Program and system

Abstract

To generate an interesting record easily during a game.SOLUTION: A program allows a computer to function as: storage means capable of storing action in a virtual space of a character operable by a user as log data; and generation means for generating summary data summarizing the character's action until resumption when the user resumes the character's action in the virtual space at least on the basis of a learned model that has learned on the basis of learning data including the log data.SELECTED DRAWING: Figure 17

Description

[Technical field]

[0001] The present invention relates to a program and a system. [Background technology]

[0002] Conventionally, a technique is known in which a user saves a game. In addition, the user inputs any text information (called "memo information") in association with the save data generated by saving. In this way, a technique is known that makes it easy to manage multiple save data (for example, see Patent Document 1, etc.).

[0003] Also, in a table-top role playing game (TRPG), for example, the game master may shine a spotlight on a character who plays an important role in the progression of the scenario, and display an image capturing only the avatar. On the other hand, at other times, an image overlooking the entire virtual space may be displayed. In this way, a recording technique for generating a play record video with a variety of display modes is known (for example, Patent Document 2, etc.). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2022-188862 A [Patent Document 2] Patent No. 7018617 Summary of the Invention [Problem to be solved by the invention]

[0005] When a game progresses, for example, if a record of the game played is kept as a play diary, the user can recall the previous content and enjoy the game. However, records such as play diaries are often simply output of fixed phrases, and for many users, fixed phrases are often uninteresting and they end up not reading them. In addition, it is a heavy burden for the user to manually input all of the play diaries, and there is a problem that it is not easy to generate a play diary.

[0006] However, in the conventional technology, the play log is not very interesting, and it is not possible to easily generate a record when playing a game.

[0007] An object of the present invention is to easily generate an interesting record when playing a game. [Means for solving the problem]

[0008] In order to solve the above problems, the present invention provides a program comprising: Computer, A storage means capable of storing actions of a user-controllable character in a virtual space as log data; The device functions as a generating means for generating summary data summarizing the actions of the character up to the time the user resumes actions of the character in the virtual space, based on a trained model trained on learning data including at least the log data, when the user resumes actions of the character in the virtual space. Effect of the Invention

[0009] According to the present invention, when playing a game, an interesting record can be easily generated. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of a system configuration according to an embodiment of the present invention. [Diagram 2] FIG. 13 is a diagram illustrating an example of pre-processing. [Diagram 3]FIG. 11 illustrates an example of an execution process. [Figure 4] FIG. 1 is a diagram showing an example of the overall process of AI learning and execution. [Diagram 5] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device. [Figure 6] FIG. 1 is a network diagram showing an example of an AI configuration. [Figure 7] FIG. 11 is a diagram showing an example of input in the first example. [Figure 8] FIG. 13 is a diagram showing a first example of a moving image. [Figure 9] FIG. 11 is a diagram showing a second example of a moving image. [Figure 10] FIG. 13 is a diagram showing a third example of a moving image. [Figure 11] FIG. 13 is a diagram showing a fourth example of a moving image. [Figure 12] FIG. 11 is a diagram showing a first example of output data. [Figure 13] FIG. 11 is a diagram showing a second example of output data. [Figure 14] FIG. 13 is a diagram showing a third example of output data. [Figure 15] FIG. 13 is a diagram showing a fourth example of output data. [Figure 16] FIG. 13 is a diagram illustrating an example of the overall process. [Figure 17] FIG. 2 is a diagram illustrating an example of a functional configuration. [Figure 18] FIG. 13 is a diagram showing a configuration example in which an auxiliary device is used. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment will be described with reference to the drawings.

[0012] [System configuration example] Fig. 1 is a diagram showing an example of a system configuration according to the present embodiment. For example, as shown in Fig. 1, a system 1 mainly includes user terminals 20A, 20B, and 20C (hereinafter, these may be collectively referred to as "user terminal 20") and a server 11.

[0013] Hereinafter, the person who manages the server 11 will be referred to as the "administrator 5." In addition, the people who operate the user terminals 20A, 20B, and 20C will be referred to as the "user 4A," the "user 4B," and the "user 4C" (hereinafter, these may be collectively referred to as the "user 4").

[0014] The administrator 5 is a person who operates the information processing service provided by the system 1. On the other hand, the user 4 is a person who uses the information processing service provided by the system 1. The administrator 5 and the user 4 differ in which information processing device they operate: the server 11, which is an example of a management device, or the user terminal 20. Hereinafter, the user 4 will be a player of the game, and the administrator 5 will manage the game and the server 11.

[0015] Although the example shown in FIG. 1 has three user terminals 20 and one server 11, the number of servers 11, the number of user terminals 20, the number of administrators 5, and the number of users 4 are not important.

[0016] The server 11 and the user terminal 20 are connected to be able to communicate with each other via a communication network 2. For example, the communication network 2 is the Internet, a mobile communication system (for example, a public line based on 4G (4th Generation, fourth generation mobile communication standard) or 5G (5th Generation, fifth generation mobile communication standard)), a wireless network such as Wi-Fi (registered trademark), or a combination of these.

[0017] The user terminal 20 downloads a program for playing a game (hereinafter referred to as a "game program") from the server 11, or accesses the server 11 to provide a game service. Note that communication with the server 11 is not required to play a game. In other words, the user terminal 20 may download a program or install it from a medium to create an environment for playing a game.

[0018] [Examples of AI (Artificial Intelligence) learning and execution] Hereinafter, AI learns through "pre-processing." AI in the learning stage, i.e., "pre-processing," will be referred to as the "learning model A1." Then, once learning has progressed to a certain extent, the learning model A1 becomes the "trained model A2." Hereinafter, the execution stage in which output processing is executed using the trained model A2 will be referred to as the "execution process."

[0019] The "pre-processing" is performed before the "execution processing". However, the "pre-processing", that is, the trained model A2 may continue to train before the "execution processing".

[0020] [Pre-processing example] 2 is a diagram showing an example of pre-processing. For example, the pre-processing is performed by the server 11.

[0021] The learning model A1 performs learning by inputting learning data D1. That is, the learning model A1 performs so-called "supervised" learning.

[0022] The learning data D1 includes known log data and is data associated with a "correct answer" for this log data. Specifically, the learning data D1 includes log data indicating the game play results and the play process, such as the eleventh data D11, the twelfth data D12, the thirteenth data D13, etc. (including a data group that combines a plurality of data such as the eleventh data D11, the twelfth data D12, and the thirteenth data D13. Hereinafter, simply referred to as "log data"), and the correct answer data D20.

[0023] The learning model A1 learns a correspondence relationship that outputs correct answer data D20 for input of log data based on input of learning data D1.

[0024] The log data will be described in detail later.

[0025] Furthermore, it is preferable that the learning model A1 learns using big data D4. For example, the big data D4 is data on the Internet. However, the big data D4 may be data input by an administrator 5 or the like.

[0026] [Example of execution process] 3 is a diagram showing an example of the execution process. For example, the execution process is performed by the user terminal 20, or by the user terminal 20 and the server 11 working together.

[0027] The trained model A2 is in a state where the trained model A1 has been trained through pre-processing. That is, when the pre-processing shown in FIG. 2 is executed, the trained model A2 is generated.

[0028] When unknown data D2 is input, the trained model A2 generates output data D3 for the unknown data D2.

[0029] The unknown data D2 is unknown log data, that is, data for which the "correct answer" to the log data is unknown at the time of input. Specifically, the unknown data D2 includes unknown log data indicating the game play results and the play process, such as the twenty-first data D21, the twenty-second data D22, the twenty-third data D23, etc. (including the case of a data group that combines a plurality of data such as the twenty-first data D21, the twenty-second data D22, and the twenty-third data D23). For example, the unknown data D2 is composed of the same type of data as the learning data D1 and the log data.

[0030] When the output data D3 is generated, the output data D3 is transmitted to, for example, the user terminal 20. Thereafter, the user terminal 20 outputs an output screen or the like to the user 4 based on the output data D3.

[0031] The output data D3 and the output based on the output data D3 will be described in detail later.

[0032] Fig. 4 is a diagram showing an example of the overall process of AI learning and execution. The relationship between the pre-processing shown in Fig. 2 and the execution process shown in Fig. 3 is as shown in Fig. 4.

[0033] Note that the pre-processing and the execution processing do not have to be executed in the consecutive order as illustrated in the figure. Therefore, it is not essential that the period in which preparation is performed by the pre-processing and the period in which the execution processing is performed thereafter are consecutive. Therefore, the execution processing may be executed after a time has elapsed from the pre-processing, once the trained model A2 has been created. Also, once the trained model A2 has been generated, the execution processing may be executed by repurposing the trained model A2.

[0034] The learning data D1 and unknown data D2 are different between the learning process and the execution process. Also, the AI ​​is a learning model A1 in the learning stage, but when learning progresses to a certain extent, it becomes a trained model A2. In this way, the trained model A2 trained using big data D4 as training data is a so-called "generative AI."

[0035] The eleventh data D11 included in the learning data D1 and the twenty-first data D21 included in the unknown data D2 (hereinafter, the twelfth data D12 and the twenty-second data D22, etc. have the same relationship) are the same data type. That is, the eleventh data D11 and the twenty-first data D21 are both log data.

[0036] In the learning data D1, the "correct answer" is known, whereas in the unknown data D2, the "correct answer" is unknown. Specifically, the learning data D1 includes the correct answer data D20, whereas the unknown data D2 does not include the correct answer data D20. Therefore, in the learning data D1, the relationship between the log data and the correct answer data D20 is known.

[0037] On the other hand, the unknown data D2 does not include the correct answer data D20, and the “correct answer” for the unknown data D2 is unknown. The trained model A2 generates output data D3 for the unknown data D2 based on the correlation between the training data D1 trained in pre-processing and the correct answer data D20.

[0038] A part of the execution process may be replaced by a process using a table, etc. In this way, the pre-processing in the process using a table, etc. (so-called rule-based processing) is a process of preparing for inputting a table (also called a look-up table (LUT) or a mathematical expression, etc.).

[0039] [Example of hardware configuration of information processing device] 5 is a hardware configuration diagram of an information processing device. The information processing device is a server 11, a user terminal 20, etc. Hereinafter, the information processing device is assumed to have the same hardware configuration as the server 11. For example, the information processing device is a workstation or a general-purpose computer such as a personal computer. However, each information processing device may have a different hardware configuration.

[0040] The server 11 mainly includes a processor 111, a memory 112, a storage 113, an input / output interface 114, and a communication interface 115. In addition, each component of the server 11 is connected to a communication bus .

[0041] The processor 111 executes a series of instructions contained in a server program 11P stored in the memory 112 or the storage 113, thereby achieving processing and control.

[0042] The processor 111 is, for example, an arithmetic device and a control device such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an MPU (Micro Processing Unit), an FPGA (Field-Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or a combination thereof.

[0043] The memory 112 is a main storage device (which is volatile) that stores the server program 11P and data, etc. For example, the server program 11P is loaded from the storage 113. The data includes data input to the server 11 and data generated by the processor 111. For example, the memory 112 is a RAM (Random Access Memory) or other volatile memory.

[0044] The storage 113 is an auxiliary storage device (non-volatile) that stores the server program 11P and data, etc. The storage 113 is, for example, a ROM (Read-Only Memory), a hard disk drive, a flash memory, or other non-volatile storage device. The storage 113 may also be a removable storage device such as a memory card. As another example, the storage 113 may be an external storage device. With this configuration, for example, in a scene where multiple user terminals 20 are used, such as an amusement facility, it becomes possible to collectively update the server program 11P or data.

[0045] The input / output interface 114 is an interface that connects external devices, such as a monitor, an input device (for example, a keyboard or a pointing device), an external storage device, a speaker, a camera, a microphone, and a sensor, to the server 11.

[0046] The processor 111 also communicates with external devices via an input / output interface 114. The input / output interface 114 is, for example, a Universal Serial Bus (USB), a Digital Visual Interface (DVI), a High-Definition Multimedia Interface (HDMI (registered trademark)), wireless, or other terminal.

[0047] The communication interface 115 communicates with other devices (e.g., the user terminal 20, etc.) connected to the communication network 2. For example, the communication interface 115 is a wired communication interface such as a Local Area Network (LAN), or a wireless communication interface such as Wireless Fidelity (Wi-Fi), Bluetooth (registered trademark), or Near Field Communication (NFC).

[0048] However, the information processing device is not limited to the above hardware configuration. For example, the user terminal 20 may further include a sensor such as a camera. Various data acquired by the user terminal 20 using the sensor may be transmitted to the server 11.

[0049] [Examples of learning model and trained model configuration] 6 is a network diagram showing an example of the configuration of an AI. The learning model A1 and the trained model A2 are, for example, AIs having a configuration shown in the following network.

[0050] Hereinafter, the learning model A1 and the trained model A2 will be described as being implemented on the server 11, i.e., on the cloud. However, a part or all of the learning model A1 and the trained model A2 may be implemented on the user terminal 20, etc.

[0051] The network 300 has, for example, an input layer L1, an intermediate layer L2 (also called a "hidden layer"), and an output layer L3.

[0052] The input layer L1 is a layer that inputs data.

[0053] The intermediate layer L2 converts the data input in the input layer L1 based on weights (e.g., coefficients used for multiplication) and biases (e.g., adding a constant), etc. The results of processing in this way in the intermediate layer L2 are transmitted to the output layer L3.

[0054] The output layer L3 is a layer that outputs output contents, etc.

[0055] Then, through learning, weight coefficients (for example, coefficients for input characters or images are changed in learning) and parameters changed through learning are optimized. Note that the network 300 is not limited to the network structure shown in the figure. In other words, the AI ​​may be realized by other machine learning.

[0056] For example, the AI ​​may be configured to perform preprocessing such as dimensionality reduction (for example, a process that converts a relationship of three or more dimensions into a relationship that can be obtained by simple calculations of three dimensions or less) using "unsupervised" machine learning. It is desirable to process the relationship between input and output using simple calculations such as linear expressions. This type of calculation reduces calculation costs and makes it possible to accurately determine the degree of deterioration.

[0057] In addition, the AI ​​may undergo processing to reduce overfitting, such as dropout. In addition, preprocessing such as dimensionality reduction and normalization may be performed.

[0058] The AI ​​may have a network structure such as a CNN (Convolution Neural Network). In addition, for example, the network structure may have a configuration such as an LLM (Large Language Model), an RNN (Recurrent Neural Network), or an LSTM (Long Short-Term Memory). In other words, the AI ​​may have a network structure other than deep learning.

[0059] The AI ​​may also have hyperparameters. In other words, the AI ​​may be configured such that some of the settings are performed by a user, etc. Furthermore, the AI ​​may specify features to be learned, or the user may set some or all of the features to be learned.

[0060] Furthermore, the learning model A1 and the trained model A2 may use other machine learning. For example, the learning model A1 and the trained model A2 may be preprocessed by normalization using an unsupervised model. Furthermore, the learning may be reinforcement learning (a learning method in which an AI is made to make a choice and an evaluation (reward) is given for the choice, resulting in a larger evaluation), etc.

[0061] In the learning, data expansion or the like may be performed. That is, in order to increase the amount of learning data used in the learning of the learning model A1, a single piece of experimental data or the like may be expanded and pre-processed to generate multiple pieces of learning data. In this way, if the amount of learning data can be increased, the learning of the learning model A1 can be further advanced.

[0062] Furthermore, the learning model A1 and the trained model A2 may be configured to perform transfer learning, fine tuning, or the like. That is, since the user terminal 20 often has a different execution environment for each device, the settings may be different for each device according to the execution environment. For example, the basic configuration of the AI ​​is trained on another information processing device. After that, each information processing device may be further trained or configured for further optimization to each execution environment.

[0063] [Example of log data] The log data is generated in accordance with the progress of the game when the game is played on the user terminal 20. The unknown data D2 may be generated based on an operation by the user 4 (for example, an operation to save the game, etc.), or may be automatically generated in the background by the user terminal 20 in accordance with the progress of the game.

[0064] The log data is data that indicates the progress of playing a game.

[0065] In the following, an example will be described in which the eleventh data D11 in the pre-processing and the twenty-first data D21 in the execution processing are the first data.

[0066] The first data is data indicating a profile of a character appearing in the game. Or, the first data is data indicating a profile of a user 4 who performs operations on the game. For example, the first data is input by the user 4 when starting the game. However, the first data may be acquired from the user terminal 20 or another database, etc.

[0067] Specifically, the first data includes setting items such as name, background, occupation, and friendships.

[0068] The name is the real name, abbreviation, pseudonym, etc. of the user 4. The name is also identification information such as a nickname set for the character.

[0069] The background is the user's 4 history or the in-game history set for the character.

[0070] The occupation is the occupation or work history of the user 4. The occupation is an in-game occupation set for the character.

[0071] A friendship is a relationship with another person who is or has been involved with the user 4 or character.

[0072] The second data is information on events that occurred in the game before the play log was generated, or data indicating the process of generating the game play log. For example, the second data is generated in the background while the user 4 is playing the game.

[0073] Specifically, the second data is image data (the image data is a still image or a video) recorded from a screen showing play by user 4 (the screen may be from the viewpoint of user 4, another user, or another viewpoint such as a bird's-eye view). In addition, the second data is process information such as the content of an event played by user 4, play results, achievements, total play time, or other participants.

[0074] For example, when an event or a "battle" occurs during game play, the second data is data showing the results of the event or the "battle," the operation content, the enemy character encountered, and various images. Therefore, the second data is in the form of image data, text data, or other recorded data.

[0075] An event has a specific goal, conditions for participation, or a period during which it can be participated in the game, and ends when the specific goal is achieved, the specific conditions are met, or a specific period of time has passed. Specifically, when an event occurs, an event-specific item may be acquired, an event-specific character may appear, or an event-specific benefit may be obtained, depending on the period during which the event occurs or the actions taken within the event. Events may also include "battles" and the like. Furthermore, when an event occurs, various events occur, and there are many scenes that are worth seeing.

[0076] The third data is data showing output screens output in the game until the play log is generated. For example, the third data is image data recorded of the output screens output when the user 4 plays the game, or related image data.

[0077] The third data is image data showing the play process outputted in the game until the play log is generated. In particular, the third data is preferably generated mainly from the play process that is the highlight of the game until the play log is generated.

[0078] [Example of execution process in RPG] In the following, the type of game is assumed to be an RPG (role-playing game). Also, when the game progresses and the player saves, the game will start from the point where the player saved the game.

[0079] In the following example, the output is made from the time when the previous save was performed until the instruction by the user 4. However, the time period to which the output corresponds may be set by the user 4 or may be the start time of the game, etc.

[0080] When the game is saved, the game is paused, that is, the action in the virtual space of the character operated by the user 4 is paused. When the save data is loaded, the game is resumed, that is, the action in the virtual space of the character operated by the user 4 is resumed. However, the pause and resumption of the game is not limited to saving, and the game may be paused and resumed, for example, when the user 4 issues a predetermined command.

[0081] Fig. 7 is a diagram showing an example of input in Example 1. For example, when a game is played on the user terminal 20 with respect to the server 11 on which the trained model A2 generated by the pre-processing shown in Fig. 2 is implemented, unknown data D2 is transmitted to the server 11.

[0082] In addition, the trained model A2 has learned actual diary examples through pre-processing, i.e., through learning using big data D4. Therefore, the trained model A2 understands the format for writing a diary (for example, writing the date and writing the details of an action).

[0083] In addition, based on the big data D4, the trained model A2 may extract and collect strategy information for the target game.

[0084] The unknown data D2 is transmitted to the server 11, for example, when a so-called save point is reached during game play. However, the unknown data D2 does not have to be transmitted all at once, and the constituent data may be divided and transmitted to the server 11 while the game is in progress.

[0085] In the first example, the unknown data D2 includes process text data D201 and video data D202, and is transmitted to the server 11.

[0086] The process text data D201 is text information indicating characteristic events in the gameplay, such as "Item XX was obtained," "An event was cleared in cooperation with six friends," and "Boss XX was defeated." For example, the process text data D201 is generated by the user 4 inputting a sentence or a keyword. Alternatively, the process text data D201 may be generated by an AI based on the keyword input by the user 4 or the content of the gameplay.

[0087] Fig. 8 is a diagram showing a first example of a video. For example, the first video data D2021 is data recorded mainly on movement scenes in a RPG, as shown in Fig. 8. In this way, the log data may include data showing the play in a format other than text. In this case, the video data D202 is subjected to image analysis to extract keywords, parameters, etc.

[0088] 9 is a diagram showing a second example of the video. Specifically, the second video data D203 may include a scene in which a player competes against an opponent for an event. That is, when a "battle" occurs, for example, an output screen as shown in the second video data D203 is displayed.

[0089] For example, the second video data D203 includes an output screen in which a character is made to perform a special action. In the second video data D203, the name of the action in which the special action was performed (hereinafter referred to as "special action name D204") is output. The special action name D204 indicates the name of a so-called "special move" or "magic", etc.

[0090] Furthermore, in the second video data D203, character highlighting D2022 in which a character who performed the action of the special action name D204 is close-up is output. For example, the character highlighting D2022 is output in a so-called "cut-in" format.

[0091] In this way, the second video data D203 includes highlight scenes in which special action names D204 or character highlighting D2022 or the like are output.

[0092] 10 is a diagram showing a third example of the video. Specifically, the third video data D2023 is data recorded mainly on scenes in which an item D205 is obtained in a game. It is preferable that the item D205 is a rare item that can only be obtained at an event or the like.

[0093] The log data may also include item information such as related events, time of acquisition, acquisition location, rarity of the item D205 (so-called "rarity"), type, quantity, price (price in in-game currency), characteristics (characters that can be used, etc.), or effects.

[0094] 11 is a diagram showing a fourth example of the video. Specifically, the fourth video data D2024 may include a representative scene, such as a so-called "boss battle."

[0095] For example, the fourth video data D2024 includes an output screen in which a strong enemy (such as a character that appears in a "boss battle" or a high-level character that gives a hard time in a "battle") appears. In the second video data D203, a screen in which a special character such as a boss character D206 appears is output. The boss character D206 is a rare character that only appears in events, etc. The log data may also include other information related to the boss character D206.

[0096] The log data may include data that is not directly visible to the user 4. For example, data used in the background, such as play time or a character's movement range, may be included as a profile. Other data, such as the character's name, status, parameters, equipment, and participants, may be included in the log data.

[0097] [Example output] 12 is a diagram illustrating a first example of output data. For example, the trained model A2 generates first output data D31 through execution processing.

[0098] The first output data D31 is generated, for example, in a text format. Note that the first output data D31 is not limited to a text format and may be generated in a format including an image. Also, the output is not limited to a text and an image and may include a sound.

[0099] The first output data D31 includes explanatory texts such as a first explanatory text D311, a second explanatory text D312, and a third explanatory text D313.

[0100] The text included in the first output data D31 is generated based on the big data D4 in the same manner as the sentence structure of an actual diary, etc. On the other hand, proper nouns, etc. appearing in the text included in the first output data D31 are proper character names, etc. appearing in the game.

[0101] The first explanatory text D311 is text that explains events ("△△" is the name of the event) and the like that occurred during game play. The items that the first explanatory text D311 explains are summaries of events that were participated in, opponents played against ("◆◆◆◆" is the name of a representative opponent), and incidents that occurred during play ("□□□" is the name of a character that actually participated in the game).

[0102] The second explanation text D312 is a text that reflects the difficult gameplay process based on the log data. Furthermore, the second explanation text D312 is a text that reflects the gameplay process in which a special action such as "executing a special move XXX" was performed based on the log data.

[0103] The third explanatory text D313 is a text that explains the characteristics of the acquired item based on the log data. As shown in the third explanatory text D313, the "level" (or the time required to complete the item) may be compared with other users (or a recommended level set in advance), and a favorable evaluation such as a low level of completion may be output.

[0104] The first output data D31 is generated at a time point that is set in advance, at a time point when the user 4 performs an operation to open a play log, or at a time point when an operation to open a window or the like that is set in advance is performed (hereinafter referred to as a "command time point"). Specifically, the first output data D31 is generated at a time point when the description column of an item is opened, at a time point when an event ends, or at a time point when an item is acquired, and output is performed based on the first output data D31.

[0105] In this example, the command time is the time when the game is suspended and resumed. Specifically, when user 4 performs an operation to open the play log, the character's actions are suspended, and the play log is generated and displayed to user 4. Then, when user 4 performs an operation to close the play log, the character's actions are resumed. In this case, a summary is generated with the actions before the play log is opened as the actions up to the resumed time. In this way, a summary up to any time point may be generated based on the operation of user 4.

[0106] 13 is a diagram illustrating a second example of output data. For example, the trained model A2 generates second output data D32 through execution processing.

[0107] Hereinafter, an example will be described in which the second output data D32 is output to an operation screen for performing a save. However, the output based on the second output data D32 is not limited to the operation screen for performing a save, and may be output to a dedicated screen for viewing a play log, a start screen, a save data loading screen, or the like.

[0108] The second output data D32 includes an output based on the first output data D31, and a summary image D321 generated based on the video data D202. For example, the summary image D321 is an image that shows an excerpt of the contents of the save data from the video data D202. The summary image D321 may be a still image or a video.

[0109] The summary image D321 is output as a highlight scene, or a characteristic scene that gives an overview of the conquered event, etc. Note that the summary image D321 is preferably a few still images or a video of about a few seconds.

[0110] The summary text is, for example, a text generated based on the first output data D31. Therefore, it is preferable that the summary text is generated mainly based on keywords. In this way, the summary is not limited to a text sentence, but may include a list of words, an image, an animation, information on the Internet, data of other people, and the like.

[0111] It is preferable that the output based on the second output data D32 is small enough to fit on one screen including GUIs used for other functions. Therefore, in the output based on the second output data D32, the summary text is preferably a few words or short sentences. Therefore, it is preferable that the summary text is generated to be about the length of a heading or summary.

[0112] FIG. 14 is a diagram showing a third example of output data. For example, the trained model A2 generates third output data D33 by execution processing. The screen shown in FIG. 14 is an example of a screen output on a dedicated screen specialized for displaying a play log. The time when the operation to open this dedicated screen, i.e., the screen shown in FIG. 14, is performed is the command time.

[0113] 14 based on the third output data D33 is output, for example, when the user 4 performs an operation to open the play diary, when an event ends, when a certain amount of time has elapsed while the game is in progress, when a save point is reached, etc. The play diary may also be output when a certain period of time has elapsed while the game is in progress.

[0114] The third output data D33 includes an output based on the first output data D31, etc. That is, the output based on the third output data D33 indicates a summary up to the command time based on the log data.

[0115] The output based on the third output data D33 preferably includes a heading D331 or advice D332, etc. Note that there may be a plurality of headings D331 or advice D332.

[0116] The heading D331 is generated by a few characters centered on a keyword. For example, the heading D331 is a text that notifies a notable event that has recently occurred, such as the completion of an event.

[0117] The advice D332 analyzes the current state of play based on the log data, and indicates information that is useful for the subsequent progress of the game. For example, the advice D332 indicates effective items and methods of dealing with techniques and the like by the character (for example, techniques that are effective against a struggling enemy, or items that have high defensive power against techniques used by a struggling enemy). Specifically, the advice D332 indicates the use of an effective item or technique against a struggling enemy, such as "You are having more and more difficulties with XX. XX is effective." The advice D332 also indicates items that are easy to obtain in the current situation, or items that will be useful in the future, such as "You can get △△ around here. It is useful for ◆◆."

[0118] The third output data D33 may be generated by limiting the log data to the period from the time when the most recent save was performed to the time when the command was issued.

[0119] 15 is a diagram illustrating a fourth example of output data. For example, the trained model A2 generates fourth output data D34 through execution processing.

[0120] The fourth example is an example in which an output is performed based on the fourth output data D34 in, for example, a fighting game, an action game, or a shooting game.

[0121] Even in games other than RPGs, text showing a summary, a heading D331, or advice D332, etc. may be output.

[0122] [Overall processing example] FIG. 16 is a diagram showing an example of overall processing. In the following example, the overall processing is performed successively with pre-processing and execution processing. Specifically, the pre-processing is step S01. Furthermore, the execution processing is steps S02 to S04. However, the overall processing may include processing other than these. Furthermore, the pre-processing and execution processing do not have to be successive. In other words, as long as the pre-processing is performed before the execution processing, there may be a gap between the pre-processing and the execution processing.

[0123] In step S01, the server 11 inputs learning data D1 including log data and answer data to train the learning model A1. It is preferable to use big data D4 for training the learning model A1. Then, when step S01 is performed, a trained model A2 is generated. In this way, when the learning model A1 is trained to become the trained model A2, the execution process is performed using the trained model A2.

[0124] In step S02, the server 11 inputs unknown data D2. For example, step S02 is executed in the background in parallel with the progress of the game, that is, transmitted from the user terminal 20 to the server 11 without the user 4 being aware of it. The unknown data D2 may include data generated in the server 11.

[0125] In step S03, the server 11 judges whether it is the time to issue a command. Next, if it is the time to issue a command (YES in step S03), the server 11 proceeds to step S04. On the other hand, if it is not the time to issue a command (NO in step S03), the server 11 proceeds to step S02. That is, step S04 and subsequent steps are executed in response to an operation such as opening the play log.

[0126] In step S04, the server 11 generates the output data D3. For example, the time when the output data D3 is generated, that is, the time when step S04 is executed, is set in advance.

[0127] In step S05, the server 11 performs output based on the output data D3. For example, the time when the output is to be performed or the screen to be output, that is, the time when step S05 is to be performed and the target, etc. are set in advance.

[0128] [Example of functional configuration] 17 is a diagram illustrating an example of a functional configuration of a system 1. For example, the system 1 is a journal output system including a learning device 31 and an execution device 32.

[0129] The learning device 31 includes a learning data input means 1F1 and a learning means 1F2.

[0130] The learning data input means 1F1 performs a learning data input procedure for inputting the learning data D1 including the log data and the correct answer data D20. For example, the learning data input means 1F1 is realized by the communication interface 115 or the like.

[0131] The learning means 1F2 performs a learning procedure in which the learning model A1 is trained using the training data D1 to generate a trained model A2. For example, the learning means 1F2 is realized by the processor 111 or the like.

[0132] The execution device 32 includes a storage means 1F10 and a generation means 1F4. It is preferable that the execution device 32 further includes an unknown data input means 1F3 and an output means 1F5. The storage means 1F10 may be included in the learning device 31. Alternatively, the storage means 1F10 may be shared by both the learning device 31 and the execution device 32.

[0133] The unknown data input means 1F3 performs an unknown data input procedure for inputting unknown data D2 including unknown log data to the trained model A2 generated by the training means 1F2. For example, the unknown data input means 1F3 is realized by the communication interface 115 or the like.

[0134] The generating means 1F4 performs a generating procedure for generating summary data summarizing the character's actions up to the time of resuming the action of the character in the virtual space based on the trained model A2. For example, the generating means 1F4 is realized by the processor 111 or the like.

[0135] The output means 1F5 performs an output procedure to output to the user terminal 20 based on the output data D3 including the summary data generated by the generation means 1F4. For example, the output means 1F5 is realized by the communication interface 115 or the like.

[0136] The storage unit 1F10 performs a storage procedure for storing log data, etc. For example, the storage unit 1F10 is realized by the storage 113 or the like.

[0137] The learning device 31 and the execution device 32 are, for example, the server 11. However, the learning device 31 and the execution device 32 may be different information processing devices.

[0138] With the above configuration, the burden on the user 4 in generating records when playing the game, such as a play log, can be reduced as the game progresses. For example, the play log is generated automatically without any operation by the user 4. However, the play log may be modified or added to by the user 4.

[0139] If there is an output showing a summary of such a play log or the like, User 4 can recall the content up to the previous time, etc., and for example, User 4 who has stopped playing the game for a long time, or User 4 who is playing different games simultaneously, can recall how far he or she has progressed and can smoothly resume the game.

[0140] On the other hand, it is a heavy burden for the user 4 to input all the text when making a record such as a play diary. For this reason, there are cases where the user 4 abandons making the play diary midway.

[0141] The progress of a game differs from person to person. Furthermore, even the same user 4 plays differently. Therefore, it is desirable to generate a play log according to the play. By referring to the log data of such individual play contents, the play log can reflect the situation according to the play.

[0142] If the play log is different for each play, the user 4 can play the game over and over again without getting bored because the play log changes with each play, which is appealing. Furthermore, since the play log reflects the play results and the play process, it is generated to be original rather than using standard phrases. If the play log changes each time, the user 4 can view a more interesting play log than a play log written in standard phrases. Furthermore, the play log does not require the user 4 to manually enter everything, so the user can enjoy the play log easily. In this way, an attractive output can be provided to the user 4.

[0143] The type of game is not limited to RPG. As long as a play log is output during the progress of the game, the type of game is not limited. For example, the type of game may include sports, action, puzzle, or fighting games.

[0144] [Variations] The unknown data D2 may be pre-processed. The pre-processing may include a process of limiting the unknown data D2. For example, the pre-processing is preferably such that the video data D202, which is the third data input as the unknown data D2, is limited to data at important points in time. In particular, the data volume of the video data D202 tends to be large if it is long. Therefore, the data volume can be reduced by limiting the video data D202.

[0145] For example, the unknown data D2 includes all output screens from the start time to the command time. Therefore, the preprocessing is a process of excluding data from a predetermined time before the command time (e.g., 10 minutes) from the unknown data D2. In this way, when the preprocessing is performed to narrow down the unknown data D2 to the most recent data, it is possible to output data that is mainly new information.

[0146] In addition, when extracting highlights, the preprocessing may be a process of narrowing down the unknown data D2 to a point where the profile changed suddenly or a point where the character was in trouble (for example, 10 minutes before and after the point to be identified). When preprocessing is performed in this way, the amount of data to be processed is reduced, and the execution process can be sped up.

[0147] For example, a point in time when so-called "hit points (HP)" suddenly decrease is often a time when the character is in trouble. In addition, when a so-called "battle" is long, it is often a time when the character is in trouble. If such a point in time can be searched for using log data, etc., it is possible to identify the point in time when the character is in trouble.

[0148] The point in time when the profile changes suddenly is often the point in time when the user 4 makes an effort to temporarily strengthen the parameters of the character. After such a point in time, it is often the highlight when the strengthened character plays an active role. If such a point in time can be searched for in the log data, etc., the point in time when the character plays an active role can be identified.

[0149] In this way, it is desirable to perform preprocessing in which not all of the unknown data D2 is input to the trained model A2, but rather carefully selected data is input to the trained model A2.

[0150] [Other embodiments] In the above example, the information processing device performs both pre-processing for the learning model and execution processing using the learned model. However, the pre-processing and execution processing do not have to be performed by the same information processing device. In addition, the pre-processing and execution processing do not have to be consistently performed by one information processing device. In other words, each process and data storage, etc. may be performed by an information system, etc., composed of multiple information processing devices.

[0151] [About the play diary] The play journal may have any name, medium type, format, or information structure as long as it describes the game play. In other words, within the game, the play journal may be operated or output using the GUI described above.

[0152] On the other hand, when generating a play log in text format, logs, diaries, various records, blogs, reports, comments, tweets, or articles that describe things other than the game may be used as reference for learning. In other words, the learning data may include data other than what is called a "play log."

[0153] The learning process may be additionally performed after the execution process or before the execution process.

[0154] The above-mentioned processing may be performed by an information processing device other than the server 11 and the user terminal 20 in an auxiliary manner.

[0155] Fig. 18 is a diagram showing a configuration example using an auxiliary device. Compared to the example shown in Fig. 1, the configuration shown in Fig. 18 differs in that an auxiliary device 60 is added. Note that the auxiliary device 60 may be a configuration that is used temporarily.

[0156] The auxiliary device 60 is an information processing device installed near the user terminal 20 (in this example, it is installed near the user terminal 20A, but it may be installed near other devices), etc. The auxiliary device 60 executes a part or all of a specific process on behalf of the user terminal 20 or the server 11.

[0157] For example, the auxiliary device 60 is provided with a device specialized for graphic processing and performs graphic processing at high speed. In this way, so-called edge computing or the like may be performed by installing the auxiliary device 60 or the like. In this way, the above-mentioned processing may be executed by utilizing the hardware resources of various information processing devices. Therefore, the above-mentioned processing may be executed by an information processing device different from the above-mentioned one.

[0158] The above-described processes and data used in the processes executed in this embodiment may be executed and stored by an information processing system. For example, the information processing system may execute or store the data in a plurality of information processing devices in order to realize redundant, distributed, parallel, or a combination of these processes or storage. Therefore, the present invention may be realized in devices other than the hardware configurations shown above and in systems other than the devices shown above.

[0159] In addition, the program according to the present invention is not limited to a single program, but may be a collection of multiple programs. In addition, the program according to the present invention is not limited to being executed by a single device, but may be executed by multiple information processing devices. Furthermore, the role allocation of each information processing device is not limited to the above example. In other words, a part or all of the above-mentioned processing may be executed by an information processing device different from the above-mentioned information processing device.

[0160] Furthermore, a part or all of the means realized by the program can be realized by hardware such as an integrated circuit. Furthermore, the program may be provided by being recorded on a non-transitory recording medium readable by a computer. The recording medium refers to, for example, a hard disk, an SD card (registered trademark), an optical disk such as a DVD, or a server on the Internet. Therefore, the program may be distributed via a telecommunication line such as the Internet.

[0161] Furthermore, the information processing devices that make up the information processing system may be located overseas.

[0162] The present invention is not limited to the above-mentioned embodiments. Therefore, the present invention can be modified or modified without departing from the technical gist of the invention. Therefore, all technical matters included in the technical ideas described in the claims are the subject of the present invention. The above-mentioned embodiments are preferred examples. Those skilled in the art can realize various modifications from the disclosed contents, and such modifications are included in the technical scope described in the claims. [Explanation of symbols]

[0163] 1: System 1F1: Learning data input means 1F2: Learning methods 1F3: Means for inputting unknown data 1F4: Generation means 1F5: Output method 1F10: Storage means 4: User 5:Administrator 11: Server 20: User terminal 31: Learning device 32: Execution device 60: Auxiliary equipment D1: Training data D11: 11th data D12: 12th data D13: 13th data D2: Unknown data D20: Correct data D201: Process text data D202:Video data D2021: First video data D203: Second video data D2022: Character Emphasis D2023: Third video data D2024: 4th video data D204:Special action name D205:Item D206: Boss character D21: 21st data D22: Data No. 22 D23: 23rd data D3: Output data D31: First output data D311: First explanatory text D312: Second explanatory text D313: Third explanatory text D32: Second output data D321: Summary image D33: Third output data D331 : Heading D332: Advice D34: 4th output data D4: Big Data A1: Learning model A2: Trained model

Claims

1. Computer, A storage means capable of storing actions of a user-controllable character in a virtual space as log data; a generation means for generating summary data summarizing the actions of the character up until the user resumes the action of the character in the virtual space, based on a trained model trained on training data including at least the log data, when the user resumes the action of the character in the virtual space; A program that functions as a

2. The learning data is Further comprising answer data indicating a summary of the game play. The program according to claim 1.

3. The log data is First data indicating a character appearing in a game or a profile of the user; second data indicating event information occurring before the resumption of the action or a process before the resumption of the action; and third data showing an output screen output before the action is resumed. The program according to claim 1.

4. A storage means capable of storing actions of a user-controllable character in a virtual space as log data; a generation means for generating summary data summarizing the actions of the character up until the user resumes the action of the character in the virtual space, based on a trained model trained on training data including at least the log data, when the user resumes the action of the character in the virtual space; A system comprising:

Images