Chat system, program for chat system, email system, and program for email system

Abstract

To provide a chat system that enables a user to easily interact with pre-trained artificial intelligence means on an existing talk screen of a user terminal.SOLUTION: A chat system 100 includes a user terminal 110, a first server 120, and a second server 130. When a user inputs arbitrary instruction command information PT in a state where a bot 121 is designated as a talk partner on a talk screen 113 of the user terminal, the user terminal transmits the instruction command information to the first server, the bot 121 of the first server transmits the instruction command information to the second server, the second server uses pre-trained artificial intelligence means 131 of the second server to generate text data with contents based on the instruction command information, and transmits the generated text data GT obtained by the execution to the user terminal via the bot of the first server, and the user terminal displays the generated text data on the talk screen.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a chat system that includes a user terminal and a server and allows free communication of text data between the user terminal and the server, a chat system program, an e-mail system, and an e-mail system program. [Background technology]

[0002] Conventionally, as a message sending and receiving system, a chat system has been known which is composed of an information processing device having a chat server function, an information processing device used by a client, an information processing device used by an operator, an information processing device for storing external data, and an image forming device having a printing function (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-47719 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the chat system, which is the conventional message sending and receiving system described above, was configured to allow communication between an information processing device used by a client and an information processing device used by other clients, or between an information processing device used by a client and an information processing device used by an operator. Therefore, it was limited to chatting between clients, or between a client and an operator, and there was a problem that it was difficult to communicate with chat GPT, which is an example of a pre-trained artificial intelligence means, in the chat system.

[0005] Therefore, the present invention solves the problems of the prior art as described above, that is, the object of the present invention is to provide a chat system, which is a message sending and receiving system, a program for the chat system, an email system, which is a message sending and receiving system, and a program for the email system, which allow a user to easily interact with a chat GPT, which is an example of a pre-trained artificial intelligence means, in a message sending and receiving window such as an existing talk screen or an existing sent message window of a user terminal. [Means for solving the problem]

[0006] The invention of claim 1 is a chat system comprising a user terminal and a server, and capable of freely communicating text data between the user terminal and the server, wherein when a user inputs any instruction or command information with a bot designated as a talk partner on the talk screen of the user terminal, the user terminal transmits the input instruction or command information to a first server, the bot of the first server transmits the received instruction or command information to a second server different from the first server, the second server generates text data based on the instruction or command information using a pre-trained artificial intelligence means of the second server, and transmits the generated text data obtained by the execution to the bot of the first server, the bot of the first server transmits the received generated text data 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 configuring the chat system as described in claim 1, in addition to the above-mentioned problem, in such a way that prohibited words can be freely set on the management screen of an administrator terminal capable of communicating with the first server, and when data containing pre-set prohibited words is entered on the talk screen of the user terminal, the bot of the first server that receives the data determines that the received data contains prohibited words, does not send the received data to the second server, and sends information to the user terminal that the data contains unavailable words.

[0008] The invention of claim 3 further solves the above-mentioned problem by configuring the chat system as described in claim 2, and further configuring the management screen of an administrator terminal capable of communicating with the first server to freely display historical information of interactions between a user terminal and a bot of the first server on the talk screen of the user terminal, the historical information including transmission date and time information, user identification information, IP address information, instruction and command information entered on the talk screen, and information on whether or not generated text data has been returned from the pre-trained artificial intelligence means of the second server.

[0009] The invention according to claim 4 further solves the above-mentioned problem by being configured such that, in addition to the configuration of the chat system described in any one of claims 1 to 3, masking of word attributes included in data sent from a user terminal to a bot of the first server can be freely set on an administration screen of an administrator terminal capable of communicating with the first server, and when data including characters of a word attribute of a masking preset is input on the talk screen of the user terminal, the bot of the first server that receives the data determines that the received data includes characters of a word attribute of a masking, converts the characters of the word attribute of the masking in the received data to another arbitrary character of the same word attribute, and then transmits the converted data to the second server, the second server executes text data generation based on the converted data using the pre-trained artificial intelligence means of the second server, and transmits the generated text data obtained by the execution to the bot of the first server, and the bot of the first server changes the other arbitrary character part of the received generated text data that was converted when sending to the second server back to the character before conversion, and then transmits the changed generated text data to the user terminal.

[0010] The invention of claim 5 further solves the above-mentioned problem by, in addition to the chat system configuration described in claim 4, being configured such that on the management screen of an administrator terminal capable of communicating with the first server, users who can use the bot of the first server on the talk screen of a user terminal can be freely set based on user identification information.

[0011] The invention of claim 6 further solves the above-mentioned problem by, in addition to the configuration of the chat system described in claim 5, allowing the user to freely create talk groups including bots and other users on the settings screen of the user terminal, and by configuring the user terminal to transmit the inputted instruction and command information to a first server when a talk group is specified as a talk partner on the talk screen and the user inputs any instruction and command information.

[0012] The invention of claim 7 is a program for a chat system that can freely communicate text data between a user terminal and a server, which solves the above-mentioned problem by having an input determination step of determining whether or not any instruction command information has been input by a user with a bot designated as a talk partner on the talk screen of the user terminal, a first instruction command transmission step in which the user terminal transmits the input instruction command information to a first server, a second instruction command transmission step in which the bot of the first server transmits the received instruction command information to a second server different from the first server, a generation execution step in which the second server generates text data based on the instruction command information using a pre-trained artificial intelligence means of the second server, a first generated data transmission step in which the second server transmits the generated text data obtained by the execution to the bot of the first server, a second generated data transmission step in which the bot of the first server transmits the received generated text data to the user terminal, and a display step in which the user terminal displays the received generated text data on the talk screen.

[0013] The invention of claim 8 is an electronic mail system comprising a user terminal and a server, and capable of freely communicating text data between the user terminal and the server, in which when a user inputs any instruction or command information with the address of a bot specified as the destination in the sending message window of the user terminal, the user terminal transmits the input instruction or command information to a first server, the bot of the first server transmits the received instruction or command information to a second server different from the first server, the second server generates text data based on the instruction or command information using a pre-trained artificial intelligence means of the second server, and transmits the generated text data obtained by the execution to the bot of the first server, the bot of the first server transmits the received generated text data to the user terminal, and the user terminal displays the received generated text data in the receiving message window, thereby solving the above-mentioned problem.

[0014] The invention of claim 9 is a program for an email system capable of freely communicating text data between a user terminal and a server, which solves the above-mentioned problem by having an input determination step of determining whether or not any instruction command information has been input by a user with the address of a bot specified as the destination in the sending message window of the user terminal, a first instruction command transmission step in which the user terminal transmits the input instruction command information to a first server, a second instruction command transmission step in which the bot of the first server transmits the received instruction command information to a second server different from the first server, a generation execution step in which the second server generates text data based on the instruction command information using the pre-trained artificial intelligence means of the second server, a first generated data transmission step in which the second server transmits the generated text data obtained by the execution to the bot of the first server, a second generated data transmission step in which the bot of the first server transmits the received generated text data to the user terminal, and a display step in which the user terminal displays the received generated text data in the receiving message window. Effect of the Invention

[0015] The chat system and e-mail system of the present invention, by being equipped with a user terminal and a server, not only allows for the communication of text data between the user terminal and the server, but also provides the following unique effects.

[0016] According to the chat system of the invention of claim 1, simply adding a bot of the first server to the talk screen of an existing chat makes it possible to freely interact with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, so that a user can easily interact with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, via the bot of the first server on the talk screen of the user terminal.

[0017] According to the chat system of the invention of claim 2, in addition to the effect of the invention of claim 1, for example, by presetting words such as "confidential," "personal information," and "My Number" as prohibited words, if the prohibited words are included in the data entered by the user, the bot of the first server detects the prohibited words and stops the exchange with the chat GPT, which is an example of the pre-trained artificial intelligence means of the second server, and information indicating that the data contains unusable words is sent to the user terminal, thereby prohibiting undesirable use by the user. In other words, since the transmission of information to chat GPT, which is an example of the second server's pre-trained artificial intelligence means, is restricted, it is possible to avoid information leakage to other terminals via chat GPT, which is an example of the second server's pre-trained artificial intelligence means.

[0018] According to the chat system of the invention of claim 3, in addition to the effect of the invention of claim 2, information regarding which user entered what content, when, where, and whether they obtained any results is displayed on the management screen, so that the administrator can check whether the user's usage is appropriate.

[0019] According to the chat system of the invention of claim 4, in addition to the effects of the invention of any one of claims 1 to 3, for example, by setting in advance masking of word attributes that can identify individuals, such as name, address, telephone number, and email address, for data from a user terminal to a bot on the first server, if the data entered by the user contains characters with these word attributes, the bot on the first server converts the characters with these word attributes into other arbitrary characters with the same word attributes and then transmits the converted data to the second server, and text data generation is performed based on the converted data, thereby preventing the chat GPT, which is an example of a pre-trained artificial intelligence means on the second server, from memorizing information about characters with word attributes that can identify individuals. In other words, since the content sent to Chat GPT, which is an example of the second server's pre-trained artificial intelligence means, is converted into characters that cannot be used to identify individuals, it is possible to avoid the leakage of personally identifiable information to other terminals via Chat GPT, which is an example of the second server's pre-trained artificial intelligence means. Furthermore, when the bot of the first server receives generated text data from the second server, the other arbitrary character part of the received generated text data that was converted when it was sent to the second server is modified to return it to the character before conversion, and the modified generated text data is sent to the user terminal, so that modified generated text data that basically conforms to the intent of the instruction command information entered by the user can be obtained. In other words, the characters converted when the bot on the first server sends to the second server are converted back to the original characters when the bot on the first server receives from the second server, thereby preventing unwanted information leakage to the second server or to other terminals via the second server, and ensuring consistency between the instructions and commands from the user terminal and the responses to the user terminal.

[0020] According to the chat system of the invention of claim 5, in addition to the effect of the invention of claim 4, a user is identified based on user identification information, and users who can interact with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, are specified and restricted via a bot on the first server, so that an administrator can easily set usage restrictions and permissions for Chat GPT for each employee member.

[0021] According to the chat system of the invention of claim 6, in addition to the effect of the invention of claim 5, it is possible to communicate with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, via a bot of the first server during a group discussion on the talk screen, so that users can obtain advice and information from Chat GPT during group discussions and share the obtained advice and information with other members of the same group.

[0022] According to the chat system of the invention of claim 7, similar to the effect achieved by the invention of claim 1, by simply adding a bot of the first server to the talk screen of an existing chat, it becomes possible to freely interact with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, so that a user can easily interact with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, via the bot of the first server on the talk screen of the user terminal.

[0023] According to the email system of the invention of claim 8, similar to the effect achieved by the invention of claim 1, it is possible to freely communicate with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, simply by specifying the address of the bot of the first server as the destination in the sending message window of an existing email app, so that a user can easily communicate with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, via the bot of the first server in the message sending and receiving windows of the sending message window and receiving message window of the user terminal.

[0024] According to the program of the email system of the invention of claim 9, similar to the effects achieved by the inventions of claims 1 and 8, it is possible to freely communicate with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, simply by specifying the address of the bot of the first server as the destination in the sending message window of an existing email app, so that the user can easily communicate with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, via the bot of the first server in the message sending and receiving windows of the sending message window and receiving message window of the user terminal. [Brief description of the drawings]

[0025] [Figure 1] FIG. 1 is a diagram showing the concept of a chat system according to a first embodiment of the present invention. [Diagram 2]FIG. 2 is a chart showing an example of the operation of the chat system according to the first embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram showing an example of a talk screen of a user terminal of the chat system according to the first embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing an example of a talk screen on a smartphone user terminal of the chat system according to the first embodiment of the present invention. [Diagram 5] 1A and 1B are diagrams showing an example of setting prohibited words on an administration screen of a chat system according to a first embodiment of the present invention, and a diagram showing a state when a prohibited word is entered on a talk screen. [Figure 6] FIG. 2 is a diagram showing a state in which a log is displayed on the management screen of the chat system according to the first embodiment of the present invention. [Figure 7] 1A and 1B are diagrams showing an example of masking settings on an administration screen of a chat system according to a first embodiment of the present invention, and a diagram showing a state when characters to be masked are entered on a talk screen. [Figure 8] FIG. 4 is a diagram for explaining an example of a masking operation of the chat system according to the first embodiment of the present invention. [Figure 9] FIG. 2 is a diagram showing an example of settings for users who can use a bot on the management screen of the chat system according to the first embodiment of the present invention. [Figure 10] FIG. 1 is a diagram showing an example of a group chat exchange on a talk screen of a user terminal in a chat system according to a first embodiment of the present invention. [Figure 11] 13A and 13B are diagrams showing an example of an input in a sending message window, which is a message sending / receiving window, and a display example in a receiving message window, which is a message sending / receiving window, of an electronic mail system according to a second embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0026] The chat system, which is a message sending and receiving system of the present invention, comprises a user terminal and a server, and when a user inputs instruction and command information as arbitrary data with a bot designated as a talk partner on the talk screen of the user terminal, the user terminal transmits the input instruction and command information as data to a first server, which is a server, and the bot of the first server transmits the received instruction and command information as data to a second server different from the first server, and the second server generates text data based on the instruction and command information as data using the pre-trained artificial intelligence means of the second server, and transmits the generated text data obtained by this generation to the bot of the first server, and the bot of the first server transmits the received generated text data to the user terminal, and the user terminal displays the received generated text data on the talk screen.As long as the user can easily interact with the chat GPT, which is an example of the pre-trained artificial intelligence means of the second server, via the bot of the first server on the talk screen of the user terminal, the specific implementation may be any one. In addition, the program of the chat system of the present invention includes an input determination step of determining whether or not a user has input instruction and command information as arbitrary data with a bot designated as a talk partner on the talk screen of the user terminal, a first instruction and command transmission step in which the user terminal transmits the instruction and command information as input data to a first server, which is a server, a second instruction and command transmission step in which the bot of the first server transmits the instruction and command information as received data to a second server different from the first server, a generation execution step in which the second server generates text data based on the instruction and command information as data using the pre-trained artificial intelligence means of the second server, a first generated data transmission step in which the second server transmits the generated text data obtained by the execution to the bot of the first server, a second generated data transmission step in which the bot of the first server transmits the received generated text data to the user terminal, and a display step in which the user terminal displays the received generated text data on the talk screen, so that the specific embodiment may be any as long as the user can easily interact with the chat GPT, which is an example of the pre-trained artificial intelligence means of the second server, via the bot of the first server on the talk screen of the user terminal. Furthermore, the email system, which is a message sending and receiving system of the present invention, comprises a user terminal and a server, and when a user inputs instruction and command information as arbitrary data with the address of a bot specified as the destination in the sending message window of the user terminal, the user terminal sends the input instruction and command information as data to a first server, which is a server, and the bot of the first server sends the received instruction and command information as data to a second server different from the first server, and the second server generates text data based on the instruction and command information as data using the pre-trained artificial intelligence means of the second server, and sends the generated text data obtained by this execution to the bot of the first server, and the bot of the first server sends the received generated text data to the user terminal, and the user terminal displays the received generated text data in the receiving message window.As long as the user can easily interact with the chat GPT, which is an example of the pre-trained artificial intelligence means of the second server, via the bot of the first server in the message sending and receiving window of the sending message window and the receiving message window of the user terminal, the specific embodiment may be any one. The program of the electronic mail system of the present invention includes an input determination step of determining whether or not a user has input instruction command information as arbitrary data with the address of a bot specified as the destination in a sending message window of a user terminal; a first instruction command transmission step of the user terminal transmitting the instruction command information as input data to a first server which is a server; a second instruction command transmission step of the bot of the first server transmitting the instruction command information as received data to a second server different from the first server; a generation execution step of the second server executing text data generation based on the instruction command information as data using pre-trained artificial intelligence means of the second server; The specific implementation may be any as long as it has a first generated data transmission step in which the server transmits the generated text data obtained by execution to a bot of the first server, a second generated data transmission step in which the bot of the first server transmits the received generated text data to a user terminal, and a display step in which the user terminal displays the received generated text data in a received message window, thereby allowing the user to easily interact with Chat GPT, which is an example of a pre-trained artificial intelligence means of the second server, via the bot of the first server in the message sending and receiving windows of the sending message window and the receiving message window of the user terminal.

[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 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. Furthermore, a server (chat server) that mediates the exchange of text data between the user terminal and other terminals may receive text data from the user terminal and may have the same physical configuration as the first server or may have a different configuration. A chat talk screen is a screen that displays the exchange of text and file data with one or more people (including bots) in chronological order on a single screen. EXAMPLES

[0028] A chat system 100, which is a message sending / receiving system according to a first embodiment of the present invention, will be described below with reference to FIGS. 1 is a diagram showing the concept of chat system 100 according to the first embodiment of the present invention, FIG. 2 is a chart showing an example of the operation of chat system 100 according to the first embodiment of the present invention, FIG. 3 is a diagram showing an example of talk screen 113 of user terminal 110 of chat system 100 according to the first embodiment of the present invention, FIG. 4 is a diagram showing an example of talk screen 113 of user terminal 110 of chat system 100 according to the first embodiment of the present invention when user terminal 110 of chat system 100 according to the first embodiment of the present invention is a smartphone, FIG. 5(A) is a diagram showing an example of setting prohibited words PB on management screen 114 of chat system 100 according to the first embodiment of the present invention, FIG. 5(B) is a diagram showing the state when prohibited words PB are entered on talk screen 113 of user terminal 110, and FIG. FIG. 7(A) is a diagram showing a log displayed on an administration screen 114 of a chat system 100; FIG. 7(A) is a diagram showing an example of masking settings on administration screen 114 of chat system 100, which is the first embodiment of the present invention; FIG. 7(B) is a diagram showing the state when characters to be masked are entered on talk screen 113 of a user terminal 110; FIG. 8 is a diagram explaining an example of masking operation in chat system 100, which is the first embodiment of the present invention; FIG. 9 is a diagram showing an example of settings of users available to bot 121 on administration screen 114 of chat system 100, which is the first embodiment of the present invention; and FIG. 10 is a diagram showing an example of group talk exchange on talk screen 113 of user terminal 110 of chat system 100, which is the first embodiment of the present invention.

[0029] As shown in FIG. 1, a chat system 100 according to a first embodiment of the present invention includes a user terminal 110 and a server. Chat system 100 is configured so that data DT such as text data can be freely communicated between user terminal 110 and a server, which is an example of a chat server. The chat server may be configured separately from first server 120 or second server 130, or may be configured in common with first server 120 or second server 130. It is assumed that a chat application is installed on the user terminal 110. Then, the browser 112 displayed on the display unit 111 of the user terminal 110 displays a talk screen 113 of the chat application. Moreover, on the screen of the chat application displayed by the browser 112, a bot 121 is added as a talk partner, and the bot 121 is freely specified on the talk screen 113.

[0030] In this embodiment, when a user inputs instruction command information PT, which is a so-called prompt, as arbitrary data DT with a bot 121 specified as a talk partner on the talk screen 113 of the user terminal 110, the user terminal 110 transmits the instruction command information PT as the input data DT to the first server 120, which is a server. Then, the bot 121 of the first server 120 transmits the instruction command information PT as the received data DT to the second server 130 different from the first server 120. Furthermore, the second server 130 executes generation of text data based on the instruction command information PT as the data DT, using the pre-trained artificial intelligence means 131 of the second server 130.

[0031] For example, chat GPT is used as an example of the pre-trained artificial intelligence means 131. Then, the second server 130 transmits the generated text data GT obtained through the execution to the bot 121 of the first server 120. Then, the bot 121 of the first server 120 transmits the received generated text data GT to the user terminal 110. The user terminal 110 is configured to display the received generated text data GT on the talk screen 113.

[0032] This allows free interaction with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, simply by adding the bot 121 of the first server 120 to the talk screen 113 of an existing chat (message). As a result, the user can easily interact with 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 on the talk screen 113 of the user terminal 110.

[0033] Next, an example of the operation of the chat system 100 will be described in more detail. As shown in FIG. 2, in step S1, as an input determination step, the user terminal 110 determines whether or not the user has input instruction command information PT, which is a prompt as arbitrary data DT, with the bot 121 specified as the talk partner on the talk screen 113 of the user terminal 110.

[0034] More specifically, as shown in FIG. 3, in the left column of the talk screen 113 of the user terminal 110, the bot 121 is selected and designated as a talk partner by a user operation. When the bot 121 is specified as a conversation partner, the interaction between the user and the bot 121 is displayed in the right-hand area. Then, when an example of a prompt such as "What are the top five languages ​​used in the world?" is entered and a send operation such as pressing the Enter key or pressing the Send button is performed, it is determined that instruction command information PT as data DT has been entered and the process proceeds to step S2; on the other hand, if it is determined that it has not yet been entered, step S1 is repeated.

[0035] In step S2, as a first instruction / command transmitting step, user terminal 110 transmits instruction / command information PT as input data DT to first server 120 which is a server. In step S3, as a second instruction / command transmission step, the bot 121 of the first server 120 transmits the instruction / command information PT as the received data DT to the second server 130 different from the first server 120.

[0036] In step S4, as a generation execution step, the second server 130 executes generation of text data based on the instruction command information PT using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. By executing this, generated text data GT is obtained, for example, which has the following contents: "1. Chinese (Mandarin), 2. Spanish, 3. English, 4. Arabic, 5. Hindi."

[0037] In step S5, as a first generated data transmission step, the second server 130 transmits the generated text data GT obtained by the execution to the bot 121 of the first server 120. In step S6, as a second generated data transmission step, the bot 121 of the first server 120 transmits the received generated text data GT to the user terminal 110. In step S7, as a display step, the user terminal 110 displays the received generated text data GT on the talk screen 113 as shown in FIG.

[0038] As a result, as described above, by simply adding the bot 121 of the first server 120 to the talk screen 113 of an existing chat, it becomes possible to freely interact with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. As a result, the user can easily interact with 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 on the talk screen 113 of the user terminal 110. Although an example has been described in which 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, which is a prompt, the generated data is not limited to text format data. The generated data is not limited to generated text data GT, but may be image data such as photographs and videos.

[0039] As shown in FIG. 4, when the user terminal 110 is a smartphone, the configuration is the same as that shown in FIG. It should be noted that a rich menu can be displayed below the talk screen 113 by setting the management screen 114 described later. More specifically, as an example of a rich menu, a button for asking a question to the chat GPT, a button for requesting a summary from the chat GPT, and a help button can be set. For example, if the user operates a button to ask a question to the chat GPT after inputting something, instruction command information PT is sent to inform the user of the content previously input. Furthermore, after the user inputs something, if the user operates a button to request a summary from the chat GPT, instruction command information PT is sent to the user to create a summary of the previously inputted content. Furthermore, when the user operates the help button, instruction command information PT for asking a question is transmitted, and the user is asked on the talk screen 113 what he or she is having trouble with.

[0040] Furthermore, in this embodiment, as shown in FIG. 5(A), prohibited words PB can be freely set on an administration screen 114 displayed on a browser 112 of a user terminal 110, which is an example of an administrator terminal capable of communicating with the first server 120. For example, it is assumed that "confidential", "personal information", "confidential", and "credit card" are set as prohibited words PB.

[0041] 5B, it is assumed that instruction command information PT is input as data DT including prohibited words PB of "personal information" that are preset on the talk screen 113 of the user terminal 110. Then, the bot 121 of the first server 120 that receives the data determines that the instruction command information PT as the received data DT contains the prohibited word PB of "personal information." The bot 121 of the first server 120 is configured not to send the received instruction command information PT to the second server 130, but to send to the user terminal 110 an example of information indicating that an unavailable word is included, such as "The text contains an unavailable word. Please try using a different expression."

[0042] As a result, for example, by presetting words such as "confidential," "personal information," and "My Number" as prohibited words PB for data DT, if the prohibited word PB is included in the instruction command information PT as data DT entered by a user, the bot 121 of the first server 120 detects the prohibited word PB and stops communication with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, and sends information to the user terminal 110 that an unusable word is included. As a result, undesirable use by users can be prohibited. In other words, the transmission of information to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, is restricted. As a result, it is possible to prevent information leakage to other terminals via the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0043] In addition, in this embodiment, as shown in Figure 6, on an administration screen 114 displayed on a browser 112 of a user terminal 110, which is an example of an administrator terminal capable of communicating with the first server 120, historical information of interactions between the user terminal 110 and a bot 121 of the first server 120 on a talk screen 113 of the user terminal 110 can be freely displayed. The history information items include the access date and time, which is transmission date and time information, the user ID, which is user identification information US, IP address information, the channel, which is chat application type information, the action, which is the type of prompt, the input text, which is the instruction command information PT entered on the talk screen 113, and the result, which is information on whether or not a reply has been received of the generated text data GT from the pre-trained artificial intelligence means 131 of the second server 130. Then, the information is displayed for each item. This allows information regarding which user entered what content, when, where, and whether or not they obtained any results to be displayed on the management screen 114. As a result, the administrator can check whether the user's usage is appropriate or not.

[0044] Furthermore, in this embodiment, as shown in Figure 7 (A), on an administration screen 114 displayed on a browser 112 of a user terminal 110, which is an example of an administrator terminal capable of communicating with the first server 120, masking of word attributes contained in data DT from the user terminal 110 to a bot 121 of the first server 120 can be freely set. For example, suppose that the word attributes "name," "address," "telephone number," "My Number," and "email address" are selected and masking is set.

[0045] Then, as shown in FIG. 7(B), assume that a file of an employee list containing characters WD with a pre-set masking word attribute is input as an example of data DT on the talk screen 113 of the user terminal 110, and a prompt "↑Tell me who here has not been transferred in the last three years" is input as instruction and command information PT. Here, the employee list file contains characters with the attribute "name", which is an example of the characters WD of the masking word attribute, as employee names. Then, by a send operation, a file of the employee list including the characters WD with the preset masking word attribute and a prompt "↑Tell me who here has not been transferred in the last three years" as instruction and command information PT are sent from the user terminal 110 to the first server 120.

[0046] Here, the command information PT does not include anything to be masked. Since the other file, an employee list, contains the masking target, the masking process will be described using the employee list file as an example. As shown in FIG. 8, an employee list file is transmitted from a user terminal 110 to a first server 120. Then, the bot 121 of the first server 120 that receives the data determines that the employee list file of the received data DT contains characters WD with the masking word attribute. Here, the bot 121 is configured to be able to determine the attributes of “name,” “address,” “telephone number,” “My Number,” and “email address” when scanning data DT such as text based on the database of the first server 120. Regarding the determination of word attributes, the bot 121 of the first server 120 may refer to a list of word attributes previously stored in a database and determine, for example, that it is a name attribute, an address attribute, etc., or may determine that it is a name attribute, an address attribute, etc. from the context of that part of the text data, or may determine that it is a name attribute, an address attribute, etc. from the way that part of the text data is written (style format).

[0047] More specifically, the names of employees, which are the word attribute of "name" listed in the employee directory, are detected. Then, the bot 121 of the first server 120 converts the employee name, which is the character WD of the masking word attribute, in the employee list file of the received data DT into a combination of "name", which is an example of another arbitrary character WD1 of the same word attribute, and a number such as "1". Thereafter, the bot 121 of the first server 120 transmits the employee list file of the converted data DT1 to the second server 130 together with a prompt. The bot 121 of the first server 120 stores a list of the conversions (a table showing the correspondence between before and after the conversion).

[0048] Thereafter, the second server 130 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 employee list file and prompts of the converted data DT1. As an example, we will select people who have not been transferred for three years for the word attributes "Name 1," "Name 2," etc., which are converted from the joining date information and past transfer history information written in the employee register file. Then, "There are 10 people: Name 1, Name 3, Name 5, Name 7, . . . " is obtained as an example of generated text data GT. Next, the second server 130 transmits the generated text data GT obtained by the execution to the bot 121 of the first server 120.

[0049] Then, the bot 121 of the first server 120 changes the part of the received generated text data GT, which was converted from another arbitrary character WD1 when it was sent to the second server 130, back to the character WD before conversion. The bot 121 of the first server 120 refers to the list (pre-conversion correspondence table) saved at the time of conversion and changes it back to the characters WD before conversion. For example, if "Suzuki Emi" is converted to "Name 1", then "Name 1" is changed back to "Suzuki Emi" (reverse conversion). Then, as an example of the generated text data GT1 after the change, "The 10 people are Emi Suzuki, Ichiro Tanaka, John Smith, Amy Marshall, . . . " is obtained. Thereafter, the bot 121 of the first server 120 is configured to transmit the modified generated text data GT1 to the user terminal 110.

[0050] As a result, for example, by setting in advance masking of word attributes that can identify an individual, such as name, address, telephone number, and email address, for data DT sent from the user terminal 110 to the bot 121 of the first server 120, if the data DT entered by the user contains characters WD of these word attributes, the bot 121 of the first server 120 will convert the characters WD of these word attributes into other arbitrary characters WD1 of the same word attribute and then send the converted data DT1 to the second server 130, and text data generation will be performed based on the converted data DT1. As a result, as shown in FIG. 8, it is possible to prevent the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, from memorizing information about the characters WD with the word attribute that can identify an individual. In other words, the content sent to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, is converted into characters that cannot identify individuals. As a result, it is possible to prevent leakage of personally identifiable information to other terminals via the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0051] Furthermore, when the bot 121 of the first server 120 receives the generated text data GT from the second server 130, the portion of the received generated text data GT that was converted into another arbitrary character WD1 when it was sent to the second server 130 is changed back to the character WD before conversion, and the changed generated text data GT1 is sent to the user terminal 110. As a result, as shown in FIG. 7(B) and FIG. 8, it is possible to obtain generated text data GT1 after modification that basically conforms to the intent of the command information PT input by the user. In other words, the characters converted when the bot 121 of the first server 120 transmits to the second server 130 are restored to the original characters when the bot 121 of the first server 120 receives from the second server 130. As a result, it is possible to avoid unintended information leakage to the second server 130 or to other terminals via the second server 130, while ensuring consistency between the instruction and command content from the user terminal 110 and the response content to the user terminal 110.

[0052] Note that, as an example of data DT, an example of masking text data contained in an employee directory file, which is a file for a spreadsheet software with a cell-format display, has been described. However, the data DT to be masked is not limited to files for spreadsheet software. For example, when the data DT is image data such as a photograph or video, the bot 121 uses an image recognition means to determine whether or not there is a masking target, and when it determines that there is a masking target, it masks the target part and replaces it with another part having the same attributes before transmitting it to the second server 130.

[0053] The bot 121 of the first server 120 saves a list of the conversions (a table showing the correspondence between before and after the conversion). Then, the bot 121 changes (reverse-converts) the generated data received from the second server 130 by referring to the list (pre-conversion correspondence table) saved at the time of conversion to return it to its pre-conversion state, and then transmits the changed generated data to the user terminal 110. The generated data and the changed generated data are not limited to text data, but may be image data such as photographs and videos.

[0054] In addition, in this embodiment, as shown in Figure 9, in an administration screen 114 displayed on a browser 112 of a user terminal 110, which is an example of an administrator terminal capable of communicating with the first server 120, the users who can use the bot 121 of the first server 120 on the talk screen 113 of the user terminal 110 can be freely set based on user identification information US. For example, by inputting information for identifying an individual, such as a user's email address, as an example of the user identification information US and operating a user addition button, the bot 121 of the first server 120 can be used.

[0055] As a result, users are identified based on the user identification information US, and users who can interact with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, through the bot 121 of the first server 120 are specified and restricted. As a result, administrators can easily set usage restrictions and permissions for Chat GPT for each employee.

[0056] Furthermore, in this embodiment, on the setting screen of the chat application of the user terminal 110, a talk group including the bot 121 and other users can be freely created. For example, as shown in FIG. 10, the sales group as a talk group includes a user, Emi Suzuki, another user, Nakamura, and a bot 121. It is assumed that the sales group is designated as the talk group on the talk screen 113 as the talk partner, and the user inputs an arbitrary instruction command information PT. In response to this, the user terminal 110 is configured to transmit the input instruction command information PT to the first server 120.

[0057] This makes it possible to communicate with 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 during a group discussion on the talk screen 113. As a result, users can get advice and information from chat GPT during group discussions, and share the advice and information they get with other members in the same group.

[0058] In this case, in order to clearly indicate that the instruction and command information PT is directed to the bot 121, it is advisable to put "to the bot" at the beginning of the instruction and command information PT. In addition, by operating a button to ask the chat GPT a question or a button to request a summary from the chat GPT in the rich menu as shown in FIG. 4, it is possible to clearly indicate that the information is an instruction or command to the bot 121. This means that the bot 121 will essentially not respond, even when a user asks another user a question during a group discussion. As a result, it is possible to prevent the bot 121 from mistakenly starting an exchange with the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, and replying to the question.

[0059] The chat system 100 thus obtained as the first embodiment of the present invention includes a user terminal 110 and a server. When a user inputs instruction command information PT as arbitrary data DT in a state where a bot 121 is designated as a talk partner on a talk screen 113 of the user terminal 110, the user terminal 110 transmits the instruction command information PT as the input data DT to a first server 120, which is a server. The bot 121 of the first server 120 transmits the instruction command information PT as the received data DT to a second server 130 different from the first server 120. The second server 130 then uses the pre-trained artificial intelligence (AI) of the second server 130 to The stage 131 is used to generate text data based on instruction command information PT as data DT, and the generated text data GT obtained by the execution is transmitted to the bot 121 of the first server 120. The bot 121 of the first server 120 transmits the received generated text data GT to the user terminal 110, and the user terminal 110 displays the received generated text data GT on the talk screen 113. This allows the user to easily interact with the chat GPT, which is an example of a pre-trained artificial intelligence means 131 of the second server 130, on the talk screen 113 of the user terminal 110 via the bot 121 of the first server 120.

[0060] Furthermore, the prohibited words PB can be freely set on the management screen 114 of the administrator terminal which can communicate with the first server 120, and when instruction command information PT as data DT containing the previously set prohibited words PB is input on the talk screen 113 of the user terminal 110, the bot 121 of the first server 120 which receives it determines that the instruction command information PT as the received data DT contains the prohibited words PB and does not send the instruction command information PT as the received data DT to the second server 130, but instead sends information to the user terminal 110 indicating that it contains unusable words. This makes it possible to prohibit undesirable use by users and to avoid information leakage to other terminals via the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0061] In addition, on the management screen 114 of the administrator terminal capable of communicating with the first server 120, historical information of interactions between the user terminal 110 and the bot 121 of the first server 120 on the talk screen 113 of the user terminal 110 can be freely displayed, and the historical information includes transmission date and time information, user identification information US, IP address information, instruction command information PT entered on the talk screen 113, and information on whether or not a reply of generated text data GT has been received from the pre-trained artificial intelligence means 131 of the second server 130, allowing the administrator to confirm whether or not the user's use is appropriate.

[0062] Furthermore, on the management screen 114 of the administrator terminal capable of communicating with the first server 120, masking of the word attribute included in the data DT from the user terminal 110 to the bot 121 of the first server 120 can be freely set, and when the data DT including the character WD of the word attribute of the masking set in advance is input on the talk screen 113 of the user terminal 110, the bot 121 of the first server 120 that receives it determines that the received data DT includes the character WD of the word attribute of the masking, converts the character WD of the word attribute of the masking in the received data DT into another arbitrary character WD1 of the same word attribute, and transmits the converted data DT1 to the second server 130, and the second server 130 executes text data generation of the content based on the converted data DT1 using the pre-trained artificial intelligence means 131 of the second server 130, and transmits the generated text data GT obtained by the execution to the bot 121 of the first server 120, and the bot 121 of the first server 120 receives the data DT including the character WD of the word attribute of the masking. In the received generated text data GT, the portion of the other arbitrary character WD1 that was converted when sending to the second server 130 is changed back to the character WD before conversion, and then the changed generated text data GT1 is sent to the user terminal 110. This makes it possible to prevent the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, from memorizing information about the character WD of a word attribute that can identify an individual, and prevents leakage of personally identifiable information to other terminals via the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Furthermore, it is possible to obtain changed generated text data GT1 that is basically in line with the intention of the instruction command information PT entered by the user, thereby preventing unintended information leakage to the second server 130 and unintended information leakage to other terminals via the second server 130, and ensuring consistency between the instruction command content from the user terminal 110 and the response content to the user terminal 110.

[0063] In addition, the management screen 114 of the administrator's terminal, which can communicate with the first server 120, is configured so that the users who can use the bot 121 of the first server 120 on the talk screen 113 of the user terminal 110 can be freely set using user identification information US, so that the administrator can easily set usage restrictions and permissions for the chat GPT for each employee member.

[0064] Furthermore, on the settings screen of the user terminal 110, talk groups including the bot 121 and other users can be freely created, and when a talk group is specified as a talk partner on the talk screen 113 and the user inputs any instruction command information PT, the user terminal 110 is configured to send the input instruction command information PT to the first server 120, allowing the user to obtain advice and information from the chat GPT during a group discussion and share the obtained advice and information with other members in the same group.

[0065] Furthermore, the program of the chat system 100 according to the first embodiment of the present invention includes an input determination step S1 for determining whether or not instruction and command information PT has been input as arbitrary data DT by the user with the bot 121 designated as a talk partner on the talk screen 113 of the user terminal 110; a first instruction and command transmission step S2 in which the user terminal 110 transmits the instruction and command information PT as the input data DT to a first server 120 which is a server; a second instruction and command transmission step S3 in which the bot 121 of the first server 120 transmits the instruction and command information PT as the received data DT to a second server 130 different from the first server 120; The system has a generation execution step S4 for generating text data of the content, a first generated data transmission step S5 for the second server 130 to transmit the generated text data GT obtained by the execution to the bot 121 of the first server 120, a second generated data transmission step S6 for the bot 121 of the first server 120 to transmit the received generated text data GT to the user terminal 110, and a display step S7 for the user terminal 110 to display the received generated text data GT on the talk screen 113, so that the user can easily interact with 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 on the talk screen 113 of the user terminal 110, and thus has a tremendous effect. EXAMPLES

[0066] Next, an e-mail system, which is a message sending / receiving system according to a second embodiment of the present invention, will be described with reference to Figs. 11(A) and 11(B). Here, Figure 11(A) is a diagram showing an example of input in a sending message window 115, which is a message sending / receiving window of a user terminal 110 of an email system which is the second embodiment of the present invention, and Figure 11(B) is a diagram showing an example of a display in a receiving message window 116, which is a message sending / receiving window of a user terminal 110 of an email system which is the second embodiment of the present invention. The email system of the second embodiment is a system in which the talk screen 113 of the chat application of the chat system 100 of the first embodiment is changed to a message sending / receiving window of an email application, and since many elements are common to the chat system 100 of the first embodiment, detailed explanations of the common points will be omitted.

[0067] The electronic mail system is configured so that data DT, such as text data, can be freely communicated between a user terminal 110 and a server, which is an example of a mail server. The mail server may be configured separately from the first server 120 or the second server 130, or may be configured in common with the first server 120 or the second server 130. As shown in FIG. 11(A), assume that the address of bot 121 is specified as the destination in a sending message window 115 displayed on browser 112 of user terminal 110, and then the user inputs instruction command information PT as arbitrary data DT to perform a sending operation. Then, user terminal 110 transmits instruction command information PT as input data DT to first server 120 which is a server.

[0068] Next, the bot 121 of the first server 120 transmits the instruction command information PT as the received data DT to a second server 130 different from the first server 120 . Then, the second server 130 executes generation of text data based on the instruction command information PT using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, the second server 130 transmits the generated text data GT obtained through the execution to the bot 121 of the first server 120. Next, the bot 121 of the first server 120 transmits the received generated text data GT to the user terminal 110. Then, as shown in FIG. 11(B), the user terminal 110 is configured to display the received generated text data GT in a received message window 116.

[0069] This makes it possible to freely communicate with the chat GPT, an example of a pre-trained artificial intelligence means 131 of the second server 130, simply by specifying the address of the bot 121 of the first server 120 as the destination in the sending message window 115 of an existing email application. As a result, the user can easily interact with chat GPT, which is an example of a pre-trained artificial intelligence means 131 of the second server 130, via the bot 121 of the first server 120 in the message sending and receiving windows of the sending message window 115 and the receiving message window 116 of the user terminal 110.

[0070] In addition, a bot address insertion button 115a may be displayed in the outgoing message window 115 of a user who has been granted permission to use the bot 121. When the user operates this bot address insertion button 115a, the bot address AD, which is the email address of the bot 121, is inserted into the destination field. This allows the user to set the destination to the bot 121 simply by operating the bot address insertion button 115a. As a result, users can easily interact with Chat GPT, an example of a pre-trained artificial intelligence means 131 of the second server 130.

[0071] Furthermore, in the email system of this embodiment, it is of course possible to set prohibited words PB, similar to the chat system 100 of the first embodiment described above. A detailed description thereof will be omitted. Furthermore, in the electronic mail system of this embodiment, similarly to the chat system 100 of the first embodiment described above, it is of course possible to freely display historical information of exchanges between the user terminal 110 and the bot 121 of the first server 120 on the management screen 114. A detailed explanation thereof will be omitted. Furthermore, in the electronic mail system of this embodiment, if the bot 121 of the first server 120 determines that the data DT (including attachments) sent in the send message window 115 contains characters WD with a pre-set masking word attribute, it can of course convert the characters WD into other characters WD1 (perform masking) and send them to the second server 130, and reverse-convert the generated text data GT received from the second server 130. A detailed description of this will be omitted. Furthermore, in the electronic mail system of this embodiment, it is of course possible to freely set users who can use the bot 121 of the first server 120 by using the user identification information US. A detailed description thereof will be omitted.

[0072] The electronic mail system according to the second embodiment of the present invention thus obtained comprises a user terminal 110 and a server. When a user inputs instruction command information PT as arbitrary data DT in a state where a bot address AD, which is the address of a bot 121, is specified as a destination in a sending message window 115 of the user terminal 110, the user terminal 110 transmits the instruction command information PT as the input data DT to a first server 120, which is a server, and the bot 121 of the first server 120 transmits the instruction command information PT as the received data DT to a second server 130 different from the first server 120, and the second server 130 uses pre-trained artificial intelligence means 131 of the second server 130 to send the instruction command information PT as the received data DT. The system is configured to generate text data based on command information PT, and transmit the generated text data GT obtained by the generation to bot 121 of first server 120, which in turn transmits the received generated text data GT to user terminal 110, which in turn displays the received generated text data GT in received message window 116. This allows the user to easily interact with chat GPT, an example of a pre-trained artificial intelligence means 131 of second server 130, via bot 121 of first server 120 in the message sending / receiving window of existing sent message window 115 and received message window 116 of user terminal 110.

[0073] Moreover, the program of the e-mail system according to the second embodiment of the present invention includes an input determination step (S1) of determining whether or not instruction command information PT has been input as arbitrary data DT by the user with a bot address AD, which is the address of the bot 121, specified as a destination in the sending message window 115 of the user terminal 110; a first instruction command transmission step (S2) of the user terminal 110 transmitting the instruction command information PT as the input data DT to a first server 120 which is a server; a second instruction command transmission step (S3) of the bot 121 of the first server 120 transmitting the instruction command information PT as the received data DT to a second server 130 different from the first server 120; and a step of the second server 130 generating text data based on the instruction command information PT using the pre-trained artificial intelligence means 131 of the second server 130. The system has a generation execution step (S4) in which the second server 130 transmits the generated text data GT obtained by execution to the bot 121 of the first server 120, a first generated data transmission step (S5) in which the second server 130 transmits the generated text data GT obtained by execution to the bot 121 of the first server 120, a second generated data transmission step (S6) in which the bot 121 of the first server 120 transmits the received generated text data GT to the user terminal 110, and a display step (S7) in which the user terminal 110 displays the received generated text data GT in the received message window 116. This has a significant effect, as it allows the user to easily interact with 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 in the message sending and receiving windows of the existing sent message window 115 and received message window 116 of the user terminal 110. [Explanation of symbols]

[0074] 100 ··· Chat system (email system) 110 User terminal 111... Display section 112 ··· Browser 113 ··· Chat screen 114: (Administrator terminal) Administration screen 115 - Send Message Window 115a··· Bot address insertion button 116 Received Message Window 120 1st Server 121 ··· Bot 130 Second Server 131 ··· Pre-trained artificial intelligence means (Chat GPT) PT: Prompt DT...Data DT1: Post-conversion data (post-conversion instruction command information) GT: Generated text data GT1: Generated text data after modification PB: Forbidden words WD: (predefined) masking word attribute character WD1: Any other character with the same word attribute US ··· User identity AD ··· Bot address

Claims

1. A chat system including a user terminal and a server, and capable of freely communicating text data between the user terminal and the server, When a user inputs any instruction command information with a bot designated as a talk partner on a talk screen of the user terminal, the user terminal transmits the input instruction command information to a first server, The bot of the first server transmits the received instruction command information to a second server different from the first server; The second server executes text data generation based on the instruction command information using the pre-trained artificial intelligence means of the second server, and transmits the generated text data to the bot of the first server; The bot of the first server transmits the received generated text data to the user terminal; A chat system characterized in that the user terminal is configured to display the received generated text data on a talk screen.

2. A prohibited word can be freely set on a management screen of an administrator terminal capable of communicating with the first server, The chat system described in claim 1, characterized in that when data containing predetermined prohibited words is input on the talk screen of the user terminal, the bot of the first server that receives the data determines that the received data contains prohibited words, does not send the received data to the second server, and instead sends information to the user terminal that the data contains unusable words.

3. The chat system described in claim 2, characterized in that the management screen of an administrator terminal capable of communicating with the first server can freely display historical information of interactions between a user terminal and a bot of the first server on the talk screen of the user terminal, and the historical information includes transmission date and time information, user identification information, IP address information, instruction and command information entered on the talk screen, and information on whether or not generated text data has been returned from a pre-trained artificial intelligence means of the second server.

4. In a management screen of an administrator terminal capable of communicating with the first server, masking of word attributes included in data from a user terminal to a bot of the first server can be freely set, When data including characters of a preset masking word attribute is input on the talk screen of the user terminal, the bot of the first server that receives the data determines that the received data includes characters of a masking word attribute, converts the characters of the masking word attribute in the received data into other arbitrary characters of the same word attribute, and then transmits the converted data to the second server; The second server generates text data based on the converted data using the pre-trained artificial intelligence means of the second server, and transmits the generated text data to the bot of the first server; A chat system as described in any one of claims 1 to 3, characterized in that the bot of the first server is configured to change any other arbitrary character part of the received generated text data that was converted when sending it to the second server back to the character before conversion, and then send the changed generated text data to the user terminal.

5. The chat system described in claim 4, characterized in that the management screen of an administrator terminal capable of communicating with the first server is configured to freely set users who can use the bot of the first server on the talk screen of a user terminal based on user identification information.

6. A user can freely create a talk group including the bot and other users on the setting screen of the user terminal; The chat system described in claim 5, characterized in that when a user inputs any instruction or command information while a talk group is specified as a talk partner on the talk screen, the user terminal transmits the input instruction or command information to the first server.

7. A chat system program that allows text data to be freely exchanged between a user terminal and a server, an input determination step of determining whether or not any instruction command information is input by the user with a bot designated as a talk partner on a talk screen of the user terminal; a first instruction / command transmission step in which the user terminal transmits the input instruction / command information to a first server; a second instruction / command transmission step in which the bot of the first server transmits the received instruction / command information to a second server different from the first server; a generation and execution step in which the second server executes generation of text data based on instruction command information by using the pre-trained artificial intelligence means of the second server; a first generated data transmission step in which the second server transmits generated text data obtained by the execution to the bot of the first server; A second generated data transmission step in which the bot of the first server transmits the received generated text data to a user terminal; A program for a chat system, comprising a display step in which the user terminal displays the received generated text data on a talk screen.

8. An electronic mail system including a user terminal and a server, capable of freely communicating text data between the user terminal and the server, comprising: When a user inputs any instruction command information with the address of a bot specified as the destination in a sending message window of the user terminal, the user terminal transmits the input instruction command information to a first server, The bot of the first server transmits the received instruction command information to a second server different from the first server; The second server executes text data generation based on the instruction command information using the pre-trained artificial intelligence means of the second server, and transmits the generated text data to the bot of the first server; The bot of the first server transmits the received generated text data to the user terminal; 2. An electronic mail system, wherein the user terminal is configured to display the received generated text data in a received message window.

9. A program for an e-mail system that can freely communicate text data between a user terminal and a server, an input determination step of determining whether or not any instruction command information has been input by the user with the address of the bot specified as the destination in a sending message window of the user terminal; a first instruction / command transmission step in which the user terminal transmits the input instruction / command information to a first server; a second instruction / command transmission step in which the bot of the first server transmits the received instruction / command information to a second server different from the first server; a generation and execution step in which the second server executes generation of text data based on instruction command information by using the pre-trained artificial intelligence means of the second server; a first generated data transmission step in which the second server transmits generated text data obtained by the execution to the bot of the first server; A second generated data transmission step in which the bot of the first server transmits the received generated text data to a user terminal; a display step in which the user terminal displays the received generated text data in a received message window.

Images