WO2021140827A1

WO2021140827A1 - Information processing device, information processing method, and information processing program

Info

Publication number: WO2021140827A1
Application number: PCT/JP2020/046200
Authority: WO
Inventors: 文忠直江
Original assignee: ジャングルＸ株式会社
Priority date: 2020-01-10
Filing date: 2020-12-11
Publication date: 2021-07-15
Also published as: JP6914490B2; JP2021111139A

Abstract

An information processing device 100 in an information processing system 1 comprises, as functions thereof: an attribute information acquisition unit 131 that acquires attribute information pertaining to a user; an event information collection unit 132 that collects state information pertaining to an event and varying over the time of the event; a learning unit 133 that performs machine learning on the basis of the state information pertaining to the event and generates event prediction model information; a prediction unit 134 that predicts the state of the event on the basis of the event prediction model information and dynamic data obtained by monitoring the event in real time; a value calculation unit 135 that calculates, in the state of the event, the value by unit time of the information pertaining to the event in a service provided to the user; and a billing information calculation unit 136 that aggregates the value of the information pertaining to the event.

Description

Information processing equipment, information processing methods and information processing programs

This disclosure relates to an information processing device, an information processing method, and an information processing program that calculate the value of information of an event being held.

There is a billing method called PPV (Pay per view) as a billing method for viewing video content such as movies and live broadcasts of events such as sports competitions and concerts. PPV is a method in which you are charged according to the quantity (number of works and time) of the viewed content when you watch paid content, and you can view the video content via satellite broadcasting or cable TV, or via the Internet. It is used by the providers. PPV is a billing method different from the so-called flat-rate system that allows free viewing within a predetermined period, and is a billing method that is often applied as a target of PPV separately from the flat-rate system for particularly popular content. is there.

PPV is a billing method that allows viewers to charge only for the content they want to watch, and is a billing method that can be expected to generate large profits for content that is in high demand for the provider. Further, in the case of relaying an event such as a sports competition, the profit may be returned to the athlete or team of the sports competition, which is a charging method with great merit for the athlete or team of the sports competition.

Patent Document 1 discloses a content distribution system that distributes video content to an unspecified number of viewers via an IP (Internet Protocol) network. In this system, a request for content requesting distribution is received from a mobile terminal, and the content is distributed. In this system, sports broadcasts and event broadcasts are given as examples of video contents.

Japanese Unexamined Patent Publication No. 2011-109673

By the way, in the case of relaying an event such as a sports competition in real time, it is difficult to determine the value of the sports competition, so in reality, a lot of profits can be expected, and the degree of attention is very high. The current situation is that it is applied only to some high-value events. Also, in the case of sports competitions in which teams play games such as soccer and baseball, popular athletes do not always participate, so for fans of the athlete, the sport depends on whether or not the athlete participates. The value of competition will change significantly. In addition, the value of the match may fluctuate greatly for fans depending on the situation other than the match, such as a league match. Furthermore, some games such as baseball may be canceled depending on the weather, and the value of the sports competition will fluctuate greatly depending on the situation at that time.

A technology that can evaluate the value of such an event such as a sports competition in real time was expected.

Therefore, in this disclosure, an information processing device, an information processing method, and an information processing program capable of calculating the value of event information according to the situation of an event such as a sports competition will be described.

The information processing device according to one aspect of the present disclosure includes an event status collection unit that collects status information of past events that fluctuate with the passage of time in past events, and machine learning based on the collected status information. Based on the learning unit that generates event prediction model information that predicts changes in the current event status, monitors the current event in real time, and the event prediction model information and the current event status. , A predictor that predicts changes in the status of the current event, and a service that provides users with information about the current event in the predicted status of the current event. It is provided with a value calculation unit that calculates the value for each unit time.

The information processing method in one aspect of the present disclosure includes an event status collection step performed by the event status collection unit, which collects status information of past events that fluctuate with the passage of time in past events, and a learning unit. Performs machine learning based on the collected situation information, and the learning step to generate event prediction model information that predicts the change in the situation of the event currently being performed, and the current event performed by the prediction department in real time. In the current event status, which is performed by the value calculation department, and the prediction step that monitors and predicts the change in the current event status based on the event prediction model information and the current event status. It includes a value calculation step of calculating the value of the current event information that fluctuates with the passage of time for each unit time in the service that provides the event information to the user.

In addition, the information processing program in one aspect of the present disclosure is based on an event status collection step that collects status information of past events that fluctuate with the passage of time in past events and the collected status information. Learning steps that perform machine learning to generate event prediction model information that predicts changes in the status of current events, monitor current events in real time, event prediction model information, and current event status. Forecasting steps that predict changes in the status of the current event based on, and for the service that provides information about the current event to the user in the predicted status of the current event, of the current event that fluctuates over time. Have the computer perform the value calculation step of calculating the value of the information for each unit time.

According to the present disclosure, in the past events, machine learning is performed based on the situation information of the event that fluctuates with the passage of time, and the event prediction model information that predicts the change in the situation of the event currently being performed is provided. Generate. Based on this model information and the status of the event being monitored in real time, changes in the status of the event are predicted. Therefore, it is possible to appropriately predict the situation of the event. In addition, the value of the information of the current event, which fluctuates with the passage of time, is calculated for each unit time according to the predicted event situation. This makes it possible to appropriately calculate the value of event information.

It is a functional block block diagram which shows the information processing system 1 which concerns on one Embodiment of this disclosure. It is a functional block block diagram which shows the user terminal 200 of FIG. It is a flowchart which shows the operation of the event prediction model generation processing in the information processing apparatus 100 of FIG. It is a schematic diagram which shows the storage example of the event development DB 122 of FIG. It is a flowchart which shows the operation of the event information value calculation processing in the information processing apparatus 100 of FIG. It is a schematic diagram which shows the screen display example after the service start in step S203 of FIG. It is a graph which shows the example of the increase / decrease of the event value in step S205 of FIG. It is a functional block block diagram which shows the computer 700 which concerns on one Embodiment of this disclosure.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The embodiments described below do not unreasonably limit the contents of the present disclosure described in the claims. Also, not all of the components shown in the embodiments are essential components of the present disclosure.

(Embodiment 1)
<Structure>
FIG. 1 is a functional block configuration diagram showing an information processing system 1 according to the first embodiment of the present disclosure. This information processing system 1 provides information on events being held in real time, for example, relay information of sports competition games and games of shogi and go, and predicts changes in the situation, as an example, not limited to. , A system that calculates the value of the event information for each unit time.

The event information provided by the information processing system 1 includes static data related to events held in real time, such as sports competition games and games of shogi and go, such as past competition data and their information. This is data-based event relay information consisting of aggregated data and dynamic data, for example, real-time live data.

Here, the event relay by data may be displayed as text data on the user terminal of the receiving user, or may be displayed in combination with image data or the like generated from the text data. For example, in the case of a live broadcast of a soccer match, image data (image data imitating a player, which may be represented by dots or symbols) is displayed so that the position of the player can be seen on a screen imitating a soccer field. It is displayed so that the situation of the game can be grasped by letting it.

In addition, the information processing system 1 provides information on such an event and calculates the value of the event information for each unit time in the service provided to the user. Here, the event information provided by the information processing system 1 is a service provided to the terminal used by the user by using a communication means such as the Internet or a public line, and may be a so-called Web service or a telephone. It may be a line or a broadcasting network. Since the situation of sports competition games and games of shogi and go changes from moment to moment, the value of event information per unit time also changes from moment to moment. For example, in a sports game, if an unexpected event occurs (for example, a full-base home run in the case of baseball or a hole-in-one in the case of golf), the value may rise sharply. Therefore, the information processing system 1 calculates the value of the event information for each unit time, which changes from moment to moment. Further, the information processing system 1 accumulates the calculated value and uses it as billing information when the event information is provided by PPV for a fee.

The value of event information for each unit time referred to here is a monetary value, which is a value that is the basis of PPV billing information, but can be used for predetermined benefits, such as product purchases. It may be a point or the like.

The information processing system 1 has an information processing device 100, a user terminal 200, and a network NW. The information processing device 100 and the user terminal 200 are connected to each other via a network NW. The network NW is a communication network for communication, and is not limited to the Internet, an intranet, a LAN (Local Area Network), a WAN (Wide Area Network), a wireless LAN (Wireless LAN: WLAN), and a wireless WAN (Wireless LAN). It is composed of a communication network including Wireless WAN: WWAN), Virtual Private Network (VPN), and the like.

In order to predict the status of an event, the information processing device 100 collects status information of events performed in the past, performs machine learning, generates model information for predicting a change in the status of the event, and monitors it in real time. It is a device that predicts changes in the status of an event based on the status of the event and calculates the value of the information of the event for each unit time. The information processing device 100 is not limited, but is composed of, for example, a computer (desktop, laptop, tablet, etc.) that provides various information including Web services, a device including a server device, and the like. The server device is not limited to a server device that operates independently, and may be a distributed server system or a cloud server that operates in cooperation by communicating via a network NW.

The user terminal 200 is a terminal device used by the user for receiving information on an event provided by the information processing system 1 and presenting (displaying) it to the user. It consists of computers (desktops, laptops, tablets, etc.). In this user terminal 200, an application for receiving the service of the information processing system 1 is installed, or a URL or the like for accessing the information processing device 100 is set, and the user terminal 200 is activated by tapping or double-clicking them. As a result, the service is started.

The information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130 as its functions.

The communication unit 110 is a communication interface for communicating with the user terminal 200 by wire or wirelessly via the network NW, and any communication protocol may be used as long as mutual communication can be executed. The communication unit 110 is not limited, and for example, communication is performed by a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol).

The storage unit 120 stores programs, input data, and the like for executing various control processes and each function in the control unit 130, and is not limited, but as an example, a RAM (RandomAccessMemory) and a ROM (ReadOnly). It is composed of a memory including a memory) and a storage including an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory and the like. Further, the storage unit 120 stores the user DB 121, the event development DB 122, and the event prediction model DB 123. Further, the storage unit 120 temporarily stores the data when communicating with the user terminal 200 and the data generated by each process described later.

The user DB 121 stores identification data that identifies a user who receives event information from the information processing system 1 and attribute information such as the age, gender, and place of residence of the user. The user identification data is information for logging in to the information processing system 1, may be issued by the information processing system 1, may be determined by user input, or may be a user's e-mail address or the like. Good. Further, in the information processing system 1, for example, after obtaining the consent of the user who provides the event information, the user is requested to register as a member, and at that time, the attribute information of the user is acquired. Have them enter their date of birth, gender, and place of residence to calculate their age. This attribute information is used to calculate the value of the event information for each user, as will be described later.

In the event development DB 122, dynamic data regarding the situation that occurred in real time in the event is collected and stored together with the static data. Dynamic data is time-series data that records events that occur in sports competitions, games such as shogi and go, and specifically, sports such as when the game starts and when the game starts and when the free kick occurs. This is textual information that documents live data of events such as competitions. The static data is past competition data related to sports competitions, shogi, and Go games, and aggregated data thereof.

Since the dynamic data stored in the event development DB 122 is the target data for machine learning as described later, text information such as sports competitions, shogi and go games is stored in a structured state. The structured (annotated) state is not a limitation, but as an example, the text information is decomposed into phrase units, and the words contained in the phrase and this phrase are "when", "who (which team)", and " It is a state of being decomposed into an element tag indicating which of the elements such as "where (position in the competition field)", "what was done", and "what kind of result was obtained".

As will be described later, the event prediction model DB 123 stores model information for predicting the event status, which is generated by machine learning based on the dynamic data stored in the event development DB 122. The model information for predicting the situation of the event is not limited, but as an example, when a current event such as a sports competition or a game of shogi or go, for example, in the case of soccer, a free kick or a corner kick occurs, It can be predicted that a goal event may occur in the near future. That is, this model information is model information for predicting an event that will occur in the near future in the event.

The control unit 130 controls the entire operation of the information processing device 100 by executing a program stored in the storage unit 120, and is not limited to, but as an example, a CPU (Central Processing Unit), an MPU ( Equipment including MicroProcessingUnit), GPU (GraphicsProcessingUnit), microprocessor (Microprocessor), processor core (Processorcore), multiprocessor (Multiprocessor), ASIC (Application-Specific IntegratedCircuit), FPGA (Field ProgrammableGateArray) Etc. The control unit 130 includes an attribute information acquisition unit 131, an event information collection unit 132, a learning unit 133, a prediction unit 134, a value calculation unit 135, and a billing information calculation unit 136. The attribute information acquisition unit 131, the event information collection unit 132, the learning unit 133, the prediction unit 134, the value calculation unit 135, and the billing information calculation unit 136 are activated by a program stored in the storage unit 120 to be an information processing device. It is executed at 100.

The attribute information acquisition unit 131 acquires the attribute information of the user who accesses the information processing device 100 from the user terminal 200. The value of the event information to be calculated for each unit time changes depending on the number of users who access the information processing device 100 at that time and receive the distribution of the event information, and the attributes of the users. Therefore, the attribute information is acquired from the user DB 121 for the user who is accessing in real time to acquire the information of the event being performed. For example, when a user wants to watch a sports competition, a game of shogi or go, etc., he / she accesses the information processing device 100 from his / her own user terminal 200, so that the user terminal 200 accesses the information processing device 100. Sometimes authentication is done. At that time, the attribute information acquisition unit 131 acquires the attribute information of the user from the user DB 121.

The attribute information acquisition unit 131 may count up the number of accesses for each attribute stored as temporary storage in the storage unit 120 from the acquired attribute information of the user, and stores the user's access status in the user DB 121. May be good.

The event information collection unit 132 collects status information of past events that fluctuate with the passage of time in past events. Specifically, it monitors the status of events such as sports competitions, shogi, and Go games in real time, and time-series dynamic data on the situations that have occurred, past competition data related to sports competitions, and theirs. Collect static data, which is the aggregated data of. These pieces of information may be obtained by collecting event status information that is monitored and acquired in real time by the prediction unit 134, which will be described later, as past data, or may be acquired from an Internet article or the like. It is desirable that the amount of information on the status of the event to be collected is sufficient for machine learning by the learning unit 133. The acquired event status information is stored in the event expansion DB 122.

The learning unit 133 monitors the event status information collected by the event information collecting unit 132 and stored in the event development DB 122, specifically, the status of events such as sports competitions and games of shogi and go in real time. Based on the dynamic data about the situation that occurred, machine learning is performed to generate event prediction model information that predicts changes in the event situation. As mentioned above, this model information is based on current events such as sports competitions and games of shogi and go, such as free kicks and corner kicks in the case of soccer, which will occur in the near future. For example, it is model information indicating that an event such as a goal is predicted to occur with a certain probability.

In the learning unit 133, for example, machine learning is performed from time-series information of a soccer game, and a pattern such that a different (or the same) event occurs after a certain event occurs is used as information as teacher data, and the machine Do learning. It is desirable that the amount of information on the status of the event to be learned is sufficient for machine learning, but when a sufficient amount of information is not stored in the event expansion DB 122, the fragmentary information is complemented. Sparse modeling, which is an information extraction technique that utilizes the sparseness of information, may be applied to the information. The generated event prediction model information is stored in the event prediction model DB 123.

The prediction unit 134 predicts a change in the event situation based on the dynamic data obtained by monitoring the event in real time and the event prediction model information generated by the learning unit 133 and stored in the event prediction model DB 123. To do. Specifically, the situation of an event such as a sports competition is monitored in real time, and based on the dynamic data regarding the occurrence of the situation, the current event prediction model information stored in the event prediction model DB 123 is used to determine the current state of the sports competition, etc. When an event such as a free kick or a corner kick occurs in the case of soccer, for example, an event that occurs in the near future, such as a goal, is predicted to occur with a certain probability.

For monitoring of events such as sports competitions performed by the prediction unit 134, for example, image data for capturing the situation of sports competition games and games of shogi and go can be directly captured from a camera installed at the game venue or the like, or It may be acquired from a TV broadcast or an Internet video site, and the captured data may be analyzed by image analysis or voice analysis, or ironware strike information that explains the situation of the event, such as an Internet article on a predetermined Web page. May be analyzed. In this case, model information for performing image analysis, voice analysis, and text analysis may be stored in the storage unit 120, but the illustration is omitted.

The value calculation unit 135 accesses the information processing device 100 from the user terminal 200 in the event situation predicted by the prediction unit 134, and provides a service to a user who is watching a sports competition, a game of shogi or go, and the like. In, the value of the information of the event is calculated for each unit time (for example, every minute). Since the value of the event information for each unit time differs depending on the customer group of the user who receives the event information, that is, the attribute of the user, the value calculation unit 135 uses the attribute information acquisition unit 131 to acquire the value of the user. Calculated for each attribute information.

For example, at the time of a goal in a soccer game or a home run in a baseball game, the user watching the game is often immersed in the game, and when such a predetermined action occurs, an event It is thought that the value of this information per unit time will increase or decrease. Also, during half-time in a soccer match or when changing innings in a baseball match, the user watching the match is not very immersive in that match, so check the status of other matches or take a break. It is thought that the value of event information per unit time increases or decreases during such a predetermined time zone. Therefore, the value calculation unit 135 increases or decreases the value of the event information for each unit time when a set predetermined time zone or a predetermined action occurs.

Also, for example, when the match time is almost fixed as in a soccer match, the value of the event information for each unit time is considered to increase or decrease depending on the remaining time of the match. Therefore, the value calculation unit 135 increases or decreases the value of the event information for each unit time by the ratio between the elapsed time of the event and the required time (for example, the match time determined by the match).

The billing information calculation unit 136 accumulates the value of the event information calculated by the value calculation unit 135 for each unit time, and provides the billing information in the service of providing the event information to the user for a fee by PPV. calculate. Since the information processing system 1 provides event information by PPV for a fee, the billing information calculation unit 136 accumulates the time required for the event.

For example, the value of an event may differ depending on the type of event because the degree of attention differs depending on the type of sports competition. In addition, the value of an event may be expected to be high in advance in the case of a very high-profile event such as a tournament final in a sports competition. Therefore, the billing information calculation unit 136 converts the fixed value predetermined for each event type and the fluctuation value calculated based on the popularity of the event to be performed into the cumulative value calculated by the value calculation unit 135. You may add.

FIG. 2 is a functional block configuration diagram showing the user terminal 200 of FIG. The user terminal 200 includes a communication unit 210, a display unit 220, an operation unit 230, a storage unit 240, and a control unit 250.

The communication unit 210 is a communication interface for communicating with the information processing device 100 by wire or wirelessly via the network NW, and any communication protocol may be used as long as mutual communication can be executed. The communication unit 210 is not limited, and for example, communication is performed by a communication protocol such as TCP / IP.

The display unit 220 is a user interface used for displaying the operation content input by the user and the transmission content from the information processing device 100, and is composed of a liquid crystal display or the like. The display unit 220 displays event information provided by the information processing device 100.

The operation unit 230 is a user interface used for the user to input operation instructions, and is composed of a keyboard, a mouse, a touch panel, and the like.

The storage unit 240 stores programs for executing various control processes and each function in the control unit 250, input data, and the like. The storage unit 240 is not limited, and as an example, a memory including a RAM, a ROM, and the like, an HDD, and the like. It is composed of storage including SSD, flash memory and the like. In addition, the storage unit 240 temporarily stores the data that has communicated with the information processing device 100.

The control unit 250 controls the entire operation of the user terminal 200 by executing a program stored in the storage unit 240, and is not limited to, but as an example, a CPU, an MPU, a GPU, a microprocessor, and a processor. It is composed of a core, a multiprocessor, an ASIC, a device including an FPGA, and the like.

<Processing flow>
The processing flow of an example of the information processing method executed by the information processing apparatus 100 of the information processing system 1 will be described. First, the flow of the event prediction model generation process, which is a part of the information processing method, executed by the information processing apparatus 100 will be described with reference to FIG. FIG. 3 is a flowchart showing the operation of the event prediction model generation process in the information processing apparatus 100 of FIG.

As the process of step S101, the event information collecting unit 132 collects the status information of the past events that fluctuate with the passage of time in the past events such as sports competitions, shogi, and go games. .. The acquired event status information is stored in the event expansion DB 122.

FIG. 4 is a schematic diagram showing a storage example of the event development DB 122 of FIG. The event status information collected in step S101 is composed of, for example, static data TX1 and dynamic data TX2 regarding the event as shown in FIG. As shown in FIG. 4, the static data TX1 is information such as the date and time when the sports competition match, which is an example of the event, was held, the opponent team, etc., and other players who participated in the match and the match are performed. It may include weather information and the like at the time of the event.

As shown in FIG. 4, the dynamic data TX2 is time-series data that records events that occur in a sports competition, which is an example of an event, and as described above, “when” and “who (which team)”. , "Where (position on the competition field)", "What did you do", "What kind of result did you get?" In addition, information on the substitution of participating players in the match may be included.

As the process of step S102, the learning unit 133 obtains the event status information collected in step S101 and stored in the event development DB 122, specifically, the status of an event such as a sports competition or a game of shogi or go. Machine learning is performed based on dynamic data about the situation that occurs by monitoring in real time. For example, in the case of soccer, machine learning is performed using information in a pattern such that a different (or the same) event occurs after a certain event occurs from the time-series information of a soccer game as teacher data.

As the process of step S103, the learning unit 133 generates event prediction model information for predicting a change in the event situation as a result of the machine learning performed in step S102. This model information is used to predict, for example, in the case of soccer, if an event such as a free kick or a corner kick occurs in a match, an event that will occur in the near future, such as a goal, will occur with a certain probability. Model information. The generated event prediction model information is stored in the event prediction model DB 123.

Next, the flow of the event information value calculation process, which is a part of the information processing method, will be described with reference to FIG. FIG. 5 is a flowchart showing the operation of the event information value calculation process in the information processing apparatus 100 of FIG. The flowchart shown in FIG. 5 shows an example in which the processes of steps S204 to S205 are performed only once, but events such as sports competitions and games of shogi and go are performed. Meanwhile, the processes of steps S204 to S205 of the flowchart shown in FIG. 5 are usually repeated a plurality of times.

As the process of step S201, the information processing apparatus 100 performs user authentication in order to receive the event information provided by the information processing system 1. Therefore, for example, the user terminal 200 is requested to input the account information and the password by the operation of the user, and the user authentication is performed by collating the registered information based on the input information. If they match, the information processing device 100 is logged in.

As the process of step S202, the attribute information acquisition unit 131 reads the user DB 121 according to the account information input by the user in step S201, and the attribute information of the user is acquired from the user DB 121. For example, in step S202, the number of accesses for each attribute stored as temporary storage in the storage unit 120 is counted up from the acquired attribute information of the user, or the access status of the user is stored in the user DB 121.

As the process of step S203, the information processing device 100 starts providing information on the event by the information processing system 1, specifically, providing status information on an event such as a sports competition, a game of shogi, or a game of Go. ..

FIG. 6 is a schematic diagram showing an example of screen display after the start of the service in step S203 of FIG. When providing the event information, the information processing apparatus 100 may generate image data from the text data which is the event information and display it on the user terminal 200 in combination with the image data FL shown in FIG. The image data FL is, for example, an example in the case of a soccer match, in which the score which is the result of the soccer match is displayed at the upper part of the screen, and the goal scene is displayed as the trajectory of the ball on the screen imitating the soccer field. Is shown.

As the process of step S204, the prediction unit 134 monitors the event in real time and obtains dynamic data, and machine learning is performed in step S102, and the event prediction generated in step S103 and stored in the event prediction model DB 123. Changes in the status of the event are predicted based on the model information. For example, if a current event such as a sports competition, such as a free kick or a corner kick, occurs in the case of soccer, it is predicted that an event that will occur in the near future, such as a goal, will occur with a certain probability. ..

As the process of step S205, the value calculation unit 135 accesses the information processing device 100 from the user terminal 200 in the event situation predicted in step S204, and watches sports competitions, games of shogi and go, and the like. The value of the event information in the service provided to the user for each unit time is calculated. The calculation of the value of the event information performed in step S205 for each unit time is calculated for each user attribute information acquired in step S202.

As the process of step S206, the billing information calculation unit 136 accumulates the value of the event information calculated in step S205 for each unit time, and provides the event information to the user for a fee by PPV. Billing information is calculated. If the match or game has not ended after the process of step S206, the process returns to the process of step S204.

FIG. 7 is a graph showing an example of increase / decrease in event value in step S205 of FIG. The polygonal line L1 shown in FIG. 7 is a graph showing the passage of time of the event value calculated in step S205. For example, at the match start timing T1 shown in FIG. 7, the event value is a predetermined value as shown in the polygonal line L1. It has become. After that, the event value changes with the passage of time, and gradually decreases at the polygonal line L1 shown in FIG. 7.

For example, at the start of a match, the user is likely to be immersed in the match or game, so the event value shows a certain value as shown in FIG. 7, but with the passage of time, the match If the situation becomes stalemate and the immersiveness in the game or game gradually diminishes, it is considered that the user is more likely to look at other information, so the event value gradually decreases. Further, for example, as shown in FIG. 7, when a predetermined action occurs at the timing T2, the event value increases. After that, the increase / decrease in the event value is repeated until the timing T3 at the end of the game, and becomes 0 at the timing T3.

Further, the hatching section S1 shown in FIG. 7 shows the cumulative value of the event value calculated in step S205, and this value becomes the billing information calculated in step S206. As a result, the increased event value as in the timing T2 is reflected in the billing information, the billing information is also increased, and the event value is reflected in the billing information when the event value is provided by PPV for a fee.

<Effect>
As described above, the information processing device and the information processing method according to the present embodiment are used for information on the status of events that have been performed in the past, such as sports competitions, games of shogi and go, and the like, which fluctuate with the passage of time. Perform machine learning based on dynamic data. This machine learning generates event prediction model information that predicts changes in the event situation. Predict changes in the status of events based on dynamic data obtained by monitoring events in real time and event prediction model information. This makes it possible to analyze the situation of the event and make an appropriate prediction.

In addition, in the predicted event situation, the value of the information of the event per unit time (for example, every minute) in the service provided to the user who is watching the sports competition or the game of shogi or go. calculate. At this time, the value of the event information for each unit time is calculated for each user attribute information. This makes it possible to calculate the appropriate event value according to the type and situation of the event.

Furthermore, the calculated value of the event is accumulated, and the billing information when the service is provided by PPV for a fee is calculated. As a result, the value of the event that increases or decreases depending on the event status is reflected in the billing information, so that it is possible to appropriately charge according to the event status.

(Embodiment 2 (program))
FIG. 8 is a functional block configuration diagram showing an example of the configuration of the computer (electronic computer) 700. The computer 700 includes a CPU 701, a main storage device 702, an auxiliary storage device 703, and an interface 704.

Here, each function constituting the attribute information acquisition unit 131, the event information collection unit 132, the learning unit 133, the prediction unit 134, the value calculation unit 135, and the billing information calculation unit 136 according to the first embodiment is provided. Details of the control program (information processing program) for realization will be described. These functional blocks are implemented in the computer 700. The operation of each of these components is stored in the auxiliary storage device 703 in the form of a program. The CPU 701 reads the program from the auxiliary storage device 703, expands it to the main storage device 702, and executes the above-described processing according to the program. Further, the CPU 701 secures a storage area corresponding to the above-mentioned storage unit in the main storage device 702 according to the program.

Specifically, the program is based on an event status collection step that collects status information of past events that fluctuate over time in past events and the collected status information on the computer 700. Learning steps that perform machine learning to generate event prediction model information that predicts changes in the status of current events, monitor current events in real time, event prediction model information, and current event status A predictive step that predicts changes in the status of the current event based on, and a service that provides users with information about the current event in the predicted status of the current event of the current event that fluctuates over time. It is a control program that realizes a value calculation step that calculates the value of information for each unit time and a computer.

The auxiliary storage device 703 is an example of a tangible medium that is not temporary. Other examples of non-temporary tangible media include magnetic disks, magneto-optical disks, CD-ROMs, DVD-ROMs, semiconductor memories, etc. connected via interface 704. When this program is distributed to the computer 700 via the network, the distributed computer 700 may expand the program to the main storage device 702 and execute the above-described processing.

Further, the program may be for realizing a part of the above-mentioned functions. Further, the program may be a so-called difference file (difference program) that realizes the above-mentioned function in combination with another program already stored in the auxiliary storage device 703.

Although the embodiments related to the disclosure have been described above, these can be implemented in various other embodiments, and can be implemented by making various omissions, replacements, and changes. These embodiments and modifications, as well as those omitted, replaced and modified, are included in the technical scope of the claims and the equivalent scope thereof.

<Additional notes>
The matters described in each of the above embodiments will be added below.

(Appendix 1) The event status collection unit that collects the status information of the past events that fluctuate with the passage of time in the past events, and the machine learning based on the collected status information, which is currently performed. A learning unit that generates event prediction model information that predicts changes in the status of the current event, monitors the current event in real time, and based on the event prediction model information and the current event status, the current event status The value of the current event information that fluctuates over time in the predictor that predicts the change of the current event and the service that provides the user with the current event information in the predicted current event situation. An information processing device including a value calculation unit for calculation.

(Appendix 2) The information processing described in (Appendix 1) is calculated by changing the value of the information of the current event for each unit time according to the ratio between the elapsed time of the current event and the required time. apparatus.

(Appendix 3) The description in (Appendix 1) or (Appendix 2), which comprises a billing information calculation unit that accumulates the value of the current event information for each unit time in the service and calculates the billing information of the service to the user. Information processing device.

(Appendix 4) The billing information calculation unit calculates service billing information by adding a fixed value predetermined for each event type and a variable value calculated based on the popularity of the current event. , (Appendix 3).

(Appendix 5) An attribute information acquisition unit for acquiring user attribute information is provided, and the value calculation unit calculates the value of the current event information for each unit time for each user attribute indicating the user's attribute (Appendix 5). The information processing apparatus according to any one of 1) to (Appendix 4).

(Appendix 6) The value calculation unit increases or decreases the value of the information of the current event for each unit time when a predetermined action set occurs in the event, whichever of (Appendix 1) to (Appendix 5). Information processing device described in Crab.

(Appendix 7) The information described in any of (Appendix 1) to (Appendix 6) in which the value calculation unit increases or decreases the value of the information of the current event for each unit time in the case of a predetermined time zone of the event. Processing equipment.

(Appendix 8) The prediction unit analyzes the imaging data for capturing the event, determines the event status, and predicts the change in the event status, according to any one of (Appendix 1) to (Appendix 7). Information processing device.

(Appendix 9) The prediction unit acquires information explaining the event status from a predetermined Web page, determines the event status, and predicts a change in the event status, from (Appendix 1) to (Appendix 8). The information processing device according to any one.

(Appendix 10) The event status collection step of collecting the status information of past events that fluctuate with the passage of time in the past events performed by the event status collection department, and the collected status information performed by the learning department. A learning step that performs machine learning based on the above to generate event prediction model information that predicts changes in the status of the current event, and the prediction department monitors the current event in real time and event prediction model information. And, based on the current event status, the prediction step that predicts the change in the current event status, and the value calculation department provides the user with information on the current event in the predicted current event status. An information processing method including a value calculation step for calculating the value of information of a current event that fluctuates with the passage of time for each unit time in the service to be processed.

(Appendix 11) An event status collection step that collects status information of past events that fluctuate over time in past events, and machine learning based on the collected status information, which is currently being performed. A learning step that generates event prediction model information that predicts changes in the status of an existing event, monitors the current event in real time, and based on the event prediction model information and the current event status, the current event status Calculates the unit-time value of current event information that fluctuates over time in a service that provides users with current event information in a predictive step that predicts changes and the current event situation that was predicted. An information processing program for making an electronic computer execute the value calculation step to be performed.

1 Information processing system, 100 information processing device, 110 communication unit, 120 storage unit, 121 user DB, 122 event development DB, 123 event prediction model DB, 130 control unit, 131 attribute information acquisition unit, 132 event information collection unit, 133 Learning unit, 134 prediction unit, 135 value calculation unit, 136 billing information calculation unit, 200 user terminal, 210 communication unit, 220 display unit, 230 operation unit, 240 storage unit, 250 control unit, NW network

Claims

An event status collection unit that collects status information of the past events that fluctuate over time in past events,
A learning unit that performs machine learning based on the collected situation information and generates event prediction model information that predicts changes in the situation of the event that is currently being performed.
A prediction unit that monitors the current event in real time and predicts a change in the current status of the event based on the event prediction model information and the current status of the event.
With a value calculation unit that calculates the value of the current event information that fluctuates over time in a service that provides the user with the current event information in the predicted current event situation. An information processing device including.
The information processing device according to claim 1, wherein the value calculation unit calculates the value of the current information of the event for each unit time by changing it according to the ratio of the current elapsed time of the event to the required time.
The information processing according to claim 1 or 2, further comprising a billing information calculation unit that accumulates the value of the current event information in the service for each unit time and calculates the billing information of the service to the user. apparatus.
The billing information calculation unit
Predetermined fixed values for each type of event and
The information processing device according to claim 3, wherein the billing information for the service is calculated by adding the fluctuation value calculated based on the current popularity of the event.
It is provided with an attribute information acquisition unit that acquires the attribute information of the user.
The information processing according to any one of claims 1 to 4, wherein the value calculation unit calculates the value of the current event information for each unit time for each user attribute indicating the user's attribute. apparatus.
The value calculation unit increases or decreases the value of the current information of the event for each unit time when a predetermined action set occurs in the event, according to any one of claims 1 to 5. The information processing device described in.
The information processing according to any one of claims 1 to 6, wherein the value calculation unit increases or decreases the value of the current information of the event for each unit time in a predetermined time zone of the event. apparatus.
The one according to any one of claims 1 to 7, wherein the prediction unit analyzes the imaging data for imaging the event, determines the situation of the event, and predicts the change in the situation of the event. Information processing device.
Any one of claims 1 to 8, wherein the prediction unit acquires information explaining the status of the event from a predetermined Web page, determines the status of the event, and predicts a change in the status of the event. The information processing apparatus according to item 1.
The event status collection step of collecting the status information of the past events that fluctuate with the passage of time in the past events performed by the event status collection department, and
A learning step performed by the learning unit to perform machine learning based on the collected situation information and generate event prediction model information for predicting a change in the situation of the event currently being performed.
A prediction step performed by the prediction unit that monitors the current event in real time and predicts a change in the current status of the event based on the event prediction model information and the current status of the event.
In the predicted current situation of the event performed by the value calculation unit, the value of the information of the current event that fluctuates with the passage of time in the service that provides the information of the current event to the user for each unit time is calculated. An information processing method including a value calculation step to be calculated.
An event status collection step that collects status information of the past events that fluctuate over time in past events, and
A learning step that performs machine learning based on the collected situation information and generates event prediction model information that predicts a change in the situation of the event that is currently being performed.
A prediction step that monitors the current event in real time and predicts a change in the current status of the event based on the event prediction model information and the current status of the event.
A value calculation step for calculating the unit-time value of the current event information that fluctuates over time in a service that provides the user with the current event information in the predicted current event situation. An information processing program for making a computer execute.