement, ask questions about the information, etc., to interact with the user. The program for the artificial intelligence system of the present invention includes a talk screen display step in which the browser of the user terminal displays a talk screen that can freely communicate with the pre-trained artificial intelligence means of the server, a designation operation determination step in which it is determined whether or not an operation of designating a document file or an operation of designating URL information that is location information for predetermined information has been performed in the browser of the user terminal, an upload step in which the user terminal uploads the document file or the URL information to the server when a designation operation has been performed, a talk screen data transmission step in which the server creates talk screen data including a page of the document file or a page of the predetermined information in the display content based on the received document file or URL information and transmits the talk screen data to the user terminal, a talk screen data display step in which the user terminal displays the received talk screen data in the browser, and an input / transmission operation of instruction / command information is performed in the browser of the user terminal. The specific implementation of the system may be any as long as it has an instruction / command input / send operation determination step for determining whether or not an input / send operation has occurred, an instruction / command sending step for the user terminal to send instruction / command information to the server when an input / send operation has occurred, a text data generation step for the server to generate text data about the content information specified by the loaded document file or URL information using the pre-trained artificial intelligence means based on the received instruction / command information, a generated data sending step for the server to send the generated text data obtained by the execution to the user terminal, and a generated data display / audio output step for the user terminal to display the received generated text data in a browser or output it as audio, thereby allowing the user to view the content and send instruction / command information to the pre-trained artificial intelligence means to create a summary, point out problems, point out areas for improvement, ask questions about the information, etc., to interact with the system.

[0027] For example, the user terminal may be a desktop personal computer terminal, a notebook personal computer terminal, a smartphone terminal, a tablet terminal, or the like that sends and receives information, and may be any terminal that can be freely connected to a server via a communication network including a wide area network, such as the Internet, a local network, or a telephone line. Also, the servers may each be a single server or multiple servers on a cloud. The pre-trained artificial intelligence means may be composed of an interactive model, also known as a large-scale language model, such as ChatGPT (Generative Pre-trained Transformer) (hereinafter referred to as ChatGPT), and may be configured to be installed on one server or multiple servers on the cloud. In addition, a document file refers to an electronic data file whose contents include character information, and the data file format may be a simple text data format, a document data format, a cell-type spreadsheet file format, a pixel-type image file format such as a photo or video, etc., which allows characters to be read using an image recognition means or which allows characters to be read using a voice recognition means, or any format that allows characters to be directly recognized or indirectly recognized by converting voice to characters. The characters also include the source code of a program. Furthermore, the URL information (Uniform Resource Locator information), which is the location information for the specified information, may be any information that can identify a website page in HTML format or a document file as the specified information obtained by accessing a web server. EXAMPLES

[0028] An artificial intelligence system 100 according to an embodiment of the present invention will be described below with reference to FIGS. Here, FIG. 1 is a diagram showing the concept of an artificial intelligence system 100 which is an embodiment of the present invention, FIG. 2 is a chart diagram showing an example of the operation of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 3 is a diagram showing an example of an AI document screen 112 as a talk screen of a browser 111 of a user terminal 110 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 4(A) is a diagram showing an example of specifying a document file DF in a document registration window 116 of a browser 111 of a user terminal 110 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 4(B) is a diagram showing an example of specifying specific information by URL information in a document registration window 116 of a browser 111 of a user terminal 110 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 5 is a diagram showing an example of a document file DF displayed on an AI document screen 112 of the artificial intelligence system 100 which is an embodiment of the present invention, and FIG. 6 is a diagram showing an interaction between a user of the AI ​​document screen 112 of the artificial intelligence system 100 which is an embodiment of the present invention and a chat GPT which is an example of a pre-trained artificial intelligence means 131. FIG. 7 is a diagram showing an example of a document file DF corresponding to the evidence information PF displayed on the AI ​​document screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention. FIG. 8 is a diagram showing an example of an exchange when a question having a low relevance to the document file DF is asked on the AI ​​document screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention. FIG. 9 is a diagram showing a state when the table of contents generation button 114a is operated on the AI ​​document screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention. FIG. 10 is a diagram showing a state when the page-by-page summary generation button 114b is operated on the AI ​​document screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention. FIG. 11 is a diagram showing an example of a downloaded file DL when the document download button 114c is operated on the AI ​​document screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention. FIG. 12 is a diagram showing an example of a sharing settings window 117 of the browser 111 of the user terminal 110 of the artificial intelligence system 100 according to an embodiment of the present invention.

[0029] As shown in FIG. 1, an artificial intelligence system 100 according to an embodiment of the present invention includes a user terminal 110, and a first server 120 and a second server 130 as examples of servers. Of these, the first server 120 has a database 121 and a bot 122, and the database 121 has information on the web page of the AI ​​document screen 112, which is the talk screen of the artificial intelligence system 100 displayed by the browser 111 of the user terminal 110. On the other hand, the second server 130 has a chat GPT, which is an example of a pre-trained artificial intelligence means 131.

[0030] In this embodiment, as an example, the first server 120 and the second server 130 are configured as separate entities, but they may be configured as a single shared server. Then, the user terminal 110 displays the information on the browser 111 or outputs the information as audio based on the information from the first server 120. Also, a user terminal 110 is provided to communicate with a second server 130 via a bot 122 of the first server 120 .

[0031] More specifically, when a user logs in to the artificial intelligence system 100 using the browser 111 of the user terminal 110, the browser 111 of the user terminal 110 displays the AI ​​document screen 112, which is a talk screen that can be used to freely interact with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, via the first server 120. Then, when an operation is performed in browser 111 of user terminal 110 to specify document file DF or URL information which is location information for specified information, user terminal 110 uploads the document file DF or the URL information to first server 120.

[0032] Then, the first server 120 creates talk screen data including a page of the document file DF or a page of predetermined information in the display content based on the received document file DF or URL information, and transmits the talk screen data to the user terminal 110 as an HTTP response. Then, the user terminal 110 displays the received talk screen data on the browser 111 as an AI document screen 112.

[0033] Furthermore, when an input / transmission operation of instruction command information PT is performed on the browser 111 of the user terminal 110 , the user terminal 110 transmits the instruction command information PT to the first server 120 . Then, the bot 122 of the first server 120 transmits the text information of the document file DF that has been uploaded and is in the database 121 to the second server 130, and also transmits the received instruction command information PT to the second server 130. In addition, when URL information is uploaded, the bot 122 of the first server 120 accesses the web server based on the URL information and obtains the text information of the page or the text information of the document file DF therein, and transmits it to the second server 130, and also transmits the received instruction command information PT to the second server 130.

[0034] Then, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received instruction command information PT to generate text data for the content information identified by the loaded document file DF or URL information. Then, the bot 122 of the first server 120 transmits the generated text data GT obtained through the execution to the user terminal 110. The user terminal 110 is configured to then display the received generated text data GT on an AI document screen 112 of a browser 111 or output it as voice.

[0035] As a result, the contents of the page of the uploaded document file DF or the page of the predetermined information based on the URL information are displayed on the AI ​​document screen 112. As a result, the user can view the content and send instruction and command information PT, such as creating a summary, pointing out problems or areas for improvement, or asking questions about the information, to the chat GPT, which is an example of a pre-trained artificial intelligence means 131, to interact with the chat GPT.

[0036] Next, an example of the operation of the artificial intelligence system 100 will be described in more detail. First, as an access step, the browser 111 is started in the user terminal 110, and the control unit of the user terminal 110 or the first server 120 determines whether or not an operation to access the URL of the artificial intelligence system 100 has been performed. More specifically, an HTTP request is sent from the user terminal 110 to the first server 120, and the determination is made based on whether or not the first server 120 receives the HTTP request.

[0037] When the first server 120 determines that it has received an HTTP request, it displays a login screen, for example. Then, the user performs a login operation to the artificial intelligence system 100. Then, as shown in FIG. 2, in step S1, which is a talk screen display step, the browser 111 of the user terminal 110 displays an AI document screen 112, which is a talk screen that can be freely interacted with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, via the first server 120.

[0038] As shown in FIG. 3, the AI ​​document screen 112 has, as an example, a document item display area 113, a document content display area 114, and a talk display area 115. Of these, the document item display area 113 is provided to display a document item 113a. The document content display area 114 is provided to display the contents of the document file DF corresponding to the document item 113a selected in the document item display area 113 or the contents of the predetermined information specified by the URL information.

[0039] Furthermore, the talk display area 115 is configured to display interactions between the user and the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, via the bot 122 of the first server 120. The talk display area 115 is configured like a chat screen. Here, the chat talk screen refers to a screen that displays exchanges of text and file data with one or more partners (including the bot 122) in chronological order on a single screen.

[0040] In step S2, as a designation operation determination step, user terminal 110 or first server 120 determines whether or not an operation to designate a document file DF or an operation to designate URL information, which is location information for specified information, has been performed in browser 111 of user terminal 110. More specifically, as shown in FIG. 3, it is assumed that the user operates the "+New Document" section in the document item display area 113 on the AI ​​document screen 112 displayed by the browser 111, for example.

[0041] Then, as shown in FIG. 4(A), the browser 111 displays a pop-up document registration window 116. The document registration window 116 is provided with a "File Upload" tab and a "URL" tab. When the "File Upload" tab is selected, the document registration window 116 displays a drag area 116a as a predetermined area.

[0042] Then, for example, the user uses a mouse to drag the icon of a document file DF, for example, "The Appeal of Electric Vehicles".pptx, from the drive of the memory section of the user terminal 110 or the file server to the drag area 116a, and operates the send button. In this way, when the icon of a document file DF is dragged to the drag area 116a as a specified area and the send button is operated, it is determined that an operation to specify a document file DF has been performed and the process proceeds to step S3; on the other hand, if it is determined that no operation has been performed yet, step S2 is repeated.

[0043] When the drag area 116a is clicked, the browser 111 pops up a file selection window, and a list of files is displayed in the file selection window. A desired document file DF may be selected and specified from this file list. Furthermore, as shown in FIG. 4(B), when the "URL" tab is selected in the document registration window 116, the document registration window 116 displays a URL input field 116B and a document name input field. The URL information, which is location information for the predetermined information, may be specified by inputting URL information in this URL input field 116B and operating the send button, or the file name may be input in the document name input field and the send button may be operated.

[0044] In step S3, which is an upload step, the user terminal 110 uploads to the first server 120, for example, a document file DF of “The Appeal of Electric Vehicles”.pptx or URL information. In step S4, as a talk screen data transmission step, the first server 120 creates talk screen data including, for example, a page of the document file DF, “The appeal of electric vehicles”.pptx, or a page of specified information in the display content, based on the received document file DF, for example, “The appeal of electric vehicles”.pptx, or URL information, and transmits the talk screen data to the user terminal 110.

[0045] In step S5, as shown in FIG. 5, as a talk screen data display step, the user terminal 110 displays the received talk screen data on the browser 111 as the AI ​​document screen 112. As a result, the contents of the document file DF “The Appeal of Electric Vehicles”.pptx are displayed in the document content display area 114 of the AI ​​document screen 112.

[0046] At this time, in the document item display area 113 of the AI ​​document screen 112, the document item 113a "The appeal of electric vehicles" is added to the top, and the document item 113a "The appeal of electric vehicles" becomes selected. Here, when the selection of document item 113a in document item display area 113 is changed, the document content displayed in document content display area 114 and the content of the exchange displayed in talk display area 115 are also changed accordingly.

[0047] In step S6, as an instruction / command input / transmission operation determination step, the user terminal 110 determines whether or not an input / transmission operation of instruction / command information PT has been performed in the browser 111 of the user terminal 110. For example, suppose a user enters a question such as "What are the advantages compared to gasoline-powered vehicles?" as an example of instruction command information PT in the input field 115a provided in the talk display area 115 of the AI ​​document screen 112 and operates the send button. In this case, it is determined that an input / transmission operation of instruction command information PT has been performed, and the process proceeds to step S7. On the other hand, if it is determined that no input / transmission operation has been performed, step S6 is repeated.

[0048] In step S7, the user terminal 110 transmits instruction command information PT to the first server 120 as an instruction command transmitting step. More specifically, as shown in FIG. 6, the message "What are the advantages compared to gasoline-powered vehicles?" is displayed in the talk display area 115 of the AI ​​document screen 112 together with a user icon. At this time, the bot 122 of the first server 120 transmits the text information of the document file DF that has been uploaded and is in the database 121 to the second server 130, and also transmits the received instruction command information PT to the second server 130. In addition, when URL information is uploaded, the bot 122 of the first server 120 accesses the web server based on the URL information and obtains the text information of the page or the text information of the document file DF therein, and transmits it to the second server 130, and also transmits the received instruction command information PT to the second server 130.

[0049] In step S8, as a text data generation step, the first server 120 generates text data for the content information identified by the loaded document file DF or URL information using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received instruction command information PT.

[0050] In step S9, as a generated data transmitting step, first server 120 transmits generated text data GT obtained by the execution to user terminal 110. In step S10, as a generated data display / audio output step, the user terminal 110 displays the received generated text data GT in the talk display area 115 of the AI ​​document screen 112 of the browser 111, or outputs it as audio. More specifically, as shown in Figure 6, in response to the instruction command information PT, which is the question "What are the advantages compared to gasoline-powered vehicles?", generated text data GT is displayed stating, "Since it is all electronically controlled, it is compatible with autonomous driving..."

[0051] As a result, as described above, the contents of the page of the uploaded document file DF or the page of the predetermined information based on the URL information are displayed on the AI ​​document screen 112. As a result, the user can view the content and send instruction and command information PT, such as creating a summary, pointing out problems or areas for improvement, or asking questions about the information, to the chat GPT, which is an example of a pre-trained artificial intelligence means 131, to interact with the chat GPT.

[0052] Furthermore, in this embodiment, when the first server 120 creates talk screen data, the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, reads a page of the document file DF or a page of specified information based on the document file DF or URL information. Then, the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, generates multiple pieces of question information in which the answer information is information related to the content information specified by the loaded document file DF or URL information. Subsequently, the bot 122 of the first server 120 is configured to transmit the generated question information QT to the user terminal 110.

[0053] As a result, as shown in Figure 5, multiple anticipated question information about the content information identified by the document file DF or URL information is generated, and the generated question information QT is displayed in the talk display area 115 of the AI ​​document screen 112 of the browser 111. Here, when the displayed generated question information QT is clicked on, the contents of the generated question information QT are entered into the input field 115a and transmitted as instruction command information PT to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, via the bot 122 of the first server 120. As a result, the user can first select one of the multiple pieces of question information and interact with chat GPT, which is an example of a pre-trained artificial intelligence means 131 of the second server 130, via the bot 122 of the first server 120, and easily deepen his or her understanding of the content information identified by the document file DF or URL information read by chat GPT, which is an example of a pre-trained artificial intelligence means 131, without having to read all of it himself or herself.

[0054] In addition, when the chat GPT, which is an example of the pre-trained artificial intelligence means 131, generates text data based on the instruction command information PT, the chat GPT, which is an example of the pre-trained artificial intelligence means 131, generates multiple question information in which information regarding the content information identified by the loaded document file DF or URL information serves as answer information. Then, the bot 122 of the first server 120 may be configured to transmit the generated text data GT and the generated question information QT to the user terminal 110 in this order.

[0055] As a result, the generated text data GT and the generated question information QT are displayed in this order in the talk display area 115 of the AI ​​document screen 112 of the browser 111. As a result, the user can view the generated text data GT as an answer, and then select one of the multiple generated question information QT to continue the interaction. Furthermore, multiple generated question information QT are displayed for each interaction. As a result, understanding increases with each interaction.

[0056] In addition, in this embodiment, when the chat GPT, which is an example of the pre-trained artificial intelligence means 131, generates text data based on the instruction command information PT, the chat GPT, which is an example of the pre-trained artificial intelligence means 131, generates basis information PF regarding which page or part of the content information identified by the loaded document file DF or URL information the text data is based on. Then, the bot 122 of the first server 120 transmits the generated text data GT and the basis information PF to the user terminal 110. As shown in FIG. 6, the user terminal 110 is configured to display the generated text data GT and the basis information PF in a talk display area 115 of an AI document screen 112 of a browser 111.

[0057] As a result, not only the generated text data GT but also the basis information PF are displayed in the talk display area 115 of the AI ​​document screen 112 of the browser 111. As a result, the user can easily check the accuracy and reliability (veracity) of the generated text data GT by referring to the content information specified by the original document file DF or URL information based on the evidence information PF. In other words, the user can easily confirm which part and what the text data was generated based on, without simply looking at the generated text data GT and accepting the contents of the generated text data GT.

[0058] Furthermore, in this embodiment, the text portion of the basis information PF received from the first server 120 in the talk display area 115 of the AI ​​document screen 112 of the browser 111 is linked to a portion corresponding to the basis information PF on the page of the document file DF or the page of specified information displayed in the talk display area 115 of the AI ​​document screen 112. When a text portion of the basis information PF is operated in the talk display area 115 of the AI ​​document screen 112 of the browser 111, the document content display area 114 of the AI ​​document screen 112 of the browser 111 is configured to display a portion corresponding to the basis information PF on a page of the document file DF or a page of specified information in the talk display area 115 of the AI ​​document screen 112.

[0059] This allows the user to display the area they want to check with just a click, as shown in Figure 7. As a result, the user can easily check the part that he or she wants to check in the original document file DF or the content information (predetermined information) specified by the URL information.

[0060] In addition, when a location of the basis information PF is operated in the talk display area 115 of the AI ​​document screen 112 of the browser 111, the document content display area 114 of the AI ​​document screen 112 of the browser 111 may be configured to display a location corresponding to the basis information PF on the page of the document file DF or the page of specified information in the talk display area 115 of the AI ​​document screen 112, and to display the location of the basis information PF by highlighting, etc. This allows users to simply click to highlight the area they want to check. As a result, the user can easily check the part that he or she wants to check in the content information (predetermined information) specified by the document file DF or the URL information.

[0061] In this embodiment, the instruction command information PT is to provide an explanation for the inquiry, and the chat GPT, which is an example of the pre-trained artificial intelligence means 131, calculates a correlation score between the content of the inquiry and the content information identified by the loaded document file DF or URL information. If the calculated correlation score is less than a predetermined threshold, the second server 130 is configured to send generated text data GT indicating that the answer to the inquiry is unknown to the user terminal 110 via the bot 122 of the first server 120.

[0062] As a result, as shown in Figure 8, when a question is asked about content that has a low correlation with the content information identified by the selected document file DF or URL information, an honest answer that the user does not know is displayed in the talk display area 115 of the AI ​​document screen 112 of the browser 111, or is output as audio from the speaker, without giving an answer with a low reliability. As a result, the user can understand that his / her inquiry (question) was irrelevant in relation to the content information identified by the specified document file DF or URL information, and can try a different inquiry (question). In other words, content with a low reliability is not displayed as an answer in the talk display area 115 of the AI ​​document screen 112 of the browser 111, or is not output as audio from the speaker. As a result, users can interact with Chat GPT, an example of a pre-trained artificial intelligence means 131, with peace of mind.

[0063] Furthermore, in this embodiment, as shown in FIG. 9, the AI ​​document screen 112 of the browser 111 is provided with a table of contents generation button 114a, a page-by-page summary generation button 114b, and a download button 114c. When table of contents generation button 114a is operated as an example of a first predetermined operation, user terminal 110 transmits to first server 120 instruction command information PT to generate a table of contents.

[0064] Then, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received instruction command information PT to create a table of contents, to generate table of contents information for the content information identified by the loaded document file DF or URL information. Then, the bot 122 of the first server 120 transmits the generated table of contents information GC obtained through the execution to the user terminal 110. The user terminal 110 is configured to then display the received generated table of contents information GC in a document content display area 114 , which is an example of an AI document screen 112 of the browser 111 .

[0065] As a result, the table of contents information is generated, and the generated table of contents information GC is displayed in the document content display area 114 of the AI ​​document screen 112 of the browser 111. As a result, users can easily understand what is written and in what order. This is particularly effective when no table of contents information is added to the original document file DF.

[0066] Although the operation of the table of contents generation button 114a has been described as an example of the first predetermined operation, the present invention is not limited to this. For example, the user may right-click to display a topic window and select "Generate Table of Contents" from the topics. Alternatively, a voice input operation to the effect that "a table of contents is to be generated" may be performed.

[0067] Also in this embodiment, as shown in FIG. 10, when the page-by-page summary generation button 114b is operated as an example of a second specified operation, the user terminal 110 transmits instruction command information PT to the first server 120 to create a page-by-page summary. Then, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received instruction command information PT to create a summary for each page, to generate page-by-page summary information for the content information identified by the loaded document file DF or URL information.

[0068] Then, the bot 122 of the first server 120 transmits the generated page-by-page summary information GA obtained through the execution to the user terminal 110. The user terminal 110 is configured to then display the received generated page-by-page summary information GA in a document content display area 114 , which is an example of an AI document screen 112 of the browser 111 .

[0069] As a result, summary information for each page is generated, and the generated summary information for each page GA is displayed in a document content display area 114 , which is an example of an AI document screen 112 of the browser 111 . As a result, users can easily understand what is contained on each page.

[0070] Although the operation of the page-by-page summary generation button 114b has been described as an example of the second predetermined operation, the present invention is not limited to this. For example, the user may right-click to display an item window and select "Generate page-by-page summary" from the items. Alternatively, a voice input operation to the effect that "a page-by-page summary is to be generated" may be performed.

[0071] Furthermore, in this embodiment, when the download button 114c is operated as an example of a third specified operation, the first server 120 is configured to add the generated table of contents information GC, the generated page-by-page summary information GA, and the instruction command information PT and the generated text data GT exchange information in the talk display area 115 of the AI ​​document screen 112 to the page of the document file DF or the page of specified information displayed in the browser 111 of the user terminal 110, and download them to the user terminal 110.

[0072] As a result, as shown in Figure 11, not only the pages of the document file DF or the pages of the specified information, but also the generated table of contents information GC, the generated page-by-page summary information GA, and the interaction between the chat GPT, which is an example of the pre-trained artificial intelligence means 131, and the user (instruction command information PT and generated text data GT) are downloaded as a set as a download file DL. As a result, the user can save a download file DL which is a collective record of the pages of the document file DF or of pages of given information.

[0073] Although the operation of the download button 114c has been described as an example of the third predetermined operation, the third predetermined operation is not limited to this. For example, the operation may be to right-click to display an item window and select "download document" from the items. Alternatively, a voice input operation to the effect that "I want to download the document" may be performed.

[0074] In this embodiment, as shown in FIG. 12, when the user terminal 110 uploads a document file DF or URL information to the server, the browser 111 opens a sharing setting window 117 in which other users' identification information YS can be freely input. Here, the sharing setting window 117 is provided with an input field 117a in which other user identification information YS can be freely input.

[0075] Then, based on the input of user identification information YS into input field 117a, which is an example of an input / setting operation of other user identification information YS, the operation of the add user button, and the operation of the send button, the user terminal 110 sends the other user identification information YS to the first server 120. The first server 120 is then configured to permit sharing of talk screen data between the user and other users based on the received other user identification information YS, the talk screen data including in its display content a page of the document file DF or a page of specified information based on the received document file DF or URL information.

[0076] This allows the content uploaded by users to be shared with other users. More specifically, when another user logs in to the artificial intelligence system 100 and displays the AI ​​document screen 112 in the browser 111, the document item display area 113 displays the item "The appeal of electric vehicles" as an example of a shared document file DF, and when that item is selected, the document content display area 114 displays the contents of "The appeal of electric vehicles.pptx" as an example of the document file DF for that item. As a result, the document can be shared with other users, who can then interact with Chat GPT, an example of a pre-trained artificial intelligence means 131, about the document's contents.

[0077] In this embodiment, as shown in FIG. 10, a microphone icon button 115b is provided in the input field 115a of the talk display area 115. When the microphone icon button 115b is operated, the microphone of the user terminal 110 becomes active and voice input via the microphone becomes possible. The voice input data is converted to text data in the user terminal 110, input to the input field 115a of the talk display area 115, and transmitted. In addition, at each exchange in the talk display area 115, a clipboard icon button 115c and a speaker icon button 115d are provided. When the clipboard icon button 115c is operated, the contents of the instruction command information PT and generated text data GT that are exchanged are temporarily recorded in the storage unit of the user terminal 110 as a so-called clipboard.

[0078] Furthermore, when the speaker icon button 115d is operated, the instruction command information PT and the generated text data GT, which are the exchanged information, are converted into voice data and output as voice using the speaker of the user terminal 110. This allows for viewing, speaking, and listening without the need for text input. As a result, the user can smoothly interact with the chat GPT, which is an example of a pre-trained artificial intelligence means 131, while viewing the contents of the document file DF displayed in the document content display area 114 of the AI ​​document screen 112.

[0079] The artificial intelligence system 100, which is an embodiment of the present invention obtained in this manner, includes a user terminal 110, and a first server 120 and a second server 130, which are examples of servers. The browser 111 of the user terminal 110 displays an AI document screen 112, which is a talk screen that can be freely exchanged with a chat GPT, which is an example of a pre-trained artificial intelligence means 131 of the second server 130, via the first server 120. When an operation to specify a document file DF or an operation to specify URL information, which is location information for predetermined information, is performed in the browser 111 of the user terminal 110, the user terminal 110 uploads the document file DF or the URL information to the first server 120. The first server 120 creates talk screen data including a page of the document file DF or a page of the predetermined information in the display content based on the received document file DF or URL information, and transmits the created talk screen data to the user terminal 110. The user terminal 110 then receives the document file DF or the URL information. The received talk screen data is displayed on the browser 111, and when an input / send operation of instruction command information PT is performed on the browser 111 of the user terminal 110, the user terminal 110 sends the instruction command information PT to the first server 120, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received instruction command information PT to generate text data for the content information specified by the loaded document file DF or URL information, and sends the generated text data GT obtained by the execution to the user terminal 110, and the user terminal 110 displays the received generated text data GT on the browser 111 or outputs it as audio.As a result, the user can exchange information by sending instruction command information PT to the chat GPT, which is an example of the pre-trained artificial intelligence means 131, while viewing the content, to create a summary, point out problems, point out areas for improvement, ask questions about the information, etc.

[0080] Furthermore, when chat GPT, an example of pre-trained artificial intelligence means 131, generates text data based on instruction command information PT, chat GPT, an example of pre-trained artificial intelligence means 131, generates basis information PF regarding which page or part of the content information identified by the loaded document file DF or URL information it is based on, and the first server 120 transmits the generated text data GT and basis information PF to the user terminal 110, and the user terminal 110 displays the generated text data GT and basis information PF on the browser 111.This allows the user to easily check the accuracy and reliability (veracity) of the generated text data GT by referring to the original document file DF or the content information identified by the URL information based on the basis information PF, and the user can easily check which part and what the text data was generated based on, without looking at only the generated text data GT and blindly accepting the contents of the generated text data GT.

[0081] In addition, the text portion of the basis information PF received in the browser 111 from the bot 122 of the first server 120 is linked to a portion corresponding to the basis information PF on the page of the document file DF or the page of the specified information displayed on the AI ​​document screen 112, and when a text portion of the basis information PF is operated on in the browser 111, the browser 111 is configured to display a portion corresponding to the basis information PF on the page of the document file DF or the page of the specified information on the AI ​​document screen 112, thereby allowing the user to easily check the portion they want to check in the original document file DF or the content information (specified information) identified by the URL information.

[0082] Furthermore, when the table of contents generation button 114a, which is an example of a first predetermined operation, is operated on the AI ​​document screen 112 of the browser 111, the user terminal 110 sends instruction command information PT to create a table of contents to the first server 120, and the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received instruction command information PT to create a table of contents to generate table of contents information for the content information identified by the loaded document file DF or URL information, and sends the generated table of contents information GC obtained by the execution to the user terminal 110, and the user terminal 110 displays the received generated table of contents information GC on the browser 111, so that the user can easily understand what is written and in what order.

[0083] In addition, when the page-by-page summary generation button 114b, which is an example of a second predetermined operation, is operated on the AI ​​document screen 112 of the browser 111, the user terminal 110 sends instruction command information PT to the first server 120 to create a summary for each page, and the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received instruction command information PT to create a summary for each page, to generate page-by-page summary information for the content information identified by the loaded document file DF or URL information, and sends the generated page-by-page summary information GA obtained by the execution to the user terminal 110, and the user terminal 110 displays the received generated page-by-page summary information GA on the browser 111, thereby allowing the user to easily understand what is written on which page.

[0084] Furthermore, when the download button 114c, which is an example of a third specified operation, is operated on the AI ​​document screen 112 of the browser 111, the first server 120 adds the generated table of contents information GC, the generated page-by-page summary information GA, as well as the instruction command information PT and the generated text data GT on the AI ​​document screen 112 to the page of the document file DF or the page of the specified information displayed on the browser 111 of the user terminal 110, and downloads them to the user terminal 110, thereby allowing the user to save a complete record of the page of the document file DF or the page of the specified information.

[0085] In addition, when the user terminal 110 uploads a document file DF or URL information to the first server 120, the browser 111 opens a sharing setting window 117 in which other user identification information YS can be freely input, and based on the input / setting operation of the other user identification information YS, the user terminal 110 transmits the other user identification information YS to the first server 120, and the first server 120 is configured to allow sharing of talk screen data between the user and other users based on the received other user identification information YS, the talk screen data including a page of the document file DF or a page of specified information in the display content based on the received document file DF or URL information, thereby allowing the document to be shared with other users, and the other users can also interact with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, about the contents of the document.

[0086] Furthermore, when the first server 120 creates talk screen data, the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, reads a page of the document file DF or a page of predetermined information based on the document file DF or URL information, and generates multiple pieces of related question information in which information on the content information specified by the read document file DF or URL information becomes answer information, and the bot 122 of the first server 120 transmits the generated question information QT to the user terminal 110, or when the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, generates text data based on the instruction command information PT, the pre-trained artificial intelligence means 131 of the second server 130 In this configuration, chat GPT, which is an example of pre-trained artificial intelligence means 131 of the second server 130, generates multiple pieces of related question information in which information related to content information identified by the loaded document file DF or URL information serves as answer information, and bot 122 of first server 120 transmits the generated text data GT and then the generated question information QT to user terminal 110.Therefore, a user can first select one of the multiple pieces of question information and interact with chat GPT, which is an example of pre-trained artificial intelligence means 131 of the second server 130, to easily deepen his or her understanding of the content information identified by the document file DF or URL information loaded by chat GPT, which is an example of pre-trained artificial intelligence means 131 of the second server 130, without having to read all of it himself or herself.

[0087] The program of the artificial intelligence system 100 according to the embodiment of the present invention includes a talk screen display step S1 in which the browser 111 of the user terminal 110 displays the AI ​​document screen 112, which is a talk screen that can be freely communicated with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, via the first server 120; a designation operation determination step S2 in which it is determined whether or not an operation of designating a document file DF or an operation of designating URL information, which is location information for predetermined information, has been performed in the browser 111 of the user terminal 110; an upload step S3 in which the user terminal 110 uploads the document file DF or the URL information to the first server 120 when a designation operation has been performed; a talk screen data transmission step S4 in which the first server 120 creates talk screen data including a page of the document file DF or a page of the predetermined information in the display content based on the received document file DF or URL information, and transmits the talk screen data to the user terminal 110; and a talk screen data display step S5 in which the user terminal 110 displays the received talk screen data on the browser 111. In the browser 111 of the user terminal 110, a command input / transmission operation determination step S6 is performed to determine whether or not an input / transmission operation of command information PT has been performed. When an input / transmission operation has been performed, the user terminal 110 transmits the command information PT to the first server 120 in a command transmission step S7. Based on the received command information PT, the first server 120 uses a chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate text for the content information specified by the read document file DF or URL information. The method includes a text data generating step S8 in which the bot 122 of the first server 120 generates text data, a generated data transmitting step S9 in which the bot 122 of the first server 120 transmits the generated text data GT obtained by the execution to the user terminal 110, and a generated data display / audio output step S10 in which the user terminal 110 displays the received generated text data GT on the browser 111 or outputs it as audio. This allows the user to make a summary, point out problems, point out improvements, and so on to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, while viewing the content.The effect is enormous, as it is possible to exchange information by sending instruction and command information PTs such as questions about information. [Explanation of symbols]

[0088] 100 ··· Artificial Intelligence Systems 110 User terminal 111 ··· Browser 112 ··· AI document screen (talk screen) 113 Document item display area 113a... Document item 114 Document content display area 114a··· Table of contents generation button 114b... Page summary generation button 114c··· Download button 115 ··· Talk display area 115a··· Input field 115b Microphone icon button 115c··· Clipboard icon button 115d··· Speaker icon button 116 Document Registration Window 116a... Drag area 116b... URL input field 117 ··· Shared Settings Window 117a··· Input field 120 First Server (Server) 121 ··· Database 122 Bot 130 Second Server (Server) 131 ··· Pre-trained AI method (Chat GPT) DF Document file PT... Directive command information GT: Generated text data PF: Basis information GC ··· Generated Table of Contents Information GA Generates page-by-page summary information DL: Download file YS User Identification Information QT ··· Generate question information

Claims

1. An artificial intelligence system comprising a user terminal and a server, the user terminal displaying or outputting audio based on the server, The browser of the user terminal displays a talk screen that can freely communicate with the pre-trained artificial intelligence means of the server, When an operation for designating a document file or an operation for designating URL information, which is location information for predetermined information, is performed in a browser of the user terminal, the user terminal uploads the document file or the URL information to a server; The server creates talk screen data including a page of the document file or a page of predetermined information in the display content based on the received document file or URL information, and transmits the created talk screen data to the user terminal; The user terminal displays the received talk screen data on a browser, When an instruction command information is input and transmitted in a browser of the user terminal, the user terminal transmits the instruction command information to a server; The server uses the pre-trained artificial intelligence means based on the received instruction command information to generate text data for the content information specified by the loaded document file or URL information, and transmits the generated text data to the user terminal; An artificial intelligence system characterized in that the user terminal is configured to display the received generated text data on a browser or output it as voice.

2. When the pre-trained artificial intelligence means generates text data based on instruction command information, the pre-trained artificial intelligence means generates basis information regarding which page or part of the content information specified by the loaded document file or URL information the text data is based on; The server transmits the generated text data and the grounds information to a user terminal; 2. The artificial intelligence system according to claim 1, wherein the user terminal is configured to display the generated text data and the basis information on a browser.

3. A text portion of the basis information received from the server in the browser is linked to a portion corresponding to the basis information in a page of the document file or a page of the predetermined information displayed on the talk screen, The artificial intelligence system described in claim 2, characterized in that when a text portion of the basis information is operated in the browser, the browser displays a portion of the document file page or a specified information page corresponding to the basis information on the talk screen.

4. When a first predetermined operation is performed on a talk screen of the browser, the user terminal transmits instruction command information to a server to generate a table of contents; The server uses the pre-trained artificial intelligence means based on the received instruction command information for creating a table of contents to generate table of contents information for the content information specified by the loaded document file or URL information, and transmits the generated table of contents information obtained by the execution to the user terminal; 4. The artificial intelligence system according to claim 1, wherein the user terminal is configured to display the received generated table of contents information on a browser.

5. When a second predetermined operation is performed on the talk screen of the browser, the user terminal transmits instruction command information to the server to generate a summary for each page; The server uses the pre-trained artificial intelligence means to generate page-by-page summary information for the content information specified by the loaded document file or URL information based on the received instruction command information for generating a page-by-page summary, and transmits the generated page-by-page summary information to the user terminal; 5. The artificial intelligence system according to claim 4, wherein the user terminal is configured to display the generated page-by-page summary information received on a browser.

6. The artificial intelligence system described in claim 5, characterized in that when a third specified operation is performed on the talk screen of the browser, the server adds generated table of contents information, generated summary information for each page, as well as instruction command information on the talk screen and generated text data to the page of the document file or the page of specified information displayed in the browser of the user terminal, and downloads them to the user terminal.

7. When the user terminal uploads a document file or URL information to a server, the browser opens a sharing setting window in which other users' identification information can be freely input, and the user terminal transmits the other users' identification information to the server based on the input / setting operation of the other users' identification information; The artificial intelligence system described in claim 6, characterized in that the server is configured to allow sharing of talk screen data between a user and another user based on the received other user identification information, the talk screen data including a page of a document file or a page of specified information in the display content based on the received document file or URL information.

8. When the server creates the talk screen data, the pre-trained artificial intelligence means reads a page of the document file or a page of predetermined information based on the document file or URL information, and generates a plurality of pieces of question information in which information on the content information specified by the read document file or URL information becomes answer information; The server transmits the generated question information to the user terminal. or When the pre-trained artificial intelligence means generates text data based on instruction command information, the pre-trained artificial intelligence means generates a plurality of pieces of question information in which information on the content information specified by the loaded document file or URL information serves as answer information; 8. The artificial intelligence system according to claim 7, wherein the server is configured to transmit the generated text data and the generated question information to the user terminal in that order.

9. A program for an artificial intelligence system having a user terminal and a server, the user terminal displaying or outputting audio based on the server, a talk screen display step in which a browser of the user terminal displays a talk screen that can freely communicate with the pre-trained artificial intelligence means of the server; a designation operation determination step of determining whether or not an operation of designating a document file or an operation of designating URL information, which is location information of predetermined information, has been performed in a browser of the user terminal; an upload step in which, when the designation operation is performed, the user terminal uploads a document file or URL information to a server; a talk screen data transmission step in which the server creates talk screen data including a page of the document file or a page of predetermined information in the display content based on the received document file or URL information, and transmits the talk screen data to the user terminal; a talk screen data display step of the user terminal displaying the received talk screen data on a browser; an instruction command input / transmission operation determination step of determining whether or not an instruction command information input / transmission operation has been performed in a browser of the user terminal; an instruction command transmission step of transmitting instruction command information to a server by the user terminal when the input / transmission operation is performed; a text data generating step in which the server generates text data for the content information specified by the loaded document file or URL information by using a pre-trained artificial intelligence means based on the received instruction command information; a generated data transmission step in which the server transmits generated text data obtained by the execution to a user terminal; A program for an artificial intelligence system, comprising a generated data display / voice output step in which the user terminal displays the received generated text data on a browser or outputs it as voice.

Images