Artificial intelligence system and program for artificial intelligence system

Abstract

To provide an artificial intelligence system capable of obtaining an answer with searched contents on the Web as a request without using a search engine of a browser.SOLUTION: An artificial intelligence system 100 includes a user terminal 110 and servers (120, 130). The user terminal 110 communicates with the server 120, and a browser 111 of the user terminal displays a talk screen 112. When a user inputs request information PT, which is instruction command information, on the talk screen, the user terminal transmits the input request information to the server. The server uses pre-learned artificial intelligence means to generate text data with contents based on contents of a website that has been pre-learned as an answer to the request information, and transmits the generated text data GT obtained by the execution to the user terminal. The user terminal displays the received generated text data on the talk screen.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an artificial intelligence system including a user terminal and a server, in which the user terminal can freely communicate with pre-trained artificial intelligence means of the server, and a program therefor. [Background technology]

[0002] Conventionally, there is known an information processing device that includes a language data receiving unit that receives language data in response to a request from a user terminal, a language data processing unit that processes the language data to generate basic summary information that forms the basis for generating a summary, a transmitting unit that transmits presentation information including the basic summary information to the user terminal, an editing information receiving unit that receives editing information related to the presentation information from the user terminal, and a summary generation unit that provides the editing information to a large-scale language model that receives input of the basic summary information and generates a summary sentence that reflects the editing information (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2023-73095 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional information processing devices described above were limited to generating summaries of basic summary information using large-scale language models, and therefore had the problem that users could not obtain answers to the content they were looking for on the web unless they used the browser's search engine to search websites.

[0005] Therefore, the present invention is intended to solve the problems of the prior art as described above, that is, the object of the present invention is to provide an artificial intelligence system and a program thereof that can obtain answers to the content desired on the web as a request without using a browser's search engine. [Means for solving the problem]

[0006] The invention of claim 1 is an artificial intelligence system comprising a user terminal and a server, wherein the user terminal is capable of freely communicating with the server's pre-trained artificial intelligence means, wherein the user terminal communicates with the server, the user terminal's browser displays a talk screen, and when a user inputs request information, which is instruction and command information, on the talk screen, the user terminal transmits the input request information to the server, and the server uses the pre-trained artificial intelligence means to generate text data based on the content of a website pre-trained as a response to the request information, transmits the generated text data obtained by the execution to the user terminal, and the user terminal displays the received generated text data on the talk screen, thereby solving the above-mentioned problem.

[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 for requested information, the pre-trained artificial intelligence means generates basis information regarding which page or part of the content information identified by the loaded URL information the text data is based on, the server transmits the generated text data and basis information to the user terminal, and the user terminal displays the generated text data and basis information on the talk screen.

[0008] The invention of claim 3 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 or claim 2, when the pre-trained artificial intelligence means generates text data for requested information, the text data is generated to suggest one or more plans to the user based on the content of the pre-trained website, and the generated text data obtained by the execution is transmitted to the user terminal.

[0009] The invention of claim 4 further solves the above-mentioned problem by being configured such that, in addition to the configuration of the artificial intelligence system described in claim 3, when the pre-trained artificial intelligence means generates text data for requested information, as a preliminary step of proposing one or more plans to the user based on the content of the pre-trained website, the server uses the pre-trained artificial intelligence means to generate text data about the conditions necessary for plan selection, and transmits the generated text data about the conditions necessary for plan selection obtained by the execution to the user terminal, and when information about the necessary conditions is input by the user on the talk screen, the user terminal transmits the input information about the necessary conditions to the server, and the server uses the pre-trained artificial intelligence means to generate text data about content that proposes one or more plans to the user based on the content of the pre-trained website taking into account the necessary conditions, and transmits the generated text data obtained by the execution to the user terminal.

[0010] The invention of claim 5 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 4, being configured such that when the server uses the pre-trained artificial intelligence means to generate text data based on the content of a website pre-trained as a response to request information, the server uses the pre-trained artificial intelligence means to add topic information to the request information indicating that it is about travel.

[0011] The invention of claim 6 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 4, being configured such that when the server uses the pre-trained artificial intelligence means to generate text data based on the content of a website pre-trained as a response to request information, the server uses the pre-trained artificial intelligence means to add topic information to the request information indicating that it is about real estate.

[0012] The invention of claim 7 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 4, being configured such that when the server uses the pre-trained artificial intelligence means to generate text data based on the content of a website pre-trained as a response to request information, the server uses the pre-trained artificial intelligence means to add topic information to the request information indicating that it is about used cars.

[0013] The invention of claim 8 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 4, being configured such that when the server uses the pre-trained artificial intelligence means to generate text data based on the content of a website pre-trained as a response to request information, the server uses the pre-trained artificial intelligence means to add topic information to the request information indicating that it is about job hunting.

[0014] The invention of claim 9 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 4, being configured such that when the server uses the pre-trained artificial intelligence means to generate text data based on the content of a website pre-trained as a response to request information, the server uses the pre-trained artificial intelligence means to add topic information to the request information indicating that it is about eating and drinking.

[0015] The invention according to claim 10 is a program of an artificial intelligence system in which a user terminal can communicate with pre-trained artificial intelligence means of a server. The user terminal communicates with the server, and a talk screen display step in which a browser of the user terminal displays a talk screen, an input transmission operation presence / absence determination step of determining whether or not request information, which is instruction command information, has been input by the user on the talk screen and a transmission operation has been performed, a request transmission step in which the user terminal transmits the input request information to the server, a text generation step in which the server executes generation of text data of content based on the content of a pre-learned website as an answer to the request information using the pre-trained artificial intelligence means, a text transmission step in which the server transmits the generated text data obtained by the execution to the user terminal, and a text display step in which the user terminal displays the received generated text data on the talk screen, thereby solving the above-described problems.

Effect of the Invention

[0016] The artificial intelligence system of the present invention includes a user terminal and a server, so that not only can the user terminal communicate with the pre-trained artificial intelligence means of the server, but also the following specific effects can be achieved.

[0017] According to the artificial intelligence system of the invention according to claim 1, since generated text data of content based on the content of a website is displayed on the talk screen for a request, the user can obtain an answer of content based on the content of the website for the request. That is, an answer to the content being searched for on the web as a request can be obtained without using the search engine of the browser.

[0018] According to the artificial intelligence system of the invention of claim 2, in addition to the effects achieved by the invention of claim 1, not only the generated text data but also the basis information is displayed on the talk screen, 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 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.

[0019] According to the artificial intelligence system of the invention of claim 3, in addition to the effects of the invention of claim 1 or claim 2, one or more plans are proposed in the generated text data in response to the user's request information, allowing the user to adopt a plan that they like. If there is grounds information, the user can access and apply based on the grounds information.

[0020] According to the artificial intelligence system of the invention of claim 4, in addition to the effects achieved by the invention of claim 3, the system asks the user for condition information necessary for proposing a plan, and after receiving the necessary condition information from the user, a plan is selected and generated text data for the proposed plan is generated, so that the user can receive a proposed plan that meets his or her conditions. For example, users can receive suggestions such as travel plans that match conditions such as family structure / number of people, destination, number of days / duration, real estate purchasing plans that match conditions such as family structure and place of work, used car purchasing plans that match conditions such as family structure, automatic transmission-only driver's license, dealer location area, and car size, job change / employment plans that match conditions such as work area, qualifications held, and place of work, and dining plans that match conditions such as family structure / number of people, budget, allergies, location, day of the week, and time of day.

[0021] According to the artificial intelligence system of the invention of claim 5, in addition to the effects achieved by the invention of claim 4, the system asks the user for condition information necessary for proposing a travel plan, and after receiving the necessary condition information from the user, a travel plan is selected and generated text data for the proposed travel plan is generated, so that the user can receive a proposed travel plan that meets his or her conditions. In other words, you can receive travel plan suggestions that match your family composition, number of people, destination, number of days, and duration.

[0022] According to the artificial intelligence system of the invention of claim 6, in addition to the effects achieved by the invention of claim 4, the user is asked about condition information necessary for proposing a real estate plan, and after receiving the necessary condition information from the user, a real estate plan is selected and generated text data for the proposed real estate plan is generated, so that the user can receive a proposed real estate plan that meets his or her conditions. In other words, you can receive proposals for real estate purchasing plans that match your family composition and work location.

[0023] According to the artificial intelligence system of the invention of claim 7, in addition to the effects achieved by the invention of claim 4, the system asks the user for condition information necessary for proposing a plan for a used car, and after receiving the necessary condition information from the user, a plan for a used car is selected and generated text data for the proposed plan for a used car is generated, so that the user can receive a proposal for a plan for a used car that meets his or her conditions. In other words, customers can receive suggestions for used car purchasing plans that match their family composition, automatic transmission-only driver's license, dealer location area, and car size.

[0024] According to the artificial intelligence system of the invention of claim 8, in addition to the effects achieved by the invention of claim 4, the system asks the user for condition information necessary for proposing a job search plan, and after receiving the necessary condition information from the user, a job search plan is selected and generated text data for the proposed job search plan is generated, so that the user can receive a proposed job search plan that matches his or her conditions. In other words, you can receive job change and employment plans that match your work area, qualifications, and work location.

[0025] According to the artificial intelligence system of the invention of claim 9, in addition to the effects achieved by the invention of claim 4, the system asks the user for condition information necessary for proposing a dining plan, and after receiving the necessary condition information from the user, a dining plan is selected and generated text data for the proposed dining plan is generated, so that the user can receive a proposed dining plan that meets his or her conditions. In other words, you can receive suggestions for dining plans that match your family composition and number of people, budget, allergies, location, day of the week, and time of day.

[0026] According to the program of the artificial intelligence system of the invention of claim 10, similar to the effect achieved by the invention of claim 1, generated text data based on the content of the website in response to the request information is displayed on the talk screen, so that the user can obtain a response to the request based on the content of the website. This means you can get the answers you're looking for on the web as you request them without using your browser's search engine. [Brief description of the drawings]

[0027] [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 travel request information entered on a talk screen displayed on a browser of a user terminal of an artificial intelligence system according to an embodiment of the present invention. [Figure 4] FIG. 13 is a diagram showing an example of generated text data displayed as an answer on the talk screen of the artificial intelligence system according to an embodiment of the present invention. [Diagram 5] FIG. 13 shows an example of generated text data displayed on a talk screen of an artificial intelligence system according to an embodiment of the present invention with basis information added thereto. [Figure 6] A figure showing an example in which generated text data regarding the conditions necessary for plan selection is displayed on the talk screen of an artificial intelligence system that is an embodiment of the present invention, and necessary condition information is input. [Figure 7] A figure showing the appearance when the prompt item "Make a reservation with this content" is operated on the talk screen of the artificial intelligence system which is an embodiment of the present invention, and the browser displays the plan application site. [Figure 8] A diagram explaining the operation when a main topic is specified on the talk screen displayed on the browser of a user terminal of the artificial intelligence system according to an embodiment of the present invention. [Figure 9] A figure showing an example of a chat screen displayed on a browser of a user terminal of an artificial intelligence system according to an embodiment of the present invention, in which desired information about real estate is entered as an example, and generated text data is displayed as a response about real estate. [Figure 10] This figure shows an example of a chat screen displayed on the browser of a user terminal of an artificial intelligence system according to an embodiment of the present invention, in which desired information about a used car is entered as an example, and generated text data is displayed as a response about the used car. [Figure 11] FIG. 13 shows an example of a chat screen displayed on a browser of a user terminal of an artificial intelligence system according to an embodiment of the present invention, in which a job search request is entered as an example, and generated text data is displayed as a response to the job search. [Figure 12]A figure showing an example of a chat screen displayed on the browser of a user terminal of an artificial intelligence system according to an embodiment of the present invention, in which a request for food and drink is entered as an example, and generated text data is displayed as a response regarding food and drink. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] The artificial intelligence system of the present invention comprises a user terminal and a server, and the user terminal communicates with the server, the browser of the user terminal displays a talk screen, and when the user inputs request information, which is instruction and command information, on the talk screen, the user terminal transmits the input request information to the server, and the server uses a pre-trained artificial intelligence means to generate text data based on the content of a website that has been pre-trained as a response to the request information, transmits the generated text data obtained by this execution to the user terminal, and the user terminal displays the received generated text data on the talk screen.As long as the user can obtain an answer to the content they are looking for on the web as their request without using the browser's search engine, the specific implementation of the system can be any one. The program for the artificial intelligence system of the present invention includes a talk screen display step in which a user terminal communicates with a server and a browser of the user terminal displays a talk screen; an input transmission operation determination step in which a user inputs request information, which is instruction command information, on the talk screen and a transmission operation is determined to have been performed; a request transmission step in which the user terminal transmits the input request information to the server; and a text generation step in which the server uses the pre-trained artificial intelligence means to generate text data based on the content of a website pre-trained as a response to the request information. The specific implementation can be any one as long as it has a text transmission step in which the server transmits the generated text data obtained by execution to the user terminal, and a text display step in which the user terminal displays the received generated text data on the talk screen, thereby enabling the user to obtain an answer to the content they are looking for on the web as requested without using the browser's search engine.

[0029] 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 server may 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. EXAMPLES

[0030] An artificial intelligence system 100 according to an embodiment of the present invention will be described below with reference to FIGS. 1 is a diagram showing the concept of an artificial intelligence system 100 according to an embodiment of the present invention, FIG. 2 is a chart showing an example of the operation of the artificial intelligence system 100 according to an embodiment of the present invention, FIG. 3 is a diagram showing a state in which, as an example, requested information PT about a trip is input on a talk screen 112 displayed by a browser 111 of a user terminal 110 of the artificial intelligence system 100 according to an embodiment of the present invention, FIG. 4 is a diagram showing an example of generated text data GT displayed as an answer on the talk screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention, FIG. 5 is a diagram showing an example in which grounds information PF is added to the generated text data GT and displayed on the talk screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention, FIG. 6 is a diagram showing an example in which generated text data GT1 regarding the contents of the conditions necessary for plan selection is displayed on the talk screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention, and necessary condition information is input, and FIG. 7 is a diagram showing an example in which a prompt item 112g of "Apply for reservation with this content" is operated on the talk screen 112 of the artificial intelligence system 100 according to an embodiment of the present invention, and FIG. 8 is a diagram for explaining the operation when a main topic is specified on the talk screen 112 displayed by the browser 111 of the user terminal 110 of the artificial intelligence system 100 according to an embodiment of the present invention. FIG. 9 is a diagram showing an example in which desired information PT about real estate is input as an example on the talk screen 112 displayed by the browser 111 of the user terminal 110 of the artificial intelligence system 100 according to an embodiment of the present invention, and generated text data GT is displayed as a response to the real estate. FIG. 10 is a diagram showing an example in which desired information PT about used cars is input as an example on the talk screen 112 displayed by the browser 111 of the user terminal 110 of the artificial intelligence system 100 according to an embodiment of the present invention, and generated text data GT is displayed as a response to the used cars. FIG. 11 is a diagram showing an example in which desired information PT about job hunting is input as an example on the talk screen 112 displayed by the browser 111 of the user terminal 110 of the artificial intelligence system 100 according to an embodiment of the present invention, and generated text data GT is displayed as a response to the job hunting.FIG. 1 is a diagram showing an example in which request information PT about eating and drinking is input on a talk screen 112 displayed on a browser 111 of a user terminal 110 of an artificial intelligence system 100 according to an embodiment of the present invention, and generated text data GT is displayed as a response about eating and drinking.

[0031] 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 which are examples of servers. Among these, the first server 120 has a bot 121 which is also a display program. On the other hand, the second server 130 has a chat GPT, which is an example of a pre-trained artificial intelligence means 131. As a technical concept, the first server 120 and the second server 130 may have a common physical configuration, or may have physically different configurations. The user terminal 110 is provided so as to be able to communicate freely 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. More specifically, the user terminal 110 communicates with the first server 120 , and the browser 111 of the user terminal 110 displays a talk screen 112 .

[0032] When the user inputs request information PT, which is instruction command information also called a prompt, on the talk screen 112, the user terminal 110 transmits the input request information PT to the first server 120. 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, to generate text data based on the content of the pre-trained website as a response to the request information PT. Then, the first server 120 transmits the generated text data GT obtained through the execution to the user terminal 110. Then, the user terminal 110 is configured to display the received generated text data GT on the talk screen 112.

[0033] As a result, generated text data GT with contents based on the contents of the website in response to the request information PT is displayed on the talk screen 112. As a result, users can get answers to their queries that are based on the content of the website. In other words, a user can get answers to the content he or she is looking for on the Web without using the browser's 111 search engine.

[0034] The user terminal 110 may be a smartphone. Furthermore, the request information PT, which is instruction and command information, may be input by voice. For example, when the microphone icon is operated, the microphone of the user terminal 110 becomes active. When a voice input is made, the browser 111 converts the input voice into text, inputs the text data into the input field 112d on the talk screen 112, and transmits it to the bot 121 of the first server 120 as request information PT. Furthermore, when user terminal 110 displays the received generated text data GT on talk screen 112 of browser 111, browser 111 may be configured to output the contents of the generated text data GT as voice using a speaker.

[0035] Next, the operation of the artificial intelligence system 100 will be described in more detail. As shown in FIG. 2, in step S1, as a talk screen display step, the browser 111 of the user terminal 110 communicates with the first server 120 and displays the talk screen 112. More specifically, as shown in FIG. 3, the browser 111 accesses the first server 120 based on predetermined URL information, makes an HTTP request, and displays the talk screen 112 upon receiving an HTTP response from the first server 120.

[0036] The talk screen 112 has, for example, a board item display area 112a, a talk display area 112c, and a prompt list display area 112f. Among these, the board item display area 112a displays document items and board items 112b which are also exchange items. In addition, the talk display area 112c is provided with an input field 112d. Furthermore, the talk display area 112c displays the interaction between the user and the chat GPT, which is an example of a pre-trained artificial intelligence means 131, via the bot 121. Furthermore, when the selection of board item 112b is changed, the content of the exchange between the user in talk display area 112c and chat GPT, which is an example of a pre-trained artificial intelligence means 131 via bot 121, is switched. Furthermore, prompt items 112g, which are standard instruction and command information items, are displayed in the prompt list display area 112f.

[0037] In step S2, as an input / transmit operation determination step, the user terminal 110 determines whether or not a transmission operation has been performed by inputting request information PT, which is instruction command information also called a prompt, on the talk screen 112 by the user. More specifically, a text to be the request information PT is input in the input field 112d, and it is determined whether or not the send button or the enter key has been operated as a sending operation. For example, as shown in FIG. 3, assume that "I would like to take a three-night, four-day trip to Okinawa next month, so please help me come up with a plan!" is entered as an example of text that becomes the request information PT, and the send button is operated. Then, it is determined that an input / send operation has occurred. In this way, if it is determined that an input / transmission operation has been performed, the process proceeds to step S3, and on the other hand, if it is determined that no input / transmission operation has been performed, step S2 is repeated.

[0038] In step S3, as a request transmission step, the user terminal 110 transmits the input request information PT to the first server 120. For example, as an example of the request information PT, a message saying "I want to plan a 3-night and 4-day trip to Okinawa next month, so please consider a plan!" is sent to the first server 120. In step S4, as the text generation step, the first server 120 uses ChatGPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to execute the generation of text data of content based on the content of the pre-trained website as an answer to the request information PT. For example, based on the content of the pre-trained website, text data such as "Yes, here are the following plans. On the first day of Plan A..." is generated as an example of the answer.

[0039] In step S5, as the text transmission step, the first server 120 transmits the generated text data GT obtained by the execution to the user terminal 110. For example, the generated text data GT such as "Yes, here are the following plans. On the first day of Plan A..." is transmitted to the user terminal 110. In step S6, as shown in FIG. 4, as the text display step, the user terminal 110 displays the received generated text data GT on the talk screen 112. More specifically, the generated text data GT such as "Yes, here are the following plans. On the first day of Plan A..." is displayed on the talk screen 112.

[0040] As a result, as described above, the generated text data GT of the content based on the content of the website for the request information PT is displayed on the talk screen 112. As a result, the user can obtain an answer of the content based on the content of the website for the request. That is, without using the search engine of the browser 111, the user can obtain an answer to the content being searched for on the web as a request.

[0041] When the generated text data GT is displayed on the talk screen 112, the content of the generated text data GT may be output as audio using a speaker. In addition, when a speaker icon displayed in response to the generated text data GT displayed on the talk screen 112 is operated, the contents of the generated text data GT are output as voice using a speaker.

[0042] Furthermore, in this embodiment, when the chat GPT, which is an example of the pre-trained artificial intelligence means 131, generates text data for the request 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 URL information is based on. Then, the first server 120 transmits the generated text data GT and the basis information PF to the user terminal 110. Then, as shown in FIG. 5, the user terminal 110 is configured to display the generated text data GT and the basis information PF on the talk screen 112.

[0043] As a result, not only the generated text data GT but also the basis information PF are displayed on the talk screen 112. 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 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. The user can cause the browser 111 to display the content of the basis website by clicking or tapping on the basis information PF.

[0044] Similar to the configuration in which grounds information PF is added to generated text data GT, data of photographs and videos according to the plan may be collected and displayed on talk screen 112. This allows not only textual information but also image information such as photos and videos to be displayed on the talk screen 112. As a result, users can be shown image information and easily imagine the contents of the plan as an example.

[0045] In addition, in this embodiment, when the chat GPT, which is an example of the pre-trained artificial intelligence means 131, generates text data for the request information PT, it generates text data that proposes one or more plans to the user based on the content of the pre-trained website. The first server 120 is configured to transmit the generated text data GT obtained by the execution to the user terminal 110. As a result, as shown in FIG. 3 and FIG. 4, one or more plans are proposed in the generated text data GT for the user's request information PT. As a result, users can choose the plan they like best. If there is basis information PF, an application can be made by accessing based on the basis information PF.

[0046] Furthermore, in this embodiment, when chat GPT, an example of pre-trained artificial intelligence means 131, generates text data for request information PT, as a preliminary step to proposing one or more plans to the user based on the contents of the pre-trained website, the first server 120 uses chat GPT, an example of pre-trained artificial intelligence means 131, to generate text data regarding the conditions necessary for plan selection. For example, as an example of the conditions necessary for selecting a plan, text data is generated stating, "Yes, if you have any conditions regarding the number of participants (family composition, adults, children), destination (destination within Okinawa Prefecture), and departure date and time, please let us know!" Then, the first server 120 transmits to the user terminal 110, as an example of generated text data GT1 regarding the conditions necessary for the plan selection obtained by the execution, the message: "Yes, if you have any conditions regarding the number of participants (family composition, adults, children), destination (destination within Okinawa Prefecture), and departure date and time, please let us know!"

[0047] As a result, as shown in FIG. 6, an example of generated text data GT1 regarding the conditions necessary for plan selection, such as "Yes, please let us know if you have any conditions regarding the number of participants (family composition, adults, children), destination (destination within Okinawa Prefecture), and departure date and time!" is displayed on the talk screen 112. As a result, the user can understand what the necessary condition information PT1 is and can input the necessary condition information PT1.

[0048] Next, when the user inputs information PT1 about the necessary conditions on the talk screen 112, the user terminal 110 transmits the input information PT1 about the necessary conditions to the first server 120. Then, the first server 120 generates text data proposing one or more plans to the user based on the content of the website that has been pre-trained taking into account the necessary conditions using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. The first server 120 is configured to transmit the generated text data GT obtained by the execution to the user terminal 110.

[0049] As a result, the user is asked about condition information necessary for proposing a plan, and after receiving the necessary condition information from the user, a plan is selected and generated text data GT regarding the plan proposal is generated. As a result, users can receive proposals for plans that match their requirements. For example, you can receive suggestions for travel plans that match your family composition, number of people, destination, number of days, and duration.

[0050] Next, the prompt items 112g displayed in the prompt list display area 112f in FIG. 3 to FIG. 6 will be described. The prompt item 112g is a standard instruction command information item that is a prompt that has been set and registered in advance. When a prompt item 112 g is selected, the content of the request information PT, which is the instruction command information of the selected prompt item 112 g, is input into the input field 112 d of the talk screen 112 . The contents of the request information PT of the prompt item 112g entered in the input field 112d are configured to be transmitted to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, via the bot 121 of the first server 120.

[0051] This allows the contents of the request information PT that has been set and registered in advance regarding the contents before and after the exchange to be transmitted simply by performing a selection operation. As a result, the user can issue detailed instructions, for example, that have been pre-registered, without having to input text from a keyboard. Furthermore, you can get answers to your detailed instructions and commands. For example, assume that a selection operation is performed on the prompt item 112g of "Apply for reservation with this content." Then, as shown in FIG. 7, based on the URL information on which the plan is based, browser 111 displays, as an example, the website WB of the travel agency offering the proposed plan, and on that website WB, the departure date and time, number of people, destination, and other conditions can be entered into input field WB1, and all that remains to be done is to press the application button.

[0052] More specifically, based on the prompt item 112g "Make a reservation with this content," the user terminal 110 transmits to the first server 120 request information PT, which is instruction command information to the effect that "Make a reservation with this content on the plan's website." 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, to generate URL information that is the basis of the plan and input text data based on the contents of the plan. Then, the first server 120 transmits the generated text data GT for input obtained through the execution to the user terminal 110. Then, based on the URL information contained in the generated text data GT, the browser 111 of the user terminal 110 opens the website WB of the travel agency of the proposed plan, as an example, and based on the input data contained in the generated text data GT, the user enters the plan contents conditions such as departure date and time, number of people, destination, etc. into the input field WB1 of the website WB of the travel agency of the proposed plan. This allows you to simply press the application button. As a result, the user can complete the application procedure simply by operating the application button.

[0053] In addition, if Plan A to Plan C have been proposed as multiple plans and the user wishes to apply for Plan A among Plans A to C, the user enters "Plan A" in input field 112d and operates the "+" on the right side of prompt item 112g "Make a reservation with this content." Then, the user terminal 110 transmits to the first server 120 request information PT, which is instruction and command information to the effect that "submit a reservation application on the website of the plan with the contents of plan A." In other words, you can select only one of the multiple plans and apply.

[0054] In addition, when the prompt item 112g "Suggest another plan!" is selected, the first server 120 generates text data proposing to the user one or more plans different from the previously proposed plan based on the content of a website pre-trained using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. The first server 120 is configured to transmit the generated text data GT obtained by the execution to the user terminal 110.

[0055] Furthermore, when the prompt item 112g "A slightly more expensive plan!" is selected, the first server 120 generates text data proposing to the user one or more plans that are more expensive than the previously proposed plan based on the content of the website pre-trained using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. The first server 120 is configured to transmit the generated text data GT obtained by the execution to the user terminal 110.

[0056] On the other hand, when the prompt item 112g "Give me a cheaper plan!" is selected, the first server 120 generates text data proposing to the user one or more plans that are less expensive than the previously proposed plan based on the content of the website that has been pre-trained using chat GPT, an example of the pre-trained artificial intelligence means 131 of the second server 130. The first server 120 is configured to transmit the generated text data GT obtained by the execution to the user terminal 110.

[0057] Next, the main topic setting function will be described. In this embodiment, the user terminal 110 can freely specify a main topic for the bot 121 of the first server 120 . The specification may be made by operating a pin mark button 112e provided at the exchange location in the talk display area 112c of the talk screen 112 of the browser 111. Alternatively, the item name of the board item 112b may be specified. Furthermore, for example, the message "Set main topic" and information on the main topic to be specified may be entered in input field 112d of talk screen 112 of browser 111.

[0058] For example, "travel" is specified as main topic information TP1. The main topic information TP1 is the main information among the topic information TP described later. Then, as shown in FIG. 8, when the user inputs “Tell me about plans for Okinawa!” as an example of requested information PT on the talk screen 112 of the browser 111 while the main topic is being specified, the user terminal 110 transmits the input requested information PT to the first server 120. Then, the bot 121 of the first server 120 adds the main topic information TP1 to the received request information PT and transmits it to the second server .

[0059] Then, the second server 130 executes generation of text data based on the request information PT and the main topic information TP1 using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. The second server 130 is configured to transmit the generated text data GT obtained by the execution to the first server 120.

[0060] As a result, when a main topic is being specified on the talk screen 112 of the browser 111, the main topic information TP1 is always included in the information from the bot 121 to the chat GPT, which is an example of the pre-trained artificial intelligence means 131, in the interaction between the user and the chat GPT, which is an example of the pre-trained artificial intelligence means 131, and the generated text data GT generated by the chat GPT, which is an example of the pre-trained artificial intelligence means 131, has content that is in line with the main topic. As a result, it is possible to ensure that the content of consultations, etc., is consistent (the content is consistent) in interactions between the user and chat GPT, which is an example of the pre-trained artificial intelligence means 131. This means that even if a user asks a question multiple times, the answers stay on topic. As a result, you can avoid gradually drifting away from the main topic as you continue asking questions.

[0061] When canceling the main topic setting, the user may operate pin mark button 112e again to cancel the setting, or may input, for example, “Cancel main topic setting” in input field 112d of talk screen 112 of browser 111. In addition, when the main topic is being set on the talk screen 112 of the browser 111, the talk screen 112 of the browser 111 may be configured to display a message indicating that the main topic is being set, or the talk screen 112 of the browser 111 may be configured to display a message indicating that the main topic is being set, such as "Main topic "Travel" being set," as well as the main topic information TP1. This allows a user to interact with chat GPT, which is an example of a pre-trained artificial intelligence means 131, while checking that a main topic is being set and what the main topic information TP1 is. This means you can avoid forgetting to unsubscribe and continuing the conversation when you want to move on to the next topic. It also helps to avoid forgetting what the main topic was set to as you continue to exchange messages.

[0062] In this embodiment, as an example of a main topic setting function, when the first server 120 generates text data based on the content of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 is configured to add topic information TP indicating that it is about travel to the request information PT and send it to chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. As an example, when the board item 112b "Travel Agency" is selected in the board item display area 112a, the bot 121 of the first server 120 may be configured to add topic information TP indicating that it is about travel to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. On the other hand, if a board item display area 112a for displaying board items 112b is not provided, the bot 121 of the first server 120 may be configured to always add topic information TP indicating that it is about travel to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0063] As a result, the user is asked about condition information required for proposing a travel plan, and after receiving the necessary condition information from the user, a travel plan is selected and generated text data GT regarding the travel plan proposal is generated. As a result, users can receive travel plan suggestions that meet their requirements. In other words, you can receive travel plan suggestions that match your family composition, number of people, destination, number of days, and duration. In addition, for websites that chat GPT, which is an example of pre-trained artificial intelligence means 131, will pre-train, the range of websites that will be pre-trained may be specified in advance by an administrator using URL information or site map information. For example, the websites of multiple travel agencies may be pre-specified.

[0064] Next, as shown in FIG. 9, as an example, when the board item 112b "Real Estate Brokerage" is selected in the board item display area 112a, the bot 121 of the first server 120 may be configured to add topic information TP indicating that it is about real estate to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. On the other hand, if a board item display area 112a for displaying board items 112b is not provided, the bot 121 of the first server 120 may be configured to always add topic information TP indicating that it is about real estate to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. In this embodiment, as an example of a main topic setting function, when the first server 120 generates text data based on the content of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 is configured to add topic information TP indicating that it is about real estate to the request information PT and send it to chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0065] This allows the user to be asked about condition information required for proposing a real estate plan, and after receiving the necessary condition information from the user, a real estate plan is selected and generated text data GT regarding the real estate plan proposal is generated. As a result, users can receive plan proposals for real estate that meet their criteria. In other words, you can receive proposals for real estate purchasing plans that match your family composition and work location.

[0066] Although not shown in Figure 9, as mentioned above, when chat GPT, an example of pre-trained artificial intelligence means 131, generates text data for request information PT, as a preliminary step of proposing one or more plans to the user based on the contents of the pre-trained website, the first server 120 may use chat GPT, an example of pre-trained artificial intelligence means 131, to generate text data regarding the conditions necessary for plan selection, and transmit the generated text data GT1 regarding the conditions necessary for plan selection obtained by the above operation to the user terminal 110. Then, when the user inputs information PT1 about the necessary conditions on the talk screen 112, the user terminal 110 transmits the input information PT1 about the necessary conditions to the first server 120. Then, the first server 120 generates text data proposing one or more plans to the user based on the content of the website that has been pre-trained taking into account the necessary conditions using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, the first server 120 naturally transmits the generated text data GT obtained through the execution to the user terminal 110. In addition, for websites that chat GPT, an example of a pre-trained artificial intelligence means 131, pre-trains, the range of websites of multiple real estate agents to be pre-trained may be specified in advance by an administrator using URL information and site map information.

[0067] Also, as shown in FIG. 10, as an example, when the board item 112b "Purchasing a Used Car" is selected in the board item display area 112a, the bot 121 of the first server 120 may be configured to add topic information TP indicating that it is about a used car to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. On the other hand, if a board item display area 112a for displaying board items 112b is not provided, the bot 121 of the first server 120 may be configured to always add topic information TP indicating that it is about used cars to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. In this embodiment, as an example of a main topic setting function, when the first server 120 generates text data based on the content of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 is configured to add topic information TP indicating that it is about used cars to the request information PT and send it to chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0068] Thus, the user is asked about condition information necessary for proposing a plan for a used car, and after receiving the necessary condition information from the user, a plan for a used car is selected and generated text data GT for the proposal of the plan for the used car is generated. As a result, users can receive proposals for used cars that meet their requirements. In other words, customers can receive suggestions for used car purchasing plans that match their family composition, automatic transmission-only driver's license, dealer location area, and car size.

[0069] Although not shown in Figure 10, as mentioned above, when chat GPT, an example of pre-trained artificial intelligence means 131, generates text data for request information PT, as a preliminary step to proposing one or more plans to the user based on the contents of the pre-trained website, the first server 120 may use chat GPT, an example of pre-trained artificial intelligence means 131, to generate text data regarding the conditions necessary for plan selection, and transmit the generated text data GT1 regarding the conditions necessary for plan selection obtained by the above operation to the user terminal 110. For example, the generated text data GT1 may ask the user questions about the conditions necessary for selecting a plan, such as the user's car history, preferred type of car, frequency of use (e.g., only on weekends), time of use (e.g., mostly at night), family composition, etc.

[0070] Then, when the user inputs information PT1 about the necessary conditions on the talk screen 112, the user terminal 110 transmits the input information PT1 about the necessary conditions to the first server 120. Then, the first server 120 generates text data proposing one or more plans to the user based on the content of the website that has been pre-trained taking into account the necessary conditions using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, the first server 120 naturally transmits the generated text data GT obtained through the execution to the user terminal 110.

[0071] For example, if the main time of use is at night, we will recommend a used car with a bright body color that is highly visible. Also, if your family consists of 1-2 people, you will choose a 2-door car; if your family consists of 3-5 people, you will choose a 4-seater or larger car such as a sedan or SUV; and if your family consists of 6 or more people, you will choose a minivan. Furthermore, if the user's car history includes many European cars and the type of car they like is European, used European cars will be selected and suggested. In addition, for websites that chat GPT, an example of a pre-trained artificial intelligence means 131, pre-trains, the range of websites of multiple used car dealers to be pre-trained may be specified in advance by an administrator using URL information and site map information.

[0072] Furthermore, as shown in FIG. 11, as an example, when the board item 112b "job search" is selected in the board item display area 112a, the bot 121 of the first server 120 may be configured to add topic information TP indicating that it is about job searching to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. On the other hand, if a board item display area 112a for displaying board items 112b is not provided, the bot 121 of the first server 120 may be configured to always add topic information TP indicating that it is about job hunting to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. In this embodiment, as an example of a main topic setting function, when the first server 120 generates text data based on the content of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 is configured to add topic information TP indicating that it is about job hunting to the request information PT and send it to chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0073] As a result, the user is asked about condition information necessary for proposing a plan for job hunting, and after receiving the necessary condition information from the user, a plan for job hunting is selected and generated text data GT for the proposal of a plan for job hunting is generated. As a result, users can receive job search plans that match their criteria. In other words, you can receive job change and employment plans that match your work area, qualifications, and work location.

[0074] Although not shown in Figure 11, as mentioned above, when chat GPT, an example of pre-trained artificial intelligence means 131, generates text data for request information PT, as a preliminary step to proposing one or more plans to the user based on the contents of the pre-trained website, the first server 120 may use chat GPT, an example of pre-trained artificial intelligence means 131, to generate text data regarding the conditions necessary for plan selection, and transmit the generated text data GT1 regarding the conditions necessary for plan selection obtained by the above operation to the user terminal 110. Then, when the user inputs information PT1 about the necessary conditions on the talk screen 112, the user terminal 110 transmits the input information PT1 about the necessary conditions to the first server 120. Then, the first server 120 generates text data proposing one or more plans to the user based on the content of the website that has been pre-trained taking into account the necessary conditions using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, the first server 120 naturally transmits the generated text data GT obtained through the execution to the user terminal 110. In addition, for websites that chat GPT, which is an example of the pre-trained artificial intelligence means 131, pre-trains, the range of websites that multiple job search and recruitment agents (intermediaries) pre-train may be specified in advance by an administrator using URL information and site map information.

[0075] Also, as shown in FIG. 12, as an example, when the board item 112b of “Restaurant” is selected in the board item display area 112a, the bot 121 of the first server 120 may be configured to add topic information TP indicating that it is about eating and drinking to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. On the other hand, if a board item display area 112a for displaying board items 112b is not provided, the bot 121 of the first server 120 may be configured to always add topic information TP indicating that it is about eating and drinking to the request information PT and send it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. In this embodiment, as an example of a main topic setting function, when the first server 120 generates text data based on the content of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 is configured to add topic information TP indicating that it is about eating and drinking to the request information PT and send it to chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0076] As a result, the user is asked about condition information necessary for proposing an eating and drinking plan, and after receiving the necessary condition information from the user, an eating and drinking plan is selected and generated text data GT about the proposed eating and drinking plan is generated. As a result, users can receive dining plan suggestions that match their requirements. In other words, you can receive suggestions for dining plans that match your family composition and number of people, budget, allergies, location, day of the week, and time of day.

[0077] Although not shown in Figure 12, as mentioned above, when chat GPT, an example of pre-trained artificial intelligence means 131, generates text data for request information PT, as a preliminary step to proposing one or more plans to the user based on the contents of the pre-trained website, the first server 120 may use chat GPT, an example of pre-trained artificial intelligence means 131, to generate text data regarding the conditions necessary for plan selection, and transmit the generated text data GT1 regarding the conditions necessary for plan selection obtained by the above operation to the user terminal 110. Then, when the user inputs information PT1 about the necessary conditions on the talk screen 112, the user terminal 110 transmits the input information PT1 about the necessary conditions to the first server 120. Then, the first server 120 generates text data proposing one or more plans to the user based on the content of the website that has been pre-trained taking into account the necessary conditions using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, the first server 120 naturally transmits the generated text data GT obtained through the execution to the user terminal 110. In addition, for websites that chat GPT, an example of a pre-trained artificial intelligence means 131, pre-trains, the range of websites of multiple food and beverage introduction providers to be pre-trained may be specified in advance by an administrator using URL information and site map information.

[0078] Furthermore, in Fig. 7, only the application for a travel plan has been explained, but for real estate, used cars, job hunting, and dining shown in Fig. 9 to Fig. 12, as in the case of travel, by operating the prompt item 112g of "Apply for reservation with this content", the browser 111 will display the website WB of the plan, and the user will be able to enter the conditions in the input field WB1 and then just press the application button. Detailed explanations will be omitted.

[0079] The artificial intelligence system 100 thus obtained, which is an embodiment of the present invention, comprises a user terminal 110, a first server 120 and a second server 130 which are examples of servers, the first server 120 has a bot 121 which is also a display program, the second server 130 has a chat GPT which is an example of a pre-trained artificial intelligence means 131, the user terminal 110 communicates with the first server 120, the browser 111 of the user terminal 110 displays a talk screen 112, and when a user inputs request information PT which is instruction command information on the talk screen 112, the user terminal 110 transmits the input request information PT to the first server 120. The first server 120 uses chat GPT, an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate text data based on the pre-trained content of the website as a response to the request information PT, and transmits the generated text data GT obtained by the above processing to the user terminal 110, which then displays the received generated text data GT on the talk screen 112. This allows the user to obtain a response based on the content of the website in response to the request, and to obtain an answer to the content they were looking for on the web as their request without using the search engine of the browser 111.

[0080] Furthermore, when chat GPT, an example of pre-trained artificial intelligence means 131, generates text data for request 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 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 talk screen 112.This allows the user to easily check the accuracy and reliability (veracity) of the generated text data GT by referring to 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, when the chat GPT, which is an example of the pre-trained artificial intelligence means 131, generates text data for the request information PT, it generates text data that proposes one or more plans to the user based on the contents of the pre-trained website, and transmits the generated text data GT obtained by this execution to the user terminal 110, so that the user can adopt a plan they like and access and apply for it based on the basis information PF.

[0082] Furthermore, when chat GPT, which is an example of pre-trained artificial intelligence means 131, generates text data for request information PT, as a preliminary step of proposing one or more plans to the user based on the contents of the pre-trained website, the first server 120 executes text data generation of contents regarding conditions necessary for plan selection using chat GPT, which is an example of pre-trained artificial intelligence means 131, and transmits generated text data GT1 of contents regarding conditions necessary for plan selection obtained by the execution to the user terminal 110. When information PT1 regarding the necessary conditions is input by the user on the talk screen 112, the user terminal 110 transmits the input information PT1 regarding the necessary conditions to the first server 120, and the first server 120 transmits the information PT1 of the pre-trained artificial intelligence means 131 of the second server 130 to the user terminal 110. The system is configured to generate text data proposing one or more plans to the user based on the content of a website that has been pre-learned while taking into account necessary conditions using chat GPT, which is an example of the system, and to transmit the generated text data GT obtained by the execution to the user terminal 110. This allows the user to receive proposals for plans that match his / her conditions. For example, the user can receive proposals for plans that match the conditions of family structure / number of people, destination, number of days / period, real estate purchase plans that match the conditions of family structure and place of work, used car purchase plans that match the conditions of family structure, automatic transmission only driver's license, dealer location area, and car size, job change / employment plans that match the conditions of work area, qualifications held, and place of work, and dining plans that match the conditions of family structure / number of people, budget, allergies, location, day of the week, and time period.

[0083] In addition, when the first server 120 generates text data based on the contents of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 adds topic information TP indicating that it is about travel to the request information PT and uses chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, so that the user can receive suggestions for travel plans that meet his or her conditions, such as family composition / number of people, destination, number of days / period.

[0084] Furthermore, when the first server 120 generates text data based on the content of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 adds topic information TP indicating that it is about real estate to the request information PT and uses chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, so that the user can receive proposals for real estate plans that meet his or her conditions, and can receive proposals for real estate purchasing plans that meet the conditions of family composition and place of work.

[0085] In addition, when the first server 120 generates text data based on the content of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 is configured to add topic information TP indicating that it is about used cars to the request information PT and use chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, so that the user can receive proposals for plans for used cars that meet his or her conditions, and can receive proposals for used car purchasing plans that meet the conditions of family composition, automatic transmission-only driver's license, dealership location area, and car size.

[0086] Furthermore, when the first server 120 uses chat GPT, an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate text data based on the content of a pre-trained website as a response to the request information PT, the bot 121 of the first server 120 adds topic information TP indicating that it is about job hunting to the request information PT and uses chat GPT, an example of the pre-trained artificial intelligence means 131 of the second server 130, so that the user can receive proposals for job hunting plans that match his or her conditions, and can receive proposals for job change / employment plans that match the conditions of work area, qualifications held, and work location.

[0087] In addition, when the first server 120 generates text data based on the contents of a pre-trained website as a response to the request information PT using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, the bot 121 of the first server 120 adds topic information TP indicating that it is about eating and drinking to the request information PT and uses chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, so that the user can receive suggestions for eating and drinking plans that meet his or her conditions, such as family composition / number of people, budget, allergies, location, day of the week, and time of day.

[0088] Furthermore, 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 user terminal 110 communicates with the first server 120 and the browser 111 of the user terminal 110 displays the talk screen 112, an input transmission operation presence / absence determination step S2 in which it is determined whether or not a transmission operation has been performed by inputting request information PT, which is instruction command information, on the talk screen 112 by the user, and a request transmission step S3 in which the user terminal 110 transmits the input request information PT to the first server 120, and the first server 120 transmits the request information PT using a chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. The system has a text generation step S4 in which the first server 120 generates text data based on the contents of the website that has been pre-learned as an answer to the request, a text transmission step S5 in which the first server 120 transmits the generated text data GT obtained by the above execution to the user terminal 110, and a text display step S6 in which the user terminal 110 displays the received generated text data GT on the talk screen 112.This allows the user to obtain an answer based on the contents of the website in response to the request, and has a significant effect in that the user can obtain an answer to the content he or she is looking for on the web without using the search engine of the browser 111. [Explanation of symbols]

[0089] 100 ··· Artificial Intelligence Systems 110 User terminal 111 ··· Browser 112 ··· Chat screen 112a Board item display area 112b Board items (document items, communication items) 112c...Talk display area 112d... Input field 112e··· Pin mark button 112f Prompt list display area 112g Prompt item (standard instruction information item) 120 1st Server 121 ··· Bot 130 Second Server 131 ··· Pre-trained AI method (Chat GPT) PT: Request information (instruction and command information) PT1 - Information about necessary conditions GT: Generated text data GT1: Generated text data (content about conditions required for plan selection) PF: Basis information TP ··· Topic Information TP1 ··· Main Topic Information WB ··· (the travel agency's) website WB1 ... (website) field

Claims

1. An artificial intelligence system comprising a user terminal and a server, wherein the user terminal can communicate with the pre-trained artificial intelligence means of the server, the user terminal communicates with the server, and the browser of the user terminal displays a talk screen, when request information, which is instruction command information, is input by the user on the talk screen, the user terminal transmits the input request information to the server, the server uses the pre-trained artificial intelligence means to execute the generation of text data of content based on the content of the pre-learned website as an answer to the request information, and transmits the generated text data obtained by the execution to the user terminal, The artificial intelligence system is characterized in that the user terminal is configured to display the received generated text data on the talk screen.

2. When the pre-trained artificial intelligence means generates text data for the request information, the pre-trained artificial intelligence means generates basis information on which page or which part of the content information specified by the loaded URL information is based, the server transmits the generated text data and the basis information to the user terminal, 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 the talk screen.

3. When the pre-trained artificial intelligence means generates text data for the request information, the artificial intelligence system according to claim 1 or claim 2 is characterized in that it executes the generation of text data of content for proposing one or more plans to the user based on the content of the pre-learned website, and transmits the generated text data obtained by the execution to the user terminal.

4. As a stage prior to proposing one or more plans to the user based on the content of the pre-learned website when the pre-trained artificial intelligence means generates text data for the request information, the server uses the pre-trained artificial intelligence means to execute the generation of text data of content regarding the conditions necessary for plan selection, and transmits the generated text data of content regarding the conditions necessary for plan selection obtained by the execution to the user terminal, when information about the necessary conditions is input by the user on the talk screen, the user terminal transmits the input information about the necessary conditions to the server, The server executes generation of text data of the content for proposing one or more plans to the user based on the content of the pre-learned website considering necessary conditions using pre-learned artificial intelligence means, and transmits the generated text data obtained by the execution to the user terminal. The artificial intelligence system according to claim 3, characterized in that it is configured as such.

5. When the server executes generation of text data of the content based on the content of the pre-learned website as an answer to the desired information using pre-learned artificial intelligence means, the server adds topic information indicating that it is about travel to the desired information and uses the pre-learned artificial intelligence means. The artificial intelligence system according to claim 4, characterized in that it is configured as such.

6. When the server executes generation of text data of the content based on the content of the pre-learned website as an answer to the desired information using pre-learned artificial intelligence means, the server adds topic information indicating that it is about real estate to the desired information and uses the pre-learned artificial intelligence means. The artificial intelligence system according to claim 4, characterized in that it is configured as such.

7. When the server executes generation of text data of the content based on the content of the pre-learned website as an answer to the desired information using pre-learned artificial intelligence means, the server adds topic information indicating that it is about used cars to the desired information and uses the pre-learned artificial intelligence means. The artificial intelligence system according to claim 4, characterized in that it is configured as such.

8. When the server executes generation of text data of the content based on the content of the pre-learned website as an answer to the desired information using pre-learned artificial intelligence means, the server adds topic information indicating that it is about job hunting to the desired information and uses the pre-learned artificial intelligence means. The artificial intelligence system according to claim 4, characterized in that it is configured as such.

9. When the server executes generation of text data of the content based on the content of the pre-learned website as an answer to the desired information using pre-learned artificial intelligence means, the server adds topic information indicating that it is about food and beverage to the desired information and uses the pre-learned artificial intelligence means. The artificial intelligence system according to claim 4, characterized in that it is configured as such.

10. A program of an artificial intelligence system in which a user terminal can communicate with pre-trained artificial intelligence means of a server, a talk screen display step in which the user terminal communicates with the server and the browser of the user terminal displays a talk screen; an input transmission operation presence / absence determination step of determining whether or not request information, which is instruction command information, has been input by the user on the talk screen and a transmission operation has been performed; a request transmission step in which the user terminal transmits the input request information to the server; a text generation step in which the server executes generation of text data of content based on the content of a pre-learned website as an answer to the request information using the pre-trained artificial intelligence means; a text transmission step in which the server transmits the generated text data obtained by the execution to the user terminal; and a text display step in which the user terminal displays the received generated text data on the talk screen, characterized by being a program of an artificial intelligence system.

Images