State prediction system, state prediction method, and state prediction program

Abstract

This situation prediction system comprises an acquisition unit, a prediction unit, and an output unit. The acquisition unit acquires information relating to racehorses. The prediction unit predicts the future situation of racehorses from the acquired information pertaining to the racehorses by using a prediction model that predicts the future situation of the racehorses from the information relating to the racehorses. The output unit outputs prediction results and the reason for predictions.

Description

[Technical Field]

[0001] The present invention relates to a condition prediction system and the like. [Background technology]

[0002] In horse racing, a public sport, racehorses are auctioned. Because racehorses are traded at auctions while they are still young, buyers must predict the future condition of the racehorse before bidding. However, there are cases where a purchased racehorse does not grow as expected. There are also cases where an injury prevents a horse from competing in enough races and the horse is forced to retire. For this reason, it is desirable to have a system that can predict the future condition of a racehorse.

[0003] The racehorse potential prediction system in Patent Document 1 uses a learning model to predict lifetime winnings. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-149853 Summary of the Invention [Problem to be solved by the invention]

[0005] The potential prediction system of Patent Document 1 may have difficulty interpreting the prediction results when predicting the future condition of a racehorse.

[0006] In order to solve the above problems, the object is to provide a condition prediction system etc. that can easily interpret the results of predicting the future condition of a racehorse. [Means for solving the problem]

[0007] In order to solve the above problems, the condition prediction system of the present invention comprises an acquisition means for acquiring information about a racehorse, a prediction means for predicting the future condition of the racehorse from the acquired information about the racehorse using a prediction model that predicts the future condition of the racehorse from the information about the racehorse, and an output means for outputting the results of the prediction and the reason for the prediction.

[0008] The condition prediction method of the present invention obtains information about a racehorse, uses a prediction model that predicts the future condition of the racehorse from the information about the racehorse, predicts the future condition of the racehorse from the obtained information about the racehorse, and outputs the prediction result and the reason for the prediction.

[0009] The recording medium of the present invention non-temporarily records a prediction program that causes a computer to execute the following processes: a process of acquiring information about a racehorse; a process of predicting the future state of the racehorse from the acquired information about the racehorse using a prediction model that predicts the future state of the racehorse from the information about the racehorse; and a process of outputting the results of the prediction and the reason for the prediction. [Effects of the Invention]

[0010] According to the present invention, it is possible to easily interpret the results of predicting the future condition of a racehorse. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating an example of a configuration of a first exemplary embodiment of the present invention. [Figure 2] FIG. 1 is a diagram illustrating an example of a configuration of a prediction system according to a first exemplary embodiment of the present invention. [Figure 3] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 5] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 6] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 7] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 8] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 9] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 10] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 11] FIG. 2 is a diagram showing an example of a display screen in the first embodiment of the present invention. [Figure 12] FIG. 2 is a diagram illustrating an example of an operation flow of the prediction system according to the first exemplary embodiment of the present invention. [Figure 13] FIG. 2 is a diagram illustrating an example of an operation flow of the prediction system according to the first exemplary embodiment of the present invention. [Figure 14] FIG. 10 is a diagram illustrating an example of the configuration of a prediction system according to a second exemplary embodiment of the present invention. [Figure 15] FIG. 10 is a diagram showing an example of an operation flow of a prediction system according to a second embodiment of the present invention. [Figure 16] FIG. 10 is a diagram illustrating an example of the configuration of another embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0012] A first embodiment of the present invention will be described in detail with reference to the drawings. FIG. 1 is a diagram showing an example of a racehorse prediction system. As an example, the racehorse prediction system includes a condition prediction system 10, a user terminal device 20, and an information management server 30. The condition prediction system 10 is connected to the user terminal device 20 via a network. The condition prediction system 10 is also connected to the information management server 30 via the network.

[0013] The condition prediction system 10 is a system that predicts the future condition of a racehorse. The condition prediction system 10 predicts, for example, the future condition of a racehorse before auction. A racehorse before auction is, for example, a racehorse owned by a breeder. The condition prediction system 10 may also predict the future condition of a racehorse that has not yet reached the age to compete in races. The future condition of a racehorse is, for example, information regarding the evaluation of the racehorse in the future beyond the time of prediction. The future condition of a racehorse is, for example, at least one of the auction price, health condition, maintenance costs, race results, and winnings. The auction price is the winning bid price of the racehorse at auction. The health condition is, for example, the presence or absence of future injuries. Furthermore, the future condition of a racehorse may be at least one of the following: weight change, muscle mass change, training time, a trainer suitable for the racehorse, a stable to which the racehorse is entrusted, a jockey suitable for the racehorse, a suitable race type, running style, a suitable race distance, a preferred race development, the time of first race, the time of last race, and the period during which the racehorse is eligible to race. The future condition of a racehorse is not limited to the above.

[0014] The condition prediction system 10 predicts the future condition of a racehorse, for example, using a prediction model that predicts the future condition of a racehorse from information about the racehorse. The condition prediction system 10 then outputs the prediction result and the reason for the prediction.

[0015] The information about the racehorse is, for example, information that may affect the future condition of the racehorse. The information about the racehorse is, for example, at least one of information about the parent horse, the racehorse's biological information at the time of prediction, and its breeding history. The information about the racehorse is not limited to the above. The reason for the prediction is, for example, information that is the basis for the prediction model to predict the future condition of the racehorse. The reason for the prediction is, for example, an item of the information about the racehorse that has a greater influence than other items on the prediction result of the racehorse's future condition when the prediction model predicts the racehorse's future condition.

[0016] The prediction model is, for example, a trained model generated using a machine learning algorithm. The condition prediction system 10, for example, learns the relationship between information about racehorses that have run in races in the past and the future condition of the racehorse. The condition prediction system 10 then generates a prediction model that predicts the future condition of the racehorse from information about the racehorse that is the target of prediction. The prediction model may be a trained model generated outside the condition prediction system 10. The prediction model will be described later.

[0017] The user terminal device 20 is, for example, a terminal device owned by a person who uses the prediction results of the condition prediction system 10. A person who uses the prediction results is, for example, a person who places a bid at a racehorse auction. A person who uses the prediction results may be a seller at the auction or the organizer of the auction. A person who uses the prediction results may be a person who invests in a racehorse owned by a corporation or an individual. A person who invests in a racehorse owned by a corporation or an individual is also called a fractional horse owner. A person who uses the prediction results may also be a reporter or a commentator. A person who uses the prediction results is not limited to the above examples. The information management server 30 is, for example, a server that stores information about racehorses.

[0018] Condition prediction system 10 acquires information about racehorses from, for example, information management server 30. Condition prediction system 10 then inputs the acquired information about racehorses and predicts the future condition of the racehorses using a prediction model. After predicting the future condition of the racehorse, condition prediction system 10 outputs the prediction result and the reason for the prediction to, for example, user terminal device 20.

[0019] The condition prediction system 10 may acquire information about the racehorse from multiple information management servers 30. The condition prediction system 10 may also acquire information about the racehorse from the user terminal device 20 that is input by the user of the user terminal device 20.

[0020] The state prediction system 10 may output the prediction result and the reason for the prediction to multiple user terminal devices 20. For example, the state prediction system 10 may output the prediction result and the reason for the prediction to user terminal devices 20 used by multiple users. The number of user terminal devices 20 and information management servers 30 may be set as appropriate.

[0021] The following describes the configuration of the state prediction system 10. Fig. 2 is a diagram showing an example of the configuration of the state prediction system 10. The state prediction system 10 includes an acquisition unit 11, a prediction unit 12, an output unit 13, a generation unit 14, and a storage unit 15.

[0022] The acquisition unit 11 acquires information about racehorses. The information about racehorses is, for example, information that may affect the future condition of the racehorses. The acquisition unit 11 acquires information about parent horses, biological information about the horse's body, and its breeding history as information about the racehorses. If the racehorse to be predicted has run in a race, the acquisition unit 11 may acquire the racing record of the racehorse to be predicted. The information about the parent horses is, for example, at least one of the name, sex, breeder, trainer, stable, whether or not it has been injured, training time history, times for each race distance, racing record, winnings, running style, stamina rating, and auction price. The racing record is, for example, at least one of the racecourse, race distance, weather, ranking, race development, track characteristics, number of runners, ranking, and winnings in races in which the horse has run in the past. The racing record may include the age at the time of the first race and the age at which the horse retired. The information about the parent horses may also include information about the sibling horses of the racehorse to be predicted. Information on sibling horses includes, for example, at least one of the following: name, sex, breeder, trainer, stable, whether or not the horse has been injured, training times by age, times by race distance, track record, prize money won, running style, and auction price. Information on parent horses and information on sibling horses is not limited to the above. Biological information includes at least one of the following: sex, weight, weight change, blood data, and muscle mass. Biological information is not limited to the above. Training history includes, for example, at least one of the following: breeder, trainer, and training time history. Trainer and training time history is obtained when training has begun. Training history is not limited to the above.

[0023] When multiple prediction models are used to predict the future state of a racehorse, the acquisition unit 11 may acquire the selection result of the prediction model from the user terminal device 20. The selection result of the prediction model is input to the user terminal device 20 by, for example, an operation of a person who uses the prediction result. The acquisition unit 11 may also acquire from the user terminal device 20 the selection of display items that are input to the user terminal device 20 by an operation of a person who uses the prediction result.

[0024] When condition prediction system 10 generates a prediction model, acquisition unit 11 may acquire information about the racehorse and the future condition of the racehorse as training data for generating the prediction model. Acquisition unit 11 stores the acquired information about the racehorse and the future condition of the racehorse in memory unit 15, for example.

[0025] The prediction unit 12 predicts the future state of the racehorse from the acquired information about the racehorse using a prediction model that predicts the future state of the racehorse from information about the racehorse. The prediction unit 12 also extracts the reason why the prediction model predicted the future state of the racehorse as the reason for the prediction. The prediction unit 12, for example, acquires parameters used when the prediction model predicted the future state of the racehorse. The prediction unit 12 then extracts the reason for the prediction from parameters that contribute significantly to predicting the future state of the racehorse.

[0026] The prediction unit 12 predicts, for example, as the future state of a racehorse, at least one of the auction price of the racehorse, the maintenance costs of a purchased racehorse, and the prize money that the purchased racehorse will earn. The auction price of a racehorse is the winning bid price at a racehorse auction. The maintenance costs of a racehorse are the costs paid to continuously own a racehorse. The maintenance costs of a racehorse are, for example, the costs of feeding, maintaining the health, and training the racehorse. The maintenance costs of a racehorse may also be the costs of entrusting a purchased racehorse to a stable. The maintenance costs of a racehorse are not limited to the above. The amount of prize money that a purchased racehorse will earn is the amount of prize money that the purchased racehorse will earn when it competes in a race in the future. The prediction unit 12 may predict, as the future state of a racehorse, the amount of prize money that a purchased racehorse will earn and the maintenance costs for each age of the horse. The prediction unit 12 may predict the amount of prize money and maintenance costs to be earned by the purchased racehorse on a monthly basis. The period for predicting the amount of prize money and maintenance costs to be earned by the purchased racehorse can be set as appropriate.

[0027] The prediction unit 12 may predict future income and expenses as the future condition of the racehorse based on the auction price of the racehorse, the maintenance costs of the purchased racehorse, and the prize money to be won by the purchased racehorse. The prediction unit 12 predicts, for example, the auction price of the racehorse, the maintenance costs of the purchased racehorse up to a certain point in the future, and the prize money to be won by the purchased racehorse. The prediction unit 12 then predicts the income and expenses at a certain point in the future by subtracting the auction price of the racehorse and the accumulated amount of maintenance costs of the purchased racehorse from the total amount of prize money to be won by the purchased racehorse. The prediction unit 12 predicts future income and expenses, for example, monthly. The interval at which future income and expenses are predicted is not limited to monthly and may be determined appropriately depending on the preferences of the person using the prediction results of the condition prediction system 10.

[0028] When predicting the future income and expenditure of a purchased racehorse, the prediction unit 12 may predict the future income and expenditure based on the purchase price of the racehorse, the maintenance costs of the purchased racehorse, and the prize money that the purchased racehorse will win. The maintenance costs of the purchased racehorse may be a predetermined amount set for each month or year. Furthermore, the future state of the racehorse predicted by the prediction model is not limited to the above example.

[0029] The prediction unit 12 may predict the future state of a racehorse using a prediction model according to the purpose of the prediction. For example, if the purpose of the prediction is to predict the auction price, the prediction unit 12 predicts the auction price from information about the racehorse using a prediction model that predicts the auction price as the future state of the racehorse. Also, for example, if the purpose of the prediction is to predict winning prize money, the prediction unit 12 predicts the winning prize money from information about the racehorse using a prediction model that predicts winning prize money as the future state of the racehorse.

[0030] The prediction unit 12 may predict the recommendation level from information about the racehorse, for example, using a prediction model that predicts the recommendation level for purchasing a racehorse as the future state of the racehorse. The recommendation level for purchase is calculated, for example, using an index that is preset by an expert who evaluates racehorses.

[0031] The prediction unit 12 may predict the future state of a racehorse using a prediction model that places weight on items that a user considers important. When predicting the future state of a racehorse using multiple prediction models, the prediction unit 12 may determine the prediction result by weighting the prediction result of each prediction model. For example, the prediction unit 12 weights the prediction result of each prediction model depending on which of the multiple prediction models the result of which is considered important. The prediction unit 12 may also predict the recommendation level from information about the racehorse using a prediction model that predicts the recommendation level for purchasing a racehorse depending on items that a person using the prediction results considers important. For example, when a person using the prediction results considers pedigree important, the prediction unit 12 predicts the recommendation level from information about the racehorse using a prediction model that places weight on data related to pedigree when making the prediction.

[0032] The prediction unit 12 may predict the future state of a racehorse using a prediction model according to the age of the racehorse being predicted. The prediction unit 12 predicts the future state of the racehorse, for example, using a prediction model for 0-year-olds, a prediction model for 1-year-olds, and a prediction model for 2-year-olds. The age categories used when making predictions using prediction models according to age are not limited to those described above.

[0033] The prediction unit 12 may predict the future state of a racehorse using a prediction model according to the attributes of the person who will use the prediction results. The attributes of the person who will use the prediction results may be, for example, a beginner, intermediate, or advanced player. The attributes of the person who will use the prediction results may also be classified as an auctioneer, auction participant, horse owner, trainer, or reporter. The classification of the attributes of the person who will use the prediction results is not limited to the above examples.

[0034] The output unit 13 outputs the prediction result of the racehorse's future condition and the reason for the prediction. The output unit 13 outputs the prediction result of the racehorse's future condition and the reason for the prediction, for example, to the user terminal device 20. The output unit 13 may output the prediction result and the reason for the prediction to a display device (not shown) connected to the condition prediction system 10. The output unit 13 may also output the prediction result of the racehorse's future condition and the reason for the prediction to, for example, a server that distributes auction information.

[0035] When predictions are made for multiple items regarding the future state of a racehorse, the output unit 13 may output prediction results for the multiple items. The output unit 13 outputs, for example, the auction price and the amount of winning prize money as prediction results for the future state of the racehorse. When the auction price and the amount of winning prize money are output as prediction results for the future state of the racehorse, the output unit 13 outputs, for example, the reason for predicting the auction price and the reason for predicting the amount of winning prize money as the reason for the prediction. The output unit 13 may also output prediction results for the future state of items other than the auction price and the reason for the prediction, for each price range of the auction price.

[0036] When the prediction unit 12 predicts future income and expenditure, the output unit 13 may output the prediction results regarding future income and expenditure as information over time. When the prediction unit 12 predicts future income and expenditure, the output unit 13 outputs, for example, information regarding income and expenditure by horse age as a graph. When outputting information regarding income and expenditure by horse age as a graph, the output unit 13 outputs, for example, a graph showing the accumulated amount of expenses and the accumulated amount of income by horse age. The output unit 13 may also output a graph showing the difference between the accumulated amount of expenses and the accumulated amount of income by horse age as income and expenditure. Furthermore, when the user of the prediction results is a fractional horse owner, the output unit 13 may use the investment amount as a fractional horse owner instead of the auction price and output information on expenses and income corresponding to the investment amount.

[0037] The output unit 13 may add information on items of information about the racehorse that are emphasized in predicting the future condition of the racehorse as reference information to the prediction result together with the prediction result. Items that are emphasized in predicting the future condition of the racehorse are, for example, items that frequently affect the future condition of the racehorse. Furthermore, when outputting information on items that are emphasized in predicting the future condition of the racehorse, the output unit 13 may output data that highlights items that correspond to the reason for the prediction. The output unit 13 may output items of information about the racehorse that are selected by the person using the prediction result as reference information.

[0038] The output unit 13 may output information about the parent horses of the racehorse to be predicted. The output unit 13 may output information about the parent horses of the racehorse to be predicted when the age of the racehorse to be predicted is below a standard. For example, when the age of the racehorse to be predicted is such that there is little information about the race results and breeding history of the racehorse, the output unit 13 outputs information about the race results and breeding history of the parent horses as reference information. The age standard and the items to be output are set in advance. The output unit 13 may also output performance data of racehorses with similar attributes to the racehorse to be predicted as reference information. A racehorse with similar attributes is, for example, a racehorse with a similar auction price and breeding history to the racehorse to be predicted. A racehorse with similar attributes may also be a racehorse with a similar pedigree to the racehorse to be predicted. Racehorses with similar attributes are not limited to the above examples. The output unit 13 outputs, as reference information, information on races in which racehorses with attributes similar to those of the racehorse being predicted have run, and winning prize money.

[0039] The output unit 13 may output data that highlights an item selected by a person using the prediction result from among the reference information. The highlighting is performed, for example, by changing at least one of the color, font size, font thickness, and decoration around the font from other items. The output unit 13 outputs, as reference information, for example, at least one or more items from among age, sex, weight, sire, dam, breeder, and training history. Furthermore, if there is an item from the reference information that corresponds to the reason for prediction, the output unit 13 may output data that highlights the item that corresponds to the reason for prediction.

[0040] The output unit 13 may output, as the reason for the prediction, items that are negative factors for the prediction result. A negative factor is an item that, among items that have a large influence on the future condition of a racehorse, has a large influence on the prediction that the racehorse's evaluation will be lowered. A large influence means, for example, that when a certain item is changed, the predicted result of the racehorse's future condition fluctuates more than other items. When the public competition is horse racing, for example, if the parent horse has a history of injury or illness, an item related to the health condition is extracted as a negative factor.

[0041] The output unit 13 may output the reason for the prediction as a sentence. The output unit 13 outputs a sentence indicating the reason for the prediction based on, for example, information about a racehorse that has a high influence on the prediction of the racehorse's future state. For example, the relationship between the information about a racehorse that has a high influence on the prediction of the racehorse's future state and the sentence indicating the reason for the prediction is set in advance. When the publicly managed competition is horse racing and the reason for the prediction is winning prize money, the output unit 13 may output, for example, a sentence such as "This horse is recommended because it is expected to win a lot of prize money" as the reason for the prediction.

[0042] The output unit 13 may output an image of the racehorse together with the prediction result and the reason for the prediction. The output unit 13 may also output an image of the racehorse during training together with the prediction result and the reason for the prediction. The output unit 13 may also output an image of a parent horse or sibling horse of the racehorse being predicted. The image may be either a still image or a video.

[0043] The output unit 13 may output the prediction result and the reason for the prediction superimposed on the image of the racehorse. The output unit 13 may also output either the prediction result or the reason for the prediction superimposed on the image of the racehorse.

[0044] FIG. 3 shows an example of a display screen for the prediction results of a racehorse's future state. The example of the display screen in FIG. 3 is a display screen for the prediction results when predicting the auction price as the prediction result of the racehorse's future state. In the example of the display screen in FIG. 3, the horse name, predicted price, and reason for the racehorse being predicted are displayed as a list. In the example of the display screen in FIG. 3, the predicted price is the auction price predicted by the prediction model. In the example of the display screen in FIG. 3, the reason for the prediction is output by the prediction model along with the prediction result. The reason for the prediction may be multiple items.

[0045] Figure 4 shows an example of a display screen that further displays the amount of prize money that a racehorse will win, in addition to the example of the display screen in Figure 3. In the example of the display screen in Figure 4, the predicted auction price is displayed as the predicted price, and the predicted prize money to be won is displayed as the predicted amount to be won.

[0046] Figure 5 shows an example of a display screen that further displays information about the racehorse to be predicted in addition to the example of the display screen in Figure 3. In the example of the display screen in Figure 5, the names of the breeder, sire, and dam of the racehorse to be predicted are also displayed. The information about the racehorse to be displayed together with the prediction results is not limited to the above example.

[0047] FIG. 6 shows an example of a display screen displaying changes in income and expenditure related to a racehorse as a graph. In the example of the display screen of FIG. 6, a graph is displayed in which the horizontal axis represents the age of the racehorse being predicted, and the vertical axis represents the amount of expenditure and income. In the example of the display screen of FIG. 6, a graph is displayed in which the auction price, expenditure representing the total accumulated amount of expenses necessary for maintenance, and income representing the accumulated amount of winnings are displayed. Among the graphs in the example of the display screen of FIG. 6, the graph indicated by the dashed line represents the accumulated amount of the auction price and the total accumulated amount of expenses necessary for maintenance. Among the graphs in the example of the display screen of FIG. 6, the graph indicated by the solid line represents the accumulated amount of winnings. The reason for the prediction may be superimposed on the graph in the example of the display screen of FIG. 6. Furthermore, the graph in the example of the display screen of FIG. 6 may be displayed in combination with another example of the display screen.

[0048] FIG. 7 shows an example of a display screen in which negative factors are further displayed as prediction reasons in the example display screen of FIG. 3. In the example display screen of FIG. 7, positive factors indicate positive factors. Positive factors are items that have a large influence on the prediction of a higher price among items that have a large influence on the prediction of a higher price. In the example display screen of FIG. 7, negative factors are shown as minus factors. Negative factors are items that have a large influence on the prediction of a lower price among items that have a large influence on the prediction of a lower price.

[0049] FIG. 8 shows an example of a display screen in the example of the display screen of FIG. 3 , in which, for a racehorse with a low auction price, the predicted auction price, the predicted reason for the low auction price, and factors that lead to a higher evaluation contrary to the predicted reason are displayed. The example of the display screen of FIG. 8 is a display screen that displays the reason for the low predicted price and factors that lead to a higher evaluation for a racehorse with a low predicted price. The example of the display screen of FIG. 8 displays the predicted price indicating the predicted auction price and the price reason indicating the reason for the prediction. Furthermore, the example of the display screen of FIG. 8 displays factors that lead to a higher prediction result as evaluation reasons. Factors that lead to a higher evaluation are, for example, items that lead to a higher winnings despite a low auction price. For example, if a horse's health condition is lowering the auction price, but its training time is improving and it is expected that the winnings will be higher, the training time is displayed as a factor that leads to a higher evaluation.

[0050] FIG. 9 shows an example of a display screen in addition to the example of the display screen of FIG. 3, which further displays reference information. In the example of the display screen of FIG. 9, the prediction result and the reason for the prediction are displayed in the left box. In the example of the display screen of FIG. 9, information about racehorse B is displayed as reference information in the right box. In the example of the display screen of FIG. 9, the horse's age, breeder, trainer, pedigree, weight, and training history are displayed as reference information. The items displayed as reference information are not limited to those described above. Furthermore, in the example of the display screen of FIG. 9, when a racehorse is selected in the predicted finishing order column, reference information about the selected racehorse may be displayed in the reference information column.

[0051] FIG. 10 shows an example of a display screen that outputs images of racehorses in the example of the display screen of FIG. 9. In the example of the display screen of FIG. 10, images of racehorses are displayed on the left side of the lower row. When a racehorse is selected in the predicted result column, the image of the selected racehorse may be displayed in the image display area. Furthermore, instead of the image of the racehorse to be predicted, an image of the parent horse of the racehorse to be predicted may be displayed. The image of the parent horse of the racehorse to be predicted may be an image of the parent horse when it ran in a race in the past. Furthermore, video of the racehorse during training may be displayed as the image of the racehorse. The image of the racehorse is obtained from the information management server 30, for example.

[0052] FIG. 11 shows an example of the display screen in which the prediction result and the reason for the prediction are superimposed on the image of the racehorse in the example of the display screen in FIG. 10. In the example of the display screen in FIG. 11, the reason for the prediction is displayed as being of good pedigree. The reason for the prediction displayed on the image of the racehorse may be a plurality of items. Also, either the prediction result or the reason for the prediction may be superimposed on the image of the racehorse.

[0053] When generating a prediction model in the condition prediction system 10, the generation unit 14 generates a prediction model that predicts the future condition of a racehorse from information about the racehorse. The generation unit 14, for example, learns the relationship between the information about the racehorse and the future condition of the racehorse, and generates a prediction model that predicts the future condition of the racehorse from the information about the racehorse. The generation unit 14 may generate a prediction model that predicts multiple items regarding the future condition of a racehorse. The generation unit 14 generates a prediction model that predicts, for example, the auction price and winnings.

[0054] When the prediction unit 12 predicts the future state of a racehorse using one of a plurality of prediction models, the generation unit 14 may generate each of the plurality of prediction models used by the prediction unit 12 for prediction.

[0055] When generating a prediction model for 0-year-olds, the generation unit 14 generates the prediction model by learning, for example, the relationship between information about the racehorse, including the racing records of its parent horses, and the future condition of the racehorse. When generating a prediction model for 1-year-olds, the generation unit 14 generates the prediction model by learning, for example, the relationship between information about the racehorse, including the biological information about the racehorse, and the future condition of the racehorse. The biological information of the racehorse is, for example, one or more of gender, coat, gait, weight, body length, weight change, physical condition change, blood data, and personality. The biological information of the racehorse is not limited to the above. When generating a prediction model for 2-year-olds, the generation unit 14 generates the prediction model by learning, for example, the relationship between information about the racehorse, including training history, and the future condition.

[0056] When generating a prediction model according to an item that a user of the prediction results values, the generation unit 14 generates the prediction model by, for example, learning the relationship between information about the racehorse, including information about the item that the user values, and the racehorse's future condition. When generating a prediction model that values ​​pedigree, the generation unit 14 generates the prediction model by, for example, learning the relationship between information about the racehorse, including the parent horse's biological information and the parent horse's racing record, and the racehorse's future condition. When generating a prediction model according to an item that a user of the prediction results values, the generation unit 14 may generate the prediction model by increasing the weight of the item that the user values. When increasing the weight of the item that the user values, the generation unit 14 generates the prediction model, for example, so that the coefficient of the feature value related to the item that the user values ​​is larger than the coefficient of the feature value related to other items.

[0057] The generation unit 14 generates a prediction model using, for example, a learning algorithm based on factorized asymptotic Bayesian inference. When performing learning using a learning algorithm based on factorized asymptotic Bayesian inference, the generation unit 14 performs case classification using decision tree rules, with information about the racehorse as input data and the racehorse's future state as ground truth data. The generation unit 14 then generates a learning model that predicts the racehorse's future state using a linear model that combines different explanatory variables for each case. The generation unit 14 generates the learning model by sequentially optimizing the data's case classification conditions, generating a prediction model by optimizing the combination of explanatory variables, and deleting unnecessary prediction models. This method of generating a learning model is also called heterogeneous mixture learning, as it combines prediction models with different combinations of explanatory variables. Generating a prediction model using heterogeneous mixture learning makes it possible to explain the prediction results of the racehorse's future state using case classification conditions that have a strong influence on the prediction results, thereby improving the interpretability of the prediction results. A heterogeneous mixture learning technique is disclosed, for example, in U.S. Patent Application Publication No. 2014 / 0222741.

[0058] The learning algorithm used in the machine learning to generate the prediction model is not limited to the above example. For example, the generation unit 14 may generate a learning model that predicts the future state of a racehorse from information about the racehorse by deep learning using a neural network. When generating such a learning model, the generation unit 14, for example, varies the data for each item and generates a prediction model that extracts items that have a large impact on the future state of the racehorse as reasons for the prediction based on changes in the future state of the racehorse. Then, the generation unit 14 varies the data for each item and extracts items that have a large impact on the future state of the racehorse as reasons for the prediction.

[0059] The memory unit 15 stores, for example, a prediction model. When multiple prediction models are used, the memory unit 15 stores multiple prediction models. When the condition prediction system 10 generates a prediction model, the memory unit 15 may store data used as training data that associates information about the racehorse with the future condition of the racehorse. When reference information is added to the prediction result, the memory unit 15 may store data used as the reference information. The prediction model used by the prediction unit 12 may be stored in a storage means other than the memory unit 15.

[0060] The user terminal device 20 acquires the prediction result and the reason for the prediction from the state prediction system 10. Then, the user terminal device 20 outputs the prediction result and the reason for the prediction to, for example, a display device (not shown).

[0061] When a user selects a prediction model, the user terminal device 20 acquires, for example, the name of the prediction model input by the user as the result of the selection of the prediction model. Then, the user terminal device 20 outputs the input name of the prediction model to the state prediction system 10.

[0062] For example, a smartphone, a tablet computer, a notebook computer, or a desktop computer is used as the user terminal device 20. The terminal device used as the user terminal device 20 is not limited to the above examples.

[0063] The information management server 30 is, for example, a server that stores or manages information about racehorses. The information management server 30 may be a plurality of servers installed according to the content of the information about racehorses. The information about racehorses may be stored in a storage device managed by the information management server 30. The information management server 30 may also store images of racehorses.

[0064] An explanation will be given of the operation of the condition prediction system 10 of the racehorse prediction system when predicting the future condition of a racehorse. Figure 12 is a diagram showing an example of the operation flow when the condition prediction system 10 predicts the future condition of a racehorse.

[0065] The acquisition unit 11 acquires information about a racehorse for which the future state of the racehorse is to be predicted (Step S11). The acquisition unit 11 acquires information about the racehorse from the information management server 30, for example.

[0066] When information about the racehorse is acquired, the prediction unit 12 uses a prediction model that predicts the future state of the racehorse from the information about the racehorse, and predicts the future state of the racehorse from the information about the racehorse acquired by the acquisition unit 11 (step S12).

[0067] When the future state of the racehorse is predicted, the output unit 13 outputs the prediction result and the reason for the prediction (step S13). The output unit 13 outputs the prediction result and the reason for the prediction to, for example, the user terminal device 20.

[0068] The user terminal device 20 receives the prediction result and the reason for the prediction and displays the prediction result and the reason for the prediction on, for example, a display device.

[0069] A description will be given of the operation when generating a prediction model in the state prediction system 10. Fig. 13 is a diagram showing an example of the operation flow when the state prediction system 10 generates a prediction model.

[0070] The acquisition unit 11 acquires information about the racehorse and the future state of the racehorse (step S21). Upon acquiring the information about the racehorse and the future state of the racehorse, the generation unit 14 learns the relationship between the information about the racehorse and the future state of the racehorse, and generates a prediction model that predicts the future state of the racehorse from the information about the racehorse (step S22). Upon generating the prediction model, the generation unit 14 stores the generated prediction model in the storage unit 15 (step S23).

[0071] The condition prediction system 10 of the racehorse prediction system of this embodiment acquires information about racehorses and predicts the future condition of the racehorse using a prediction model. The condition prediction system 10 then outputs the prediction results and the reason for the prediction to, for example, a user terminal device 20. By outputting the prediction results of the racehorse's future condition along with the reason for the prediction, people who use the prediction results can easily interpret the prediction results of the racehorse's future condition. Therefore, by using the condition prediction system 10, it is possible to easily interpret the prediction results of the racehorse's future condition.

[0072] When outputting information regarding the income and expenditure of a racehorse, the condition prediction system 10 can output information that can be used as a reference by people using the prediction results when considering the profitability of the racehorse, for example, by showing the difference between the auction price and maintenance costs and the prize money won as income and expenditure. Also, when outputting information regarding the income and expenditure of a racehorse as a graph, the condition prediction system 10 can output the information regarding the income and expenditure that is the prediction result in a format that is visually easy for users to understand.

[0073] When multiple prediction models are used, the condition prediction system 10 can use a prediction model according to an item that is important to the person using the prediction results, and output the prediction result according to the item that is important to the person using the prediction results, along with the reason for the prediction. Also, when a prediction model according to the age of the racehorse is used, the condition prediction system 10 can output, for example, an appropriate prediction result according to the age of the preliminary racehorse, and the reason for the prediction.

[0074] When outputting reference information together with the prediction result, the state prediction system 10 outputs the prediction result and the reason for the prediction together with the reference information, so that a person using the prediction result can refer to the reason for the prediction and the reference information and more easily interpret the reason for the prediction.

[0075] (Second embodiment) A second embodiment of the present invention will be described in detail with reference to the drawings. Fig. 14 is a diagram showing an example of the configuration of a state prediction system 100 according to this embodiment. The state prediction system 100 includes an acquisition unit 101, a prediction unit 102, and an output unit 103.

[0076] The acquisition unit 101 acquires information about racehorses. The prediction unit 102 predicts the future state of the racehorse from the acquired information about the racehorse using a prediction model that predicts the future state of the racehorse from the information about the racehorse. The output unit 103 outputs the prediction result and the reason for the prediction.

[0077] Here, the acquisition unit 11 of the first embodiment is an example of the acquisition unit 101. The acquisition unit 101 is also an aspect of acquisition means. The prediction unit 12 of the first embodiment is an example of the prediction unit 102. The prediction unit 102 is also an aspect of prediction means. The output unit 13 of the first embodiment is an example of the output unit 103. The output unit 103 is also an aspect of output means.

[0078] A description will be given of the operation of the state prediction system 100. Fig. 15 is a diagram showing an example of the operation flow of the state prediction system 100.

[0079] The acquisition unit 101 acquires information about a racehorse (step S101). Once the information about the racehorse has been acquired, the prediction unit 102 predicts the future state of the racehorse from the acquired information about the racehorse using a prediction model that predicts the future state of the racehorse from the information about the racehorse (step S102). Once the future state of the racehorse has been predicted, the output unit 103 outputs the prediction result and the reason for the prediction (step S103).

[0080] The condition prediction system 100 of this embodiment predicts the future condition of a racehorse using a prediction model. The condition prediction system 10 then outputs the prediction result of the racehorse's future condition and the reason for the prediction. As a result, the condition prediction system 10 makes it easy to interpret the prediction result of the racehorse's future condition.

[0081] Each process in the state prediction system 10 of the first embodiment and the state prediction system 100 of the second embodiment can be realized by executing a computer program on a computer. Fig. 16 shows an example of the configuration of a computer 200 that executes a computer program that performs each process in the state prediction system 10 of the first embodiment and the state prediction system 100 of the second embodiment. The computer 200 includes a CPU (Central Processing Unit) 201, a memory 202, a storage device 203, an input / output I / F (Interface) 204, and a communication I / F 205.

[0082] The CPU 201 reads and executes computer programs for performing each process from the storage device 203. The CPU 201 may be configured by a combination of multiple CPUs. Furthermore, the CPU 201 may be configured by a combination of a CPU and another type of processor. For example, the CPU 201 may be configured by a combination of a CPU and a graphics processing unit (GPU). The memory 202 is configured by a dynamic random access memory (DRAM) or the like, and temporarily stores the computer programs executed by the CPU 201 and data being processed. The storage device 203 stores the computer programs executed by the CPU 201. The storage device 203 is configured by, for example, a non-volatile semiconductor storage device. Other storage devices such as a hard disk drive may also be used for the storage device 203. The input / output I / F 204 is an interface that receives input from an operator and outputs display data, etc. The communication I / F 205 is an interface that transmits and receives data between the user terminal device 20 and the information management server 30. Furthermore, the user terminal device 20 and the information management server 30 may also have a similar configuration.

[0083] The computer program used to execute each process can also be distributed by storing it on a computer-readable recording medium that non-temporarily records program data. Examples of recording media that can be used include magnetic tapes for recording data and magnetic disks such as hard disks. Optical disks such as CD-ROMs (Compact Disc Read Only Memory) can also be used as recording media. Non-volatile semiconductor storage devices can also be used as recording media.

[0084] The present invention has been described above using the above-described embodiment as an example. However, the present invention is not limited to the above-described embodiment. In other words, the present invention can be applied in various aspects that can be understood by a person skilled in the art within the scope of the present invention. [Explanation of symbols]

[0085] 10. State Prediction System 11 Acquisition Department 12 Prediction Department 13 Output section 14 Generation part 15 Storage section 20 User terminal device 30 Information Management Server 100 State Prediction System 101 Acquisition Department 102 Prediction Department 103 Output section 200 computers 201 CPU 202 memory 203 Storage device 204 Input / Output Interface 205 Communication I / F

Claims

1. An acquisition means for acquiring information about a racehorse, including at least the racehorse's biological information and breeding history; a prediction means for predicting the auction price of a racehorse from the acquired information about the racehorse using a prediction model that predicts the auction price of the racehorse from information about the racehorse, and extracting a reason for the prediction, which is information showing the basis for the prediction result, based on the influence of the auction price on the prediction result; an output means for outputting the auction price prediction result and the reason for the prediction; A state prediction system comprising:

2. the prediction means extracts the prediction reason based on a case classification that has a greater influence on the result of the auction price prediction in the prediction model using a decision tree than other case classifications; The condition prediction system according to claim 1 .

3. the prediction means further predicts the maintenance costs of the racehorse for which the auction price has been predicted and the prize money to be won, and predicts future income and expenditure based on the predicted auction price, maintenance costs, and prize money; The state prediction system according to claim 1 or 2.

4. the prediction means predicts the auction price using a prediction model according to the age of the racehorse to be predicted; The condition prediction system according to any one of claims 1 to 3.

5. the output means outputs information about the parent horse of the racehorse to be predicted when the age of the racehorse to be predicted is below a standard. The condition prediction system according to any one of claims 1 to 4.

6. the output means outputs performance data of racehorses having attributes similar to those of the racehorse to be predicted. The state prediction system according to any one of claims 1 to 5.

7. The information about the racehorse further includes information about the parent horse. The condition prediction system according to any one of claims 1 to 6.

8. further comprising a generation means for learning the relationship between information about racehorses and the auction prices of racehorses, and generating a prediction model for predicting the auction prices of racehorses from information about the racehorses that are the subject of prediction; The condition prediction system according to any one of claims 1 to 7.

9. A computer comprising: Acquire information about the racehorse, including at least the racehorse's biological information and breeding history; using a prediction model that predicts the auction price of a racehorse from information about the racehorse, predicting the auction price of the racehorse from the acquired information about the racehorse, and extracting a reason for the prediction, which is information that indicates the basis for the prediction result, based on the influence of the auction price on the prediction result; outputting the auction price prediction result and the reason for the prediction; State prediction methods.

10. A process for acquiring information about a racehorse, including at least biological information and breeding history of the racehorse; a process of predicting the auction price of a racehorse from the acquired information about the racehorse using a prediction model that predicts the auction price of a racehorse from information about the racehorse, and extracting a reason for the prediction, which is information that indicates the basis of the prediction result based on the influence of the auction price on the prediction result; a process of outputting the auction price prediction result and the reason for the prediction; A state prediction program that causes a computer to execute the above.

Images