Prediction system, prediction method, and prediction program

Abstract

This prediction system comprises an acquisition unit, a prediction unit, and an output unit. The acquisition unit acquires information relating to a race for which the race arrival order in a public competition is to be predicted. The prediction unit uses a prediction model for predicting the race arrival order from the information relating to the race to predict the race arrival order from the information relating to the race. The output unit outputs prediction results and prediction reasons.

Description

[Technical Field]

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

[0002] In publicly managed sports games, many factors, for example, regarding the race conditions and the condition of the participating athletes, can affect the outcome of a race. While the influence of many factors makes predicting the outcome of a race difficult, this difficulty can also make predicting the outcome of a race one of the enjoyments for enthusiasts. However, for example, beginners may have difficulty knowing which items of information about the race to focus on when predicting the outcome of a race. Therefore, it is desirable to have a system that can provide information related to predicting the finishing order of a race.

[0003] The information processing device of Patent Document 1 predicts race results using a learning model generated based on data relating to the race bodies and the like in past races and the race results.

[0004] The information processing system in Patent Document 2 compiles the reasons for predictions made by multiple people when predicting the results of races in publicly managed racing events, and displays the results on a display device. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 6857776 [Patent Document 2] Japanese Patent Application Laid-Open No. 2016-157381 Summary of the Invention [Problem to be solved by the invention]

[0006] The information processing devices of Patent Documents 1 and 2 may have difficulty in properly presenting the basis for predicting the finishing order of a race.

[0007] In order to solve the above problem, an object of the present invention is to provide a prediction system etc. that can easily interpret the results of predicting the finishing order of a race. [Means for solving the problem]

[0008] In order to solve the above problems, the prediction system of the present invention comprises an acquisition means for acquiring information about a race in a publicly managed competition for which the finishing order of the race is to be predicted, a prediction means for predicting the finishing order of the race from the acquired information about the race using a prediction model that predicts the finishing order of the race from the information about the race, and an output means for outputting the result of the prediction and the reason for the prediction.

[0009] The prediction method of the present invention obtains information about a race in a publicly managed race for which the finishing order is to be predicted, uses a prediction model that predicts the finishing order of the race from the information about the race, predicts the finishing order of the race from the obtained information about the race, and outputs the prediction result and the reason for the prediction.

[0010] 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 race in a publicly managed competition that is the subject of a prediction of the finishing order of the race; a process of predicting the finishing order of the race from the acquired information about the race using a prediction model that predicts the finishing order of the race from the information about the race; and a process of outputting the results of the prediction and the reasons for the prediction. [Effects of the Invention]

[0011] According to the present invention, it is possible to easily interpret the results of predicting the finishing order of a race. [Brief explanation of the drawings]

[0012] [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 illustrating an example of an operation flow of the prediction system according to the first exemplary embodiment of the present invention. [Figure 10] 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 11] 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 12] 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 13] FIG. 10 is a diagram illustrating an example of the configuration of another embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0013] 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 race result prediction system. As an example, the race result prediction system includes a prediction system 10, a user terminal device 20, and an information management server 30. The prediction system 10 is connected to the user terminal device 20 via a network. The prediction system 10 is also connected to the information management server 30 via the network.

[0014] The prediction system 10 is a system for predicting the results of a publicly managed sporting event. The publicly managed sporting event may be, for example, horse racing. The publicly managed sporting event may also be bicycle racing, boat racing, or auto racing. Examples of publicly managed sporting events are not limited to the above, and any type of sport may be used as long as it is a sport hosted by a public institution as a gambling event. The prediction system 10 predicts the finishing order of a race using, for example, a prediction model that predicts the finishing order of a race based on information about the race. The prediction system 10 then outputs the prediction result and the reason for the prediction. The reason for the prediction is, for example, information used as the basis for the prediction model's prediction of the finishing order of a race. The reason for the prediction is, for example, an item of the information about the race that has a greater influence on the predicted result of the finishing order than other items when the prediction model predicts the finishing order of a race. The reason for the prediction may also be an item of the information about the race that has a degree of influence on the predicted result of the finishing order of a race that is equal to or greater than a preset standard when the prediction model predicts the finishing order of a race. The prediction model is, for example, a trained model generated using a machine learning algorithm. The prediction system 10, for example, learns the relationship between information about races and the finishing order of races in past races, and generates a prediction model that predicts the finishing order of races from the information about the races. The prediction model may be a learning model generated outside the prediction system 10. The prediction model will be described later.

[0015] The user terminal device 20 is, for example, a terminal device carried by a person who uses the prediction results of the prediction system 10. A person who uses the prediction results is, for example, a person who purchases betting tickets for a race. A person who uses the prediction results may be a person in charge of devising race lineups. A person who uses the prediction results may also be a reporter or commentator. A person who uses the prediction results is not limited to the above examples.

[0016] The information management server 30 is, for example, a server that holds information about races of publicly managed sports games. Information about the races is, for example, the conditions of the race and the attributes of the sports bodies that will compete in the race. A sports body is an entity that participates in a race. The attributes of a sports body are information about each sports body that participates in the race. If the publicly managed sports game is horse racing, the sports body is a horse. If the publicly managed sports game is horse racing, the attributes of a sports body also include information about the jockey. If the publicly managed sports game is bicycle racing, boat racing, or auto racing, the sports body is a runner. The attributes of a sports body may also include information about bicycles, boats, or motorcycles. Information about the races is not limited to the above examples.

[0017] The prediction system 10 acquires information about a race from, for example, the information management server 30. The prediction system 10 then inputs the information about the race acquired from the information management server 30 and predicts the race result using a prediction model. After predicting the race result, the prediction system 10 outputs the prediction result and the reason for the prediction to the user terminal device 20.

[0018] The prediction system 10 may acquire information about the race from a plurality of information management servers 30. The prediction system 10 may also acquire information about the race from the user terminal device 20.

[0019] The prediction system 10 may output the prediction result and the reason for the prediction to multiple user terminal devices 20. For example, the 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.

[0020] The following describes the configuration of the prediction system 10. Fig. 2 is a diagram showing an example of the configuration of the prediction system 10. The prediction system 10 includes an acquisition unit 11, a prediction unit 12, an output unit 13, a model generation unit 14, and a storage unit 15.

[0021] The acquisition unit 11 acquires information about races of publicly managed racing events. The information about the race is, for example, information that may relate to the finishing order of the race. The acquisition unit 11 acquires, as information about the race, for example, race conditions and attributes of the racing objects.

[0022] When the publicly managed competition is horse racing, the race conditions include, for example, information about the racecourse. The race conditions may also include race setting conditions and conditions that participating horses must meet. The race conditions are, for example, at least one of the following: distance, type of track, conditions for participating horses, weight, race rating, racecourse, weather, track condition, number of participating horses, and running direction. The type of track is, for example, turf, dirt, or hurdles. The conditions for participating horses are entry conditions stipulated by, for example, the age and gender of the horses. The track condition is, for example, information indicating the moisture content of the track. The running direction is, for example, information indicating whether the race will be run counterclockwise or clockwise. When the publicly managed competition is horse racing, the race conditions are not limited to the above examples.

[0023] When the public sport is horse racing, the attributes of the competition are the attributes of the participating horses. The attributes of the participating horses are information about each participating horse. The attributes of the participating horses are, for example, at least one of lane number, gate number, odds, age, sex, weight, weight change, blood data, muscle mass, training status, health condition, rest history, race participation history, weight carried, running style, track record, sire, dam, owner, stable, trainer, and breeder. The lane number may be the horse number. The training status is, for example, the time and time change for each distance during training. The running style is set, for example, by classification as a front-runner, leading horse, sprinter, or trailing horse. The attributes of the participating horses may include the track records of the sire and dam. Track records are, for example, the race conditions in past races, the attributes of the participating horses at the time of the race, prize money won, and race development. Race development is, for example, positioning and winning margin. For example, the positioning is the ranking and time in each section when all sections of the race are divided into predetermined distances. The margin of victory is, for example, the time difference between a horse that is ranked higher or lower than a horse that is ranked lower. The attributes of the participating horses are not limited to the above examples.

[0024] When the prediction model predicts the race results using information on the paddock, the acquisition unit 11 may acquire information on the paddock of the participating horses as attributes of the participating horses. The information on the paddock of the participating horses is, for example, one or more of the gait of the participating horses, the condition of their body, and whether or not they are excited. The gait is, for example, the length of the stride and the walking speed of the participating horses. The body is, for example, the coat of the participating horses, the condition of their muscles, and whether or not they are sweating. Whether or not they are excited indicates, for example, whether or not they are calm or excited. The information on the paddock of the participating horses is not limited to the above examples.

[0025] The acquisition unit 11 acquires paddock information for the participating horses, for example, from a server that detects the condition of the participating horses from images of the paddock taken by image recognition processing. The acquisition unit 11 may also acquire evaluation results from a person who evaluates the condition of the participating horses in the paddock. The acquisition unit 11 may also acquire paddock information for the participating horses, as determined by a person who purchases a betting ticket, from the user terminal device 20. When acquiring paddock information for the participating horses from the user terminal device 20, the paddock information for the participating horses is, for example, input into the user terminal device 20 by a person who purchases a betting ticket.

[0026] When the publicly managed sport is Keirin, the race conditions are, for example, at least one of the racecourse, race distance, and weather. Furthermore, the attributes of the racers are at least one of the riders' height, weight, age, running style, odds, and track record. However, examples of the race conditions and attributes of the racers when the publicly managed sport is Keirin are not limited to the above.

[0027] When the publicly managed sport is boat racing, the race conditions are, for example, at least one of the racecourse, race distance, and weather. Furthermore, the attributes of the racers are at least one of the racers' height, weight, age, rank, odds, and race record. However, examples of the race conditions and attributes of the racers when the publicly managed sport is boat racing are not limited to the above.

[0028] When the publicly managed sport is auto racing, the race conditions are, for example, at least one of the racecourse, the presence or absence of handicaps, and the weather. Furthermore, the attributes of the racers are at least one of the riders' height, weight, age, affiliation, class, odds, and race record. The attributes of the racers may also include start exhibition information. When the publicly managed sport is auto racing, examples of the race conditions and the attributes of the racers are not limited to those mentioned above.

[0029] When multiple prediction models are used, the acquiring unit 11 may acquire a selection result of a prediction model from the user terminal device 20. The selection result of a prediction model may be, for example, a selection of a prediction model input to the user terminal device 20 by an operation of a person who uses the prediction results, acquired from the user terminal device 20. The acquiring unit 11 may also acquire a selection of display items input to the user terminal device 20 by an operation of a person who uses the prediction results, from the user terminal device 20.

[0030] When the prediction system 10 generates a prediction model, the acquisition unit 11 may acquire the race conditions, the attributes of the athletes, and the race results as training data for generating the prediction model. Furthermore, when the prediction model to be generated uses the past track records of the athletes as input data, the acquisition unit 11 may acquire the past track records of the athletes. The acquisition unit 11 stores the acquired race conditions, the attributes of the athletes, and the race results in the storage unit 15, for example.

[0031] The prediction unit 12 predicts the finishing order of a race from the acquired information about the race using a prediction model that predicts the finishing order of a race from information about the race. The prediction unit 12 also extracts the reason why the prediction model predicted the finishing order of the race as the reason for the prediction. For example, the prediction unit 12 obtains parameters used when the prediction model predicted the finishing order of the race, and extracts the reason for the prediction from parameters that contribute greatly to the prediction of the finishing order.

[0032] The prediction unit 12 may predict the finishing order of a race using a prediction model according to the timing of predicting the finishing order of the race. For example, the prediction unit 12 may predict the finishing order of a race using different prediction models up until the day before the race and on the day of the race.

[0033] When the publicly managed sporting event is horse racing, the prediction unit 12 may make predictions using different prediction models up until the paddock start time and after the paddock start time. For example, the prediction unit 12 predicts the finishing order of the race using a prediction model that does not use paddock information about the participating horses as input until the paddock start time. Then, after the paddock start time, the prediction unit 12 predicts the finishing order of the race using a prediction model that uses paddock information about the participating horses as input. Furthermore, whether or not to use paddock information in the prediction may be selected by the person using the prediction results. In this case, the prediction unit 12 predicts the finishing order of the race using a prediction model that corresponds to the selection.

[0034] The prediction unit 12 may predict the race development using a prediction model that predicts the race development. For example, when the race is divided into predetermined distances, the prediction unit 12 predicts the ranking for each section. Then, the prediction unit 12 sets the ranking for each section and the finishing order at the finish line as the prediction results.

[0035] The prediction unit 12 may predict the finishing order of a race using a prediction model according to the attributes of a person who will use the prediction results. The attributes of a person who will use the prediction results may be, for example, a beginner, intermediate, or advanced player. The attributes of a person who will use the prediction results may also be a betting ticket purchase history, a budget, or a betting ticket payout history. The prediction unit 12 may predict the finishing order of a race using a prediction model generated for each item that is important to the person who will use the prediction results. For example, when making a prediction for a person who places importance on the race development, the prediction unit 12 predicts the finishing order of the race using information related to the race development as input. When the publicly managed competition is horse racing, the prediction unit 12 predicts the finishing order of the race using, for example, a prediction model that includes the running style of the participating horses and their rankings by distance in past races as input. Furthermore, the prediction unit 12 may predict the finishing order of a race using a prediction model that includes the racing record of the sire and the racing record of the dam as input for a person who places importance on the pedigree of the participating horses.

[0036] The output unit 13 outputs the predicted result of the finishing order of the race and the reason for the prediction. The output unit 13 outputs the predicted result of the finishing order of the race and the reason for the prediction, for example, to the user terminal device 20. The output unit 13 may output the predicted result of the finishing order of the race and the reason for the prediction to a display device (not shown) connected to the prediction system 10. The output unit 13 may also output the predicted result of the finishing order of the race and the reason for the prediction to a server that distributes the predicted results of the race.

[0037] The output unit 13 outputs the reason for the prediction for each competing body, for example. The output unit 13 may output the reason for the prediction for all predicted finishing orders in one race. The output unit 13 may, for example, output items that have a high degree of contribution to the predicted result for many competing bodies among the competing bodies participating in the race. Furthermore, the output unit 13 may weight the items according to the finishing order in the race and output the items that have a high degree of contribution to the predicted result.

[0038] The output unit 13 may output, together with the prediction results, information on items of information about the race that a predetermined person considers important when predicting the finishing order of a race, as reference information. The predetermined person may be, for example, a person who uses the prediction results, a commentator, or an expert. The predetermined person may be other than the above. The items that a predetermined person considers important when predicting the finishing order of a race are, for example, items that the predetermined person considers to have a high frequency of affecting the race result. For example, if the predetermined person considers that the race result is often determined by pedigree and running style among the information about the race, the predetermined person may consider information related to pedigree and running style. The output unit 13 may output, for example, information on items that a person who uses the prediction results considers important when predicting the finishing order of a race, by adding it to the prediction results. The items that a predetermined person considers important when predicting the finishing order of a race may be set by a prediction expert when generating a prediction model. Furthermore, when outputting information on items that a predetermined person considers important when predicting the finishing order of a race, the output unit 13 may output data highlighting items that correspond to the reason for the prediction. The output unit 13 may output, as reference information, an item selected by a person who uses the prediction results from among the information about the race. The output unit 13 may output data that highlights an item selected by a person who uses the prediction results from among the reference information. The highlighting is performed by, for example, changing at least one of the color, font size, font thickness, and decoration around the font from other items.

[0039] When the publicly managed sporting event is horse racing, the output unit 13 outputs, for example, at least one of the following items as reference information: weight, running style, sire, dam, trainer, and track record. Furthermore, when there is an item among the items of reference information that corresponds to the reason for the prediction, the output unit 13 may output data that highlights the item that corresponds to the reason for the prediction.

[0040] The output unit 13 may output, as the reason for the prediction, an item that is a negative factor for the prediction result. A negative factor is an item that has a large influence on the prediction of a lower finishing order among items that have a large influence on the result of the prediction of the finishing order. A large influence means, for example, that when a certain item is changed, the result of the prediction of the finishing order changes more than other items.

[0041] In the case of horse racing, for example, if a horse suited to short distances enters a race with a long distance, the race distance is extracted as a negative factor. In addition, for example, race history, health condition, changes in time during training, or changes in weight may be extracted as negative factors.

[0042] 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 race that has a high impact on the prediction of the finishing order of the race. For example, the relationship between the information about the race that has a high impact on the prediction of the finishing order of the race and the sentence indicating the reason for the prediction is set in advance. In the case where the publicly managed competition is horse racing and the reason for the prediction is distance, the output unit 13 may output, for example, a sentence such as "This horse is good at long distances, so it is recommended" as the reason for the prediction.

[0043] When the prediction unit 12 predicts the race development, the output unit 13 may output the results of the prediction of the race development. The output unit 13 may, for example, output a display screen that displays the ranking for each section on top of a plan view of the racecourse.

[0044] The output unit 13 may output an image of the race object. The output unit 13 may also output an image of a past race whose result is similar to the predicted result.

[0045] The output unit 13 may output the prediction result and the reason for the prediction superimposed on an image of the competing body participating in the race. Alternatively, the output unit 13 may output the prediction result and the reason for the prediction superimposed on an image of the competing body participating in the race. Alternatively, the output unit 13 may output the prediction result and the reason for the prediction superimposed on an image of a past race whose result is similar to the predicted result.

[0046] If there is a difference between information about a past race and information about the race to be predicted, the output unit 13 may output the content of that difference. For example, the output unit 13 outputs the content of the difference between information about a past race and information about the race to be predicted, for an item of information about the race that, if changed, would change the finishing order. If the publicly managed competition is horse racing, the output unit 13 outputs, for example, the difference between the weight of a racehorse in a past race and the weight of a racehorse in the race to be predicted as the increase or decrease in horse weight. The output unit 13 may also output the difference between the training time at the time of the past race and the training time at the time of prediction.

[0047] When the publicly managed sporting event is a horse race, the output unit 13 may output an image of the participating horses in the paddock. The output unit 13 may also output the prediction result and the reason for the prediction superimposed on the image of the participating horses in the paddock.

[0048] The output unit 13 may output an image of a past race of the participating horse. The output unit 13 may output the prediction result and the reason for the prediction superimposed on the image of the participating horse's past race. Furthermore, the output unit 13 may output an image of the sire, dam, sibling, or horse with similar attributes instead of the image of the participating horse.

[0049] The output unit 13 may output only the reason for the prediction out of the results of the prediction of the finishing order of the race and the reasons for the prediction. For example, if a person using the prediction results of the prediction system 10 wishes to refer only to the reasons for the prediction and does not wish to refer to the results of the prediction of the finishing order of the race, the output unit 13 outputs only the reason for the prediction out of the results of the prediction of the finishing order of the race and the reasons for the prediction. The setting to output only the reason for the prediction is performed, for example, by an operation of the person using the prediction results.

[0050] The output unit 13 may output the above-mentioned information together with the prediction result and the reason for the prediction. Alternatively, the output unit 13 may output the above-mentioned information together with either the prediction result or the reason for the prediction.

[0051] FIG. 3 shows an example of a display screen showing the results of a prediction when the finishing order of a race is predicted when the publicly managed sport is horse racing. In the example display screen of FIG. 3, the racecourse name, race number, race distance, and course type are displayed at the top of the screen. In the example display screen of FIG. 3, the finishing order indicates the finishing order of the race in the predicted results. The lane indicates the lane number into which the participating horses will enter at the start. The horse name indicates the name of the participating horse. Furthermore, the reason for the prediction indicates the item of the reason for the prediction that the prediction model outputs together with the prediction result. The reason for the prediction may be multiple items.

[0052] FIG. 4 shows an example of a display screen in which negative factors are further displayed as reasons for the prediction in the example display screen of FIG. 3. In the example display screen of FIG. 4, positive factors indicate positive factors. Positive factors are items that have a large influence on the prediction of a high finishing order among items that have a large influence on the result of the prediction of the finishing order. In the example display screen of FIG. 4, negative factors are shown as minus factors. Negative factors are items that have a large influence on the prediction of a low finishing order among items that have a large influence on the result of the prediction of the finishing order.

[0053] FIG. 5 shows an example of a display screen in addition to the example of the display screen in FIG. 4, which further displays reference information. In the example of the display screen in FIG. 5, information about racehorse B is displayed as reference information in the right frame. In the example of the display screen in FIG. 5, the horse's age, stable, trainer, pedigree, weight, and race record are displayed as reference information. The items displayed as reference information are not limited to those mentioned above. Furthermore, in the example of the display screen in FIG. 5, 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.

[0054] FIG. 6 shows an example of a display screen that outputs images of the participating horses in the example display screen of FIG. 5. In the example display screen of FIG. 6, images of the participating horses are displayed on the left side of the lower row. When a participating horse is selected in the predicted finishing order column, the image of the selected participating horse may be displayed in the image display area. Furthermore, instead of the image of the participating horse, an image of the participating horse's parent horse may be displayed. Furthermore, as the image of the participating horse, footage from a past race or training may be displayed. Images of the participating horses are obtained, for example, from the information management server 30.

[0055] FIG. 7 shows an example of a display screen that outputs images of the participating horses in the paddock in the example display screen of FIG. 5. In the example display screen of FIG. 7, images of the participating horses in the paddock are displayed on the left side of the lower row. In the example display screen of FIG. 7, information indicating the condition of the participating horses is superimposed on the image of the participating horses in the paddock. In the example display screen of FIG. 7, information indicating the condition of the participating horses is displayed, such as that the coat is in good condition. When one of the participating horses is selected in the predicted finishing order column, the image of the selected participating horse in the paddock may be displayed in the area where the paddock video is displayed.

[0056] FIG. 8 shows an example of a display screen that outputs images of participating horses in the paddock and reference information. In the example of the display screen in FIG. 8, images of participating horses in the paddock are displayed in the paddock video section. In the example of the display screen in FIG. 8, the predicted ranking, condition, lane number, horse name, jockey name, superimposed weight, and weight change amount for the displayed participating horse are superimposed on the image of the paddock video. In the example of the display screen in FIG. 8, an image of a selected participating horse and reference information may be displayed on an image displaying the entire paddock.

[0057] When generating a prediction model in the prediction system 10, the model generation unit 14 generates a prediction model that predicts the finishing order of a race from information about the race. The model generation unit 14 learns, for example, the relationship between information about the race and the finishing order of races held in the past, and generates a prediction model that predicts the finishing order of a race from the information about the race.

[0058] The model 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 model generation unit 14 performs case classification using decision tree rules with information about the race as input data and the race's finishing order as ground truth data. The model generation unit 14 then generates a learning model that predicts the race's finishing order using a linear model that combines different explanatory variables for each case. The model 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 type of learning model generation method is also called heterogeneous mixture learning because it combines prediction models with different combinations of explanatory variables. Generating a prediction model using heterogeneous mixture learning makes it possible to explain the results of race finishing order predictions using case classification conditions that have a strong impact 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.

[0059] The learning algorithm used in the machine learning to generate the prediction model is not limited to the above example. For example, the model generation unit 14 may generate a learning model that predicts the finishing order of a race from information about the race by deep learning using a neural network. When generating such a learning model, the model generation unit 14, for example, varies the data of each item and generates a prediction model that extracts items that have a large influence on the finishing order of the race as the reason for the prediction based on changes in the finishing order of the race. Then, the model generation unit 14 varies the data of each item and extracts items that have a large influence on the finishing order of the race as the reason for the prediction.

[0060] When the prediction unit 12 predicts the race development, the model generation unit 14 may generate a prediction model that predicts the race development from information about the race. When generating a prediction model that predicts the race development, the prediction unit 12 generates the prediction model using, for example, information about the race that includes at least one of the rankings or times for each section in past races as learning data.

[0061] The storage unit 15 stores, for example, a prediction model. When multiple prediction models are used, the storage unit 15 stores multiple prediction models. When the prediction system 10 generates a prediction model, the storage unit 15 may store data relating to past races and the finishing order of the races. When reference information is added to the prediction results, the storage 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 storage unit 15.

[0062] The user terminal device 20 acquires the prediction result and the reason for the prediction from the 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).

[0063] 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's operation. Then, the user terminal device 20 outputs the input name of the prediction model to the prediction system 10.

[0064] 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.

[0065] The information management server 30 is, for example, a server that stores or manages information related to the race. The information management server 30 may be a plurality of servers installed according to the content of the information related to the race. The information related to the race may be stored in a storage device managed by the information management server 30. The information management server 30 may also store images of the competing bodies.

[0066] The following describes the operation of the race result prediction system 10 when predicting the finishing order of a race. Fig. 9 is a diagram showing an example of the operation flow when the prediction system 10 predicts the finishing order of a race.

[0067] The acquisition unit 11 acquires information about a race for which the finishing order of a race in a publicly managed competition is to be predicted (step S11). The acquisition unit 11 acquires information about the race from the information management server 30, for example.

[0068] When the information about the race is acquired, the prediction unit 12 predicts the finishing order of the race from the information about the race acquired by the acquisition unit 11 using a prediction model that predicts the finishing order of the race from the information about the race (step S12).

[0069] When the finishing order of the race 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.

[0070] The following describes the operation of generating a prediction model in the prediction system 10. Fig. 10 is a diagram showing an example of the operation flow when the prediction system 10 generates a prediction model.

[0071] The acquisition unit 11 acquires information about races and race results for races that have been held in the past (step S21). Upon acquiring the information about the races and the race results, the model generation unit 14 learns the relationship between the information about the races and the race results, and generates a prediction model that predicts the finishing order of the race from the information about the race (step S22). Upon generating the prediction model, the model generation unit 14 stores the generated prediction model in the storage unit 15 (step S23).

[0072] The prediction system 10 of the race result prediction system of this embodiment acquires information about races in publicly managed racing games and predicts the finishing order of the race using a prediction model. The prediction system 10 then outputs the prediction results and the reasons for the prediction to, for example, a user terminal device 20. By outputting the reasons for the prediction along with the results of the prediction of the finishing order of the race, people who use the prediction results can easily interpret the results of the prediction of the finishing order of the race. Therefore, by using the prediction system 10, it is possible to easily interpret the results of the prediction of the finishing order of the race.

[0073] When multiple prediction models are used, the prediction system 10 can output the reason for the prediction along with the prediction result that is in line with the preferences of the person who will use the prediction result, for example, by using a prediction model that corresponds to the selection of the person who will use the prediction result. Also, when a prediction model that corresponds to the timing of the prediction is used, the prediction system 10 can output the appropriate prediction result and the reason for the prediction, for example, depending on the timing of the prediction.

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

[0075] (Second embodiment) A second embodiment of the present invention will be described in detail with reference to the drawings. Fig. 11 is a diagram showing an example of the configuration of a prediction system 100 according to this embodiment. The 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 a race in a publicly managed racing game for which the finishing order of the race is to be predicted. The prediction unit 102 predicts the finishing order of the race from the acquired information about the race, using a prediction model that predicts the finishing order of the race from the information about the race. 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] The following describes the operation of the prediction system 100. Fig. 12 is a diagram showing an example of the operation flow of the prediction system 100.

[0079] The acquisition unit 101 acquires information about a race in a publicly managed game for which the finishing order of the race is to be predicted (step S101). Once the information about the race has been acquired, the prediction unit 102 predicts the finishing order of the race from the acquired information about the race using a prediction model that predicts the finishing order of the race from the information about the race (step S102). Once the finishing order of the race has been predicted, the output unit 103 outputs the prediction result and the reason for the prediction (step S103).

[0080] The prediction system 100 of this embodiment uses a prediction model to predict the finishing order of a race in a publicly managed racing game. The prediction system 10 then outputs the results of the prediction of the finishing order of the race and the reasons for the prediction. As a result, the prediction system 10 can easily interpret the results of the prediction of the finishing order of the race.

[0081] Each process in the prediction system 10 of the first embodiment and the prediction system 100 of the second embodiment can be realized by executing a computer program on a computer. Fig. 13 shows an example of the configuration of a computer 200 that executes a computer program that performs each process in the prediction system 10 of the first embodiment and the 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 stored and distributed on a computer-readable recording medium that non-temporarily stores 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] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. [Appendix 1] an acquisition means for acquiring information about a race in which the finishing order of a publicly managed gaming event is to be predicted; a prediction means for predicting the finishing order of a race from the acquired information about the race using a prediction model that predicts the finishing order of the race from information about the race; an output means for outputting the result of the prediction and the reason for the prediction; A prediction system comprising: [Appendix 2] the output means outputs, from the information about the race, information about an item that a predetermined person considers important when predicting the finishing order of the race, by adding the information about the race to the prediction result; 10. The prediction system of claim 1. [Appendix 3] the output means displays at least one of the result of the prediction and the reason for the prediction superimposed on an image of the competing object participating in the race. 3. The prediction system of claim 1 or 2. [Appendix 4] the output means outputs, as the reason for the prediction, items that are negative factors for the result of the prediction. 4. The prediction system of any one of appendixes 1 to 3. [Appendix 5] the output means outputs a difference between information about past races and information about the race to be predicted. 5. The prediction system of any one of appendixes 1 to 4. [Appendix 6] the prediction means predicts the finishing order of the race using a prediction model according to an attribute that utilizes the result of the prediction; 6. The prediction system of any one of appendixes 1 to 5. [Appendix 7] the prediction means predicts the finishing order of the race using a prediction model according to the timing of predicting the finishing order of the race; 7. The prediction system of any one of appendixes 1 to 6. [Appendix 8] The publicly managed gaming event is horse racing, the output means outputs an image of the horses running in the race taken in the paddock or an image of the horses running in a past race; 8. The prediction system of any one of appendixes 1 to 7. [Appendix 9] The publicly managed gaming event is horse racing, When the age of the horse to be predicted is below a standard, the output means outputs at least one of an image of the parent horse of the horse to be entered in the race and information about the parent horse's race. 9. The prediction system of any one of appendixes 1 to 8. [Appendix 10] The publicly managed gaming event is horse racing, The information about the race includes at least one of the following: the condition of the participating horses in the paddock, the age of the participating horses, the sex of the participating horses, the running style of the participating horses, the jockeys riding the participating horses, the weight changes of the participating horses, the pedigree of the participating horses, the weather at the time of the race, the track characteristics at the time of the race, and the race distance. 10. The prediction system of any one of appendixes 1 to 9. [Appendix 11] The system further includes a model generation means for learning the relationship between information about races held in the past and the finishing order of the races, and for generating a prediction model for predicting the finishing order of the races from the information about the races. 11. The prediction system of any one of appendixes 1 to 10. [Appendix 12] Obtaining information about a race in which the finishing order of the race is to be predicted in a publicly managed racing game; predicting the order of finish in a race from the acquired information about the race using a prediction model that predicts the order of finish in a race from information about the race; outputting the result of the prediction and the reason for the prediction; Forecasting methods. [Appendix 13] A process of acquiring information about a race in which the finishing order of a publicly managed racing event is to be predicted; a process of predicting the order of finish in a race from the acquired information about the race using a prediction model that predicts the order of finish in a race from information about the race; A process of outputting the result of the prediction and the reason for the prediction. A non-transitory recording medium for recording a prediction program that causes a computer to execute the above.

[0085] 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]

[0086] 10 Prediction Systems 11 Acquisition Department 12 Prediction Department 13 Output section 14 Model Generation Unit 15 Storage section 20 User terminal device 30 Information Management Server 100 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 race in which the finishing order of a publicly managed gaming event is to be predicted; a prediction means for predicting the finishing order of a race from the acquired information about the race using a prediction model that predicts the finishing order of the race from information about the race; an output means for outputting the result of the prediction and the reason for the prediction, and for outputting an image of the competing body participating in the race with at least one of the result of the prediction and the reason for the prediction superimposed thereon; A prediction system comprising:

2. An acquisition means for acquiring information about a race in which the finishing order of a race in a publicly managed gaming event is to be predicted; a prediction means for predicting the finishing order of a race from the acquired information about the race using a prediction model that predicts the finishing order of the race from information about the race; an output means for outputting the result of the prediction and the reason for the prediction, and outputting the difference in content between information about past races and information about the race to be predicted; A prediction system comprising:

3. An acquisition means for acquiring information about a race in which the finishing order of a race in a publicly managed gaming event is to be predicted; a prediction means for predicting the order of finish in a race from the acquired information about the race using a prediction model corresponding to the attributes of a person who will use the prediction results, out of prediction models for predicting the order of finish in a race from information about the race; an output means for outputting the result of the prediction and the reason for the prediction; A prediction system comprising:

4. An acquisition means for acquiring information about a race in which the finishing order of a race in a publicly managed gaming event is to be predicted; a prediction means for predicting the finishing order of a race from the acquired information about the race using a prediction model corresponding to the timing of predicting the finishing order of the race, among prediction models for predicting the finishing order of the race from information about the race; an output means for outputting the result of the prediction and the reason for the prediction; A prediction system comprising:

5. An acquisition means for acquiring information about a race for which the finishing order of a horse race is to be predicted; a prediction means for predicting the finishing order of a race from the acquired information about the race using a prediction model that predicts the finishing order of the race from information about the race; an output means for outputting the results of the prediction and the reason for the prediction, and outputting images of the horses in the paddock or images of the horses in past races; A prediction system comprising:

6. An acquisition means for acquiring information about a race for which the finishing order of a horse race is to be predicted; a prediction means for predicting the finishing order of a race from the acquired information about the race using a prediction model that predicts the finishing order of the race from information about the race; an output means for outputting the results of the prediction and the reason for the prediction, and for outputting at least one of an image of the parent horse of the horse to be entered in the race or information about the parent horse's race if the horse's age is below a certain standard; A prediction system comprising:

7. the output means outputs, from the information about the race, information about an item that a predetermined person considers important when predicting the finishing order of the race, by adding the information about the race to the prediction result; A prediction system according to any one of claims 1 to 6.

8. the output means displays at least one of the result of the prediction and the reason for the prediction superimposed on an image of the competing object participating in the race. A prediction system according to any one of claims 2 to 6.

9. A computer comprising: Obtaining information about a race in which the finishing order of the race is to be predicted in a publicly managed racing game; predicting the order of finish in a race from the acquired information about the race using a prediction model that predicts the order of finish in a race from information about the race; outputting the result of the prediction and the reason for the prediction, and superimposing at least one of the result of the prediction and the reason for the prediction on an image of the competing body participating in the race; Forecasting methods.

10. A process of acquiring information about a race in which the finishing order of a publicly managed racing event is to be predicted; a process of predicting the order of finish in a race from the acquired information about the race using a prediction model that predicts the order of finish in a race from information about the race; a process of outputting the result of the prediction and the reason for the prediction, and superimposing at least one of the result of the prediction and the reason for the prediction on an image of the competing body participating in the race; A prediction program that causes a computer to execute the following.

Images