Method and apparatus for recommending golf course on basis of score prediction

Abstract

A method and an apparatus for recommending a golf course on the basis of score prediction are presented. The method for recommending a golf course on the basis of score prediction comprises the steps of: predicting an expected score of a user for a target golf course; using the expected score of the user through an artificial intelligence-based score prediction model so as to analyze the suitability of the target golf course in a user-customized manner; and recommending a golf course to the user on the basis of the suitability of the target golf course.

Description

Score Prediction-Based Golf Course Recommendation Method and Device

[0001] The embodiments disclosed in this specification relate to a method and apparatus for recommending golf courses, and more specifically, to a method and apparatus for predicting a user's expected score for a golf course and each hole based on artificial intelligence technology, and recommending a golf course suitable for the user's golf skill level using the user's expected score.

[0002] As living standards improve, golf, once considered a luxury sport, is becoming increasingly popular. Consequently, the number of people wanting to learn golf is increasing, and the demand for participation in golf tournaments is also rising.

[0003] A golf game is played at a golf course (including ancillary facilities) equipped with a golf course. Golf games can take place in an offline space with actual fields or in an online virtual space implemented through virtual simulation. When playing on an actual field, golf services can be accessed by becoming a member of a golf club equipped with a golf course or a country club equipped with other leisure facilities.

[0004] Golf courses operating both domestically and internationally can be designed in various forms depending on the facility. Since the cost and playing time involved in a golf game are significant, it is very important to select a course that suits your needs from among those with diverse characteristics.

[0005] Users who have no prior experience with golf courses or have limited experience often find it difficult to select a suitable course because they are unaware of their own skill level. They typically choose a course based on recommendations from acquaintances, but once they actually play, they realize the course does not suit them as well as they expected. This is because recommendations from acquaintances are based on subjective judgment and merely consider the average skill level of other users who have played at that particular course.

[0006] In particular, if you also consider the golf skills of your playing partners, it is not easy to select the optimal golf course suitable for the players involved.

[0007] Regarding golf course recommendations, Patent Document 1 describes an invention concerning a method and system for providing golf course and caddy platform services using artificial intelligence and big data. Patent Document 1 discloses only the content of recommending golf course courses based on scores directly entered by customers, and, like existing golf course recommendation technologies, Patent Document 1 does not present a means for accurately analyzing the suitability of a specific golf course for the parties involved in the golf game.

[0008] Meanwhile, the aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as prior art disclosed to the general public prior to the filing of the present invention.

[0009] (Patent Document 1) Korean Registered Patent No. 10-2516035 (March 30, 2023)

[0010] The embodiments disclosed in this specification aim to present a score prediction-based golf course recommendation method and apparatus that predict a user's expected score for a target golf course through an artificial intelligence-based score prediction model, analyze the suitability of the target golf course in a user-customized manner using the user's expected score, and recommend a golf course suitable for the user based on the suitability of the target golf course.

[0011] Other objects and advantages of the present invention may be understood from the following description and will be more clearly understood by one embodiment. Furthermore, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0012] As a technical means for achieving the aforementioned technical task, a score prediction-based golf course recommendation method performed by a score prediction-based golf course recommendation device comprises: a step of predicting a user's expected score for a target golf course; a step of analyzing the suitability of the target golf course in a user-customized manner using the user's expected score through an artificial intelligence-based score prediction model; and a step of recommending a golf course to the user based on the suitability of the target golf course.

[0013] According to another embodiment, a score prediction-based golf course recommendation device for performing a score prediction-based golf course recommendation method comprises a memory for storing an artificial intelligence-based score prediction model, at least one processor, a control unit for predicting a user's expected score for a target golf course through the artificial intelligence-based score prediction model, analyzing the suitability of the target golf course using the user's expected score, and selecting a golf course to recommend to the user based on the suitability of the target golf course, and an input / output unit for providing a user interface that outputs the expected score and the selected golf course.

[0014] Another embodiment is a computer-readable recording medium on which a program for performing the score prediction-based golf course recommendation method is recorded.

[0015] Another embodiment is performed by the score prediction-based golf course recommendation device and is a computer program stored on a medium to perform the score prediction-based golf course recommendation method.

[0016] According to any one of the aforementioned means for solving the problem, a score prediction-based golf course recommendation method and device can be presented that predicts a user's expected score for a target golf course through an artificial intelligence-based score prediction model, analyzes the suitability of the target golf course in a user-customized manner using the user's expected score, and recommends a golf course suitable for the user based on the suitability of the target golf course.

[0017] In addition, according to any one of the aforementioned means for solving the problem, a score prediction-based golf course recommendation method and device can be presented that can calculate the probability of a user's expected score for a golf course where the user has not played a golf game, through an artificial intelligence-based score prediction model based on the user's user information and the golf course information of the target golf course.

[0018] In addition, according to any one of the aforementioned means for solving the problem, a score prediction-based golf course recommendation method and device can be presented that predicts an expected score for each user of a user group based on user information of a user group including other users and golf course information of a target golf course, and analyzes the suitability of a target golf course based on the difference in expected scores for each user of the user group to output the golf course with the smallest difference in expected scores.

[0019] The effects obtainable from the disclosed embodiments are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the disclosed embodiments belong from the description below.

[0020] The attached drawings illustrative of preferred embodiments disclosed in this specification serve to further enhance understanding of the technical concept disclosed in this specification, along with specific details for implementing the invention; therefore, the contents disclosed in this specification should not be interpreted as being limited only to the matters described in such drawings.

[0021] FIG. 1 is a block diagram illustrating a score prediction-based golf course recommendation device according to one embodiment.

[0022] FIGS. 2 and FIGS. 3 are conceptual diagrams illustrating the operation of a score prediction-based golf course recommendation device according to one embodiment.

[0023] FIGS. 4 and 5 are diagrams illustrating user ability data processed by a score prediction-based golf course recommendation device according to one embodiment.

[0024] FIG. 6 is a diagram illustrating hole data processed by a score prediction-based golf course recommendation device according to one embodiment.

[0025] FIGS. 7 and FIGS. 8 are drawings illustrating an expected score processed by a score prediction-based golf course recommendation device according to one embodiment.

[0026] FIGS. 9 and 10 are drawings illustrating a screen showing a golf course output by a score prediction-based golf course recommendation device according to one embodiment.

[0027] FIG. 11 is a flowchart illustrating a score prediction-based golf course recommendation method according to one embodiment.

[0028] Various embodiments are described in detail below with reference to the attached drawings. The embodiments described below may be implemented in various different forms. In order to explain the features of the embodiments more clearly, detailed descriptions of matters widely known to those skilled in the art to which the following embodiments belong have been omitted. Additionally, parts of the drawings unrelated to the description of the embodiments have been omitted, and similar parts throughout the specification have been given similar reference numerals.

[0029] Throughout the specification, when a configuration is described as being "connected" to another configuration, this includes not only cases where they are "directly connected," but also cases where they are "connected with another configuration in between." Furthermore, when a configuration is described as "including" another configuration, this means that, unless specifically stated otherwise, it does not exclude other configurations but may include additional configurations.

[0030] First, the terms used in this specification will be explained.

[0031] A golf course is a golf course designed to put the ball into the hole cup with the fewest strokes. A golf course is usually designed with 18 holes, and playing 18 holes is called one round, and the game is sometimes played in several rounds.

[0032] A stroke is the act of striking a ball with a club. The number of strokes made from the tee shot to putting, until the ball is placed into the hole, is accumulated and processed as a score. The user with the lowest score on each hole or the entire course wins the golf match. The standard number of strokes designated for a specific hole is Par, and there are achievements such as Birdie (one stroke less than Par), Eagle (two strokes less than Par), Bogey (one stroke more than Par), Double Bogey (two strokes more than Par), and Hole-in-One (putting the ball into the hole in one shot with a tee shot).

[0033] A golf course area refers to the geographical regions that constitute a golf course, and includes the teeing ground, fairway, green, rough, bunker, and hazard. The teeing ground is the area where play begins at the hole and where the tee shot is hit; it is also called the tee box. The fairway is a wide grassy area where the second shot is taken. The green is the area where the hole cup is located and where putting takes place. The rough is an area covered with dense grass, a bunker is an obstruction area filled with sand, and a hazard is an obstruction area in the form of a lake.

[0034] Golf course recommendation technology can recommend specific golf courses to users based on various criteria, such as random selection or advertising sponsorship. Golf course recommendation technology can recommend offline golf courses equipped with actual fields or golf courses in an online virtual space implemented through virtual golf simulations (e.g., screen golf).

[0035] The primary recommendation method applied to existing golf course recommendation technologies statistically suggests courses based on the golf ratings of users with similar skill levels, rather than the user's own ability. The golf rating used for recommendations refers to the average level within a user group that includes the user and other users. In other words, the golf rating simply represents the average score. Since the diverse types of golf courses are not taken into account when calculating the rating, courses recommended by this conventional method may include those that are unsuitable for the user's actual skill level.

[0036] When users of the same skill level play on the same golf course, variations exist among them because the types of holes they are familiar with or confident in differ; consequently, their actual scores may be higher or lower than their actual skill level. In other words, since every golf course has a different layout, every hole exhibits different characteristics, and each user has different courses where they perform well, judging an individual's suitability for a course based solely on statistical skill level figures is problematic in terms of accuracy.

[0037] Furthermore, when playing partners are present, a golf course of appropriate difficulty should be recommended to the participants by considering the skill difference between them; however, existing golf course recommendation methods do not assess the suitability of a course for each individual, which creates a problem in that they cannot recommend a course that takes into account the skill differences of the participants.

[0038] To solve this problem, the score prediction-based golf course recommendation device according to the present embodiment predicts the user's expected score for a target golf course through an artificial intelligence-based score prediction model, analyzes the suitability of the target golf course in a user-customized manner using the user's expected score, and recommends a golf course suitable for the user based on the suitability of the target golf course.

[0039] Two major problems can be solved through the score prediction-based golf course recommendation device according to the present embodiment.

[0040] First, because golf courses are recommended based on an individual's round skill data, users can identify which courses are easy, average, or difficult for them based on the predicted scores inferred by the AI ​​model. In particular, the AI ​​model can predict the expected score even for courses the user has never played before, based on their ability level.

[0041] Second, the AI ​​model calculates the skill difference between companions and can persuasively recommend, based on data, a golf course suitable for everyone that minimizes the standard deviation of scores among them.

[0042] The embodiments will be described in detail below with reference to the attached drawings.

[0043] FIG. 1 is a block diagram illustrating a score prediction-based golf course recommendation device according to one embodiment.

[0044] A score prediction-based golf course recommendation device (100) can perform the operation of predicting a user's expected score for a target golf course, the operation of analyzing the suitability of the target golf course in a user-customized manner using the user's expected score, and the operation of recommending a golf course suitable for the user based on the suitability of the target golf course.

[0045] The score prediction-based golf course recommendation device (100) can interact with a user account through a user terminal and can enable the golf user to receive golf services by communicating with an administrator server or golf simulation device that operates the golf course. The score prediction-based golf course recommendation device (100) may also be implemented within an administrator server or golf simulation device.

[0046] According to one embodiment, the score prediction-based golf course recommendation device (100) may be implemented in the form of a device, and according to another embodiment, it may also be implemented as a server-client system. In this case, the device may be implemented as a computer, portable terminal, television, wearable device, etc., which can connect to a remote server via a network or to other devices and servers. Here, the computer includes, for example, a notebook, desktop, or laptop equipped with a web browser, and the portable terminal may include, for example, any type of handheld-based wireless communication device that ensures portability and mobility, such as PCS (Personal Communication System), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), GSM (Global System for Mobile communications), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet), smartphone, and Mobile WiMAX (Mobile Worldwide Interoperability for Microwave Access). Additionally, the television may include IPTV (Internet Protocol Television), Internet TV, terrestrial TV, cable TV, etc.Furthermore, wearable devices are types of information processing devices that can be worn directly on the human body, such as watches, glasses, accessories, clothing, and shoes, and can connect to a server at a remote location or to another terminal via a network, either directly or through another information processing device.

[0047] The score prediction-based golf course recommendation device (100) may be implemented as a computer capable of communicating via a network with a user terminal having an application or web browser installed for interaction with the user, or it may be implemented as a cloud computing server. The score prediction-based golf course recommendation device (100) may include a storage device capable of storing data, or it may store data through a database (200).

[0048] Referring to FIG. 1, a score prediction-based golf course recommendation device (100) according to one embodiment may include an input / output unit (110), a control unit (120), a communication unit (130), and a memory (140).

[0049] The input / output unit (110) may include an input unit for receiving input from a user and an output unit for displaying information such as the result of performing a task or the status of a score prediction-based golf course recommendation device (100). For example, the input / output unit (110) may include an operation panel for receiving user input and a display panel for displaying a screen. According to an embodiment, the input / output unit (110) may receive data and output the result of processing it.

[0050] Specifically, the input unit may include devices capable of receiving various forms of user input, such as a keyboard, physical buttons, a touch screen, a camera, or a microphone. Additionally, the output unit may include a display panel or a speaker. However, the input / output unit (110) is not limited thereto and may include a configuration that supports various inputs and outputs.

[0051] According to the embodiment, a camera constituting the input / output unit (110) can acquire an image by photographing a golfer or a golf course, etc. And as the image is analyzed by the control unit (120), the input / output unit (110) can output the generated information through a display panel, etc.

[0052] The control unit (120) controls the overall operation of the score prediction-based golf course recommendation device (100) and may include a processor such as a CPU, GPU, etc. The control unit (120) may control other components included in the score prediction-based golf course recommendation device (100) to perform the score prediction-based golf course recommendation method.

[0053] For example, the control unit (120) may execute a program stored in memory (140), read a file stored in memory (140), or store a new file in memory (140). Additionally, for example, the control unit (120) may include at least one processor and may analyze an image or image frame (a still image included in a video) received through the input / output unit (110) by executing a program for performing a score prediction-based golf course recommendation method.

[0054] The communication unit (130) can perform wired or wireless communication with another device or network. To this end, the communication unit (130) may include a communication module that supports at least one of various wired or wireless communication methods. For example, the communication module may be implemented in the form of a chipset.

[0055] The communication unit (130) can receive data from other devices, such as an external database or a golf simulation device, and transmit it to the memory (140) and the control unit (120).

[0056] The wireless communication supported by the communication unit (130) may be, for example, generational mobile communication, Wi-Fi (Wireless Fidelity), Wi-Fi Direct, Bluetooth, Ultra Wide Band (UWB), or Near Field Communication (NFC). Additionally, the wired communication supported by the communication unit (130) may be, for example, USB or HDMI (High Definition Multimedia Interface).

[0057] Various types of data, such as files, applications, and programs, can be installed and stored in the memory (140). The control unit (120) may access and use the data stored in the memory (140) or store new data in the memory (140). Additionally, the control unit (120) may execute a program installed in the memory (140). Referring to FIG. 1, a program for performing a score prediction-based golf course recommendation method may be installed in the memory (140).

[0058] According to one embodiment, the memory (140) can store an artificial intelligence-based score prediction model. The memory (140) can store information about a golf course and information about a hole. The memory (140) can store information about a user (e.g., information about user ability).

[0059] According to one embodiment, the control unit (120) can predict the user's expected score for a target golf course through an artificial intelligence-based score prediction model, analyze the suitability of the target golf course using the user's expected score, and select a golf course suitable for the user based on the suitability of the target golf course.

[0060] The input / output unit (110) can provide a user interface that outputs an expected score and a selected golf course.

[0061] In the process of predicting the user's expected score, the control unit (120) can calculate the probability of the user's expected score through an artificial intelligence-based score prediction model based on the user's user information and the golf course information of the target golf course. The user information may include information expressing the user's golf ability in numerical terms. For example, the user information may include golf ability data or data processed from it. The target golf course may include golf courses where the user has not played a golf game. The score prediction model may refer to previous round records for golf courses where a golf game has been played. That is, it may refer to past play records.

[0062] In the process of predicting the user's expected score, the control unit (120) can calculate the user's expected score (including probability) using a score prediction model for golf courses where the user has not played golf. The control unit (120) can calculate the user's expected score for the entire golf course and provide the probability as a reference value. Alternatively, the control unit (120) can calculate the user's expected score for each hole constituting the entire golf course and calculate the user's expected score for the entire golf course based on the user's expected score for each hole.

[0063] The control unit (120) can calculate a set of predicted scores with multiple probabilities for each hole during the process of predicting the user's predicted score. The input / output unit (110) can sort and output the set of predicted scores with multiple probabilities during the process of outputting the predicted score.

[0064] The control unit (120) can calculate a suitability score during the process of analyzing the suitability of the target golf course. Here, the suitability score may include information that numerically expresses whether the target golf course is suitable for the user and the degree thereof.

[0065] The control unit (120) can calculate the individual difficulty of the target golf course for the user based on the user's expected score and the user's reference score (e.g., the user's average score, etc.) during the process of analyzing the suitability of the target golf course. Here, the reference score may include a score set by statistically calculating the results of the user playing golf for a predetermined period.

[0066] The control unit (120) may calculate a user's standard score based on the user's average score, the user's handicap score, or a combination thereof, during the process of analyzing the suitability of the target golf course. Here, the average score is a score statistically calculated based on the user's past play records for a golf course or hole. The handicap score may refer to a score representing the difference between the standard number of strokes set for each golf course or hole and the user's average score. The average score and handicap score may be received from user input or from a golf simulation device, a database, etc.

[0067] The control unit (120) can calculate the difficulty of the target golf course for the user based on the difference between the user's expected score and the user's reference score, and analyze the suitability of the target golf course using the difficulty of the target golf course.

[0068] In the process of analyzing the suitability of a target golf course, the control unit (120) can calculate the preference for the target golf course for the user based on the user's preferred course type, the user's past play records, or a combination thereof, and calculate a suitability score for the target golf course using the expected score and the preference for the target golf course. The control unit (120) can calculate the preference for the target golf course for the user based on the user's preferred course type, the user's past play records, the user's review information, or a combination thereof. The user's preferred course type, the user's past play records, and the user's review information may be received as user input or from a golf simulation device, a database, etc. The preferred course type may be set according to user selection, and the type of course played may be utilized as the preferred course type when past play records are accumulated.

[0069] In the process of analyzing the suitability of a target golf course, the control unit (120) can calculate the difficulty of the target golf course for the user based on the difference between the user's expected score and the user's reference score, calculate the preference of the target golf course for the user, and calculate the suitability score of the target golf course by applying weights to the difficulty of the target golf course and the preference of the target golf course and summing them up.

[0070] In the process of predicting the user's expected score, the control unit (120) can predict the expected score for each user in the user group based on user information of the user group including other users and golf course information of the target golf course.

[0071] The control unit (120) can analyze the suitability of the target golf course based on the difference in expected scores for each user in the user group during the process of analyzing the suitability of the target golf course.

[0072] The input / output unit (110) can output the golf course with the smallest difference in expected scores for each user in the user group during the process of recommending a golf course suitable for the user.

[0073] FIGS. 2 and FIGS. 3 are conceptual diagrams illustrating the operation of a score prediction-based golf course recommendation device according to one embodiment.

[0074] Referring to Fig. 2, a score prediction-based golf course recommendation device can recommend golf courses through an artificial intelligence model based on the golf ability of an individual and a companion.

[0075] For example, based on an individual's last 5 rounds, ability scores and average scores are obtained, and vectorized information of each hole of the golf course is used to predict the expected score for the corresponding hole and golf course. Based on the calculated score, easy, normal, and difficult golf courses can be classified and recommended in a personalized manner through a golf course recommendation model (500).

[0076] Referring to FIG. 3, when there are companions, the score prediction model (400) calculates the expected score of each companion, and the golf course recommendation model (500) can recommend the golf course where the score difference between them is the smallest (small standard deviation).

[0077] A score prediction-based golf course recommendation device can vectorize user ability data obtainable from golf simulations based on recent multiple rounds (e.g., driver distance, accuracy, green hit rate, short game, average number of putts, ball speed, ball flight, solid hit rate, proximity to hole, left-right deviation, front-back deviation, fairway landing rate, etc.). Additionally, the current average score can be used as reference data to quantify an individual's ability level. This reference data can be included in and updated within the ability data. The reason for vectorizing the data is that the maximum and minimum ranges of each item differ, and it allows for the rapid inference of accurate figures when used in an artificial intelligence model.

[0078] A score prediction-based golf course recommendation device vectorizes each hole based on hole data acquired from each golf course and elements used in map creation. In this process, the area and ratio of greens, bunkers, and hazards, as well as data on course length and doglegs, are directly extracted and calculated from map information using image processing. These can then be combined with raw map data existing in a database to create vectorized data. The reason for vectorizing the data is that the maximum and minimum ranges of each item differ, and it is necessary to quickly infer accurate figures when used in an artificial intelligence model.

[0079] Score prediction-based golf course recommendation devices use an artificial intelligence model to predict the expected score for a given hole by utilizing user information (such as individual golf ability data) and hole information from each golf course. This prediction is highly reliable because the AI ​​model has already learned patterns regarding the expected scores that will be calculated when inferring specific holes based on various individual ability levels.

[0080] Based on the predicted scores for each hole, one can check their predicted score (skill) for each hole, and by integrating the holes present in each golf course, the predicted final score for that golf course can be calculated. For example, the predicted final score for that golf course can be calculated by summing the predicted scores for each hole. In this case, even if the predicted scores for each hole are the same for each user, the probability value of the final score may differ for each user and the final score may differ depending on the distribution of the probability values ​​for each hole. This will be described later with reference to Fig. 8.

[0081] A score prediction-based golf course recommendation system requires criteria to distinguish whether a course is easy, average, or difficult for the current user once the predicted score for each course is generated. In other words, a suitability assessment is necessary. The criterion used for this purpose may be the user's current average score. The average score is calculated based on actual round results and individual golf ability scores generated from the results of multiple rounds. Based on the average score, courses can be classified as easy if the predicted score is lower, suitable if the difference is small or identical, and difficult if the predicted score is higher; recommendations can then be made according to the user's skill level. Recommendations based on hole-by-hole difficulty are also possible. If a user desires a course experience different from the types of courses they frequently play, recommendations considering difficulty based on individual golf ability are available. Even if a user is recommended an unfamiliar or unique course, they can proceed with the game while taking the increased difficulty into account because they know the predicted score.

[0082] A score prediction-based golf course recommendation device can calculate an estimated score for each golf course for each companion when there are multiple players. By comparing the estimated scores of the companions and the user, it is possible to recommend golf courses suitable for everyone with the least deviation, as well as courses that are difficult or easy for everyone. Through this, during a round, it is possible to provide guidance on the difficulty level of a particular golf course or hole for each user, as well as who benefits from or is disadvantaged by the course or hole, and to provide services based on the estimated score figures regarding how much a handicap should be applied.

[0083] A score prediction-based golf course recommendation device can logically recommend golf courses of appropriate difficulty according to the user's golf ability. While existing golf course recommendations determine the difficulty of a golf course / hole based on statistics derived from the results of users of a specific grade playing for several months, this embodiment enables accurate recommendations based on one's own personal ability rather than data from others.

[0084] Furthermore, when there are companions with varying skill levels, it becomes difficult to determine which golf course is suitable for playing. Through this embodiment, the estimated scores of each companion are obtained based on the course and hole, and the course with the smallest standard deviation is recommended, allowing the game to be played on a course with a difficulty level suitable for everyone. It is possible to recommend golf courses that are challenging or easy for everyone.

[0085] Additionally, the estimated scores used for golf course recommendations are utilized in golf course strategy provision technology, allowing users to receive guidance on the optimal path (result) achievable based on their current skill level, derived from the estimated scores on specific holes.

[0086] The artificial intelligence model applied to the score prediction-based golf course recommendation device may include a score prediction model (400), a golf course recommendation model (500), or a model combining these.

[0087] A score prediction model (400), a golf course recommendation model (500), or a combination thereof may apply an artificial intelligence-based network model. Here, the network model extracts features and processes the features as data. The network model comprises multiple layers connected by a network, including an input layer, a hidden layer, and an output layer. The layers may include parameters, and the parameters may include weights and / or biases between nodes. The score prediction model (400), the golf course recommendation model (500), or a combination thereof may learn the parameters to minimize a predefined loss function.

[0088] A score prediction model (400), a golf course recommendation model (500), or a model combining these can apply network models such as an Artificial Neural Network (ANN), a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), an Autoencoder, a feature extraction model, and a Decoder, but is not limited thereto, and can be implemented with various network models capable of learning to obtain an expected score, a recommended golf course, or information combining these from user information (including other user information), golf course information (including hole information), or information combining these.

[0089] The score prediction model (400) can receive user information and golf course information including hole information to predict the user's expected score. Depending on the model design, the score prediction model (400) may perform the operation of the golf course recommendation model (500). That is, the score prediction model (400) may select a golf course suitable for the user based on the expected score.

[0090] The golf course recommendation model (500) can receive an expected score from the score prediction model (400) and recommend a golf course suitable for the user. The golf course can be selected based on the result of comparing the expected score or the probability of the expected score with a reference score. The golf course recommendation model (500) can select a golf course based on pre-set rules rather than an artificial intelligence model.

[0091] FIGS. 4 and 5 are diagrams illustrating user ability data processed by a score prediction-based golf course recommendation device according to one embodiment.

[0092] A score prediction-based golf course recommendation device acquires user ability data. The score prediction-based golf course recommendation device may acquire user ability data through a golf simulation device or receive it from sources such as a database where user ability data is stored. The golf simulation device includes sensors and can acquire physical information regarding the user's swing through these sensors. The score prediction-based golf course recommendation device can extract a portion of the user ability data and utilize it as common data or specific data (by situation).

[0093] Referring to FIG. 4, a score prediction-based golf course recommendation device vectorizes user ability data and converts it into vectorized user ability data. For example, the vectorized user ability data is data in which user ability data including user ID, handicap, driver par, etc. is represented as a vector.

[0094] Referring to FIG. 5, user ability data may include numbers and items, and may include numerical values ​​or calculation formulas in units of specific games, rounds, or holes.

[0095] For example, user ability data can be specified as user ID, handicap, driver power, driver accuracy, green hit rate, short game (shots near the green), putting, driver average distance, driver ball speed, driver solid hit rate, driver average ball flight quality, iron average proximity to hole rate, iron average left-right deviation, iron average front-back deviation, iron 50m proximity to hole rate, iron 50m left-right deviation, iron 50m front-back deviation, iron 100m proximity to hole rate, iron 100m left-right deviation, iron 100m front-back deviation, iron 150m proximity to hole rate, iron 150m left-right deviation, iron 150m front-back deviation, iron 200m proximity to hole rate, iron 200m left-right deviation, iron 200m front-back deviation, etc.

[0096] For example, the handicap can be specified by green speed, wind speed, tee position, player difficulty, swing plate, concede, tour mode, hardness, course difficulty, green difficulty (slope rating), system correction value, etc.

[0097] For example, the short game can be specified by whether or not it is on the green (GIR), par, strokes, or whether or not it enters a green bunker.

[0098] FIG. 6 is a diagram illustrating hole data processed by a score prediction-based golf course recommendation device according to one embodiment.

[0099] A score prediction-based golf course recommendation device acquires area data based on map data regarding the golf course area. The score prediction-based golf course recommendation device may acquire area data through sensors or receive it from a database, etc., in which area data (e.g., images or satellite maps, etc.) is stored. For example, the score prediction-based golf course recommendation device may acquire area data based on images, such as those capturing holes constituting the golf course through an image sensor. Alternatively, the score prediction-based golf course recommendation device may acquire area data based on satellite maps, etc.

[0100] A score prediction-based golf course recommendation device can extract hole data extracted from area data based on map data regarding the golf course area.

[0101] Referring to FIG. 6, a score prediction-based golf course recommendation device vectorizes hole data and converts it into vectorized hole data. For example, vectorized hole data is data in which hole data including hole number, par number, length, etc. is represented as a vector.

[0102] Referring to Fig. 6, hole data may include numbers and items, and specific numerical values, etc.

[0103] For example, hole data can be specified as hole number, par number, total length, area inside the out-of-bounds line, fairway area, fairway area ratio, green bunker area, green bunker area ratio, fairway bunker area, fairway bunker area ratio, hazard area, hazard area ratio, rough area, rough area ratio, number of green bunkers, number of fairway bunkers, dogleg angle, average distance between tee box and fairway, minimum distance between tee box and fairway, average distance between green bunkers, minimum distance between green bunkers, average distance between green hazards, minimum distance between green hazards, etc.

[0104] FIGS. 7 and FIGS. 8 are drawings illustrating an expected score processed by a score prediction-based golf course recommendation device according to one embodiment.

[0105] When a user account completes the login, the score prediction-based golf course recommendation device obtains user information (e.g., user ability data) and hole data from a sensor or database (200).

[0106] A score prediction-based golf course recommendation device can generate vectorized user ability data by vectorizing the user's user ability data through a user data conversion model (310).

[0107] A score prediction-based golf course recommendation device can extract hole data from area data of a target golf course through a hole data conversion model (320), and vectorize the hole data to generate vectorized hole data.

[0108] A score prediction-based golf course recommendation device can combine vectorized user ability data and vectorized hole data, and input the combined vectorized user ability data and vectorized hole data into a score prediction model (400) to output the user's predicted score.

[0109] A score prediction-based golf course recommendation device analyzes the suitability of a target golf course in a user-customized manner using predicted scores and can recommend a golf course suitable for the user based on the suitability of the target golf course.

[0110] The score prediction model (400) outputs the probability of the user's predicted score based on the user's user information and the golf course information of the target golf course. The score prediction model (400) can output the predicted score for golf courses where the user has not played a golf game.

[0111] The score prediction model (400) can predict an expected score with one or more probabilities for each hole of the target golf course based on the user's user information and hole information included in the golf course information of the target golf course.

[0112] Referring to FIG. 7, a score prediction-based golf course recommendation device can calculate a set of predicted scores with multiple probabilities for each hole and sort and output the set of predicted scores with multiple probabilities.

[0113] Referring to FIG. 8, the accumulated expected score range can be output along with the probability by linking the expected score sets corresponding to multiple holes, and can also be output in sorted order.

[0114] After calculating the predicted scores for each hole, the predicted scores for the golf course can be calculated based on these predicted scores. For example, when the predicted scores for one hole are 5, 4, 6, and 3, and the predicted scores for another hole are 5, 4, 6, and 3, the predicted scores for the two holes can be 10, 9, 8, etc. Here, the accumulated predicted score of 10 can include 5+5, 4+6, 6+4, etc. The accumulated predicted score of 9 can include 5+4, 4+5, 6+3, 3+6, etc. The products of the predicted scores corresponding to each of the two holes can be summed up for each possible case. Depending on the design, different methods may be applied to calculate the probability.

[0115] When the predicted scores predicted as the top priority for each hole are added, the result may differ from the predicted score predicted as the top priority for the golf course. This is because the distribution of probability values ​​corresponding to multiple predicted scores on the golf course can vary from person to person depending on the distribution of probability values ​​corresponding to multiple predicted scores on each hole. In other words, as the course changes from the previous hole to the next, the distribution of the predicted scores on the entire golf course may change depending on the distribution of probability values ​​corresponding to the predicted score on the previous hole and the distribution of probability values ​​corresponding to the predicted score on the next hole.

[0116] By providing probabilities along with predicted scores, a score prediction-based golf course recommendation device enables probabilistic judgments based on probability for identically predicted scores and allows for selection considering probability ranges corresponding to multiple predicted scores.

[0117] FIGS. 9 and 10 are drawings illustrating a screen showing a golf course output by a score prediction-based golf course recommendation device according to one embodiment.

[0118] A score prediction-based golf course recommendation device may provide a user interface that recommends holes or golf courses. The visualized information provided through the user interface may include information visualized in various forms by varying colors, sizes, fonts, display positions, borders, the addition of symbols, the addition of highlights, animation effects, graph representations, geometric representations, or combinations thereof.

[0119] Referring to reference numeral 910, the score prediction-based golf course recommendation device calculates the individual difficulty of a target golf course for a user based on the user's predicted score and the user's reference score (e.g., average score), and can output the individual difficulty of the golf course and the reference score through a user interface. The score prediction-based golf course recommendation device can recommend one or more selected golf courses / holes.

[0120] Referring to reference numeral 920, the score prediction-based golf course recommendation device may recommend multiple golf courses / holes selected according to the individual difficulty and reference score of the golf course by selecting an icon (925) that adjusts the recommendation range. Here, the recommendation range is a factor for selecting the number of recommended golf courses. This is because if only one golf course / hole most suitable for the user is recommended, the user may want other alternatives considering geographical distance or weather.

[0121] Referring to reference numeral 1010, the score prediction-based golf course recommendation device predicts an expected score for each user in a user group based on user information of a user group including other users and golf course information of a target golf course, analyzes the suitability of a target golf course based on the difference in expected scores for each user in the user group, and outputs the golf course with the smallest difference in expected scores for each user in the user group. In this case, the golf course that has the smallest difference in expected scores and is most advantageous to user C among users A, B, and C can be selected.

[0122] Referring to reference numeral 1020, the score prediction-based golf course recommendation device can select a reference user by selecting an icon (1025) for selecting a priority user. Here, the reference user is a user who is set to receive the recommendation for the most advantageous (easy difficulty) golf course among the user group receiving golf course recommendations. For example, the reference user may be a person whose physical condition is worse than usual on the day of the game, or a person who wants to win a golf game due to business relationships.

[0123] For example, among users A, B, and C, the golf course most advantageous to user B can be selected. A score prediction-based golf course recommendation device can output golf courses that consider the difference in expected scores for each user in a user group, based on a reference user set in the user group. In this case, among users A, B, and C, a golf course that is most advantageous to user C and has a relatively small difference in expected scores can be selected.

[0124] FIG. 11 is a flowchart illustrating a score prediction-based golf course recommendation method according to one embodiment.

[0125] The score prediction-based golf course recommendation method according to the embodiment illustrated in FIG. 11 includes steps processed chronologically in the score prediction-based golf course recommendation device illustrated in FIG. 1 to FIG. 10. Even if some details regarding the score prediction-based golf course recommendation method are omitted, the details described above regarding the score prediction-based golf course recommendation device may be applied to the score prediction-based golf course recommendation method according to the embodiment illustrated in FIG. 11, and even if some details regarding the score prediction-based golf course recommendation device are omitted, the details described above regarding the score prediction-based golf course recommendation method may be applied.

[0126] Referring to Fig. 11, in S1110, the score prediction-based golf course recommendation device predicts the user's expected score for a target golf course.

[0127] In S1120, the score prediction-based golf course recommendation device analyzes the suitability of a target golf course in a user-customized manner using the user's predicted score.

[0128] In S1130, the score prediction-based golf course recommendation device recommends a golf course suitable for the user based on the suitability of the target golf course.

[0129] The step of predicting the user's expected score (S1110) may include a step of outputting the probability of the user's expected score through an artificial intelligence-based score prediction model based on the user's user information and the golf course information of the target golf course. Here, the target golf course may include a golf course where the user has not played a golf game.

[0130] The step of predicting the user's expected score (S1110) may include the step of outputting the user's expected score using a score prediction model for golf courses where the user has not played a golf game.

[0131] The step of predicting the user's expected score (S1110) may include the step of generating vectorized user ability data by vectorizing the user's ability data, the step of extracting hole data from area data of a target golf course and generating vectorized hole data by vectorizing the hole data, the step of combining the vectorized user ability data and the vectorized hole data, and the step of inputting the combined vectorized user ability data and the vectorized hole data into a score prediction model to output the user's expected score.

[0132] The step of predicting the user's expected score (S1110) may include predicting an expected score with one or more probabilities for each hole of the target golf course based on the user's user information and hole information included in the golf course information of the target golf course.

[0133] The step of predicting the user's expected score (S1110) may include the step of calculating a set of expected scores with multiple probabilities for each hole of the target golf course, and the step of sorting and outputting the set of expected scores with multiple probabilities.

[0134] The step of analyzing the suitability of the target golf course (S1120) may include the step of calculating the individual difficulty of the target golf course for the user based on the user's expected score and the user's reference score.

[0135] The step of predicting the user's expected score (S1110) may include predicting the expected score for each user in the user group based on user information of the user group including other users and golf course information of the target golf course.

[0136] The step of analyzing the suitability of the target golf course (S1120) may include the step of analyzing the suitability of the target golf course based on the difference in expected scores for each user of the user group.

[0137] The step of recommending a golf course suitable for the user (S1130) may include the step of outputting the golf course with the smallest difference in expected scores for each user in the user group.

[0138] The step of recommending a golf course to a user (S1130) may include the step of outputting a golf course that takes into account the difference in expected scores for each user in a user group based on a reference user set in a user group.

[0139] In the embodiments above, the term 'part' refers to a software or hardware component such as a field programmable gate array (FPGA) or an ASIC, and the 'part' performs certain roles. However, the 'part' is not limited to software or hardware. The 'part' may be configured to reside in an addressable storage medium or may be configured to run one or more processors. Thus, as an example, the 'part' includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables.

[0140] The functions provided within the components and 'parts' can be combined into a smaller number of components and 'parts' or separated from additional components and 'parts'.

[0141] In addition, the components and '~parts' may be implemented to play one or more CPUs, GPUs within the device or secure multimedia card.

[0142] Meanwhile, the score prediction-based golf course recommendation method according to one embodiment described herein may also be implemented in the form of a computer-readable medium that stores instructions and data executable by a computer. In this case, the instructions and data may be stored in the form of program code, and when executed by a processor, may generate a specific program module to perform a specific operation. Furthermore, the computer-readable medium may be any available medium accessible by a computer and includes both volatile and non-volatile media, as well as removable and non-removable media. Additionally, the computer-readable medium may be a computer recording medium, which may include both volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. For example, the computer recording medium may be a magnetic storage medium such as an HDD and an SSD, an optical recording medium such as a CD, DVD, or Blu-ray disc, or a memory included in a server accessible via a network.

[0143] In addition, a score prediction-based golf course recommendation method according to one embodiment described herein may be implemented as a computer program (or computer program product) comprising instructions executable by a computer. The computer program includes programmable machine instructions processed by a processor and may be implemented in a high-level programming language, an object-oriented programming language, assembly language, or machine language, etc. Additionally, the computer program may be recorded on a tangible computer-readable recording medium (e.g., memory, hard disk, magnetic / optical medium, or SSD (Solid-State Drive), etc.).

[0144] Accordingly, a score prediction-based golf course recommendation method according to one embodiment described herein may be implemented by executing a computer program as described above by a computing device. The computing device may include at least some of a processor, memory, a storage device, a high-speed interface connected to the memory and a high-speed expansion port, and a low-speed interface connected to a low-speed bus and a storage device. Each of these components may be connected to one another using various buses and may be mounted on a common motherboard or mounted in other suitable ways.

[0145] Here, the processor can process instructions within the computing device, such as instructions stored in memory or storage devices to display graphic information for providing a Graphic User Interface (GUI) on external input and output devices, such as a display connected to a high-speed interface. In another embodiment, a plurality of processors and / or a plurality of buses may be utilized together with a plurality of memories and memory types. Additionally, the processor may be implemented as a chipset comprising chips including a plurality of independent analog and / or digital processors.

[0146] In addition, memory stores information within a computing device. For example, memory may consist of volatile memory units or a set thereof. As another example, memory may consist of non-volatile memory units or a set thereof. Furthermore, memory may be other forms of computer-readable media, such as magnetic or optical discs.

[0147] And the storage device can provide a large amount of storage space to the computing device. The storage device may be a computer-readable medium or a configuration containing such a medium, and may include, for example, devices or other configurations within a Storage Area Network (SAN), and may be a floppy disk device, a hard disk device, an optical disk device, or a tape device, flash memory, or other similar semiconductor memory device or device array.

[0148] The embodiments described above are for illustrative purposes only, and those skilled in the art will understand that the embodiments described above can be easily modified into other specific forms without altering the technical concept or essential features of the embodiments described above. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0149] The scope of protection sought through this specification is defined by the claims set forth below rather than by the detailed description above, and should be interpreted to include all modifications or variations derived from the meaning and scope of the claims and the concept of equivalents.

Claims

1. In a score prediction-based golf course recommendation method performed by a score prediction-based golf course recommendation device, A step of predicting the user's expected score for a target golf course; A step of analyzing the suitability of the target golf course in a user-customized manner using the user's predicted score through an artificial intelligence-based score prediction model; and A score prediction-based golf course recommendation method comprising the step of recommending a golf course to a user based on the suitability of the target golf course.

2. In Paragraph 1, The step of predicting the above user's expected score is, A score prediction-based golf course recommendation method comprising the step of outputting the probability of the user’s predicted score through the artificial intelligence-based score prediction model based on the user information of the user and the golf course information of the target golf course.

3. In Paragraph 1, The above-mentioned target golf course includes a golf course where the user has not played a golf game, and The step of predicting the above user's expected score is, A score prediction-based golf course recommendation method comprising the step of outputting the user's predicted score using the score prediction model for a golf course where the user has not played the golf game.

4. In Paragraph 1, The step of predicting the above user's expected score is, A step of vectorizing the user ability data of the above user to generate vectorized user ability data; A step of extracting hole data from area data of the above-mentioned target golf course, and vectorizing the hole data to generate vectorized hole data; A step of combining the above vectorized user ability data and the above vectorized hole data; and A score prediction-based golf course recommendation method comprising the step of inputting the combined vectorized user ability data and vectorized hole data into the score prediction model to output the user's predicted score.

5. In Paragraph 1, The step of predicting the above user's expected score is, A score prediction-based golf course recommendation method comprising the step of predicting an expected score having one or more probabilities for each hole of a target golf course based on user information of the user and hole information included in the golf course information of the target golf course.

6. In Paragraph 1, The step of predicting the above user's expected score is, A step of calculating a set of predicted scores with multiple probabilities for each hole of the above-mentioned target golf course; and A score prediction-based golf course recommendation method comprising the step of sorting and outputting the set of predicted scores having the plurality of probabilities.

7. In Paragraph 1, The step of analyzing the suitability of the above-mentioned target golf course is, A score prediction-based golf course recommendation method comprising the step of calculating the individual difficulty of the target golf course for the user based on the user's predicted score and the user's reference score.

8. In Paragraph 1, The step of predicting the above user's expected score is, The method includes the step of predicting an expected score for each user of a user group based on user information of a user group including other users and golf course information of the target golf course. The step of analyzing the suitability of the above-mentioned target golf course is, A score prediction-based golf course recommendation method comprising the step of analyzing the suitability of the target golf course based on the difference in expected scores for each user of the user group.

9. In Paragraph 8, The step of recommending a golf course to the above user is, A score prediction-based golf course recommendation method comprising the step of outputting the golf course with the smallest difference in expected scores for each user of the above user group.

10. In Paragraph 8, The step of recommending a golf course to the above user is, A score prediction-based golf course recommendation method comprising the step of outputting a golf course that considers the difference in expected scores for each user of the user group based on a reference user set in the user group.

11. Memory for storing an artificial intelligence-based score prediction model; A control unit comprising at least one processor, which predicts a user's expected score for a target golf course through the artificial intelligence-based score prediction model, analyzes the suitability of the target golf course using the user's expected score, and selects a golf course to recommend to the user based on the suitability of the target golf course; and A score prediction-based golf course recommendation device comprising an input / output unit that provides a user interface for outputting the above-mentioned predicted score and the above-mentioned selected golf course.

12. In Paragraph 11, In the process of predicting the user's expected score, the above control unit, A score prediction-based golf course recommendation device that calculates the probability of the user’s predicted score through the artificial intelligence-based score prediction model based on the user information of the user and the golf course information of the target golf course.

13. In Paragraph 11, The above-mentioned target golf course includes a golf course where the user has not played a golf game, and A score prediction-based golf course recommendation device, wherein the control unit calculates the user’s expected score using the score prediction model for golf courses where the user has not played the golf game, in the process of predicting the user’s expected score.

14. In Paragraph 11, In the process of predicting the user's expected score, the control unit calculates a set of expected scores with multiple probabilities for each hole, and A score prediction-based golf course recommendation device in which the above input / output unit sorts and outputs the set of predicted scores having the plurality of probabilities during the process of outputting the predicted score.

15. In Paragraph 11, A score prediction-based golf course recommendation device, wherein the control unit calculates the individual difficulty of the target golf course for the user based on the user's expected score and the user's reference score during the process of analyzing the suitability of the target golf course.

16. In Paragraph 11, In the process of predicting the user's expected score, the control unit predicts the expected score for each user of the user group based on user information of the user group including other users and golf course information of the target golf course. A score prediction-based golf course recommendation device, wherein the control unit analyzes the suitability of the target golf course based on the difference in expected scores for each user of the user group during the process of analyzing the suitability of the target golf course.

17. In Paragraph 11, In the process of analyzing the suitability of the target golf course, the above control unit, Calculate the reference score of the user based on the user's average score, the user's handicap score, or a combination thereof, and Calculate the difficulty of the target golf course for the user based on the difference between the user's expected score and the user's reference score, and A score prediction-based golf course recommendation device that calculates a suitability score of the target golf course using the difficulty level of the target golf course.

18. In Paragraph 11, In the process of analyzing the suitability of the target golf course, the above control unit, Calculate the preference for the target golf course for the user based on the user's preferred course type, the user's past play records, or a combination thereof, and A score prediction-based golf course recommendation device that calculates a suitability score of a target golf course using the above-mentioned predicted score and the above-mentioned preference of the target golf course.

19. In Paragraph 11, In the process of analyzing the suitability of the target golf course, the above control unit, Calculate the difficulty of the target golf course for the user based on the difference between the user's expected score and the user's reference score, and Calculate the preference for the above target golf course for the above user, and A score prediction-based golf course recommendation device that calculates a suitability score of a target golf course by applying weights to the difficulty level of the target golf course and the preference of the target golf course and summing them.

Images