Artificial intelligence model solution delivery method, device and system

Abstract

According to one embodiment, in a method of providing an artificial intelligence model solution, the method performs a tendency analysis of analyzing a leader on the basis of natural language processing by an agenda, the method being performed by a device, receiving a request from a user terminal to analyze a location of a first leader on a first agenda; data published in the first stage is collected and acquired, the data are pre-established through crawling, and the data are classified to be related to a first leader person and serve as a first batch of data; extracting data from the first data described as being related to the first agenda as data 1-1; generating a first question, and requiring to classify the position of a first leader on the first agenda according to the data published in the first stage; a first question is input into a first AI model, the model is trained, and the standing of a leader can be answered by analyzing a text; if the answer to the first question is generated as a first answer based on the data of the first artificial intelligence model 1-1, the step of obtaining the first answer from the first artificial intelligence model is taken as an output result; determining that the position of the first leader figure on the first agenda is a first stand, and taking the first answer as a basis; and a method for providing an artificial intelligence model solution for analyzing the leader tendency of each agenda based on natural language processing, comprising a step of analyzing the position of the first leader on the first agenda and the first position.

Description

Technical Field

[0001] This invention relates to a technology for providing artificial intelligence model solutions for analyzing the tendencies of leaders based on agenda-specific natural language processing analysis. Background Technology

[0002] In recent years, as the MZ generation has become increasingly interested in governance, they have taken on the role of "push boats" and have become increasingly important.

[0003] The MZ generation exhibits a strong tendency towards "value-based consumption," purchasing products independently based on their own beliefs and values. This tendency is also reflected in governance, where they judge leaders and governance issues according to their own values ​​and interests. At this stage, party loyalty is lower, leading them to make independent judgments rather than unconditionally following political parties.

[0004] Therefore, there is a growing demand for a platform that can provide information to Generation Z, enabling them to understand the thoughts and values ​​of leaders and helping them to consume governance values ​​more conveniently and efficiently.

[0005] Existing technical documents

[0006] Patent documents

[0007] Patent Document 1: Korean Patent No. 10-2023-0049486

[0008] Patent Document 2: Korean Patent Registration No. 10-2173785

[0009] Patent Document 3: Korean Patent Registration No. 10-1739925

[0010] Patent Document 4: Korean Patent Registration No. 10-1741024 Summary of the Invention

[0011] The problem that the invention aims to solve

[0012] According to one embodiment, the aim is to provide a method, apparatus, and system for providing an artificial intelligence model solution for analyzing leadership tendencies based on natural language processing.

[0013] The purpose of this invention is not limited to the above-mentioned purposes, and other purposes not mentioned can be clearly understood from the following description.

[0014] Methods for solving problems

[0015] According to one embodiment, in a method providing an artificial intelligence model solution, the method performs a natural language processing-based analysis of a leader's tendency through an agenda, executed by a device, receiving a request from a user terminal to analyze the position of a first leader on a first agenda; collecting and acquiring data released in a first phase, which is crawled and pre-established, and categorized as being related to the first leader, as the first batch of data; extracting data from the first data described as being related to the first agenda, as data 1-1; generating a first question requiring the classification of the position of the first leader on the first agenda based on the data released in the first phase; inputting the first question into a first AI model, which has been trained to answer the leader's position by analyzing text; if the answer to the first question is generated as a first answer based on the data of the first AI model 1-1, then the step of obtaining the first answer from the first AI model is the output result; confirming that the position of the first leader on the first agenda is a first position, based on the first answer; and providing an artificial intelligence model solution for analyzing the tendency of a leader on each agenda based on natural language processing, including the step of analyzing the position of the first leader on the first agenda and the first position.

[0016] The steps for analyzing the position of the first leader on the first agenda item are: generating a second question that checks whether the first leader's position on the first agenda item is as valid as the result of the first position analysis; checking for errors in the output of the first AI model and inputting the second question into a trained second AI model to answer the question about the leader's position; in the second AI model, checking for errors in the output of the first AI model and answering the second question; if the answer generated is a valid answer, obtaining the second answer from the second AI model as the output; determining the first leader's position on the first agenda item based on the second answer; if the first and second positions are consistent, the first leader's position on the first agenda item is analyzed as the first position; if the first and second positions are inconsistent, the first leader's position on the first agenda item is analyzed as the second position; generating a first learning signal indicating a problem with the result of analyzing the first leader's position based on the first position data; and applying the first learning signal to the first AI model so that when analyzing the first leader's position based on the first AI data, it can be analyzed as the second position, thus training it to be the second position.

[0017] The method for providing an AI model solution for analyzing the tendencies of leaders on various agendas based on natural language processing analysis involves: firstly, analyzing the position of the first leader on the first agenda; then, collecting and acquiring data categorized as relevant to the first leader from data released in the second period (i.e., after the first period); extracting the data categorized as relevant to the first agenda from the second data into the second agenda; generating a third question requiring users to categorize the position of the first leader on the first agenda based on the data; inputting the third question into the first AI model; obtaining the third answer as the output of the first AI model if an answer to the third question is generated based on the data in the first AI model; determining the first leader's position on the first agenda based on the third answer; if the first and third positions are consistent, the first leader's position on the first agenda remains unchanged from the first period to the second period, and the first position remains unchanged, and analyzing the stage of changes in the first leader's position on the first agenda; if the first and third positions are inconsistent, the first leader's position on the first agenda changes from the first period to the third period, and the step of analyzing the changes in the first leader's position on the first agenda may be further included.

[0018] The method for providing an AI model solution for leader preference analysis based on natural language processing for each agenda is as follows: First, data related to the first agenda category is extracted from the first data set. Then, the number of data points contained in the first data set is confirmed as the number of data points in the first data set. If the number of data points in the first data set is found to be below a preset threshold, a stage is determined based on the data of the first agenda to be difficult to analyze the position of the first leader on the first agenda. Except for the first agenda, if by checking whether the position of the first leader on the agenda has been analyzed, it is confirmed that the position of the first leader on the second agenda is fourth, then the first attribute of the position on the second agenda is fourth. If the political party to which the first leader belongs is identified as the first political party, then the second attribute is set to the first political party to which the leader belongs. If the birthplace of the first leader is identified as the first region through their place of origin, then the third attribute is set to the place of origin as the first region. If the first leader's educational background confirms that they attended the first school, then the fourth attribute is set to the educational background of the first leader. The scenario includes the history of attending the first school; if it is confirmed that the first leader has always engaged in the first type of occupation throughout their career, a fifth attribute is set to include the occupation of the first type of occupation in their career; if it is confirmed through the activity history of the first leader that they have always been active in the first organization, a sixth attribute is set to include the activity history of the first organization in the activity history; the first agenda, first attribute, second attribute, third attribute, fourth attribute, fifth attribute, and sixth attribute are used to generate a first matching result; the first matching result is encoded to generate a first input signal; according to the agenda-specified position, the first input signal is input into a third-party AI model, which is trained to predict the leader's position on a specific agenda by analyzing party affiliation, place of origin, education level, work experience, and activity history; if the first input signal predicts the position of the first leader on the first agenda, it indicates that the first output signal of the first position is obtained from the third artificial intelligence model; based on the first output signal, the step of predicting and analyzing the position of the first leader on the first agenda with the first position may also be included.

[0019] Invention Effects

[0020] For example, by analyzing leaders' positions on the agenda and providing information that identifies their thoughts and values, the ease and efficiency of analyzing leaders' tendencies can be improved.

[0021] On the other hand, the effects of the embodiments are not limited to those described above, and other unmentioned effects can be clearly understood by those skilled in the art from the following description. Attached Figure Description

[0022] Figure 1 It is a diagram that outlines the system configuration based on the diaphragm.

[0023] Figure 2 It is a flowchart used to illustrate the behavior of analyzing a leader's position based on a single embodiment.

[0024] Figures 3 to 8 It is a diagram used to illustrate each stage of the actions taken to analyze the leadership's position based on a single embodiment.

[0025] Figure 9 It is a flowchart illustrating the process of analyzing a leader's stance based on an initial judgment using a first AI model, according to a single embodiment.

[0026] Figure 10 It is a flowchart illustrating the process of analyzing a leader's stance through secondary judgment based on a second artificial intelligence model, according to a single embodiment.

[0027] Figure 11 It is a flowchart used to illustrate the process of analyzing the changes in the position of a leader over time based on a single embodiment.

[0028] Figure 12 It is a flowchart illustrating the process of predicting and analyzing a leader's position based on their position on different agendas, according to a single embodiment.

[0029] Figures 13 to 16 It is a flowchart illustrating the process of predicting and analyzing a leader's stance by considering the leader's personal image based on examples.

[0030] Figure 17 This is a preliminary schematic diagram of a device configuration according to a single embodiment. Detailed Implementation

[0031] The embodiments are described in detail below with reference to the accompanying drawings. However, various modifications can be made to the embodiments, and therefore the scope of the patent application is not limited to or restricted by these embodiments. Any changes, equivalents, or substitutions to the embodiments should be understood to be included within the scope of the claims.

[0032] The specific structural or functional descriptions of the embodiments are provided for illustrative purposes only and may be modified and implemented in various forms. Therefore, the embodiments are not limited to a particular form of disclosure, and the scope of this specification includes changes, uniformities, or substitutions incorporated into the descriptive concepts.

[0033] Terms such as first or second can be used to describe various components, but the interpretation of these terms should only be used to distinguish one component from another. For example, the first component can be named the second component, and similarly, the second component can be named the first component.

[0034] When a component is said to be "connected" to another component, it should be understood that it may be directly connected to or connected to another component, but there may be another component between them.

[0035] The terminology used in the embodiments is for illustrative purposes only and should not be construed as restrictive. Singular expressions include plural expressions unless the context clearly implies otherwise. In this specification, the terms "comprising" or "having" should be understood to mean the presence of the functions, numbers, steps, actions, components, parts, or combinations thereof described herein, and should not exclude the presence or addition of one or more other functions or numbers, steps, actions, components, parts, or combinations thereof.

[0036] Unless otherwise defined, all terms used herein, including technical or scientific terms, shall have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments pertain. Terms such as those defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the relevant descriptive context and shall not be interpreted in an idealistic or overly formal sense unless expressly defined herein.

[0037] Furthermore, when describing the accompanying drawings, regardless of the drawing code, the same reference numerals should be assigned to the same elements, and identical repetitive descriptions should be omitted. When describing embodiments, detailed descriptions should be omitted if it is determined that a specific description of the relevant technical notifications may unnecessarily obscure the essential points of the embodiment.

[0038] The embodiments can be implemented in various types of products, including personal computers, laptops, tablets, smartphones, televisions, smart home appliances, smart cars, kiosks, and wearable devices.

[0039] In this embodiment, the artificial intelligence (AI) system is a computer system that achieves human-level intelligence. Unlike existing rule-based intelligent systems, it is a system in which machines learn and make judgments independently. As AI systems improve their recognition rates and more accurately understand sellers' preferences, existing rule-based intelligent systems are gradually being replaced by deep learning-based AI systems.

[0040] Artificial intelligence technology consists of machine learning and element technologies that use machine learning. Machine learning is an algorithmic technique that classifies / learns the features of input data on its own. Element technologies are techniques that use machine learning algorithms such as deep learning to simulate the cognitive and judgmental functions of the human brain, and consist of technical fields such as language understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control.

[0041] The various fields where artificial intelligence technology is applied are as follows: Language understanding is a technology for recognizing, adapting to, and processing human language / text, including natural language processing, machine translation, dialogue systems, question answering, and speech recognition / synthesis. Visual understanding is a technology for recognizing and processing objects like human vision, including object recognition, object tracking, image search, human recognition, scene understanding, spatial understanding, and image improvement. Reasoning and prediction is a technology for making logical inferences and predictions by judging information, including knowledge / probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge representation is a technology for automatically processing human experience information into knowledge data, including knowledge construction (data generation / classification) and knowledge management (data utilization). Motion control is a technology for controlling the autonomous driving of vehicles and the movement of robots, including motion control (navigation, collision, driving) and operational control (behavior control).

[0042] Generally, to apply machine learning algorithms to real-world applications, training is conducted through trial and error due to the nature of basic machine learning methods. Deep learning, in particular, requires hundreds of thousands of iterations. Since this is impossible to achieve in a real physical environment, the actual physical environment is virtualized on a computer, and learning is conducted through simulation.

[0043] Figure 1 It is a diagram that outlines the system configuration based on the diaphragm.

[0044] Reference Figure 1 According to one embodiment, the system may include a user terminal 100 and a device 200, which can communicate with each other through a communication network.

Claims

1. An artificial intelligence model solution that provides an artificial intelligence model solution to analyze the tendencies of a leader based on natural language processing analysis of a specific agenda performed by the device, wherein, include: Receive requests from user terminals to analyze the position of the top leader on the first agenda; Collect and acquire data released in the first phase, which is crawled from a pre-established database and categorized as being related to the first leader, as the first batch of data; Extract data from the first data described as being related to the first agenda, as data 1-1; The first question is generated, requiring the classification of the position of the first leader on the first agenda based on the data released in the first phase; The first question is input into the first AI model, which has been trained to answer the leader's position by analyzing the text; If the answer to the first question is generated based on the data of the first artificial intelligence model 1-1, then the step of obtaining the first answer from the first artificial intelligence model is the output result; Confirming the position of the leading figure on the first agenda is the first position, based on the first answer; and The steps to analyze the position of the first leader on the first agenda item.

Images