TWI838316B - Generative chatbot system for virtual community and method thereof - Google Patents

Abstract

A generative chatbot system for virtual community and method thereof is disclosed. By connecting to a virtual community through a client for receiving chat messages, and generating an operational interface for entering a custom command when detecting a trigger signal, and then transmitting the chat messages and the custom command to a server, so that the server to integrate the chat messages into a context message with temporal logic, and transmitting the context message along with the custom command from the server to an artificial intelligence (AI) device to generate at least one response message. Subsequently, the server stores the at least one response message from the AI device in a response list and filters them, and allowing the client to select one to output to the virtual community. The mechanism is help to reduce the impact of chat interaction due to personality, eloquence or unfamiliar topics.

Description

System and method for generative chatbot in virtual community response context

The present invention relates to a chatbot system and method, and in particular to a generative chatbot system and method in a virtual community response context.

In recent years, with the popularization and rapid development of the Internet, various Internet applications have sprung up like mushrooms after rain. Among them, virtual communities are the most common.

Generally speaking, traditional virtual communities usually involve interactions with other users through the Internet, such as chatting, discussing, etc. However, since different users have different personalities, eloquence, and knowledge reserves, there may be obstacles to participating in the chat at the beginning, or when discussing unfamiliar topics, resulting in a lack of words or a dull chat. In other words, chats are prone to poor interactivity due to personality, eloquence, or unfamiliar topics.

In view of this, if the interaction in the virtual community can be detected and appropriate response suggestions or prompts can be given based on the content of the interaction, it will be able to effectively assist users in having a smooth chat. For example, in a multi-person conversation environment in a virtual community, when the topic of the chat changes to a knowledge field that they are not familiar with, if there is a chat robot that acts as a chat avatar, it can actively and quickly give users appropriate conversation suggestions. In this way, the chat interactivity of users in the virtual community can be effectively improved.

In summary, it can be seen that the prior art has long had the problem that chat interaction is poor due to personality, eloquence or unfamiliar topics. Therefore, it is necessary to propose improved technical means to solve this problem.

The present invention discloses a system and method for a generative chat robot in a virtual social group response context.

First, the present invention discloses a system of a generative chatbot in a virtual social group response scenario, the system comprising: an artificial intelligence device, a client host and a server host. The artificial intelligence device is used to receive contextual information with timing logic and custom instructions through an application programming interface (API), and input the contextual information and custom instructions into a large language model (LLM) to generate a response message, and then transmit the response message through the application programming interface. The client host comprises: a first non-transient computer-readable storage medium and a first hardware processor. The first non-transitory computer-readable storage medium is used to store a plurality of first computer-readable instructions; and the first hardware processor is electrically connected to the first non-transitory computer-readable storage medium to execute the first computer-readable instructions, so that the client host executes: connecting to the virtual community and continuously capturing a plurality of chat messages in the virtual community, each of the chat messages including time information, The system comprises a user name and a chat string; continuously detecting a trigger signal, and when a trigger signal is detected, generating an operation interface for inputting a custom command, and transmitting each of the chat messages and the custom command; and when a response prompt message is received, displaying the response prompt message on the operation interface, and allowing the selection of any one of the response prompt messages to be output to the virtual community. Then, in the server host part, it is connected to the artificial intelligence device and the client host, and the server host includes: a second non-transient computer-readable storage medium and a second hardware processor. The second non-transitory computer-readable storage medium is used to store a plurality of second computer-readable instructions; and the second hardware processor is electrically connected to the second non-transitory computer-readable storage medium to execute the plurality of second computer-readable instructions, so that the server host executes: when receiving each chat message from the client host, determining the sequence of the chat string according to the time message, determining the number of chatters in the virtual community according to the user name, and determining the number of chatters according to the chat string. The method comprises the steps of: determining the current chat topic and logic based on the keywords of the chat string, and integrating each chat message into a context message with timing logic according to the determination result; transmitting the context message and the received customized command to the artificial intelligence device through the application program interface, and receiving the corresponding response message from the artificial intelligence device to store it in the response list; and automatically selecting and loading at least one of the response messages from the response list as a response prompt message.

In addition, the present invention also discloses a method for generating a chatbot in a virtual social group response scenario, the steps of which include: connecting a server host to an artificial intelligence device and a client host respectively, wherein the artificial intelligence device has an application program interface; when the client host is connected to the virtual social group, continuously capturing multiple chat messages in the virtual social group, each of the chat messages including time information, user The client host continuously detects the trigger signal, and when the trigger signal is detected, generates an operation interface for inputting a custom command, and transmits each of the chat messages and the custom command to the server host; when the server host receives each of the chat messages from the client host, it determines the sequence of the chat strings according to the time information, determines the virtual community according to the user name, and determines the chat string sequence according to the user name. The number of chat participants in the group, and the current chat topic and logic are determined based on the keywords in the chat string, and each of the chat messages is then integrated into a context message with timing logic based on the determination result; the server host transmits the context message and the received custom command to the artificial intelligence device through the application program interface; the artificial intelligence device inputs the received context message and the custom command into the large language model to generate a response message, and transmits the response message to the server host; the server host stores the received response message in a response list, and automatically selects and loads at least one of the response messages from the response list as a response prompt message and displays it on the operation interface; and the client host allows any one of the loaded response prompt messages to be selected for output to the virtual community.

The system and method disclosed in the present invention are as described above. The difference from the prior art is that the present invention connects to the virtual community through a client host to receive chat messages, and when a trigger signal is detected, an operation interface is generated for entering custom commands, and then the chat messages and custom commands are transmitted to the server host so that the server host integrates the chat messages into contextual messages with timing logic, and transmits them together with the custom commands to the artificial intelligence device to generate response messages. Then, the server host stores the response messages from the artificial intelligence device in a response list and filters them so that the client host can select any one of them to output to the virtual community.

Through the above-mentioned technical means, the present invention can achieve the technical effect of reducing the impact of personality, eloquence or unfamiliar topics on chat interactivity.

The following will be used in conjunction with drawings and embodiments to explain the implementation of the present invention in detail, so that the implementation process of how the present invention applies technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

First, please refer to "Figure 1", which is a system block diagram of the system of the generative chatbot in the virtual social response scenario of the present invention, and the system includes: an artificial intelligence device 110, a client host 120 and a server host 130. Among them, the artificial intelligence device 110 is used to receive context information with timing logic and custom instructions through the application program interface, and input the context information and the custom instructions into the large language model to generate a response message, and then send the response message through the application program interface. In actual implementation, the artificial intelligence device 110 is a chatbot that uses a large language model, such as a generative pre-trained transformer (GPT), PaLM, Galactica, LLaMA, LaMDA or the like, and is capable of determining the current dialogue stage, topic evolution and predicting the development of the dialogue based on context information and its corresponding timing logic, and then using the predicted dialogue as a response message, and even adjusting the predicted dialogue or specifying the predicted dialogue applicable to a certain person according to the user's customized instructions.

The client host 120 includes a first non-transitory computer-readable storage medium 121 and a first hardware processor 122. The first non-transitory computer-readable storage medium 121 is used to store a plurality of first computer-readable instructions. In practical implementations, the first non-transitory computer-readable storage medium 121 may include a hard disk, an optical disk, a flash memory or the like.

The first hardware processor 122 is electrically connected to the first non-transitory computer-readable storage medium 121 for executing the first computer-readable instruction to enable the client host 120 to execute: connect to the virtual community 123 and continuously capture multiple chat messages in the virtual community 123, each of the chat messages including a time message, a user name and a chat string; continuously detect trigger signals, and when the trigger signal is detected, generate an operation interface 124 for entering a custom instruction, and transmit each of the chat messages and custom instructions; and when a response prompt message is received, display the response prompt message on the operation interface 124, and allow any one of the response prompt messages to be selected for output to the virtual community 123. In actual implementation, the trigger signal can be generated by pressing a physical button, clicking a software button on a touch screen, detecting a default keyword appearing in the virtual community 123, or at least one of the three, and the operation interface 124 is generated simultaneously. When the user enters a custom command in the operation interface 124, the client host 120 transmits the custom command to the server host 130. When the user selects one of the response prompt messages as a dialogue message in the operation interface 124, the user is allowed to edit the dialogue message first, and then the edited dialogue message is transmitted to the virtual community 123 for display.

It should be noted that the client host 120 can also be connected to the sensor 125, which is used to sense at least one of the user's physiological state, facial expression and body movement to generate user behavior information, and transmit the user behavior information to the server host 130, and the server host 130 determines the user's personality to set personality parameters. For example, physiological characteristics such as blood pressure, heartbeat, pulse, blood sugar can be sensed to determine physiological states, such as: happiness, excitement, frustration, etc.; or facial expressions and moods can be determined by sensing faces, irises, etc.; or voice characteristics can be determined by sensing the tone, length, etc. of the voice, such as: taciturn, talkative, etc. In this way, corresponding personality parameters can be set according to the sensing results, such as: extroversion, introversion, enthusiasm, coldness, etc.

Next, the server host 130 is connected to the artificial intelligence device 110 and the client host 120. The server host 130 includes a second non-transitory computer-readable storage medium 131 and a second hardware processor 132. The second non-transitory computer-readable storage medium 131 is used to store a plurality of second computer-readable instructions. In actual implementation, the difference between the second non-transitory computer-readable storage medium 131 and the first non-transitory computer-readable storage medium 121 is that the former is set in the server host 130, the latter is set in the client host 120, and the computer-readable instructions stored in the two are different. In practice, the computer-readable instructions for executing the operations of the present invention may be assembly language instructions, instruction set architecture instructions, machine instructions, machine-related instructions, microinstructions, firmware instructions, or source code or object code written in any combination of one or more programming languages, wherein the programming languages include object-oriented programming languages, such as Common Lisp, Python, C++, Objective-C, Smalltalk, Delphi, Java, Swift, C#, Perl, Ruby and PHP, as well as conventional procedural programming languages, such as C language or similar programming languages.

The second hardware processor 132 is electrically connected to the second non-transitory computer-readable storage medium 131 to execute the plurality of second computer-readable instructions to enable the server host 130 to execute: when receiving each chat message from the client host 120, determine the order of the chat string according to the time message, determine the number of chatters in the virtual community 123 according to the user name, and determine the current chat topic and logic according to the keywords in the chat string (for example, assuming that the word " Lunch", which can be regarded as a keyword and the chat topic is judged to be discussing lunch), and then each of the chat messages is integrated into a context message with timing logic according to the judgment result; the context message and the received custom command are transmitted to the artificial intelligence device 110 through the application program interface, and the corresponding response message is received from the artificial intelligence device 110 to be stored in the response list; and at least one of the response messages is automatically selected and loaded from the response list as a response prompt message. In actual implementation, the difference between the second hardware processor 132 and the first hardware processor 122 is that the former is set in the server host 130, and the latter is set in the client host 120, and both can be implemented using a central processing unit, a microprocessor or the like. In addition, the response prompt message can randomly select a response message that meets the personality parameter from the response list as the response prompt message, and the personality parameter allows the client host 120 to connect to the server host 130 for setting. For example, assuming that the personality parameter is "quiet", the server host 130 can select a response message with fewer words from the response list as the response prompt message to avoid the wording and the user's personality being too different, which makes the interlocutor who is familiar with the user's personality feel abrupt. In addition, taking contextual information with temporal logic as an example, it represents the integration of chat messages based on time sequence and language logic, and the integration results are regarded as contextual information. In fact, the number of people can be judged from the user name, the order of conversations can be judged from the time message, and the topic can be judged from the chat string. For example, if a certain word appears in the chat string relatively frequently, this word can be regarded as the topic, and it can even be judged in combination with the time message. For example: the time is noon, and the chat string appears "what to eat", the topic can be judged as "lunch discussion".

It should be particularly noted that, in actual implementation, the present invention may be partially or completely implemented based on hardware. For example, one or more components in the system may be implemented through hardware processors such as integrated circuit chips, system on chip (SoC), complex programmable logic devices (CPLD), field programmable gate arrays (FPGA), etc. The non-transitory computer-readable storage medium described in the present invention is loaded with computer-readable instructions (or computer program instructions) that are useful for the processor to implement various aspects of the present invention. The non-transitory computer-readable storage medium may be a tangible device that can retain and store instructions used by an instruction execution device. A non-transitory computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: a hard drive, a random access memory, a read-only memory, a flash memory, an optical disk, a floppy disk, and any suitable combination of the above. As used herein, a non-transitory computer-readable storage medium is not to be construed as a transient signal per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical signals through optical fiber cables), or electrical signals transmitted through wires. In addition, the computer-readable instructions described herein may be downloaded from a non-transitory computer-readable storage medium to each computing/processing device, or downloaded to an external computer device or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, hubs, and/or gateways. The network card or network interface in each computing/processing device receives the computer-readable instructions from the network and forwards the computer-readable instructions for storage in a non-transitory computer-readable storage medium in each computing/processing device.

Please refer to "FIG. 2A" and "FIG. 2B", which are flow charts of the method of the generative chatbot in the virtual community response scenario of the present invention, and the steps include: connecting the server host 130 to the artificial intelligence device 110 and the client host 120 respectively, wherein the artificial intelligence device 110 has an application program interface (step 210); when the client host 120 is connected to the virtual community 123, continuously capturing multiple chats in the virtual community 123; The client host 120 continuously detects the trigger signal, and when the trigger signal is detected, generates an operation interface 124 for inputting a custom command, and transmits each of the chat messages and the custom command to the server host 130 (step 230). When the server host 130 receives each of the chat messages from the client host 120, it determines the order of the chat strings according to the time information, The number of chat participants in the virtual community 123 is determined based on the user name, and the current chat topic and logic are determined based on the keywords in the chat string, and then each of the chat messages is integrated into a context message with a timing logic based on the determination result (step 240); the server host 130 transmits the context message and the received custom command to the artificial intelligence device 110 through the application programming interface (step 250); the artificial intelligence device 110 inputs the received context message and the custom command into a large The language model is used to generate a response message, and the response message is transmitted to the server host 130 (step 260); the server host 130 stores the received response message in a response list, and automatically selects and loads at least one of the response messages from the response list as a response prompt message and displays it on the operation interface 124 (step 270); and the client host 120 allows any one of the loaded response prompt messages to be selected for output to the virtual community 123 (step 280). Through the above steps, the virtual community 123 can be connected to the client host 120 to receive chat messages, and when a trigger signal is detected, an operation interface 124 is generated for entering custom commands, and then the chat messages and custom commands are transmitted to the server host 130, so that the server host 130 can integrate the chat messages into contextual messages with timing logic, and transmit them together with the custom commands to the artificial intelligence device 110 to generate response messages. Then, the server host 130 stores the response messages from the artificial intelligence device 110 in the response list and filters them, so that the client host 120 can select any one of them to output to the virtual community 123.

The following is explained in the form of an embodiment with reference to FIG. 3 and FIG. 4. As shown in FIG. 3, FIG. 3 is a schematic diagram of the present invention for connecting to a virtual community to receive chat messages. In actual implementation, it is assumed that a user connects to a virtual community 123, such as an online chat room, an online conference room, etc., through a client host 120. At this time, the client host 120 receives a plurality of chat messages 301 from a window interface 300 of the virtual community 123. Each chat message includes a time message (such as AM 11:30:10), a user name (such as A), and a chat string (such as what do you want to eat for lunch?). Then, the client host 120 will continue to transmit the received chat messages to the server host 130, so that the server host 130 can determine the order of the chat strings according to the time message, determine the number of chatters in the virtual community 123 according to the user name, and determine the current chat topic and logic according to the keywords in the chat strings, and then integrate all the chat messages into contextual messages with time sequence logic according to the determination results. For example, the chat strings can be sorted and integrated according to the time sequence and the natural language logic of the chat string, such as maintaining the sequence and referring to the previous chat string to maintain the coherence of the context message, and maintaining the same topic, removing meaningless chat strings, such as expression strings, tone strings (for example: "hmm", "haha", "haha"). At this time, the user can also directly enter the string in the input block 310 to chat, and the string entered by the user will not only be displayed in the chat message 301, but will also be received by the client host 120 as a chat string.

As shown in "Figure 4", "Figure 4" is a schematic diagram of applying the present invention to input custom commands in the operation interface and displaying response prompt messages. In actual implementation, the client host 120 will continue to detect trigger signals, and when the trigger signal is detected, an operation interface 410 is generated to provide the user with the opportunity to input custom commands. For example, the user can input "Answer A's question" in the input box 411 as a custom command. Then, after the user clicks the OK button 412, the client host 120 will transmit all chat messages and the input custom commands to the server host 130. In practice, the user can also add time to the custom command to make the custom command more specific, for example: "Answer A's question at 11:30:10 AM". In actual implementation, the user can generate a trigger signal by pressing a physical button, clicking a software button on a touch screen, detecting a default keyword (such as a user name, nickname, etc.) appearing in the virtual community 123, or at least one of the three.

In addition, when the server host 130 receives the response message generated by the artificial intelligence device 110 and stores it in the response list, it will automatically select and load at least one response prompt message from it to be transmitted to the client host 120, and then displayed in the selection area 413 of the operation interface 410 as shown in "Figure 4". In this way, the user does not need to think too much, and can directly select one of them according to his own preferences through the cursor, and then click the send button 414 to output it to the virtual community 123, effectively reducing the chat interactivity affected by personality, eloquence or unfamiliar topics. It should be particularly noted that the server host 130 can automatically select and load at least one response prompt message by selecting all, randomly selecting, or filtering according to personality parameters. For example, based on personality parameters, assuming that the personality parameter is "quiet", the server host 130 can select a response message with the least number of words or without extended meaning. For example, assuming that there are two response messages as follows:

1. I want to eat curry rice. Is anyone willing to join me?

2. I want to eat chicken chop rice.

At this time, the server host 130 can select the second response message as the response prompt message because it meets the condition of having the least number of words or having no extended meaning. It should be added that the personality parameter allows the client host 120 to connect to the server host 130 for setting. For example, in the input box 411, type "Personal parameter is set to be taciturn" and click the confirmation button 412 to send it to the server host 130 to complete the setting.

In summary, the difference between the present invention and the prior art is that the present invention connects to the virtual community through the client host to receive chat messages, and when a trigger signal is detected, an operation interface is generated for typing custom commands, and then the chat messages and custom commands are transmitted to the server host, so that the server host integrates the chat messages into contextual messages with timing logic, and transmits them together with the custom commands to the server host. The artificial intelligence device generates a response message, and then the server host stores the response message from the artificial intelligence device in a response list and filters it so that the client host can select any one of them to output to the virtual community. This technical means can solve the problems existing in previous technologies, thereby achieving the technical effect of reducing the impact of personality, eloquence or unfamiliar topics on chat interactivity.

Although the present invention is disclosed as above by the aforementioned embodiments, they are not used to limit the present invention. Anyone skilled in similar techniques can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of patent protection of the present invention shall be subject to the scope of the patent application attached to this specification.

110: artificial intelligence device 120: client host 121: first non-transient computer-readable storage medium 122: first hardware processor 123: virtual community 124: operation interface 125: sensor 130: server host 131: second non-transient computer-readable storage medium 132: second hardware processor 300: window interface 301: chat message 310: input block 410: operation interface 411: input box 412: confirm button 413: select block 414: send button Step 210: Connect a server host to an artificial intelligence device and a client host respectively, wherein the artificial intelligence device has an application programming interface (API) Step 220: When the client host is connected to a virtual community, it continuously captures multiple chat messages in the virtual community, each of which includes a time message, a user name, and a chat string Step 230: The client host continuously detects a trigger signal, and when the trigger signal is detected, generates an operation interface for entering a custom command, and transmits each of the chat messages and the custom command to the server host Step 240: When the server host receives each chat message from the client host, it determines the order of the chat string according to the time message, determines the number of chatters in the virtual community according to the user name, and determines the current chat topic and logic according to at least one keyword in the chat string, and then integrates each chat message into a context message with a timing logic according to the determination result. Step 250: The server host transmits the context message and the received custom command to the artificial intelligence device through the application program interface Step 260: The artificial intelligence device inputs the received context message and the custom command into a large language model (Large Language Model, LLM) to generate at least one response message, and transmit the response message to the server host Step 270: The server host stores the received response message in a response list, and automatically selects and loads at least one of the response messages from the response list as at least one response prompt message and displays it on the operation interface Step 280: The client host allows any one of the loaded response prompt messages to be selected and output to the virtual community

Figure 1 is a system block diagram of the system of the generative chatbot in the virtual community response scenario of the present invention. Figure 2A and Figure 2B are method flow charts of the method of the generative chatbot in the virtual community response scenario of the present invention. Figure 3 is a schematic diagram of the application of the present invention to connect to the virtual community to receive chat messages. Figure 4 is a schematic diagram of the application of the present invention to enter a custom command in the operation interface and display the response prompt message.

110: Artificial intelligence device

120: Client host

121: The first non-transient computer-readable storage medium

122: First hardware processor

123: Virtual community

124: Operation interface

125:Sensor

130: Server host

131: Second non-transitory computer-readable storage medium

132: Second hardware processor

Claims (10)

A system of a generative chatbot in a virtual social response context, the system comprising: an artificial intelligence device, for receiving a context message with a timing logic and a custom instruction through an application programming interface (API), and inputting the context message and the custom instruction into a large language model (LLM) to generate at least one response message, and then transmitting the response message through the application programming interface; a client host, the client host comprising: a first non-transitory computer-readable storage medium, for storing a plurality of first computer-readable instructions; and A first hardware processor, electrically connected to the first non-transitory computer-readable storage medium, for executing the first computer-readable instruction, so that the client host executes: Connecting to a virtual community and continuously capturing multiple chat messages in the virtual community, each of the chat messages comprising a time message, a user name, and a chat string; Continuously detecting a trigger signal, and when the trigger signal is detected, generating an operation interface for entering the custom instruction, and transmitting each of the chat messages and the custom instruction; and When receiving at least one response prompt message, displaying the response prompt message on the operation interface, and allowing any one of the response prompt messages to be selected for output to the virtual community; and A server host, connected to the artificial intelligence device and the client host, the server host comprising: A second non-transient computer-readable storage medium, for storing a plurality of second computer-readable instructions; and A second hardware processor, electrically connected to the second non-transient computer-readable storage medium, for executing the plurality of second computer-readable instructions, so that the server host executes: When each chat message is received from the client host, the order of the chat string is determined according to the time message, the number of chatters in the virtual community is determined according to the user name, and the current chat topic and logic are determined according to at least one keyword in the chat string, and each chat message is then integrated into the context message with the timing logic according to the determination result; The context message and the received custom command are transmitted to the artificial intelligence device through the application program interface, and the corresponding response message is received from the artificial intelligence device to be stored in a response list; and At least one of the response messages is automatically selected and loaded from the response list as the response prompt message. A system of a generative chatbot in a virtual community response scenario as in claim 1, wherein the response prompt message is randomly selected from the response list to select the response message that meets a personality parameter as the response prompt message, and the personality parameter allows the client host to connect to the server host for setting. A system of a generative chatbot in a virtual social response scenario as in claim 2, wherein the client host is connected to at least one sensor for sensing at least one of the user's physiological state, facial expression and body movement to generate a user behavior message, and the user behavior message is transmitted to the server host, and the server host sets the personality parameters based on the user behavior message. A system of a generative chatbot in a virtual community response scenario as in claim 1, wherein the trigger signal is generated by pressing a physical button, clicking a software button on a touch screen, detecting a default keyword appearing in the virtual community, or at least one of the three, and the operation interface is generated simultaneously. A system of a generative chatbot in a virtual community response scenario as in claim 4, wherein when the custom command is typed in the operating interface, the custom command is transmitted to the server host, and when one of the response prompt messages is selected as a dialogue message in the operating interface, the dialogue message is allowed to be edited first, and then the edited dialogue message is transmitted to the virtual community for display. A method for generating a chatbot in a virtual community response scenario, the steps of which include: Connecting a server host to an artificial intelligence device and a client host respectively, wherein the artificial intelligence device has an application programming interface (API); When the client host is connected to a virtual community, it continuously captures multiple chat messages in the virtual community, each of which includes a time message, a user name, and a chat string; The client host continuously detects a trigger signal, and when the trigger signal is detected, generates an operation interface for entering a custom command, and transmits each of the chat messages and the custom command to the server host; When the server host receives each chat message from the client host, it determines the order of the chat string according to the time message, determines the number of chatters in the virtual community according to the user name, and determines the current chat topic and logic according to at least one keyword in the chat string, and then integrates each chat message into a context message with a timing logic according to the determination result; The server host transmits the context message and the received custom command to the artificial intelligence device through the application program interface; The artificial intelligence device inputs the received context message and the custom command into a large language model (LLM) to generate at least one response message, and transmits the response message to the server host; The server host stores the received response message in a response list, and automatically selects and loads at least one of the response messages from the response list as at least one response prompt message and displays it on the operation interface; and the client host allows any one of the loaded response prompt messages to be selected and output to the virtual community. A method for generating a chatbot in a virtual community response scenario as in claim 6, wherein the response prompt message is randomly selected from the response list to select the response message that meets a personality parameter as the response prompt message, and the personality parameter allows the client host to connect to the server host for setting. A method for generating a chatbot in a virtual social response scenario as in claim 7, wherein the client host is connected to at least one sensor for sensing at least one of the user's physiological state, facial expression and body movement to generate a user behavior message, and the user behavior message is transmitted to the server host, and the server host sets the personality parameters based on the user behavior message. A method for generating a chatbot in a virtual community response scenario as in claim 6, wherein the trigger signal is generated by pressing a physical button, clicking a software button on a touch screen, detecting a default keyword appearing in the virtual community, or at least one of the three, and the operation interface is generated simultaneously. A method for generating a chatbot in a virtual community response scenario as in claim 9, wherein when the custom command is typed in the operating interface, the custom command is transmitted to the server host, and when one of the response prompt messages is selected as a dialogue message in the operating interface, the dialogue message is allowed to be edited first, and then the edited dialogue message is transmitted to the virtual community for display.

Images