KR-20260064937-A - APPARATUS AND METHOD FOR PROVIDING REAL-TIME SPORTS COMMENTARY BASED ON ARTIFICIAL INTELLIGENCE

KR20260064937AKR 20260064937 AKR20260064937 AKR 20260064937AKR-20260064937-A

Abstract

The present invention relates to an AI-based real-time commentary device and method for sports matches, and more specifically, to an AI-based real-time commentary device and method for selecting key agents and predicting actions in sports matches. According to an embodiment of the present invention, the AI-based real-time commentary device and method for sports matches can ensure real-time capabilities in sports match commentary. Furthermore, commentary that performs predictions based on human learning methods can explain the decision-making process to humans through game commentary, including sports matches. Additionally, the present invention can enhance the reliability of commentary by providing commentary based on the results learned by the AI regarding predictions and actions when an agent uses a specific strategy.

Inventors

조경은
김준오

Assignees

동국대학교 산학협력단

Dates

Publication Date: 20260508
Application Date: 20241030

Claims (11)

In an AI-based real-time sports commentary device, A data generation unit that generates sports game data in real time; An object tracking unit that performs multi-object tracking based on the generated data above; A behavior prediction unit that predicts the future behavior of the tracked multiple objects; and Includes an explanation generation unit that generates explanations through a large-scale language model based on the above-mentioned predicted behavior. AI-based real-time sports commentary device.
In paragraph 1, The above data generation unit Generates noise-free simulator-based total observation data and generates technical data for interactions between objects. AI-based real-time sports commentary device.
In paragraph 1, The above object extraction unit Extracting camera view observation data based on a scene viewing the entire stadium and merging it with simulation-based observation data AI-based real-time sports commentary device.
In paragraph 1, The above behavior prediction unit Based on a multi-agent reinforcement learning algorithm, it analyzes the state and environment of each agent and predicts the behavior of each agent based on the interactions between them. AI-based real-time sports commentary device.
In paragraph 1, The above explanation generation unit Generate prompts by applying the above-mentioned large-scale language model, and generate commentary based on the prompts that considers the teams and characteristics of the sports match. AI-based real-time sports commentary device.
Regarding real-time commentary methods for AI-based sports matches, Step of generating sports match data in real time; A step of performing multi-object tracking based on the collected data above; A step of predicting the future behavior of the tracked multiple objects; and A step comprising generating an explanation through a large-scale language model based on the above-mentioned predicted behavior AI-based real-time commentary method for sports matches.
In paragraph 6, The step of generating sports game data in real time mentioned above Generates noise-free simulator-based total observation data and generates technical data for interactions between objects. AI-based real-time commentary method for sports matches.
In paragraph 6, The step of performing multi-object tracking based on the collected data above Extracting camera view observation data based on a scene viewing the entire stadium and merging it with simulation-based observation data AI-based real-time commentary method for sports matches.
In paragraph 6, The step of predicting the future behavior of the aforementioned tracked multiple objects is Based on a multi-agent reinforcement learning algorithm, it analyzes the state and environment of each agent and predicts the behavior of each agent based on the interactions between them. AI-based real-time commentary method for sports matches.
In paragraph 6, The step of generating commentary through a large-scale language model based on the above-mentioned predicted behavior is Generate prompts by applying the above-mentioned large-scale language model, and generate commentary based on the prompts that considers the teams and characteristics of the sports match. AI-based real-time commentary method for sports matches.
A computer program recorded on a computer-readable recording medium that executes a real-time commentary method for an artificial intelligence-based sports game according to any one of paragraphs 6 through 10.

Description

Apparatus and Method for Providing Real-Time Sports Commentary Based on Artificial Intelligence The present invention relates to a device and method for real-time commentary on sports matches, and more specifically, to a device and method for providing real-time commentary based on artificial intelligence by selecting key agents and predicting their actions in sports matches. Traditionally, sports matches have been broadcast with human commentators analyzing and explaining the game situation in real time. However, real-time commentary presents challenges, such as the fact that the level of information provided can vary depending on the commentator's competence, and that it is difficult to accurately convey all critical information in rapidly changing game situations. In particular, real-time sports commentary must consider various variables occurring during the match in real time, and it is crucial to provide accurate and timely commentary to viewers regardless of the pace of the game. Existing research has primarily focused on developing language models that learn from human commentator data, but it faces difficulties in actively reflecting the various factors occurring during actual matches. The background technology of the present invention is disclosed in Korean Published Patent No. 10-2001-0005694. FIG. 1 is a diagram illustrating the configuration of an artificial intelligence-based real-time sports game commentary device according to an embodiment of the present invention. FIGS. 2 to 6 are drawings for illustrating a real-time commentary model for an artificial intelligence-based sports match according to an embodiment of the present invention. FIG. 7 is a flowchart of an artificial intelligence-based real-time sports game commentary device according to one embodiment of the present invention. The present invention is susceptible to various modifications and may have various embodiments; therefore, specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. In describing the present invention, detailed descriptions of related prior art are omitted if it is determined that such detailed descriptions would unnecessarily obscure the essence of the invention. Furthermore, singular expressions used in this specification and claims should generally be interpreted to mean "one or more" unless otherwise stated. Throughout the specification, when it is stated that a part is "connected (connected, in contact, combined)" with another part, this includes not only cases where they are "directly connected," but also cases where they are "indirectly connected" with other members interposed between them. Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but rather allows for the inclusion of additional components. The terms used herein are merely for describing specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as “comprising” or “having” are intended to indicate the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. The present invention will be described below with reference to the attached drawings. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification have been given similar reference numerals. FIG. 1 is a diagram illustrating the configuration of a real-time commentary device for an artificial intelligence-based sports match according to one embodiment of the present invention. Referring to FIG. 1, the real-time commentary device (100) for an artificial intelligence-based sports match includes a data generation unit (110), an object tracking unit (130), a behavior prediction unit (150), and a commentary generation unit (170). The data generation unit (110) generates data for a sports game in real time. Specifically, the data generation unit (110) generates noise-free simulator-based Full Observation (MDP) data and generates technical data for interactions between objects. Additionally, the data generation unit (110) can generate broadcast video data of the stadium using a fixed camera. At this time,