KR-20260065707-A - Customized counseling system and method through analysis of client's speech and emotional state using an artificial intelligence model based on natural language processing

KR20260065707AKR 20260065707 AKR20260065707 AKR 20260065707AKR-20260065707-A

Abstract

The present invention relates to a user terminal for providing text response information or voice response information, comprising: an output unit for outputting the text response information or the voice response information; a sensor unit for sensing the voice information of the user; a communication unit for communicating with a server device; a processor unit; and a memory unit for implementing a natural language processing-based artificial intelligence model; wherein the communication unit transmits the sensed voice information to a server device and receives a first response information based on the voice information transmitted from the server device, and the processor unit creates voice analysis information of the user based on the sensed voice information and the implemented natural language processing-based artificial intelligence model, creates a second response information reflecting the created voice analysis information in the first response information, and controls the output unit to output the created second response information in the form of a text response or the voice response.

Inventors

천상현

Assignees

천상현

Dates

Publication Date: 20260511
Application Date: 20241101

Claims (20)

In a user terminal for providing text response information or voice response information, An output unit that outputs the above text response information or the above voice response information; A sensor unit that senses the voice information of the above-mentioned user; A communication unit that communicates with a server device; Processor unit; and A memory unit for implementing a natural language processing-based artificial intelligence model; including The above communication unit transmits the sensed voice information to a server device, and Receiving first response information based on voice information transmitted from the above server device, and The above processor unit Based on the sensed voice information above, the user's voice analysis information is generated based on the implemented natural language processing-based artificial intelligence model, and A second response information is created by reflecting the voice analysis information created above in the first response information above, and Configured to control the output unit to output the second response information written above in the form of a text response or the voice response, A user terminal for providing text response information or voice response information.
In Article 1, The above processor unit Configured to convert the above-mentioned sensed voice information into text information, A user terminal for providing text response information or voice response information.
In Article 2, The above processor unit Includes natural language processing tools, The above natural language processing tool is configured to analyze the grammatical structure of the above-described converted text information to identify at least one component among the subject, object, and verb, A user terminal for providing text response information or voice response information.
In Article 2, The above processor unit Includes natural language processing tools, The above natural language processing tool is configured to extract information contained in the above converted text information as entities, A user terminal for providing text response information or voice response information.
In Article 4, The above natural language processing tool is configured to determine the meaning of the sensed voice information based on the converted text information and the extracted entities, A user terminal for providing text response information or voice response information.
In Article 2, The above processor unit Includes sentiment analysis tools, The above sentiment analysis tool is configured to identify the user's emotional state based on at least one of tone, word choice, and sentence structure included in the above converted text information. A user terminal for providing text response information or voice response information.
In Article 2, The above processor unit Includes natural language processing tools, The above natural language processing tool is configured to analyze morphemes in the above-described converted text information, and Configured to distinguish the converted text information as a dialect or standard language based on the above morphological analysis, A user terminal for providing text response information or voice response information.
In Article 6, The above sentiment analysis tool is Configured to detect changes in the user's emotional state in real time based on at least one of tone, word choice, and sentence structure included in the converted text information above. A user terminal for providing text response information or voice response information.
In Article 2, The above processor unit It can include additional response style selection tools, The above response style selection tool is configured to select a response style based on the above converted text information and at least one of a rule-based system, a decision tree model, a machine learning algorithm, and a reinforcement learning algorithm. A user terminal for providing text response information or voice response information.
In Article 9, The above response style selection tool is Based on the above-mentioned transformed text information and at least one of a rule-based system, a decision tree model, a machine learning algorithm, and a reinforcement learning algorithm Configured to select at least one response style among an age-based response style, a litigation-type-based response style, or a mixed-type response style, A user terminal for providing text response information or voice response information.
In a user terminal for providing text response information or voice response information, An output unit that outputs the above text response information or the above voice response information; A sensor unit that senses the voice information of the above-mentioned user; A communication unit that communicates with a server device; Processor unit; and Includes a memory section; and The above communication unit transmits the sensed voice information to the server device, and From the above server device Receiving user voice analysis information generated based on the above-mentioned transmitted voice information and second response information reflecting the above-mentioned voice analysis information, and The above processor unit Configured to control the output unit to output the received second response information in the form of the text response information or the voice response information. A user terminal for providing text response information or voice response information.
In a server device for providing response information, A communication unit that communicates with a user terminal; Processor unit; and A memory unit for implementing a natural language processing-based artificial intelligence model; including The above communication unit Receiving voice information from the above user terminal, and The above processor unit First response information is generated based on the received voice information and the implemented natural language processing-based artificial intelligence model, and The communication unit is configured to transmit the first response information created above to the user terminal, A server device for providing response information.
In Article 12, The above processor unit Configured to convert the received voice information into text information, A server device for providing response information.
In Article 13, The above processor unit Includes natural language processing tools, The above natural language processing tool is configured to analyze the grammatical structure of the above-described converted text information to identify at least one component among the subject, object, and verb, A server device for providing response information.
In Article 13, The above processor unit Includes natural language processing tools, The above natural language processing tool is configured to extract information contained in the above converted text information as entities, A server device for providing response information.
In Article 15, The above natural language processing tool is configured to determine the meaning of the received voice information based on the converted text information and the extracted entities, A server device for providing response information.
In Article 13, The above processor unit Includes sentiment analysis tools, The above sentiment analysis tool is configured to identify the user's emotional state based on at least one of tone, word choice, and sentence structure included in the above converted text information. A server device for providing response information.
In Article 13, The above processor unit Includes natural language processing tools, The above natural language processing tool is configured to analyze morphemes in the above-described converted text information, and Configured to distinguish the converted text information as a dialect or standard language based on the above morphological analysis, A server device for providing response information.
In Article 17, The above sentiment analysis tool is Configured to detect changes in the user's emotional state in real time based on at least one of tone, word choice, and sentence structure included in the converted text information above. A server device for providing response information.
In Article 13, The above processor unit It can include additional response style selection tools, The above response style selection tool is configured to select a response style based on the above converted text information and at least one of a rule-based system, a decision tree model, a machine learning algorithm, and a reinforcement learning algorithm. A server device for providing response information.

Description

Customized counseling system and method through analysis of client's speech and emotional state using an artificial intelligence model based on natural language processing The present invention relates to a customized counseling system and method through the analysis of a client's speech tone and emotional state using a natural language processing-based artificial intelligence model. In traditional legal counseling, it is crucial to immediately identify and incorporate a client's emotional state or conversational style; however, there are limitations in fully understanding these emotional and linguistic elements, particularly in a non-face-to-face counseling environment. This difficulty can become even more pronounced when the counselor fails to fully understand the dialect or regional expressions used by the client. Failure to properly recognize a client's speech patterns or dialects can hinder smooth communication between the counselor and the client, potentially leading to issues such as the failure to build trust or a decline in the quality of the counseling. Therefore, there is a current demand for skills that enable the accurate recognition of a client's emotional state and regional linguistic expressions during legal consultations, as well as the provision of customized counseling methods tailored to these factors. This allows counselors to respond appropriately to the client's psychological state and facilitates smooth conversation. For instance, providing prompt and clear information to a client in an urgent situation, along with responding with empathy based on their emotional state, can serve as crucial elements in enhancing the effectiveness of the counseling. Such technical necessity is essential to enhance the effectiveness of legal consultation and maintain consultation quality even in non-face-to-face sessions. FIG. 1 is a drawing for explaining a user terminal and a server device according to the present invention. FIG. 2 is a block diagram illustrating a method for providing a response according to the present invention. FIG. 3 is a diagram illustrating the creation of voice analysis information according to an embodiment of the present invention. FIG. 4 is a diagram illustrating the creation of voice analysis information according to another embodiment of the present invention. FIG. 5 is a diagram illustrating an embodiment of real-time emotion change detection according to the present invention. FIG. 6 is a diagram illustrating an example of dialect conversion according to the present invention. FIG. 7 is a diagram illustrating an embodiment related to a response generation process according to the present invention. Specific details of the embodiments are included in the detailed description and drawings. The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components. Artificial intelligence model According to one embodiment of the present invention, artificial intelligence (AI) may generally refer to the development of a computer system or machine capable of performing tasks that require human intelligence. These tasks include reasoning, learning, problem solving, natural language understanding, pattern recognition, and decision making. Specifically, artificial intelligence may be used in fields such as machine learning (ML), natural language processing (NLP), computer vision, expert systems, robotics, and deep learning (DL). According to one embodiment of the present invention, machine learning may be a subset of AI in which a machine learns from data without being explicitly programmed. As a system is exposed to more data, it can improve its performance through machine learning. Methods of machine learning include supervised learning, unsupervised learning, and reinforcement learning. Natural language processing is a field of AI that enables computers to understand, interpret, and generate human language. Through AI models based on natural language processing, applications such as chatbots, language translation, and voice assistance can be provided. Computer vision involves training models to interpret and understand visual information, such as recognizing objects in images or videos. Computer vision can be used in fields such as facial recognition, autonomous vehicles, and medical image analysis. Expert systems are AI systems that use knowledge and reasoning rules to solve complex p