TWI851306B - Active chatbot system with behavioral awareness and on-demand conversational and method thereof - Google Patents

Abstract

An active chatbot system with behavioral awareness and on-demand conversational and method thereof is disclosed. By continuous sensing a user behavior state thought a client, and transmitting the user behavior state and an on-demand conversation setting to a server for generating a rough question message with natural language structure, and then inputting the rough question message into a finite state machine to generate a precise question message, and then the server sends the precise question message to an AI platform to obtain a corresponding answer message and storing into an answer list, and filtering the answer message from the answer list according to the on-demand conversation setting as an on-demand conversation messages and transmitting to the client for output. The mechanism is help to improve the human-computer interaction and initiative of chatbot.

Description

System and method for active chat robot with behavior perception and on-demand dialogue

The present invention relates to a chatbot system and method, and in particular to an active chatbot system and method with behavior perception and on-demand dialogue.

In recent years, with the popularization and rapid development of artificial intelligence, various applications of artificial intelligence have emerged like mushrooms after rain. Among them, chatbots have attracted the most attention.

Generally speaking, traditional chatbots use a passive chat method for human-computer dialogue. That is, when the user sends a question, the chatbot will reply with an answer based on the question. If the user does not ask a question, the chatbot will not make any response. At most, it will actively reply with a welcome message or a guidance message at the beginning. Therefore, it has the problem of being unable to actively provide human-computer interactive chat.

In view of this, some manufacturers have proposed a technical means of actively asking questions based on user browsing records. For example, when a user browses an item on a web page, a chatbot actively asks whether the user wants to buy the item or introduces the item in detail. However, although this method can actively reply to messages, the interaction is stiff and rigid, and it is not humane. It cannot be called a chat, so it still cannot effectively solve the problem of actively providing human-computer interactive chat.

In summary, it can be seen that the previous technology has long been unable to actively provide human-computer interactive chat, so it is necessary to propose improved technical means to solve this problem.

The present invention discloses a system and method for an active chat robot with behavior perception and on-demand dialogue.

First, the present invention discloses a system of an active chat robot with behavior perception and on-demand dialogue, which includes: an artificial intelligence platform, a client host and a server host. The artificial intelligence platform is used to receive a precise question message through an application programming interface (API), and input the precise question message into a large language model (LLM) to generate an answer message, and then transmit the answer message to the server host through the application programming interface. Then, the client host includes: a sensor, a first non-transient computer-readable storage medium and a first hardware processor. The sensor is used to continuously sense at least one of physiological state, facial expression and body movement to generate user behavior state; the first non-transitory computer-readable storage medium is used to store multiple first computer-readable instructions; the first hardware processor is electrically connected to the first non-transitory computer-readable storage medium and the sensor to execute the multiple first computer-readable instructions, so that the client host continuously transmits the user behavior state and multiple on-demand dialogue settings, wherein the on-demand dialogue settings include time information and filtering parameters. In addition, in the part of the server host, it is connected to the client host to receive the user behavior status and the on-demand dialogue setting, and the server host includes: a finite state machine controller, a second non-transient computer-readable storage medium and a second hardware processor. Among them, the finite state machine controller integrates multiple finite state machines; the second non-transient computer-readable storage medium is used to store multiple second computer-readable instructions; the second hardware processor is electrically connected to the second non-transient computer-readable storage medium and the finite state machine controller to execute multiple second computer-readable instructions, so that the server host executes: generating a rough question message with a natural language structure according to the received user behavior status and on-demand dialogue setting; transmitting the rough question message to the client host; The finite state machine is input for parsing and converting the state of the finite state machine to generate a precise question message and transmit it to the artificial intelligence platform; an answer message corresponding to the precise question message is received from the artificial intelligence platform, and the answer message is stored in an answer list; and an answer message that meets the time message and the filter parameter is automatically selected from the answer list as an on-demand dialogue message generated according to the on-demand dialogue setting, and the on-demand dialogue message is transmitted to the client host for output.

In addition, the present invention also discloses a method for an active chat robot with behavior perception and on-demand dialogue, the steps of which include: connecting a server host to an artificial intelligence platform and a client host respectively; the client host continuously senses at least one of physiological state, facial expression and body movement through a sensor to generate a user behavior state; the client host continuously transmits the user behavior state and a plurality of on-demand dialogue settings to the server host, wherein the on-demand dialogue settings include a time message and a filtering parameter; the server host generates a rough question message with a natural language structure according to the received user behavior state and on-demand dialogue settings, and inputs the rough question message into a plurality of finite state The server-side host parses and transforms the state of the finite state machine to generate a precise question message; the server-side host transmits the precise question message to the artificial intelligence platform through the application programming interface of the artificial intelligence platform; the artificial intelligence platform inputs the precise question message into the large language model to generate an answer message, and then transmits the answer message to the server-side host through the application programming interface; the server-side host receives the answer message corresponding to the precise question message from the artificial intelligence platform, and stores the answer message in an answer list, and automatically filters out the answer message that meets the time message and the filtering parameter from the answer list as an on-demand dialogue message, and transmits the on-demand dialogue message to the client-side host for output.

The system and method disclosed in the present invention are as described above. The difference from the prior art is that the present invention continuously senses the user's behavior status through the client host, and transmits it and the on-demand dialogue setting to the server host to generate a rough question message with a natural language structure, and then inputs this rough question message into the finite state machine to generate a precise question message. Then, the server host transmits this precise question message to the artificial intelligence platform and obtains the corresponding answer message, and stores the obtained answer message in the answer list, and then selects the answer message that meets the on-demand dialogue setting as the on-demand dialogue message and transmits it to the client host for output.

Through the above-mentioned technical means, the present invention can achieve the technical effect of improving the human-machine interactivity and initiative of the chat robot.

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 active chatbot system with behavior perception and on-demand dialogue of the present invention, and the system includes: an artificial intelligence platform 110, a client host 120 and a server host 130. Among them, the artificial intelligence platform 110 is used to receive precise question messages through an application program interface, and input the precise question messages into a large language model to generate answer messages, and then send the answer messages to the server host 130 through the application program interface. In actual implementation, the artificial intelligence platform 110 is a chatbot using a large language model, such as a generative pre-trained transformer model (GPT), PaLM, Galactica, LLaMA, LaMDA or the like.

The client host 120 includes: a sensor 121, a first non-transitory computer-readable storage medium 122 and a first hardware processor 123. The sensor 121 is used to continuously sense at least one of physiological state, facial expression and body movement to generate user behavior state. In actual implementation, the sensor 121 can sense physiological characteristics such as blood pressure, heartbeat, pulse, blood sugar, etc. to determine physiological state, such as: happiness, excitement, frustration, etc.; or by sensing the face, iris, etc. to determine facial expression and mood; or by wearing sensors on the limbs of the human body, such as: three-axis acceleration sensor, gyroscope, etc. to sense the user's body movement. For example: walking, running, dancing, etc.

The first non-transitory computer-readable storage medium 122 is used to store a plurality of first computer-readable instructions. In practical implementation, the first non-transitory computer-readable storage medium 122 may include a hard disk, an optical disk, a flash memory or the like. In addition, the first computer-readable instructions refer to instructions that can be interpreted and executed by the client host 120, such as a client computer (or computer).

The first hardware processor 123 is electrically connected to the first non-transitory computer-readable storage medium 122 and the sensor 121 to execute the plurality of first computer-readable instructions so that the client host 120 continuously transmits the user behavior state and a plurality of on-demand session settings, wherein the on-demand session settings include time information and filtering parameters. Taking time messages as an example, they may include year, month, day, hour, minute, second, or even time range, etc., which are used as the basis for determining whether the answer message is related to time, for example, to determine whether the answer message has expired, set timed feedback (such as sending an on-demand dialogue message to remind you to eat at 12:00 a.m. every day), or other situations related to time, such as: morning is related to breakfast, 00:00 to 4:00 a.m. is related to sleep, national holidays are related to fixed dates, birthdays are related to specified dates, etc. Therefore, when the time falls within the morning range, answer messages related to breakfast can be filtered out, when the time falls between 00:00 and 4:00 a.m., answer messages related to sleep can be filtered out, and when the time is a national holiday, answer messages containing this national holiday can be filtered out. In addition, taking the filtering parameters as an example, the filtering parameters are used to set the reply messages that are agreed to be received and the reply messages that are refused to be received. In other words, the user can set it according to his or her own preferences, for example: set to filter out chat content containing politics and religion, set to receive only entertainment chat content, etc.

Next, in the part of the server host 130, it is connected to the client host 120 to receive the user behavior state and the on-demand dialogue setting, and the server host 130 includes: a finite state machine controller 131, a second non-transient computer-readable storage medium 132 and a second hardware processor 133. Among them, the finite state machine controller 131 integrates multiple finite state machines, for example: the finite state machine can include a Mealy Machine and a Moore Machine state machine, and at least one of them can be selected to generate a more accurate question message than a rough question message according to different requirements of the on-demand dialogue setting. In practice, each on-demand dialogue setting can be converted into a state table first, and then the transition table of the flip-flop can be set according to the excitation table of the flip-flop. Then, the input equation of each flip-flop can be obtained using the Karnaugh Map to generate the final circuit diagram of the finite state machine. The circuit diagram can then be packaged into an integrated circuit (IC) to implement the finite state machine controller 131.

The second non-transitory computer-readable storage medium 132 is used to store a plurality of second computer-readable instructions. In actual implementation, the second non-transitory computer-readable storage medium 132 is similar to the first non-transitory computer-readable storage medium 122, the only difference being that the former is a non-transitory computer-readable storage medium of the server host 130, storing computer-readable instructions (i.e., second computer-readable instructions) for execution by the server host 130, while the latter is a non-transitory computer-readable storage medium of the client host 120, storing computer-readable instructions (i.e., first computer-readable instructions) for execution by the client host 120.

The second hardware processor 133 is electrically connected to the second non-transitory computer-readable storage medium 132 and the finite state machine controller 131, and is used to execute a plurality of second computer-readable instructions to enable the server host 130 to execute: generating a rough question message with a natural language structure according to the received user behavior state and the on-demand dialogue setting; inputting the rough question message into the finite state machine for parsing and converting the state of the finite state machine, so as to Generate a precise question message and transmit it to the artificial intelligence platform 110; receive an answer message corresponding to the precise question message from the artificial intelligence platform 110, and store the answer message in an answer list; and automatically filter out answer messages that meet the time message and the filter parameters from the answer list as on-demand dialogue messages generated according to on-demand dialogue settings, and transmit the on-demand dialogue messages to the client host 120 for output. For example, assuming that the user behavior state received by the server host 130 is "exercise", the on-demand dialogue setting includes the time message "AM 08:00" and the filter parameter "only accept suggestions with low difficulty to implement", then the second hardware processor 133 will generate a corresponding rough question message according to "exercise", "AM 08:00" and "low difficulty", such as: "exercise, AM 08:00, low difficulty", and then input this rough question message into the finite state machine for parsing and converting the state of the finite state machine, for example: define the question type according to "exercise", and select "AM 08:00" according to "low difficulty". 08:00” and the scope of the question according to “low difficulty”, and then use predefined templates or grammatical rules to generate precise question messages, such as “Please list exercises that can be done at 8 a.m. and are easy to do”, “It is 8 a.m. now and I am doing exercises that are easy to do. Do you have any suggestions?”. Next, the precise question message is sent to the artificial intelligence platform 110 to obtain the corresponding answer message, and then all the answer messages are stored in the answer list, so that the second hardware processor 133 automatically selects the answer message that meets the time message and the filter parameter from the answer list as the on-demand dialogue message. For example, if the user's movement is sensed at 8 am and 6 pm, and the corresponding answer message is obtained and stored in the answer list, if the current time is evening, the answer message related to the morning will be excluded, and only the answer message related to the evening will be selected as the on-demand dialogue message. Finally, the second hardware processor 133 will drive the transmission element to actively transmit the on-demand dialogue message to the client host 120 for output. In other words, when the server host 130 receives the user's behavior status, it will trigger an active on-demand dialogue, and filter out the matching answer message as the on-demand dialogue message according to the on-demand dialogue setting.

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. The 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 (non-exhaustive list) of computer-readable storage media include: hard drives, random access memory, read-only memory, flash memory, optical disks, floppy disks, and any suitable combination of the foregoing. As used herein, non-transitory computer-readable storage media 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 various computing/processing devices, or downloaded to an external computer device or external storage device through 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 the non-transitory computer readable storage medium in each computing/processing device. 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 or similar programming languages.

Please refer to "FIG. 2A" and "FIG. 2B", which are the method flow charts of the method of the active chat robot with behavior perception and on-demand dialogue of the present invention, and the steps include: connecting the server host 130 to the artificial intelligence platform 110 and the client host 120 respectively (step 210); the client host 120 continuously senses the physiological state, facial expression and body movement through the sensor 121 The client host 120 continuously transmits the user behavior state and a plurality of on-demand dialogue settings to the server host 130, wherein the on-demand dialogue settings include a time message and a filter parameter (step 230); the server host 130 generates a rough question message with a natural language structure according to the received user behavior state and on-demand dialogue settings, and sends the rough question message to the server host 130. The question message is input into a plurality of finite state machines for parsing and converting the states of the finite state machines to generate an accurate question message (step 240); the server host 130 transmits the accurate question message to the artificial intelligence platform 110 through the application programming interface of the artificial intelligence platform 110 (step 250); the artificial intelligence platform 110 inputs the accurate question message into the large language model to generate an answer message, and then transmits the answer message through the application programming interface The server host 130 receives the answer message corresponding to the precise question message from the artificial intelligence platform 110, stores the answer message in the answer list, and automatically selects the answer message that meets the time message and the filter parameter from the answer list as the on-demand dialogue message, and transmits the on-demand dialogue message to the client host 120 for output (step 270). Through the above steps, the user's behavior status can be continuously sensed through the client host, and it can be transmitted to the server host together with the on-demand dialogue setting to generate a rough question message with a natural language structure, and then the rough question message is input into the finite state machine to generate a precise question message. Then, the server host transmits the precise question message to the artificial intelligence platform and obtains the corresponding answer message, and stores the obtained answer message in the answer list, and then filters out the answer message that meets the on-demand dialogue setting as the on-demand dialogue message and transmits it to the client host for output.

The following is explained in the form of an embodiment in conjunction with "Figures 3" to "Figure 5". As shown in "Figure 3", "Figure 3" is a schematic diagram of an active chat robot using the present invention. First, the server host 130 is connected to the artificial intelligence platform 110 and the client host 120 respectively. The client host 120 continuously senses at least one of the user's physiological state, facial expression and body movement through a sensor to generate a user behavior state, and continuously transmits the user behavior state and multiple on-demand dialogue settings to the server host 130 through an input interface, wherein the on-demand dialogue setting includes a time message and a filtering parameter. The state management module of the server host 130 generates a rough question message with a natural language structure according to the received user behavior state and the on-demand dialogue setting, and inputs the generated rough question message into the finite state machine for parsing and converting the state of the finite state machine to generate a precise question message. Then, the server host 130 transmits the precise question message to the artificial intelligence platform 110 through the API of the artificial intelligence platform 110. At this time, the artificial intelligence platform 110 inputs the precise question message into the large language model to generate an answer message, and then transmits the answer message to the server host 130 through the API. When the server host 130 receives the answer message corresponding to the precise question message from the artificial intelligence platform 110, the answer message will be stored in the answer list, and the answer message that meets the on-demand dialogue setting (i.e., time message and filter parameter) will be actively selected from the answer list as the on-demand dialogue message, and the selected on-demand dialogue message will be transmitted to the client host 120 for output through the display interface. At this point, the chatbot has completed the active transmission of the on-demand dialogue message according to the sensed user behavior state to conduct active human-computer interaction with the user. It should be particularly noted that the state management module and the active on-demand dialogue module are implemented by the hardware processor executing computer-readable instructions.

As shown in "Figure 4", "Figure 4" is a schematic diagram of the finite state machine to which the present invention is applied. In actual implementation, when a rough question message is input into the finite state machine 400, it is first possible to determine from the rough question message whether there is a user behavior state (abbreviated as state, such as: movement) in the question, then determine whether there is a time (for example: eight o'clock in the morning), and then determine whether there is a range (for example: low difficulty), and finally select a suitable predefined template for application based on the existing state, time and range for output. Among them, the predefined template refers to a question sentence template of a natural language structure that has not yet embedded a state, time, range or a combination thereof, for example: "Now is [time], and [state] of [range] is in progress. Do you have any suggestions?", wherein the brackets represent the types of vocabulary to be embedded. In the above example, the embedded question sentence is "It is 8 o'clock in the morning, and I am doing a low-difficulty exercise. Do you have any suggestions?" This question sentence is finally used as a precise question message. It should be noted that in addition to including status, time and range at the same time, it can also include only any one of them, such as: "I am in [status], please list the things I need to pay attention to based on this", "Please list five suggestions related to [status]", etc.

As shown in FIG. 5 , FIG. 5 is a schematic diagram of applying the present invention to actively filter out answer messages in an answer list. Assuming that there are multiple answer messages in the answer list 500 , when the filter parameter of the on-demand dialogue setting is newly added with “low difficulty”, the server host 130 will filter out the first answer message from the top as the on-demand dialogue message when performing the active on-demand dialogue, because the answer message limits the range of low difficulty. In addition, assuming that the time message of the on-demand dialogue setting is to set the timed feedback, and the time is "12 noon", then when the time is 12 noon, the server host 130 will filter out the answer message containing similar keywords (such as: 12 noon) from the answer list 500 as the on-demand dialogue message when actively conducting the on-demand dialogue. In this way, even if the user does not ask a question, the chatbot using the present invention will actively provide the user with the on-demand dialogue message based on the user's behavior status, timed feedback, etc., effectively improving the human-machine interaction and initiative of the chatbot. It should be noted that, in actual implementation, the server host 130 can also directly receive the user input message from the client host 120 as a precise question message (for example: please list three meals suitable for lunch), and transmit it to the artificial intelligence platform 110 through the API to obtain the corresponding answer message (for example: chicken fillet rice, chicken drumstick rice and hot pot), and then transmit this answer message to the client host 120 for output through the display interface 510.

In summary, the difference between the present invention and the prior art lies in that the client host continuously senses the user's behavior status, and transmits it and the on-demand dialogue setting to the server host to generate a rough question message with a natural language structure, and then inputs the rough question message into the finite state machine to generate a precise question message. Then, the server host transmits the precise question message to the artificial intelligence platform and obtains the corresponding answer message, and stores the obtained answer message in the answer list, and then selects the answer message that meets the on-demand dialogue setting as the on-demand dialogue message and transmits it to the client host for output. This technical means can solve the problems existing in the prior art, and thus achieve the technical effect of improving the human-computer interactivity and initiative of the chatbot.

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 platform 120: client host 121: sensor 122: first non-transient computer-readable storage medium 123: first hardware processor 130: server host 131: finite state machine controller 132: second non-transient computer-readable storage medium 133: second hardware processor 400: finite state machine 500: answer list 510: display interface Step 210: connect a server host to an artificial intelligence platform and a client host respectively Step 220: the client host continuously senses at least one of physiological state, facial expression and body movement through at least one sensor to generate a user behavior state Step 230: The client host continuously transmits the user behavior state and multiple on-demand dialogue settings to the server host, wherein the on-demand dialogue setting includes a time message and a filtering parameter Step 240: The server host generates a rough question message with a natural language structure according to the received user behavior state and the on-demand dialogue setting, and inputs the rough question message into multiple finite state machines for parsing and converting the states of the finite state machines to generate a precise question message Step 250: The server host transmits the precise question message to the artificial intelligence platform through an application programming interface (API) of the artificial intelligence platform Step 260: The artificial intelligence platform inputs the precise question message into the Large Language Model (LLM) to generate an answer message, and then transmits the answer message to the server host through the application program interface. Step 270: The server host receives the answer message corresponding to the precise question message from the artificial intelligence platform, and stores the answer message in an answer list, and automatically selects the answer message that meets the time message and the filter parameter from the answer list as an on-demand dialogue message, and transmits the on-demand dialogue message to the client host for output.

Figure 1 is a system block diagram of the system of the active chat robot with behavior perception and on-demand dialogue of the present invention. Figure 2A and Figure 2B are method flow charts of the method of the active chat robot with behavior perception and on-demand dialogue of the present invention. Figure 3 is a schematic diagram of the active chat robot using the present invention. Figure 4 is a schematic diagram of the finite state machine using the present invention. Figure 5 is a schematic diagram of actively filtering out answer messages in the answer list using the present invention.

110: Artificial Intelligence Platform

120: Client host

121:Sensor

122: First non-transitory computer-readable storage medium

123: First hardware processor

130: Server host

131: Finite state machine controller

132: Second non-transitory computer-readable storage medium

133: Second hardware processor

Claims (10)

A system of an active chatbot with behavior perception and on-demand dialogue, the system comprising: An artificial intelligence platform, for receiving a precise question message through an application programming interface (API), and inputting the precise question message into a large language model (LLM) to generate an answer message, and then transmitting the answer message through the application programming interface; A client host, the client host comprising: At least one sensor, for continuously sensing at least one of physiological state, facial expression and body movement to generate a user behavior state; A first non-transient computer-readable storage medium, for storing a plurality of first computer-readable instructions; and A first hardware processor, electrically connected to the first non-transient computer-readable storage medium and the sensor, for executing the plurality of first computer-readable instructions, so that the client host continuously transmits the user behavior state and a plurality of on-demand dialogue settings, wherein the on-demand dialogue settings include a time message and a filter parameter; and A server host, connected to the client host to receive the user behavior state and the on-demand dialogue settings, the server host including: A finite state machine controller, integrating a plurality of finite state machines (FSM); 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-transitory computer-readable storage medium and the finite state machine controller, for executing the plurality of second computer-readable instructions to enable the server host to execute: Generate a rough question message with a natural language structure according to the received user behavior state and the on-demand dialogue setting; Input the rough question message into the finite state machine for parsing and converting the state of the finite state machine to generate the precise question message and transmit it to the artificial intelligence platform; Receive the answer message corresponding to the precise question message from the artificial intelligence platform, and store the answer message in an answer list; and Automatically filter the answer message that matches the time message and the filter parameter from the answer list as the on-demand dialogue message generated according to the on-demand dialogue setting, and transmit the on-demand dialogue message to the client host for output. A system of an active chatbot with behavior perception and on-demand dialogue as in claim 1, wherein the server host selects at least one of natural language processing (NLP), generative model and template matching to generate the rough question message having a natural language structure. A system of an active chatbot with behavior perception and on-demand dialogue as in claim 1, wherein the finite state machine parses keywords and grammatical structures based on the rough question message, and transforms the state of the finite state machine based on the parsing result to determine the question type, and then uses a predefined template or grammatical rule to generate the precise question message that is more specific and clear than the rough question message. A system of an active chatbot with behavior perception and on-demand dialogue as claimed in claim 1, wherein the finite state machine includes a Mealy Machine and a Moore Machine state machine. A system of an active chatbot with behavior perception and on-demand dialogue as in claim 1, wherein the screening parameter is used to set the reply message that is agreed to be received and the reply message that is refused to be received, and the time message is used as a basis for determining whether the reply message is related to time. A method for an active chat robot with behavior perception and on-demand dialogue, the steps of which include: Connecting a server host to an artificial intelligence platform and a client host respectively; The client host continuously senses at least one of physiological state, facial expression and body movement through at least one sensor to generate a user behavior state; The client host continuously transmits the user behavior state and multiple on-demand dialogue settings to the server host, wherein the on-demand dialogue setting includes a time message and a filtering parameter; The server host generates a rough question message with a natural language structure according to the received user behavior state and the on-demand dialogue setting, and inputs the rough question message into a plurality of finite state machines for parsing and converting the states of the finite state machines to generate a precise question message; The server host transmits the precise question message to the artificial intelligence platform through an application programming interface (API) of the artificial intelligence platform; The artificial intelligence platform inputs the precise question message into a large language model (LLM) to generate an answer message, and then transmits the answer message to the server host through the application programming interface; and The server host receives the answer message corresponding to the precise question message from the artificial intelligence platform, and stores the answer message in an answer list, and automatically selects the answer message that meets the time message and the filter parameter from the answer list as an on-demand dialogue message, and transmits the on-demand dialogue message to the client host for output. A method for an active chatbot with behavior perception and on-demand dialogue as in claim 6, wherein the server host selects at least one of natural language processing (NLP), generative model and template matching to generate the rough question message having a natural language structure. A method for an active chatbot with behavior perception and on-demand dialogue as in claim 6, wherein the finite state machine parses keywords and grammatical structures based on the rough question message, and transforms the state of the finite state machine based on the parsing result to determine the question type, and then uses a predefined template or grammatical rule to generate the precise question message that is more specific and clear than the rough question message. A method for an active chatbot with behavior perception and on-demand dialogue as in claim 6, wherein the finite state machine comprises a Mealy Machine and a Moore Machine state machine. A method for an active chatbot with behavior perception and on-demand dialogue as in claim 6, wherein the screening parameter is used to set the reply message that is agreed to be received and the reply message that is refused to be received, and the time message is used as a basis for determining whether the reply message is related to time.

Images