KR-102964978-B1 - METHODS, DEVICES, AND SYSTEMS FOR PREDICTING PLAYER GROWTH POTENTIAL AND USING THIS TO MATCH AND MANAGE SPONSOR BRANDS

Abstract

One embodiment of the present invention relates to a method, apparatus, and system for predicting a player's growth potential and matching and managing sponsor brands using the same, which fuses wearable device data, game history, and player profile to predict growth potential and utilizes the results to match the optimal sponsor brand with the player.

Inventors

• 양현민

Dates

Publication Date

20260513

Application Date

20250908

Claims (3)

1. A method for predicting a player's growth potential and matching and managing sponsor brands using the same, wherein the device includes a processor, memory, a communication module, and a non-transient storage medium, and the processor executes a program stored in the non-transient storage medium. Step to collect player information; Step of collecting brand information; A step of analyzing collected player information to predict the growth potential of each player; and The method includes a step of matching a suitable brand to each player based on the above player information, growth potential and brand information for each player, and The step of collecting the above player information is: A step of receiving the first player's recent match history data; A step of receiving athlete data including the gender, sport, height, and weight of the first athlete; A step of receiving multidimensional biometric data synchronized in parallel, including heart rate, blood oxygen, electrocardiogram (ECG), body composition analysis, and skin temperature, from a wearable device worn by the first athlete; A step of dividing the above multidimensional biometric data into time units to generate biometric data for each time interval; A step of performing Z-score normalization and Min-Max scaling on the above time interval bio-data in parallel to calculate a 1-1 vector corresponding to heart rate and blood oxygen data, a 1-2 vector corresponding to electrocardiogram (ECG) and skin temperature data, and a 1-3 vector corresponding to body composition analysis data; A step of independently calculating cosine similarity, Pearson correlation coefficient, and Spearman rank correlation coefficient, respectively, and calculating a correlation indicator which is the weighted average of the cosine similarity, Pearson correlation coefficient, and Spearman rank correlation coefficient, in order to calculate the correlation between the above-mentioned vectors 1-1, 1-2, and 1-3; A step of extracting a first residual signal by removing the high-frequency band and the low-frequency band, respectively, after performing a Fourier Transform on the bio-data for each time interval as described above; A step of generating a second residual signal by performing an inverse Fourier transform on the first residual signal; A step of calculating an extended feature set including RMS (Root Mean Square), median, geometric mean, skewness, and kurtosis from the second residual signal; A step of generating a first state vector by combining the above correlation indicator and extended feature quantity; A step of reading a first state matrix from a database in which second state vectors corresponding to 'second players who are players other than the first player' are accumulated and recorded; A step of generating a second state matrix by adding the first state vector to the first state matrix; A step of classifying the above second state matrix into multiple first clusters by K-means clustering; A step of designating the first cluster containing the first state vector among the above first clusters as the second cluster; A step of analyzing the mean, variance, and similarity indicators of the rows included in the second cluster to calculate a basic physical strength growth rate, which is a value representing the relative position of the first state vector with respect to the center of the second cluster; A step of generating a second state vector by adding a basic physical strength growth rate to the first state vector; and The method includes the step of recording recent match history data and a second state vector corresponding to the first player in a database. Prediction of Athlete Growth Potential and Sponsor Brand Matching and Management Methods Using This
2. delete
3. delete

Description

Methods, devices, and systems for predicting player growth potential and using this to match and manage sponsor brands The following embodiments relate to a method, apparatus, and system for predicting a player's growth potential and matching and managing sponsor brands using the same, which fuses wearable device data, game history, and player profile to predict growth potential and utilizes the results to match the optimal sponsor brand with the player. Sports sponsorship matching has traditionally relied on limited information such as scouting reports, qualitative evaluations by coaches and agents, and past performance. This method has problems such as poor reproducibility due to scattered data sources, failure to systematically reflect physical and physiological data such as wearable sensors, and difficulty in quantitatively estimating the future growth trends of athletes, resulting in low alignment with the brand's mid-to-long-term marketing strategy. Furthermore, while the actual matching process must simultaneously consider constraints such as budget, schedule, category suitability, and brand preference, the existing simple score aggregation method makes it difficult to resolve conflicts among multiple parties and to guarantee consistent matching results under identical conditions. Recently, wearable devices have been providing multidimensional biometric data such as heart rate, blood oxygen, ECG, body composition, and skin temperature with low latency, but it is difficult to convert them into stable growth indicators in practice due to scale differences, noise, and time synchronization issues between heterogeneous signals. Meanwhile, although match history is significantly influenced by contextual factors such as league level, relative strength, and schedule density, there is no established procedure to normalize and weight these factors to summarize them into dynamic characteristics such as growth rate and acceleration. FIG. 1 is a schematic diagram showing a system for predicting a player's growth potential and matching and managing sponsor brands using the same, according to an embodiment of the present invention. FIG. 2 is a flowchart illustrating a method for predicting a player's growth potential and matching and managing sponsor brands using the same, according to an embodiment of the present invention. FIG. 3 is a flowchart illustrating the step of collecting player information for a method of predicting a player's growth potential and matching and managing sponsor brands using the same according to an embodiment of the present invention. FIG. 4 is a flowchart illustrating the steps for predicting the growth potential of each player according to an embodiment of the present invention, including the prediction of a player's growth potential and the sponsor brand matching and management method using the same. Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights. Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept. Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component. When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between. The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. 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 existence 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. In particular, where a 'step' in this specification is described as 'comprising' one or more detailed steps or sub-steps, said 'step' may be interpreted as including its own basic processing step while simultan