Prediction device, prediction method, and prediction program

Abstract

To provide a prediction apparatus which can predict a location in a golf course that requires maintenance in future.SOLUTION: Prediction means 77 predicts a location in a golf course that requires maintenance in future, on the basis of data derived from a satellite image obtained by imaging the golf course from a satellite, data derived from position information obtained from a first GPS device mounted on a cart used in the golf course and position information obtained from a second GPS device held by a player who plays golf in the golf course, and environment data of the golf course. Output means 78 outputs information indicating the location that requires maintenance.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to a prediction device, a prediction method, and a prediction program for predicting places that need maintenance in a golf course.

Background Art

[0002] The condition of the turf on a golf course is an important factor in a golf player's (hereinafter simply referred to as a player) evaluation of the golf course. In particular, since the condition of the turf's attachment to the ground, etc., has a great impact on play, the evaluation of a golf course with thorough turf maintenance is high. Also, at such a golf course, sales improve.

[0003] Generally, the maintenance of a golf course is carried out by a course manager visually checking the growth status of the turf, etc. The area of a golf course in Japan is on average 1 million square meters and is vast. Therefore, managing the entire course visually or manually leads to an increased burden on the course manager.

[0004] Note that Patent Document 1 describes that a satellite can analyze a crop field and that the overall health condition of the soil can be measured by remote detection. Also, Patent Document 1 describes transmitting a crop viability data report to an agricultural advisor, etc. Further, Patent Document 1 describes outputting a prediction of crop growth by comparing real-time data on weather conditions with a database of past weather conditions related to crop viability data.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] If it's possible to predict areas where turf will be damaged or where turf diseases will occur in the future, the burden of maintaining a vast golf course can be reduced. These areas can be collectively referred to as areas requiring maintenance. Being able to predict areas requiring maintenance in the future is desirable from the perspective of reducing the maintenance burden.

[0007] Therefore, the present invention aims to provide a prediction device, prediction method, and prediction program that can predict areas on a golf course that will require maintenance in the future. [Means for solving the problem]

[0008] The prediction device according to the present invention comprises a prediction means for predicting areas on a golf course that will require maintenance in the future, based on data derived from satellite images obtained by imaging a golf course from a satellite, location information obtained from a first GPS device attached to a cart used on the golf course, location information obtained from a second GPS device held by a player playing on the golf course, and environmental data of the golf course; and an output means for outputting information indicating areas that require maintenance. The data derived from satellite imagery includes the degree of grass growth on the ground, grass activity, and grass height; the data derived from location information obtained from the first and second GPS devices includes the cart's movement trajectory, the player's movement trajectory, and the landing point of the ball hit by the player; the environmental data includes seasonal data; a damage index value indicating the future degree of grass damage is assigned to each area defined by dividing the golf course; and the prediction means predicts areas where the grass will be damaged in the future, which will require maintenance in the future. The prediction method increases the damage index value for each area based on the number of cart movement trajectories, the number of player movement trajectories, the number of ball landing points hit by players, the poor condition of the grass on the ground, the poor condition of the grass, the shorter the grass height, and the season (spring, autumn, or winter). Areas where the damage index value exceeds a threshold are predicted to be areas where the grass will be damaged in the future. It is characterized by the following:

[0009] The prediction method according to the present invention is Computers Based on data derived from satellite imagery obtained by imaging the golf course from a satellite, location information obtained from a first GPS device attached to a cart used at the golf course, location information obtained from a second GPS device held by a player playing at the golf course, and environmental data of the golf course, the system predicts areas on the golf course that will require maintenance in the future and outputs information indicating those areas. The data derived from satellite imagery includes the degree of grass growth on the ground, grass activity, and grass height. The data derived from location information obtained from the first and second GPS devices includes the cart's movement trajectory, the player's movement trajectory, and the landing point of the ball hit by the player. Environmental data includes seasonal data. For each area defined by dividing the golf course, a damage index value indicating the future degree of grass damage is assigned, and the computer predicts areas where the grass will be damaged in the future, which will require maintenance. The computer increases the damage index value for each area based on the number of cart movements, the number of player movements, the number of ball landing points hit by players, the poor condition of the grass on the ground, the poor condition of the grass, the shorter the grass height, and whether it is spring, autumn, or winter. Areas where the damage index value exceeds a threshold are predicted to be areas where the grass will be damaged in the future. It is characterized by the following:

[0010] The prediction program according to the present invention causes a computer to perform a prediction process to predict areas on the golf course that will require maintenance in the future, and an output process to output information indicating the areas that require maintenance, based on data derived from satellite images obtained by imaging the golf course from a satellite, location information obtained from a first GPS device attached to a cart used on the golf course, location information obtained from a second GPS device held by a player playing on the golf course, and environmental data of the golf course. The data derived from satellite images includes the degree of grass growth on the ground, grass activity, and grass height. The data derived from location information obtained from the first and second GPS devices includes the cart's movement trajectory, the player's movement trajectory, and the landing point of the ball hit by the player. Environmental data includes seasonal data. For each area defined by dividing the golf course, a damage index value indicating the future degree of grass damage is assigned. The computer is used in a predictive process to predict areas where the grass will be damaged in the future and where maintenance will be needed. In the prediction process, for each area, the damage index is increased if there are many cart movement trajectories, if there are many player movement trajectories, if there are many landing points for balls hit by players, if the grass is not attached to the ground well, if the grass is not active enough, and if the grass is short. The system also increases the damage index when the season is spring, autumn, or winter, and predicts that areas where the damage index exceeds a threshold will be areas where the grass will be damaged in the future. . [Effects of the Invention]

[0011] According to the present invention, it is possible to predict areas on a golf course that will require maintenance in the future. [Brief explanation of the drawing]

[0012] [Figure 1] This is a schematic diagram showing a prediction device and various devices that provide information to the prediction device. [Figure 2] This is a block diagram showing an example configuration of a prediction device according to an embodiment of the present invention. [Figure 3] This flowchart shows an example of the processing steps in an embodiment of the present invention. [Figure 4] This is a schematic block diagram showing an example of the configuration of a computer related to the prediction device 1 of the present invention. [Figure 5] This is a block diagram illustrating the overview of the prediction device of the present invention. [Modes for carrying out the invention]

[0013] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0014] The prediction device according to an embodiment of the present invention receives information from an external device and predicts, based on data derived from the information, a location that will require maintenance in the future at a golf course. FIG. 1 is a schematic diagram showing the prediction device and various devices that provide information to the prediction device. As devices that provide information to the prediction device 1, there are a satellite 21, GPS (Global Positioning System) devices 31 and 32, and an environmental data observation device 41.

[0015] The satellite 21 images a golf course to be maintained and transmits an image obtained by the imaging to the prediction device 1. Hereinafter, an image obtained by the satellite 21 imaging the golf course is referred to as a satellite image. The prediction device 1 receives the satellite image transmitted by the satellite 21. The satellite 21 transmits the satellite image to the prediction device 1, for example, every day.

[0016] Note that the prediction device 1 may receive the satellite image from the satellite 21 via a relay device (not shown) and a communication network 50.

[0017] Each of the GPS devices 31 and 32 calculates position information indicating its own position using GPS satellites (not shown) and transmits the position information to the prediction device 1.

[0018] Here, the first GPS device 31 is a GPS device attached to a cart at the golf course. Therefore, it can be said that the position information calculated by the first GPS device 31 is information indicating the position of the cart. The first GPS device 31 periodically calculates the position information and transmits it to the prediction device 1. The first GPS device 31 calculates and transmits the position information at time intervals capable of deriving the movement trajectory of the cart.

[0019] Also, the second GPS device 32 is a GPS device held by a golfer (hereinafter simply referred to as a player). Therefore, it can be said that the position information calculated by the second GPS device 32 is information indicating the player's position. The second GPS device 32 periodically calculates position information and transmits it to the prediction device 1. The second GPS device 32 calculates and transmits position information at time intervals at which the player's movement trajectory can be derived. Also, when a predetermined operation is performed, the second GPS device 32 calculates the position information at that time, adds data (hereinafter referred to as a drop point flag) indicating that the position information is the position information indicating the drop point of the golf ball (hereinafter simply referred to as a ball), and transmits the position information with the drop point flag added to the prediction device 1. It is assumed that the player performs a predetermined operation on the second GPS device 32 when moving to the drop point of the ball during the play of golf. In response to this predetermined operation, as described above, the second GPS device 32 transmits the position information with the drop point flag added to the prediction device 1.

[0020] The prediction device 1 receives, via the communication network 50, the position information periodically transmitted by the first GPS device 31, the position information periodically transmitted by the second GPS device 32, and the position information to which the drop point flag is added.

[0021] The environmental data observation device 41 is arranged, for example, at the central point of the golf course and observes the environmental data of the golf information. The environmental data observation device 41 transmits the environmental data to the prediction device 1. The prediction device 1 receives the environmental data via the communication network 50. The environmental data observation device 41 observes at least a part of the data indicating the season, the data indicating the temperature, and the data indicating the weather as environmental data. The environmental data observation device 41 may observe all of the data indicating the season, the data indicating the temperature, and the data indicating the weather, and may further observe other types of environmental data.

[0022] The environmental data observation device 41, for example, periodically observes environmental data and transmits the environmental data to the prediction device 1.

[0023] Figure 2 is a block diagram showing an example configuration of a prediction device 1 according to an embodiment of the present invention. The prediction device 1 comprises a satellite image receiving unit 2, a position information receiving unit 3, an environmental data receiving unit 4, a first data derivation unit 5, a second data derivation unit 6, a prediction unit 7, and an output unit 8.

[0024] The satellite image receiving unit 2 is an interface for receiving satellite images from the artificial satellite 21. The satellite image receiving unit 2 receives satellite images from the artificial satellite 21 and sends those satellite images to the first data output unit 5.

[0025] Furthermore, if the prediction device 1 receives satellite images from the artificial satellite 21 via a relay device (not shown) and a communication network 50, the satellite image receiving unit 2 may be a communication interface for communicating via the communication network 50.

[0026] The location information receiving unit 3 is a communication interface for receiving location information from the first GPS device 31 and the second GPS device 32 via the communication network 50. The location information receiving unit 3 receives location information from the first GPS device 31 and location information (including location information with a drop point flag attached) from the second GPS device 32, and sends this location information to the second data output unit 6.

[0027] The environmental data receiving unit 4 is a communication interface for receiving environmental data from the environmental data observation device 41 via the communication network 50. The environmental data receiving unit 4 receives environmental data from the environmental data observation device 41 and sends that environmental data to the prediction unit 7. The prediction unit 7 stores, for example, environmental data for a time period from the present to a certain period in the past (i.e., environmental data for a certain past period).

[0028] The first data extraction unit 5 extracts data from satellite images to be used in predicting areas that will require maintenance in the future, and sends the extracted data to the prediction unit 7. The first data extraction unit 5 extracts at least some of the following as data to be used in predicting areas that will require maintenance in the future: the degree of grass growth on the ground at each location on the golf course, the activity level of the grass at each location on the golf course, the grass height at each location on the golf course, and the soil moisture content at each location on the golf course. The first data extraction unit 5 may extract all of the above data, or it may extract other types of data as well.

[0029] The second data derivation unit 6 derives data to be used to predict areas that will require maintenance in the future from the location information received from the first GPS device 31 and the location information received from the second GPS device 32 (including location information with a landing point flag attached), and sends the derived data to the prediction unit 7. The second data derivation unit 6 derives at least some of the following as data to be used to predict areas that will require maintenance in the future: the cart's movement trajectory, the player's movement trajectory, and the ball's landing point. The second data derivation unit 6 may derive all of the above data, or it may derive other types of data as well.

[0030] The second data derivation unit 6 can derive the cart's movement trajectory by arranging the locations indicated by the location information received from the first GPS device 31 in the order in which the location information was received. Since there may be more than one cart, there may also be more than one first GPS device 31. Therefore, the first GPS device 31 only needs to transmit location information with its identification information added to it to the prediction device 1. The second data derivation unit 6 can derive the movement trajectory for each cart by arranging the locations indicated by the location information received from the first GPS device 31 for each piece of identification information in the order in which the location information was received.

[0031] The second data derivation unit 6 can derive the player's movement trajectory by arranging the locations indicated by the location information received from the second GPS device 32 in the order in which the location information was received. Since there may be more than one player, there may also be more than one second GPS device 32. Therefore, the second GPS device 32 only needs to transmit location information with its identification information added to it to the prediction device 1. The second data derivation unit 6 can derive the movement trajectory for each player by arranging the locations indicated by the location information received from the second GPS device 32 for each piece of identification information in the order in which the location information was received.

[0032] The second data derivation unit 6 only needs to determine that the position indicated by the position information to which the landing point flag has been added is the landing point of the ball.

[0033] The second data derivation unit 6 holds each of the derived data (the movement trajectory of each cart, the movement trajectory of each player, and the landing point of the ball) until it is time for the prediction unit 7 to perform the prediction processing, and sends each of the derived data to the prediction unit 7 when it is time for the prediction processing.

[0034] The prediction unit 7 predicts areas on the golf course that will require maintenance in the future, based on the data derived by the first data derivation unit 5, the data derived by the second data derivation unit 6, and data from the present to the past for a certain period of time sent from the environmental data receiving unit 4.

[0035] First, let's explain using the example of predicting areas where the turf will be damaged in the future, which will require maintenance in the future. In the example below, the first data derivation unit 5 will derive at least the degree of turf attachment to the ground at each location on the golf course, the turf activity level at each location on the golf course, and the turf height at each location on the golf course. The second data derivation unit 6 will derive the movement trajectory of each cart, the movement trajectory of each player, and the landing point of each ball. Furthermore, the prediction unit 7 will receive environmental data indicating the season from the environmental data receiving unit 4.

[0036] Furthermore, it is assumed that the area where the golf course's grass grows is divided into multiple areas. The size of each area can be determined according to the ease of management for the course manager. The prediction unit 7 is assumed to have the range of each area stored in advance. For each area, the prediction unit 7 determines an index value (hereinafter referred to as the damage index value) that indicates the degree of future grass damage, based on the given data. A larger damage index value means that the grass is expected to suffer greater damage. In this example, it is assumed that initial values ​​for the damage index value are set for each area.

[0037] Let's explain using one area as an example. The more cart movement trajectories there are within an area, the greater the damage that will occur to the grass in that area in the future. Conversely, the fewer cart movement trajectories there are, the less damage that will occur to the grass in that area in the future. Similarly, the more player movement trajectories there are within an area, the greater the damage that will occur to the grass in that area in the future. Conversely, the fewer player movement trajectories there are, the less damage that will occur to the grass in that area in the future. Therefore, the prediction unit 7 increases the damage index value as the more cart movement trajectories there are in the area of ​​focus. Similarly, the prediction unit 7 increases the damage index value as the more player movement trajectories there are in the area of ​​focus.

[0038] Furthermore, at the point where the ball lands, the player hits the ball. In this process, the player often digs into the surface of the course with their golf club. Therefore, the more ball landing points there are in an area, the greater the damage that will occur to the turf in that area in the future, and the fewer ball landing points there are in an area, the less damage that will occur to the turf in that area in the future. Accordingly, the prediction unit 7 increases the damage index value as the number of ball landing points increases in the area under consideration.

[0039] Furthermore, the shorter the grass, the more susceptible it is to the effects of balls, carts, etc., while the taller the grass, the less susceptible it is to the effects of balls, carts, etc. Therefore, the prediction unit 7 increases the damage index value as the grass height decreases in the area under consideration.

[0040] Furthermore, the poorer the grass coverage on the ground, the greater the damage to the grass in that area will be in the future, and the better the grass coverage on the ground, the less damage to the grass in that area will be in the future. Therefore, the prediction unit 7 increases the damage index value in the area under consideration as the grass coverage on the ground worsens.

[0041] Furthermore, the lower the turf activity level, the greater the damage that will occur to the turf in that area in the future; and the higher the turf activity level, the smaller the damage that will occur to the turf in that area in the future. Therefore, the prediction unit 7 increases the damage index value as the turf activity level decreases in the area under consideration.

[0042] Furthermore, grass height decreases in winter and increases in summer. Therefore, if it is currently winter, the damage to the turf in the future is likely to be greater. Accordingly, the prediction unit 7 increases the damage index value if it is currently winter.

[0043] Furthermore, the number of players visiting golf courses increases in spring and autumn compared to summer and winter. Therefore, if it is currently spring or autumn, the damage to the turf in the future is likely to be greater. Accordingly, the prediction unit 7 increases the damage index value even if it is currently spring or autumn.

[0044] The prediction unit 7 changes the damage index value for each area as described above and calculates the damage index value for each area. Then, areas where the damage index value exceeds a predetermined threshold are used as the predicted locations where the turf will be damaged in the future. Note that the type of data used to calculate the damage index value is not limited to the example above.

[0045] Furthermore, we will explain using the example of predicting areas that will require maintenance in the future, specifically areas where turf diseases are likely to occur. In the example below, the first data derivation unit 5 will derive at least the soil moisture content at each location on the golf course. The second data derivation unit 6 will derive the movement trajectory of each cart and the movement trajectory of each player. The prediction unit 7 will also receive environmental data, including temperature data and weather data, from the environmental data receiving unit 4.

[0046] In this example, it is assumed that the area where the golf course is covered with grass is divided into multiple areas. The prediction unit 7 is assumed to have the boundaries of each area stored in advance. These points are the same as in the example above. The prediction unit 7 determines an index value (hereinafter referred to as the disease index value) for each area that indicates the degree of possibility of grass disease occurring in the future, based on the given data. A higher disease index value means that the likelihood of grass disease occurring in the future is predicted to be higher. In this example, it is assumed that initial values ​​for the disease index value are set for each area.

[0047] Let's explain using one area as an example. The more cart movement trajectories there are within an area, the higher the probability that turf diseases will occur in that area in the future. Conversely, the fewer cart movement trajectories there are, the lower the probability that turf diseases will occur in that area in the future. Similarly, the more player movement trajectories there are within an area, the higher the probability that turf diseases will occur in that area in the future. Conversely, the fewer player movement trajectories there are, the lower the probability that turf diseases will occur in that area in the future. Therefore, the prediction unit 7 increases the disease index value as the more cart movement trajectories there are in the area of ​​focus. Similarly, the prediction unit 7 increases the disease index value as the more player movement trajectories there are in the area of ​​focus.

[0048] Furthermore, the prediction unit 7 increases the disease index value for the area under consideration according to the soil moisture content of that area. In addition, the prediction unit 7 increases the disease index value for individual areas according to the temperature and weather conditions over a certain period in the past.

[0049] In this way, the prediction unit 7 calculates disease index values ​​for each area according to soil moisture content, the number of cart movement trajectories, the number of player movement trajectories, temperature over a certain period in the past, and weather over a certain period in the past. Note that the types of data used to calculate the disease index values ​​are not limited to the examples above.

[0050] The prediction unit 7 uses areas where the disease indicator value exceeds a predetermined threshold as the predicted location where turf diseases will occur in the future.

[0051] The output unit 8 outputs information indicating areas that will require maintenance in the future (areas where the turf will be damaged in the future, or areas where turf diseases will occur in the future). For example, the output unit 8 can display a map of the golf course divided into the aforementioned areas on a display device (not shown in Figure 2) provided on the prediction device 1, and display the areas predicted to require maintenance in the future in a predetermined color. With such a display method, the course manager can recognize the areas displayed in the predetermined color as predicted areas that will require maintenance in the future (areas where the turf will be damaged in the future, or areas where turf diseases will occur in the future). However, the output method of the predicted areas that will require maintenance in the future is not limited to the above example.

[0052] Furthermore, the prediction device 1 may also make predictions about areas where turf will be damaged in the future, and about areas where turf diseases will occur in the future.

[0053] The first data derivation unit 5, the second data derivation unit 6, the prediction unit 7, and the output unit 8 are implemented, for example, by a computer's CPU (Central Processing Unit) that operates according to a prediction program. For example, the CPU can read a prediction program from a program recording medium such as the computer's program storage device, and then operate as the first data derivation unit 5, the second data derivation unit 6, the prediction unit 7, and the output unit 8 according to that prediction program.

[0054] Next, an example of the processing steps of an embodiment of the present invention is shown. Figure 3 is a flowchart showing an example of the processing steps of an embodiment of the present invention. Matters that have already been explained will be omitted from further explanation.

[0055] In this example, the environmental data receiving unit 4 receives environmental data from the environmental data observation device 41 and sends that environmental data to the prediction unit 7 (step S1). The prediction unit 7 stores environmental data for a certain period of time from the present to the past.

[0056] Furthermore, the location information receiving unit 3 receives location information from the first GPS device 31 and location information (including location information with a landing point flag attached) from the second GPS device 32, and sends this location information to the second data output unit 6 (step S2).

[0057] The second data derivation unit 6 derives data (for example, the trajectory of the cart, the trajectory of the player, the landing point of the ball, etc.) from the position information obtained in step S2 to be used to predict places that will require maintenance in the future, and stores that data (step S3).

[0058] Then, the satellite image receiving unit 2 receives satellite images of the golf course from the artificial satellite 21 and sends those satellite images to the first data derivation unit 5 (step S4).

[0059] The first data derivation unit 5 derives data from the satellite image obtained in step S4 that will be used to predict areas that will require maintenance in the future (for example, the degree of grass growth on the ground at each location on the golf course, the activity level of the grass at each location on the golf course, the height of the grass at each location on the golf course, the soil moisture content at each location on the golf course, etc.) and sends this data to the prediction unit 7 (step S5). At this time, the second data derivation unit 6 sends the data it holds (for example, the trajectory of the cart, the trajectory of the player, the landing point of the ball, etc.) to the prediction unit 7.

[0060] Next, the prediction unit 7 predicts the locations on the golf course that will require maintenance in the future, based on the environmental data, the data derived by the second data derivation unit 6, and the data derived by the first data derivation unit 5 (step S6).

[0061] Next, the output unit 8 outputs the location predicted in step S6 (the location that will require maintenance in the future) (step S7).

[0062] According to this embodiment, the prediction unit 7 predicts areas on the golf course that will require maintenance in the future, based on environmental data, data derived from location information obtained from a first GPS device 31 attached to the cart and a second GPS device 32 held by the player, and data derived from satellite images of the golf course. Therefore, it is possible to predict areas that will require maintenance in the future.

[0063] Furthermore, the output unit 8 outputs the predicted locations. Therefore, course managers can know the locations predicted to require maintenance, and can carry out golf course maintenance efficiently.

[0064] Embodiments of the present invention can also be applied to the maintenance of sports fields with grass, such as soccer fields and rugby fields, as well as grass grounds in parks.

[0065] Furthermore, the technology described in the embodiments of the present invention may be applied to the maintenance of snow-covered mountains such as ski resorts, or to the detection of the progression of autumn foliage.

[0066] Figure 4 is a schematic block diagram showing an example of the configuration of a computer according to an embodiment of the present invention. The computer 100 comprises a CPU 1001, a main memory 1002, an auxiliary memory 1003, an interface 1004, a satellite communication interface 1005, and a communication interface 1006. The satellite communication interface 1005 corresponds to the satellite image receiving unit 2. The communication interface 1006 corresponds to the location information receiving unit 3 and the environmental data receiving unit 4.

[0067] The prediction device 1 of the embodiment of the present invention is implemented, for example, by a computer 1000. The operation of the prediction device 1 is stored in the auxiliary storage device 1003 in the form of a prediction program. The CPU 1001 reads the prediction program, expands it into the storage device 1002, and executes the processing described in the above embodiment according to the prediction program.

[0068] The auxiliary storage device 1003 is an example of a non-temporary tangible medium. Other examples of non-temporary tangible media include magnetic disks, magneto-optical disks, CD-ROMs (Compact Disk Read Only Memory), DVD-ROMs (Digital Versatile Disk Read Only Memory), and semiconductor memory, which are connected via the interface 1004.

[0069] Furthermore, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations thereof. These may be comprised of a single chip or multiple chips connected via a bus. Some or all of each component may be implemented by a combination of the aforementioned circuits, etc., and programs.

[0070] If some or all of the components are implemented by multiple information processing devices or circuits, these devices may be centrally located or distributed. For example, the information processing devices or circuits may be implemented in a form where each is connected via a communication network, such as a client-server system or a cloud computing system.

[0071] Next, an overview of the present invention will be described. Figure 5 is a block diagram showing an overview of the prediction device of the present invention. The prediction device of the present invention comprises a prediction means 77 and an output means 78.

[0072] The prediction means 77 (for example, the prediction unit 7) predicts areas on the golf course that will require maintenance in the future, based on data derived from satellite images obtained by imaging the golf course from a satellite, location information obtained from a first GPS device attached to a cart used on the golf course, location information obtained from a second GPS device held by a player playing on the golf course, and environmental data of the golf course.

[0073] The output means 78 (for example, the output unit 8) outputs information indicating the location where maintenance is required.

[0074] Such a configuration allows us to predict areas on the golf course that will require maintenance in the future.

[0075] Furthermore, the data derived from satellite images may include at least a portion of the following: the degree of grass growth on the ground, grass activity, grass height, and soil moisture content; the data derived from the location information obtained from the first GPS device and the location information obtained from the second GPS device may include at least a portion of the cart's movement trajectory, the player's movement trajectory, and the landing point of the ball hit by the player; and the environmental data may include at least a portion of the following: data indicating the season, data indicating temperature, and data indicating weather.

[0076] The prediction means 77 may also predict areas where maintenance will be needed in the future, such as areas where the grass will be damaged in the future.

[0077] The prediction means 77 may also predict areas that will require maintenance in the future, such as areas where turf diseases will occur in the future. [Industrial applicability]

[0078] The present invention is suitably applied to a predictive device that predicts areas on a golf course that will require maintenance in the future. [Explanation of Symbols]

[0079] 1. Prediction device 2. Satellite image receiving unit 3. Location information receiving unit 4. Environmental data receiving unit 5. First Data Derivation Unit 6. Second Data Derivation Unit 7. Prediction Section 8 Output section 21 Satellite 31. First GPS device 32. Second GPS device 41 Environmental data observation device

Claims

1. A predictive means for predicting areas on the golf course that will require maintenance in the future, based on data derived from satellite images obtained by imaging the golf course from a satellite, data derived from location information obtained from a first GPS device attached to a cart used on the golf course and location information obtained from a second GPS device held by a player playing on the golf course, and environmental data of the golf course. The system includes an output means that outputs information indicating the location where maintenance is required, The data derived from the aforementioned satellite imagery includes the degree of grass growth on the ground, grass activity, and grass height. The data derived from the location information obtained from the first GPS device and the location information obtained from the second GPS device includes the movement trajectory of the cart, the movement trajectory of the player, and the landing point of the ball hit by the player. The aforementioned environmental data includes seasonal data, For each area defined by dividing the aforementioned golf course, a damage index value indicating the future degree of turf damage is assigned. The prediction means is In the future, we will predict areas that will require maintenance and areas where the grass will be damaged. The prediction means is For each area, the more movement trajectories the cart leaves, the greater the damage index value; the more movement trajectories the player leaves, the greater the number of landing spots for the ball hit by the player, the worse the grass is attached to the ground, the greater the damage index value; the worse the grass is active, the greater the damage index value; the shorter the grass is, the greater the damage index value; and the more the season is spring, autumn, or winter, the greater the damage index value. Areas where the damage index value exceeds a threshold are predicted to be areas where the turf will be damaged in the future. A prediction device characterized by the following features.

2. The data derived from the aforementioned satellite image includes soil moisture content, The aforementioned environmental data includes data indicating temperature and data indicating weather. The prediction device according to claim 1.

3. The prediction means is In the future, areas that will require maintenance will be predicted, including areas where turf diseases will occur. The prediction device according to claim 1 or claim 2.

4. For each area defined by dividing the aforementioned golf course, a disease index value indicating the degree of possibility of future turf diseases is assigned. The prediction means is The disease index value is increased for each area according to the data derived from the satellite image, the location information obtained from the first GPS device, the location information obtained from the second GPS device, and the environmental data. Areas where disease indicator values ​​exceed a threshold are predicted to be areas where turf diseases will occur in the future. The prediction device according to claim 3.

5. A computer, Based on data derived from satellite images obtained by imaging the golf course from a satellite, data derived from location information obtained from a first GPS device attached to a cart used at the golf course and location information obtained from a second GPS device held by a player playing at the golf course, and environmental data of the golf course, the system predicts areas on the golf course that will require maintenance in the future. The system outputs information indicating the location where the aforementioned maintenance is required. The data derived from the aforementioned satellite imagery includes the degree of grass growth on the ground, grass activity, and grass height. The data derived from the location information obtained from the first GPS device and the location information obtained from the second GPS device includes the movement trajectory of the cart, the movement trajectory of the player, and the landing point of the ball hit by the player. The aforementioned environmental data includes seasonal data, For each area defined by dividing the aforementioned golf course, a damage index value indicating the future degree of turf damage is assigned. The aforementioned computer, In the future, we will predict areas that will require maintenance and areas where the grass will be damaged. The aforementioned computer, For each area, the more movement trajectories the cart leaves, the greater the damage index value; the more movement trajectories the player leaves, the greater the number of landing spots for the ball hit by the player, the worse the grass is attached to the ground, the greater the damage index value; the worse the grass is active, the greater the damage index value; the shorter the grass is, the greater the damage index value; and the more the season is spring, autumn, or winter, the greater the damage index value. Areas where the damage index value exceeds a threshold are predicted to be areas where the turf will be damaged in the future. A prediction method characterized by the following features.

6. On the computer, Based on data derived from satellite images obtained by imaging the golf course from a satellite, data derived from location information obtained from a first GPS device attached to a cart used at the golf course and location information obtained from a second GPS device held by a player playing at the golf course, and environmental data of the golf course, a predictive process is performed to predict areas on the golf course that will require maintenance in the future. The system executes an output process that outputs information indicating the location where the aforementioned maintenance is required. The data derived from the aforementioned satellite imagery includes the degree of grass growth on the ground, grass activity, and grass height. The data derived from the location information obtained from the first GPS device and the location information obtained from the second GPS device includes the movement trajectory of the cart, the movement trajectory of the player, and the landing point of the ball hit by the player. The aforementioned environmental data includes seasonal data, For each area defined by dividing the aforementioned golf course, a damage index value indicating the future degree of turf damage is assigned. The aforementioned computer, in the prediction process, To predict areas that will require maintenance in the future, and areas where the grass will be damaged in the future, The aforementioned computer, in the prediction process, For each area, the damage index value is increased if the cart has many movement trajectories, the damage index value is increased if the player has many movement trajectories, the damage index value is increased if the player's ball lands in many places, the damage index value is increased if the grass is not attached to the ground well, the damage index value is increased if the grass is not active enough, the damage index value is increased if the grass is short, and the process of increasing the damage index value is executed when the season is spring, autumn, or winter. Areas where the damage index value exceeds a threshold are predicted to be areas where the turf will be damaged in the future. A prediction program for that purpose.

Images