A system that provides consultation chatbots based on artificial intelligence

Abstract

To provide a consultation chatbot based on an artificial intelligence that enables correct and quick consultations.SOLUTION: A system 100 includes a server 120 and a manager electronic device 110 having authority to manage the server. The server 120 includes a database 121 including content and member information, a wireless communication circuit 123 configured to provide wireless communication with an external electronic device 200, and a processor 124 for training an artificial intelligence model 122 based on a large scale language model on the basis of the content. The server 120 provides a virtual space to which the external electronic device 200 is connected such that consultation services are provided. The processor 124 receives a query text from the external electronic device 200, extracts a prompt from the query text, generates a response message based on the content stored in the database 121 by inputting the prompt to the artificial intelligence model 122, and provides the external electronic device 200 with the response message.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a system for providing an artificial intelligence-based consultation chatbot. [Background technology]

[0002] For service industries that provide consultation services, we provide consultation chatbots using AI based on large language models (LLMs) with proprietary content developed by our company. Consultation chatbots using AI models based on large language models are used for consultation services that use AI reinforcement learning with human feedback (RLHF), such as ChatGPT4 and Gemini. Consultation chatbots based on AI models use natural language processing and machine learning technology to provide human-like conversations, thereby improving work efficiency and collecting diverse data.

[0003] The above information is provided as related art to aid in understanding the invention(s) disclosed herein, and no assertion or determination is being made as to whether any of the above is applicable as prior art in connection with the present disclosure. Summary of the Invention [Problem to be solved by the invention]

[0004] Consultation chatbots that provide consultation services may have difficulty providing accurate responses to questions if they do not reflect the characteristics of the service field they provide. Furthermore, if consultation services are provided endlessly, only free consultations that do not lead to an actual revenue model may continue, making it difficult to generate revenue, problems may arise due to increased traffic, and responses unrelated to the content may be provided, leading to users (customers) receiving incorrect information.

[0005] According to one embodiment, a system for providing a consultation chatbot based on an artificial intelligence model can enable accurate and prompt consultation by operating the consultation chatbot using an artificial intelligence model trained based on content. [Means for solving the problem]

[0006] According to an embodiment, a system for providing an AI-based consultation chatbot may include a server and an administrator electronic device having administrative authority over the server. The server may include a database including content and member information uploaded by the administrator electronic device, a wireless communication circuit configured to provide wireless communication with an external electronic device, and a processor configured to train a large-scale language model-based AI model based on the content included in the database. The server may be configured to provide a virtual space to which an external electronic device can connect via the wireless communication circuit to provide consultation services. The processor may be configured to receive a question text from the external electronic device connected to the server via the wireless communication circuit, extract a prompt from the question text to be input to the large-scale language model-based AI model, input the prompt to the large-scale language model-based AI model, thereby generating a response message based on the content stored in the database, and provide the response message to the external electronic device via the virtual space of the server.

[0007] According to one embodiment, the processor may be configured to count the amount or number of times the response messages have been provided, and based on identifying that at least one of the accumulated amount or number of times the response messages have been provided exceeds a threshold, collect and analyze a communication log of the external electronic device, and based on the analysis result, identify whether the external electronic device is eligible to join as a member, and if it is identified as a member, continuously provide the response message, and if it is identified as a non-member, stop providing the response message and provide the external electronic device with a first guidance message to guide it to join as a member via the virtual space of the server.

[0008] According to one embodiment, the first invitation message may include a link connectable to a website address that provides membership registration.

[0009] According to one embodiment, the processor may be configured to connect the external electronic device to the website based on identifying that a first time has elapsed since a first time point when the first guidance message was provided.

[0010] According to one embodiment, the processor may be configured to provide, via the wireless communication circuitry, to the external electronic device first information for rendering the virtual space, second information for rendering an avatar to be displayed within the virtual space, and third information for rendering the response message to be displayed adjacent to the avatar contained within the virtual space.

[0011] According to one embodiment, the processor may be configured to generate the avatar based on the content contained in the database.

[0012] According to one embodiment, the processor may be configured to provide the first information and the second information based on the question text.

[0013] According to one embodiment, the processor may be configured to provide a second guidance message to the external electronic device via the virtual space of the server to inform the external electronic device that the response message is being generated based on identifying that a second time has elapsed since the second time point at which the question text was received.

[0014] According to one embodiment, the processor may be configured to identify the time that has elapsed since the second point in time and provide a first visual object indicating the elapsed time together with the second guidance message to the external electronic device via the virtual space of the server.

[0015] According to one embodiment, the processor may be configured to calculate the time required to generate the response message and provide a second visual object indicating the time required together with the second guidance message to the external electronic device via the virtual space of the server.

[0016] According to one embodiment, the administrator electronic device may store history data corresponding to information related to the history of providing the response message in the database.

[0017] According to one embodiment, the processor may be configured to: identify a similarity between the question text and the content; and, based on identifying the similarity being equal to or greater than a first similarity, provide the response message to the external electronic device; and, based on identifying the similarity being less than the first similarity, identify one or more keywords in the content based on the question text, generate asking back text corresponding to the question text using the one or more keywords; and provide the asking back text to the external electronic device via the virtual space of the server.

[0018] According to one embodiment, the processor may be configured to provide a third guidance message to the external electronic device via the virtual space of the server to inform the external electronic device that the response message to the question text cannot be provided based on identifying the similarity that is equal to or less than a second similarity that is lower than the first similarity. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a block diagram illustrating components of a system for providing an artificial intelligence-based consultation chatbot according to one embodiment. [Figure 2] 1 is a flowchart illustrating the operation of a system for providing an artificial intelligence-based consultation chatbot according to one embodiment. [Figure 3] FIG. 10 is a diagram illustrating an example of consultation content provided to an external electronic device through a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 4] 10 is a flowchart illustrating an operation of providing a first guidance message in a system for providing an AI-based consultation chatbot according to an embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of an external electronic device that connects to a website via a first guidance message of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 6] FIG. 10 illustrates an example of an external electronic device displaying a virtual space and avatars of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 7a] FIG. 10 is a diagram illustrating an example of an external electronic device displaying a second guidance message of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 7b] FIG. 10 is a diagram illustrating an example of an external electronic device displaying a second guidance message of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 8]10 is a flowchart illustrating an operation of providing a counter-question text in a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 9a] FIG. 10 illustrates an example of an external electronic device displaying a response text of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 9b] FIG. 10 illustrates an example of an external electronic device displaying a response text of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 9c] FIG. 10 illustrates an example of an external electronic device displaying a response text of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 10] FIG. 1 illustrates an external electronic device using a department change service of a system for providing an artificial intelligence-based consultation chatbot according to an embodiment. [Figure 11] FIG. 10 is a diagram illustrating an example in which a response message provision history is registered through an administrator electronic device of a system for providing an AI-based consultation chatbot according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0020] The following description, taken with reference to the accompanying drawings, is provided to facilitate a comprehensive understanding of various embodiments of the present disclosure, as defined by the claims and their equivalents. Various descriptions are provided below to facilitate understanding, but these should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications to the various embodiments described herein may be made without departing from the scope and spirit of the present disclosure. Furthermore, descriptions of well-known functions and configurations may be omitted for the sake of clarity and conciseness.

[0021] FIG. 1 is a block diagram illustrating components of a system 100 for providing an artificial intelligence-based consultation chatbot according to one embodiment.

[0022] According to an embodiment, a system 100 for providing an AI-based consultation chatbot is provided. The AI-based consultation chatbot system 100 may be simply referred to as "system 100" in the following description. The system 100 according to an embodiment may be configured to receive a question text from an external electronic device 200, understand the intent of the question of a user of the external electronic device 200 from the question text, and then provide a consultation chatbot that automatically provides consultation based on a database 121 uploaded to a server 120. The consultation chatbot may be referred to as a consultation service that understands the question text received via the external electronic device 200 and written in natural language, and provides a response message corresponding to the question text based on AI based on a large-scale language model.

[0023] According to one embodiment, the system 100 may include an administrator electronic device 110, a server 120, and a website 130.

[0024] According to one embodiment, the administrator electronic device 110 may be configured to manage the overall operation of the system 100. The administrator electronic device 110 may have administrative authority over the server 120. For example, the administrator electronic device 110 may upload content to be stored in the database 121 of the server 120 and instruct the processor 124 to train the large-scale language model-based artificial intelligence model 122 based on the uploaded content. The administrator electronic device 110 may be configured to manage information provided via the website 130 or approve membership requests received via the website 130. An administrator of the system 100 may manage the overall operation of the system 100 through the administrator electronic device 110.

[0025] According to one embodiment, server 120 may include a database 121 , an artificial intelligence model 122 , wireless communication circuitry 123 , and a processor 124 .

[0026] According to one embodiment, the database 121 may include content and member information. In the present disclosure, content is a data source used to train the large language model-based artificial intelligence model 122 and may include text data. The large language model (LLM)-based artificial intelligence model 122 is an artificial intelligence model trained with text data and may be used to generate a response message to a query text. According to one embodiment, the processor 124 may be configured to train the large language model-based artificial intelligence model 122 based on the content included in the database 121. In the case of a member registered with the website 130, the member information may refer to information entered at the time of member registration on the website 130.

[0027] A large-scale language model is a language model composed of an artificial neural network pre-trained using text data. Large-scale language models can include more than 10 times more parameters than conventional general language models. Large-scale language models can be used to perform various natural language processing tasks such as text generation, language translation, question answering, and summarization, and can operate using deep learning techniques.

[0028] According to one embodiment, the administrator electronic device 110 can upload content to the database 121 of the server 120. The content can be based on the type of service provided through the server 120. For example, if the service provided through the server 120 is a medical consultation service, the content can be medical content. For example, if the service provided through the server 120 is a legal consultation service, the content can be legal content. The content is uploaded to the database 121 of the server 120 through the administrator electronic device 110, and the type and nature of the consultation service provided through the server 120 can be determined by the content registered through the administrator electronic device 110.

[0029] Training an artificial intelligence based on a large-scale language model may refer to the AI ​​model 122 understanding human language and generating a response message based on a massive amount of text data. A massive amount of content uploaded via the administrator electronic device 110 may be uploaded to the database 121. As described above, the content may be based on the type and characteristics of the consultation service provided via the system 100 according to an embodiment. The uploaded content may be organized through preprocessing processes such as removing unnecessary words and sentences and standardizing the format. A large-scale language model to be used for training is selected (e.g., GPT-3, Jurassic-1 Jumbo, Megatron-Turing NLG, etc.), and hyperparameters of the large-scale language model may be set. The hyperparameters may affect the learning speed, accuracy, etc. of the model.

[0030] According to one embodiment, the processor 124 may train the large-scale language model-based artificial intelligence model 122 based on the uploaded content. The large-scale language model-based artificial intelligence model 122 may learn from the text contained within the content and use this as a basis to generate new text or learn how to answer questions.

[0031] According to one embodiment, the processor 124 can evaluate the performance of the AI ​​model 122 based on the trained large-scale language model. For example, the processor 124 can use automated evaluation metrics to evaluate the performance of the AI ​​model 122, and based on the evaluation results, can improve the performance of the AI ​​model 122 by adjusting hyperparameters or adding content.

[0032] According to one embodiment, the wireless communication circuit 123 can be configured to provide wireless communication with the external electronic device 200. For example, the wireless communication circuit 123 can preprocess information processed by the processor 124, upconvert it to a frequency to be transmitted to the external electronic device 200, and transmit it to the external electronic device 200. For example, the wireless communication circuit 123 can downconvert information transmitted from the external electronic device 200 to a frequency that can be read by the processor 124 and provide it to the processor 124. According to one embodiment, the external electronic device 200 can be connected to the server 120 via the wireless communication circuit 123. A question text transmitted from the external electronic device 200 can be provided to the processor 124 via the wireless communication circuit 123. The processor 124 can generate a response message to the question text using the artificial intelligence model 122 and transmit the response message to the external electronic device 200 via the wireless communication circuit 123.

[0033] According to an embodiment, the server 120 may be configured to provide a virtual space to which the external electronic device 200 can connect via the wireless communication circuit 123. For example, the virtual space may be referred to as a virtual space for providing consultation services via a consultation chatbot. For example, the virtual space may be displayed on the display of the external electronic device 200 connected to the virtual space, and the consultation content provided by the consultation chatbot may be displayed through the virtual space.

[0034] According to one embodiment, the website 130 may be used to receive a membership registration request from the external electronic device 200. For example, the system 100 according to one embodiment may provide a certain amount or number of consultation services via a consultation chatbot. After a certain amount or number of consultation services have been provided, the user of the external electronic device 200 may be requested to register as a member to use additional consultation services. The external electronic device 200 may input information for membership registration via the website 130, and the administrator electronic device 110 may be configured to approve the membership registration based on the information input via the website 130. If the consultation chatbot were provided unlimitedly, only free consultation services that are not actually monetized would be continuously provided, making it difficult to generate substantial revenue. Therefore, the system 100 according to one embodiment may provide only a certain number or amount of consultation services via the consultation chatbot and provide additional consultation services to the external electronic device 200 that has registered as a member after requesting membership registration.

[0035] The operation of the system 100 for providing an artificial intelligence-based consultation chatbot according to one embodiment will now be described.

[0036] 2 is a flowchart illustrating the operation of the system 100 for providing an AI-based consultation chatbot according to an embodiment. FIG. 3 is a diagram illustrating an example of consultation content provided to the external electronic device 200 through the system 100 for providing an AI-based consultation chatbot according to an embodiment.

[0037] The operations illustrated in FIG. 2 may be referred to as operations performed by processor 124 of server 120.

[0038] Referring to FIG. 2, at operation 201, the processor 124 may be configured to receive a question text (eg, question text 301 in FIG. 3) from an external electronic device 200 connected to the server 120.

[0039] According to one embodiment, the external electronic device 200 can be connected to the server 120 to use the system 100 that provides a consultation chatbot. The server 120 can be configured to provide a virtual space to which the external electronic device 200 can connect via a wireless communication circuit 123. For example, an application that can connect to the virtual space of the server 120 can be installed in the external electronic device 200. The external electronic device 200 can connect to the virtual space of the server 120 by executing the application. FIG. 3 shows a screen displayed on the external electronic device 200 connected to the virtual space of the server 120. An avatar 310 can be displayed in the virtual space. The server 120 can provide the avatar 310 to be displayed in the virtual space.

[0040] According to one embodiment, the processor 124 can generate information for generating a virtual space and an avatar 310. The processor 124 can generate the avatar 310 and the virtual space. The processor 124 can be configured to transmit, via the wireless communication circuit 123, to the external electronic device 200, first information for rendering the virtual space, second information for rendering the avatar 310, and third information for rendering a response message, which will be described later. The first information, second information, and third information will be described later with reference to FIG. 6.

[0041] According to one embodiment, processor 124 may be configured to generate avatar 310 and a virtual space based on content included in database 121. Generating avatar 310 and a virtual space based on content by processor 124 may be referred to as generating avatar 310 reflecting characteristics indicated by the content. For example, processor 124 may analyze content (e.g., text data) included in database 121 and generate avatar 310 and a virtual space reflecting characteristics indicated by the content. For example, if database 121 includes medical content (e.g., text content about diseases, health care, hospitals, medicines, etc.), processor 124 may be configured to identify the characteristics of the content as the medical field and generate avatar 310 in the form of an image of a doctor or nurse including medical equipment such as a stethoscope and a gown. For example, if the database 121 contains legal content (e.g., text content such as statutes, precedents, penalty clauses, legal requirements, and legal effects), the processor 124 may be configured to identify the characteristics of the content as a legal field and generate an avatar 310 of an image of a judge or lawyer including legal paraphernalia such as a robe and a pew. In addition, the processor 124 may be configured to generate the avatar 310 taking into consideration the characteristics of the fields of various consultation services provided through the consultation chatbot.

[0042] An external electronic device 200 connected to the server 120 can transmit a question text. For example, a user of the external electronic device 200 can input a question text about a matter to be discussed via the system 100 on the external electronic device 200. The external electronic device 200 can provide the question text to the server 120 via the wireless communication circuit 123. The processor 124 can receive the question text via the wireless communication circuit 123 and display the received question text in the virtual space. For example, referring to FIG. 3 , question text 301 displayed in the virtual space can be displayed via the external electronic device 200.

[0043] In operation 203, the processor 124 may be configured to extract a prompt from the question text that is input to the large-scale language model-based artificial intelligence model 122.

[0044] According to one embodiment, the processor 124 may be configured to extract a prompt from question text received from the external electronic device 200. For example, the processor 124 may be configured to identify keywords in the question text and extract a prompt to be input to the large-scale language model-based artificial intelligence model 122 based on the identified keywords. Inputting a prompt to the large-scale language model-based artificial intelligence model 122 may refer to output information from the final neural network layer of the large-scale language model obtained when the prompt is input to an inference engine based on a large-scale language model. For example, as shown in FIG. 3, if the question text 301 is text such as "Please introduce Director Hong Gil-dong," the processor 124 may extract a prompt from the question text 301. In this example, the entire text "Please introduce Director Hong Gil-dong" may be extracted as the prompt.

[0045] At operation 205, the processor 124 may be configured to generate a content-based response message by inputting the prompt into the large-scale artificial intelligence model 122.

[0046] According to one embodiment, the processor 124 may input the extracted prompt to a large-scale AI model 122. The AI ​​model 122 may convert the prompt from the input language into an expression that can be processed internally by the AI ​​model 122. The expression that can be processed internally may be a data structure used by the AI ​​model 122 to understand and process the prompt. The AI ​​model 122 may store information associated with the prompt and generate a response to the prompt by performing model inference based on the expression. During the inference process, the AI ​​model 122 may connect to a database 121 containing content and utilize pre-trained information.

[0047] As described above, the AI ​​model 122 is trained based on the content contained in the database 121, and can be used to generate a response message based on the content in response to a prompt. The processor 124 can generate a response message using the AI ​​model 122. For example, referring to FIG. 3, the processor 124 can input "Please introduce me to Director Hong Gil-dong" to the large-scale language model-based AI model 122 and generate a response message 302 related to information about Director Hong Gil-dong, which is output from the AI ​​model 122.

[0048] In operation 207 , the processor 124 may be configured to provide a response message to the external electronic device 200 via the virtual space of the server 120 .

[0049] According to one embodiment, the processor 124 may be configured to provide a response message to the external electronic device 200 via the virtual space. The external electronic device 200 may receive the response message provided via the virtual space. For example, referring to FIG. 3 , a response message 302 may be displayed on a screen of the external electronic device 200 connected to the virtual space. The response message 302 may be positioned adjacent to the avatar 310. For example, a visual object such as a speech bubble may be associated with the avatar 310, and the response message 302 may be displayed within the visual object.

[0050] According to an embodiment, the system 100 can provide accurate information quickly by providing a consultation chatbot using an artificial intelligence model 122 based on a large-scale language model trained based on content contained in a database 121. Providing a response message using the artificial intelligence model 122 can prevent errors due to subjective judgment and eliminate problems that depend on the personal feelings or subjectivity of the counselor. Furthermore, accurate and quick consultations can be provided through the automated consultation chatbot without causing emotional distress to the counselor due to the user of the external electronic device 200, thereby improving customer satisfaction.

[0051] FIG. 4 is a flowchart illustrating an operation of providing a first information message 510 in the system 100 for providing an AI-based consultation chatbot according to an embodiment.

[0052] For example, if a consultation chatbot using the system 100 is provided without any restrictions, it may be difficult to provide a service that leads to visible results. To attract customers, a certain amount or number of consultation services using the consultation chatbot may be provided, and if the number or number of response messages provided exceeds a certain range, a membership subscription may be encouraged, thereby increasing the number of members. The operations shown in FIG. 4 may be referred to as operations performed by the processor 124 of the server 120.

[0053] 4, the processor 124 may be configured to provide a response message in operation 401. Operation 401 may be referenced as the operation in FIG.

[0054] In operation 403, the processor 124 may be configured to count the amount or number of times the response messages are provided.

[0055] According to one embodiment, the processor 124 may count the number or quantity of response messages provided using an artificial intelligence model based on a large-scale language model. For example, the processor 124 may count all response messages generated by the artificial intelligence model 122 and provided to the external electronic device 200, and may create a script for counting the response messages to count the cumulative number or quantity, and analyze the script to count the number or quantity of response messages provided.

[0056] At operation 405, the processor 124 may be configured to identify whether the amount or number of response message deliveries exceeds a critical value.

[0057] According to one embodiment, processor 124 may compare the counted and accumulated amount or number of response messages provided with a threshold value. For example, the threshold value may include a first threshold value corresponding to the accumulated amount of response messages provided and / or a second threshold value corresponding to the accumulated number of response messages provided. Processor 124 may determine whether at least one of the amount or number of response messages provided exceeds a threshold value. If the amount or number of response messages provided exceeds a threshold value, operation 407 may be performed. If the amount or number of response messages provided does not exceed a threshold value, operation 401 may be performed again.

[0058] In operation 407, the processor 124 may be configured to identify whether the member is registered based on a communication log of the external electronic device 200.

[0059] According to one embodiment, the processor 124 may collect and analyze a communication log of the external electronic device 200 connected to the server 120 based on determining that the amount or number of response messages provided exceeds a threshold. The communication log records communication activity between the external electronic device 200 and the server 120 and may indicate the communication time of the external electronic device 200, the connected IP address, port number, the amount of data transmitted, the protocol used, etc. The processor 124 may be configured to identify whether the external electronic device 200 has registered as a member of the website through the collection and analysis of the communication log. The membership status may be determined based on whether the external electronic device 200 has logged in as a registered member of the website. For example, if the external electronic device 200 logs in through the website and then connects to the server 120 to receive a response message, the login record of the external electronic device 200 remains in the communication log, allowing the processor 124 to identify the external electronic device 200 as a member. If the external electronic device 200 connects to the server 120 without logging in via the website and receives a response message, the processor 124 may determine that the external electronic device 200 is not a member because no login record of the external electronic device 200 is left in the communication log. However, without being limited thereto, the processor 124 may determine whether the external electronic device 200 is a member using various methods. For example, the processor 124 may determine whether the external electronic device 200 is a member using membership information stored in the database 121. If the external electronic device 200 corresponds to one of the terminals registered in the membership information, the processor 124 may determine that the external electronic device 200 is a member. If the external electronic device 200 does not correspond to a terminal registered in the membership information, the processor 124 may determine that the external electronic device 200 is a non-member.

[0060] At operation 409, the processor 124 may be configured to continually provide a response message if a membership is identified.

[0061] According to one embodiment, the processor 124 may be configured to continuously provide a response message based on identifying the member in operation 407. That is, even if the amount or number of response messages provided exceeds a threshold, the processor 124 may continuously provide the message. Since members are likely to be major customers of the service, the possibility of actual revenue generation may be high if the member is continuously provided with a service via a consultation chatbot. Therefore, since members have a high possibility of revenue generation, the processor 124 may continuously provide a response message to encourage the use of the service.

[0062] At operation 411, the processor 124 may be configured to discontinue providing the response message and provide a first invitation message 510 if a non-member is identified.

[0063] According to one embodiment, the processor 124 may be configured to, in operation 409, based on identifying the non-member, suspend providing the response message and provide the external electronic device 200 with a first invitation message 510 to invite the external electronic device 200 to join as a member via the virtual space of the server 120.

[0064] FIG. 5 illustrates an example of an external electronic device 200 connecting to a website via a first invitation message 510 of a system 100 for providing an artificial intelligence-based consultation chatbot according to an embodiment.

[0065] The first screen 500a of FIG. 5 illustrates the external electronic device 200 on which a first guidance message 510 is displayed. Referring to the first screen 500a, if the number or number of consultation messages provided exceeds a threshold, the processor 124 may stop providing the consultation messages and provide the external electronic device 200 with a first guidance message 510 inviting the user to sign up as a member. The first guidance message 510 may be displayed on the first screen 500a of the external electronic device 200 via a virtual space. The first guidance message 510 may include text such as, "For additional consultations, please inquire after signing up as a member." According to one embodiment, the first guidance message 510 may include a link 511 connectable to a website address offering membership registration. When a user inputs the link 511, the external electronic device 200 may connect to the website via the link 511.

[0066] The second screen 500b of FIG. 5 shows the external electronic device 200 connected to the website 520. For example, a user of the external electronic device 200 can connect the external electronic device 200 to the website 520 by providing user input (e.g., touch input) to a link 511 included in the first guidance message 510. When the external electronic device 200 connects to the website 520, the website 520 offering membership subscriptions can be displayed on the external electronic device 200. The website 520 receives information for membership subscription. When the user requests membership subscription after entering the information, the website 520 can provide a request for approval of the membership subscription to the administrator terminal. The administrator terminal can be configured to receive the request received via the website 520 and approve the membership subscription in accordance with the request. After membership subscription, the user can provide a question text and can additionally receive a response message provided via an AI-based consultation chatbot. For example, after membership subscription is completed, the processor 124 can again identify the user as a member after operation 413 and can continuously provide response messages accordingly.

[0067] According to one embodiment, the processor 124 may be configured to connect the external electronic device 200 to the website 520 based on determining that a first time has elapsed since the first time point when the first announcement message 510 was provided. For example, if the number or number of response messages provided exceeds a threshold and the first announcement message 510 is provided via a virtual space, the processor 124 may record the first time point when the first announcement message 510 was provided. Based on determining that the first time point has elapsed since the first time point, the processor 124 may forcibly connect the external electronic device 200 to the website 520 even without a user input on the link 511 of the first announcement message 510, thereby encouraging membership registration. For example, the processor 124 may be configured to specify the URL of the website using a location field in a response header in the server 120, and to automatically move the external electronic device 200 to the URL of the website 520 when the first time point has elapsed.

[0068] According to an embodiment, the system 100 for providing an AI-based consultation chatbot can provide content-based response messages in response to question text received from the external electronic device 200, and can naturally recruit members by forcing membership when a certain number or number of response messages are provided. For example, if the system 100 is a system 100 for providing medical consultation services, the profitability of the revenue model can be improved as the number of members increases. Revenue generation through the system 100 can increase with the number of members, such as by receiving advertising orders from hospitals or pharmaceutical companies or providing public relations for directly operated hospitals. Therefore, the method can be used to smoothly increase the number of members and generate revenue.

[0069] FIG. 6 illustrates an example of an external electronic device 200 displaying a virtual space and an avatar 310 of a system 100 for providing an artificial intelligence-based consultation chatbot according to one embodiment.

[0070] According to one embodiment, the processor 124 can generate the virtual space 610 and the avatar 310 to be displayed in the virtual space 610. The processor 124 can generate the virtual space 610 and the avatar 310 based on the content in the database 121. For example, if the content includes medical content (e.g., text data), the processor 124 can identify medical field attributes and, based on this, generate the virtual space 610 with an image of an examination room and the avatar 310 with an image of a doctor.

[0071] According to one embodiment, the processor 124 may be configured to transmit information for displaying the virtual space 610 and the avatar 310 to the external electronic device 200 connected to the server 120. The processor 124 may be configured to transmit, via the wireless communication circuit 123, to the external electronic device 200: first information for rendering the virtual space 610, second information for rendering the avatar 310 displayed within the virtual space 610, and third information for rendering a response message to be displayed adjacent to the avatar 310 included in the virtual space 610. The external electronic device 200 may render the virtual space 610 using the first information. For example, the external electronic device 200 may render the virtual space 610 as an image of a medical examination room using the first information. The external electronic device 200 may render the avatar 310 using the second information. For example, the external electronic device 200 may render the avatar 310 as an image of a doctor using the second information. The external electronic device 200 may use the third information to render a response message adjacent to the avatar 310 displayed in the virtual space 610. The third information may include a response message generated through the large-scale language model-based artificial intelligence model 122.

[0072] According to one embodiment, the processor 124 may be configured to generate an avatar 310 based on the question text. For example, if the question text is about a specific disease or a specific legal issue, the processor 124 may understand the intent of the question and provide an avatar 310 (medical professional or lawyer) and a virtual space 610 (clinic or courtroom) that are imaged to correspond to the question.

[0073] According to one embodiment, a user of the external electronic device 200 can have the same experience as receiving a consultation in a real environment when receiving a consultation service through a consultation chatbot using the system 100. While consultations provided through the AI ​​model 122 are stiff and boring, receiving consultations through the content-based virtual space 610 and avatar 310 can enhance the user experience.

[0074] 7a and 7b illustrate an example of an external electronic device 200 displaying a second guidance message of the system 100 for providing an AI-based consultation chatbot according to an embodiment.

[0075] Referring to FIG. 7a, the system 100 for providing an artificial intelligence-based consultation chatbot according to one embodiment may provide a second guidance message 711 to the external electronic device 200 to inform the external electronic device 200 that the response message 713 is being generated if the time to provide the response message 713 is delayed.

[0076] If it takes a very long time to generate the response message 713, the user of the external electronic device 200 may have difficulty determining whether the response message 713 is being generated or whether an error in the system 100 has occurred. To address this issue, the processor 124 may be configured to provide a second guidance message 711 to the external electronic device 200 via the virtual space of the server 120 when a second time has elapsed since receiving the query text 701. The second guidance message 711 may include text such as "Please wait while the AI ​​counselor searches for materials." The user can identify that the response message 713 is being generated through the second guidance message 711 provided via the external electronic device 200 and wait for the response message 713 to be provided. Once the response message 713 is generated, the response message 713 may be provided to the external electronic device 200 via the virtual space. 7a, the question text 701, the first guidance message 510, and the response message 713 may be displayed in this order. As described above, the avatar 310 may be displayed on the external electronic device 200. The second time may be set to a time for which the provision of the response message 713 is determined to be delayed.

[0077] According to one embodiment, the processor 124 may be configured to identify the time that has elapsed since the second time point and provide a first visual object 712 indicating the elapsed time together with a second guidance message 711 to the external electronic device 200 via the virtual space of the server 120. Referring to Figure 7a, the first visual object 712 may include the elapsed time along with an icon indicating that an operation is being performed to generate a response message 713. The user of the external electronic device 200 may recognize the elapsed time and confirm the amount of time they have waited via the first visual object 712.

[0078] 7b, according to one embodiment, the processor 124 may be configured to calculate the time required to generate the response message 713 and provide a second visual object 714 indicating the required time together with the second guidance message 711 to the external electronic device 200 via the virtual space of the server 120. For example, the second visual object 714 may include the required time along with text such as "estimated waiting time." Through the second visual object 714, the user of the external electronic device 200 may recognize the estimated time they must wait to receive the response message and confirm the waiting time. The second visual object 714 may include an image such as a scroll bar indicating the elapsed time relative to the required time. Through the scroll bar image, the required time, elapsed time, and remaining time may be intuitively recognized.

[0079] As described above, the system 100 for providing an AI-based consultation chatbot according to an embodiment can provide time information to a user receiving consultation services via the consultation chatbot by providing the second guidance message 711, the first visual object 712, and the second visual object 714. The user of the external electronic device 200 can wait to receive the response message 713 via the second guidance message 711, the first visual object 712, and the second visual object 714, or can use the system 100 at another time, thereby enhancing the user experience.

[0080] 8 is a flowchart illustrating an operation of providing a counter-question text in the system 100 for providing an AI-based consultation chatbot according to an embodiment. 9a, 9b, and 9c illustrate an example of an external electronic device 200 displaying a counter-question text in the system 100 for providing an AI-based consultation chatbot according to an embodiment.

[0081] The operations illustrated in FIG. 8 may be referred to as operations performed by processor 124 of server 120.

[0082] If the question text received from the external electronic device 200 is unrelated or has low relevance to the content, it may be difficult to generate a response message. In this case, even if a response message is generated and provided, there is a high probability that it will not actually be a response to the question text. Therefore, the system 100 for providing an AI-based consultation chatbot according to an embodiment may clarify the intent of the question through a counter-question (reverse question) when the similarity between the question text and the content is low.

[0083] Referring to FIG. 8, at operation 801, the processor 124 may be configured to identify a similarity between the question text and the content.

[0084] According to one embodiment, the processor 124 may identify a similarity between the question text and the content to determine whether the question text received from the external electronic device 200 is a question related to the content. For example, the processor 124 may use a vector space model (VSM). The processor 124 may represent the content and the text as a set of words and generate a vector indicating the importance of each word. The processor 124 may calculate the similarity of the vectors to identify the similarity between the content and the text. Various other methods may also be used.

[0085] At operation 803, the processor 124 may be configured to identify whether the identified similarity is less than a first similarity.

[0086] According to one embodiment, the first similarity may refer to a similarity between the content and the question text that is high enough to generate a response message to the question text. If the identified similarity is equal to or greater than the first similarity, operation 805 may be performed. If the identified similarity is less than the first similarity, operation 807 may be performed.

[0087] At operation 805, the processor 124 may be configured to provide a response message to the external electronic device 200 based on identifying the first degree of similarity or greater.

[0088] According to one embodiment, a similarity of the first similarity or greater indicates that the question text is a question about the content, so the processor 124 can generate a response message and provide the response message to the external electronic device 200. Operation 805 can be referred to as the operation shown in FIG.

[0089] At operation 807, the processor 124 may be configured to identify whether the identified similarity exceeds a second similarity that is lower than the first similarity.

[0090] According to one embodiment, the second similarity may be referred to as a similarity that is not sufficient to generate a response message, but is sufficient to determine the intent of the question through the response text and generate a response message. If the identified similarity is equal to or less than the second similarity, operation 809 may be performed. If the identified similarity exceeds the second similarity, operation 811 may be performed.

[0091] In operation 809, the processor 124 may be configured to provide a third guidance message to the external electronic device 200 via the virtual space of the server 120, informing the external electronic device 200 that a response message for the question text cannot be provided, based on identifying a similarity equal to or lower than a second similarity that is lower than the first similarity. The third guidance message may be referred to as a message informing the external electronic device 200 that the question is incorrect and a response message cannot be generated. The user of the external electronic device 200 may recognize through the third guidance message that the question text is incorrect or that a response message for the question text cannot be obtained.

[0092] At operation 811, the processor 124 may be configured to identify one or more keywords within the content based on the question text based on identifying similarities less than a first similarity and greater than a second similarity.

[0093] According to one embodiment, the processor 124 may be configured to identify one or more keywords that are highly similar to the question text based on the question text. For example, if the question text contains an error (typo), the processor 124 may search the content for and identify one or more keywords that are most similar to the word containing the error.

[0094] At operation 813, the processor 124 may be configured to generate asking back text corresponding to the question text using one or more keywords.

[0095] According to one embodiment, the processor 124 may be configured to generate a counter-question text corresponding to the question text using the identified one or more keywords. For example, if a keyword with the highest similarity to an erroneous word is found, the processor 124 may be configured to generate a counter-question text for a question about whether the word in the question text is the keyword. For example, if the content and the keyword in the question text are not highly related, the counter-question text may be generated by finding the keyword with the highest similarity.

[0096] At operation 815 , the processor 124 may be configured to provide the challenge text to the external electronic device 200 via the virtual space of the server 120 .

[0097] According to one embodiment, the processor 124 may be configured to provide the response text to the external electronic device 200, correct the question text through confirmation by the external electronic device 200, and provide a response message. For example, if it is determined through the response text that an erroneous word corresponds to the keyword, the processor 124 may replace the word with the keyword, re-identify the question text, extract a prompt from the question text, and generate a response message. This allows for smooth consultation, and if there is insufficient content to generate a response message for the response text, this information may be fed back to the administrator electronic device 110. For example, if a response occurs due to a lack of registered content sources, the processor 124 may notify the administrator electronic device 110 that there is insufficient content for the corresponding response text. The administrator electronic device 110 may provide this feedback by registering additional content.

[0098] An example of the operation is explained through Figures 9a, 9b and 9c.

[0099] FIG. 9a illustrates a case where the similarity between the content and question text 911 is less than a first similarity and greater than a second similarity. If the question text 911 is "Tell me about Gardasil," the processor 124 can identify the similarity between the question text 911 and the content. If the content is about a common cold or an infectious disease, the similarity between the question text 911 and the content may be less than the first similarity. The processor 124 can search the content for a keyword that is most similar to the question text 911 to generate a response text 912. For example, the response text 912 can include text such as "Would you like to know about Gardasil, a vaccine that prevents human papillomavirus (HPV)-related diseases?" If an affirmative response 913 is received, the processor 124 can generate a response message 914 from one or more keywords in the response text 912.

[0100] Unlike the example shown in Figure 9a, the same operation can be performed if there is an error in the question text 911. For example, if the content includes content related to obstetrics and gynecology-related diseases but there is a typographical error in the question text 911 (e.g., question text 911 such as "Tell me about Gardasil"), the processor 124 can search for "Gardasil" in the content as the keyword most similar to the typo "Gardasil." The processor 124 can generate a counter-question text 912 based on "Gardasil," which can then generate a response message 914.

[0101] FIG. 9b illustrates a case where the similarity between the content and the question text is less than a first similarity and greater than a second similarity. If the question text includes text such as "Tell me about health care during seasonal changes," the processor 124 may search for one or more keywords in the content that are most similar to "health care during seasonal changes." If the content does not include "health care during seasonal changes" but does include content about respiratory infectious diseases, the processor 124 may search for "respiratory infectious diseases" as a keyword and generate and provide response text 922. If a negative response 923 is received, the processor 124 may search for "allergic diseases" as the next most similar keyword and generate and provide response text 924. If a positive response 925 is received, the processor 124 may be configured to generate and provide a response message using the artificial intelligence model 122 from the content about allergic diseases.

[0102] 9c illustrates a case where the similarity between the content and the question text is equal to or less than the second similarity. If the content included in the database 121 is medical content and the question text includes text such as "Tell me about BTS," the processor 124 may identify that the similarity between the content and the question text is equal to or less than the second similarity. In this case, the processor 124 may be configured to provide a third guidance message to the external electronic device 200 via the virtual space of the server 120, informing the external electronic device 200 that a response message for the question text cannot be provided. The third guidance message may be referred to as a message informing the external electronic device 200 that the question is incorrect and a response message cannot be generated. The user of the external electronic device 200 may recognize from the third guidance message that the question text is incorrect or that a response message for the question text cannot be obtained.

[0103] As described above, the system 100 for providing an AI-based consultation chatbot according to an embodiment can accurately identify the question text using the counter-question text or can indicate that the question text is unrelated to the content, thereby providing an accurate response to the question text.

[0104] FIG. 10 illustrates an external electronic device 200 using the department change service of the system 100 for providing an artificial intelligence-based consultation chatbot according to one embodiment.

[0105] According to one embodiment, if a consultation with a specialized department is required, the processor 124 may provide information guiding the main consultation content for the department, and if the department is changed during the consultation, the processor 124 may process the consultation so that the consultation continues from the existing consultation. For example, referring to a first screen 1000a of FIG. 10, the external electronic device 200 may request a specialized consultation for a specific field (e.g., a women's plastic surgery clinic). Then, referring to a second screen 1000b of FIG. 10, the external electronic device 200 may change the field and request a specialized consultation for the birth / delivery field. Referring to a third screen 1000c of FIG. 10, if the field is changed from a women's plastic surgery clinic to a birth / delivery field, the previously displayed response message remains displayed, thereby providing continuity of the consultation.

[0106] FIG. 11 illustrates an example in which a response message provision history is registered through the administrator electronic device 110 of the system 100 for providing an AI-based consultation chatbot according to an embodiment.

[0107] According to one embodiment, the processor 124 may be configured to store history data corresponding to information related to the history of providing response messages in the database 121. Referring to FIG. 11, a server showing history data 1100 is shown. The administrator electronic device 110 manages the history of providing response messages stored in the database 121 and processes the registered content so that it is automatically registered as learning material for the artificial intelligence model 122. The administrator electronic device 110 also manages the history of response messages provided through consultations as data, thereby providing management for members. For example, the administrator electronic device 110 can check and view the details of consultations for each member in a virtual space. This allows for continuous management of members, and allows for more specialized and detailed consultations by training the artificial intelligence model 122 based on a large-scale language model using response messages to consultations.

[0108] The various embodiments and terms used herein are not intended to limit the technical features described herein to specific embodiments, but should be understood to include various modifications, equivalents, or alternatives of the embodiments. In connection with the description of the drawings, like reference numerals may be used for like or related components. The singular form of a noun corresponding to an item may include one or more of the item, unless the relevant context clearly dictates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," and "at least one of A, B, or C" each include any one of the items listed in the phrase, or all possible combinations thereof. Terms such as "first," "second," "initial," or "secondary" may be used simply to distinguish a corresponding element from other corresponding elements and do not limit the corresponding element in other aspects (e.g., importance or order). When one (e.g., first) component is referred to as "coupled" or "connected" to another (e.g., second) component, with or without the terms "functionally" or "communicatively," it means that the component can be coupled to the other component directly (e.g., by wire), wirelessly, or via a third component.

[0109] According to various embodiments, each of the components described above may include one or more entities, and some of the entities may be located separately in other components. According to various embodiments, one or more of the components described above may be omitted, or one or more other components or entities may be added. Alternatively or additionally, multiple components may be integrated into a single component. In such cases, the integrated component may perform one or more functions of each of the multiple components in a manner that is the same as or similar to that performed by the corresponding component of the multiple components before the integration. According to various embodiments, operations performed by a module, program, or other component may be performed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be performed in a different order, omitted, or one or more additional operations may be added.

Claims

1. In a system that provides a consultation chatbot based on artificial intelligence, A server; an administrator electronic device having administrative authority over the server; The server a database containing content uploaded by the administrator electronic device and member information; wireless communication circuitry configured to provide wireless communication with an external electronic device; and a processor configured to train a large-scale language model-based artificial intelligence model based on the content contained in the database; The server configured to provide a virtual space to which an external electronic device can connect via the wireless communication circuit to provide consultation services; The processor: receiving a query text from the external electronic device connected to the server via the wireless communication circuit; extracting a prompt from the question text to be input to the large-scale language model-based artificial intelligence model; generating a response message based on the content stored in a database by inputting the prompt into the large-scale language model-based artificial intelligence model; providing the response message to the external electronic device via the virtual space of the server; Counting the amount or number of times the response message is provided; collecting and analyzing communication logs of the external electronic device based on identifying that at least one of the accumulated provided amount or the provided number of times exceeds a threshold value; Based on the analysis result, determine whether the external electronic device is eligible to join as a member; If the member is identified, the response message is continuously provided; If the user is identified as a non-member, the server stops providing the response message and provides the external electronic device with a first guidance message for instructing the user to join as a member via the virtual space of the server. A system that provides consultation chatbots based on artificial intelligence.

2. The first announcement message is Contains a link that connects to a website address offering membership subscriptions; 10. A system for providing an artificial intelligence based consultation chatbot according to claim 1.

3. The processor: and connecting the external electronic device to the website based on identifying that a first time has elapsed since the first time point when the first guidance message was provided.

3. A system for providing an artificial intelligence based consultation chatbot according to claim 2.

4. The processor: configured to provide, via the wireless communication circuitry, to the external electronic device: first information for rendering the virtual space; second information for rendering an avatar displayed within the virtual space; and third information for rendering the response message displayed adjacent to the avatar contained within the virtual space.

10. A system for providing an artificial intelligence based consultation chatbot according to claim 1.

5. A system for providing an artificial intelligence-based consultation chatbot, A server; an administrator electronic device having administrative authority over the server; The server a database containing content uploaded by the administrator electronic device and member information; wireless communication circuitry configured to provide wireless communication with an external electronic device; and a processor configured to train a large-scale language model-based artificial intelligence model based on the content contained in the database; The server configured to provide a virtual space to which an external electronic device can connect via the wireless communication circuit to provide consultation services; The processor: receiving a query text from the external electronic device connected to the server via the wireless communication circuit; extracting a prompt from the question text to be input to the large-scale language model-based artificial intelligence model; generating a response message based on the content stored in a database by inputting the prompt into the large-scale language model-based artificial intelligence model; providing the response message to the external electronic device via the virtual space of the server; providing, via the wireless communication circuitry, to the external electronic device, first information for rendering the virtual space, second information for rendering an avatar to be displayed within the virtual space, and third information for rendering the response message to be displayed adjacent to the avatar contained within the virtual space; configured to generate the avatar based on the content contained in the database; A system that provides consultation chatbots based on artificial intelligence.

6. A system for providing an artificial intelligence-based consultation chatbot, A server; an administrator electronic device having administrative authority over the server; The server a database containing content uploaded by the administrator electronic device and member information; wireless communication circuitry configured to provide wireless communication with an external electronic device; and a processor configured to train a large-scale language model-based artificial intelligence model based on the content contained in the database; The server configured to provide a virtual space to which an external electronic device can connect via the wireless communication circuit to provide consultation services; The processor: receiving a query text from the external electronic device connected to the server via the wireless communication circuit; extracting a prompt from the question text to be input to the large-scale language model-based artificial intelligence model; generating a response message based on the content stored in a database by inputting the prompt into the large-scale language model-based artificial intelligence model; providing the response message to the external electronic device via the virtual space of the server; providing, via the wireless communication circuitry, to the external electronic device, first information for rendering the virtual space, second information for rendering an avatar to be displayed within the virtual space, and third information for rendering the response message to be displayed adjacent to the avatar contained within the virtual space; configured to provide the first information and the second information based on the question text; A system that provides consultation chatbots based on artificial intelligence.

7. The processor: and providing, to the external electronic device through the virtual space of the server, a second notification message for informing the external electronic device that the response message is being generated, based on identifying that a second time period has elapsed since the second time point when the question text was received.

10. A system for providing an artificial intelligence based consultation chatbot according to claim 1.

8. A system for providing an artificial intelligence-based consultation chatbot, A server; an administrator electronic device having administrative authority over the server; The server a database containing content uploaded by the administrator electronic device and member information; wireless communication circuitry configured to provide wireless communication with an external electronic device; and a processor configured to train a large-scale language model-based artificial intelligence model based on the content contained in the database; The server configured to provide a virtual space to which an external electronic device can connect via the wireless communication circuit to provide consultation services; The processor: receiving a query text from the external electronic device connected to the server via the wireless communication circuit; extracting a prompt from the question text to be input to the large-scale language model-based artificial intelligence model; generating a response message based on the content stored in a database by inputting the prompt into the large-scale language model-based artificial intelligence model; providing the response message to the external electronic device via the virtual space of the server; providing a second notification message to the external electronic device through the virtual space of the server to notify the external electronic device that the response message is being generated based on identifying that a second time period has elapsed since the second time point when the query text was received; Identifying the amount of time that has elapsed since the second point in time; and providing a first visual object indicating the elapsed time together with the second guidance message to the external electronic device via the virtual space of the server. A system that provides consultation chatbots based on artificial intelligence.

9. The processor: calculating the time required to generate the response message; and providing a second visual object indicating the required time together with the second guidance message to the external electronic device via the virtual space of the server.

9. A system for providing an artificial intelligence based consultation chatbot according to claim 8.

10. The administrator electronic device storing history data corresponding to information related to the history of providing the response message in the database; 10. A system for providing an artificial intelligence based consultation chatbot according to claim 1.

11. The processor: Identifying a similarity between the question text and the content; providing the response message to the external electronic device based on identifying the similarity greater than or equal to a first similarity; identifying one or more keywords in the content based on the question text based on identifying the similarity less than the first similarity; generating a question text corresponding to the question text using the one or more keywords; and providing the question text to the external electronic device via the virtual space of the server.

10. A system for providing an artificial intelligence based consultation chatbot according to claim 1.

12. The processor: and providing, to the external electronic device through the virtual space of the server, a third guidance message for informing the external electronic device that the response message for the question text cannot be provided, based on identifying the similarity equal to or less than a second similarity that is lower than the first similarity.

12. A system for providing an artificial intelligence based consultation chatbot according to claim 11.

Images