JP6642755B1 - Audio processing device - Google Patents

Abstract

An object of the present invention is to detect excessive play effectively without excessively depending on the function of a game machine itself. A sound processing device includes: a sound detection unit configured to detect an external sound; a sound determination unit configured to determine whether or not the external sound includes a game sound of a computer game; A time estimating unit for calculating the cumulative estimated value of the play time of the game, and a notifying unit for notifying the player of the first message when the cumulative estimated value exceeds the first threshold value. The time estimating unit may calculate the cumulative estimated value by multiplying the length of the voice pattern by the number of times the voice pattern is detected. [Selection diagram] FIG.

Description

  The present invention relates to a speech recognition technology in a computer game.

  With the spread of various game consoles, computer games seem to have become established as entertainment that can be enjoyed widely by adults and children. On the other hand, there are many cases where the player becomes too engrossed in the game, and spends an unexpectedly long time playing without even being aware of the player himself. Hereinafter, an event that continues to play a game longer than expected is called “excessive play”.

  As a measure for excess play, Patent Literature 1 discloses a technique for prompting a player to take a break by interrupting the game when a game image is continuously displayed for a predetermined time or more.

JP-A-2000-005448

  At present, it is not uncommon for a single home to have multiple game consoles. The player may play a plurality of games one after another. Therefore, even if the play time is measured for each game or each game machine, the excess play may not be detected properly.

  The present invention has been completed based on the recognition of the above-mentioned problems, and a main object of the present invention is to provide a technique for effectively detecting an excess play without excessively depending on the functions of the game machine itself. It is in.

  A sound processing device according to an aspect of the present invention, a sound detection unit that detects an external sound, a sound determination unit that determines whether or not the external sound includes a game sound of a computer game, based on the game sound, A time estimating unit for calculating the cumulative estimated value of the playing time of the computer game, and a notifying unit for notifying the player of the first message when the cumulative estimated value exceeds the first threshold value.

  A voice processing device according to another aspect of the present invention includes a voice detection unit that detects an external voice, and a voice determination unit that determines that the external voice includes a game sound when a predetermined voice pattern is repeatedly detected from the external voice. And a notifying unit for notifying the player of the first message when the number of consecutive detections of the voice pattern exceeds the third threshold.

  ADVANTAGE OF THE INVENTION According to this invention, it becomes easy to detect excess play effectively.

It is a system configuration diagram assumed in the present embodiment. FIG. 3 is a functional block diagram of the audio processing device. 6 is a time chart illustrating a process of determining a play time of a game. It is a flowchart which shows the process in a detection mode. It is a flowchart which shows the process in a measurement mode.

FIG. 1 is a system configuration diagram assumed in the present embodiment.
The game device 104a and the game device 104b shown in FIG. 1 (hereinafter, referred to as “game device 104” when referred to collectively or unless otherwise specified) are general devices for executing a game. The model of the game device 104a and the model of the game device 104b do not need to be the same. When executing a game, the game device 104 outputs “game sound” from a built-in speaker. The game sound referred to here includes not only background music of the game (hereinafter, referred to as “game background music”) but also so-called sound effects such as explosion sounds and shooting down sounds.

  The voice input device 102 is a known device such as a smart speaker. The voice input device 102 has a built-in microphone and speaker. The voice input device 102 detects a game sound output from each game device 104 and an utterance of a player. Details of the method of detecting and recognizing the game sound will be described later.

  The voice processing device 100 is connected to the voice input device 102. The sound processing device 100 determines whether or not a player is playing a game in any one of the game devices 104 based on a result of detection of a game sound by the sound input device 102. When the voice processing device 100 determines that the excessive play has been performed by a method described later, the voice input device 102 outputs a warning or caution message (first message) by voice. Note that the function of the voice processing device 100 may be incorporated as a part of the voice input device 102, but in the present embodiment, the voice processing device 100 and the voice input device 102 are described as being separate devices.

  The voice input device 102 does not need to be connected to the game device 104 via a communication line regardless of whether it is wired or wireless. The voice input device 102 detects the game sound of the game device 104, and the voice processing device 100 determines that the game is being played when the voice input device 102 detects the game sound. The voice input device 102 determines based on the game sound whether play of the game has been prolonged. Therefore, even if a player plays a game while replacing a plurality of types of game devices 104, or plays a plurality of types of games in order, the sound processing device 100 can recognize that the player continues the game. . The voice processing device 100 can effectively detect the excess play without depending on the model of the voice input device 102 or the type of the game.

FIG. 2 is a functional block diagram of the audio processing device 100.
Each component of the audio processing device 100 includes a computing unit such as a CPU (Central Processing Unit) and various coprocessors, a storage device such as a memory and a storage, hardware including a wired or wireless communication line connecting them, and a storage device. And is provided by software that supplies processing instructions to the computing unit. The computer program may be configured by a device driver, an operating system, various application programs located in an upper layer thereof, and a library that provides a common function to these programs. Each block described below is not a configuration in a hardware unit but a block in a functional unit.

  The voice input device 102 acquires a voice such as a game sound. Further, the voice input device 102 can also interpret the voice of the player when speaking and convert the speech content into character information. The voice input device 102 outputs character information designated by the voice processing device 100 as voice information.

The voice processing device 100 includes a voice detection unit 110, a notification unit 112, a data processing unit 114, and a data storage unit 116.
The voice detection unit 110 acquires voice information from the voice input device 102. The notifying unit 112 causes the voice input device 102 to output a voice message by transmitting a message (character information) to the voice input device 102. The data storage unit 116 stores various data such as programs. The data processing unit 114 performs various processes based on the data acquired by the voice detection unit 110 and the data stored in the data storage unit 116. The data processing unit 114 also functions as an interface of the voice detection unit 110, the notification unit 112, and the data storage unit 116.

The data processing unit 114 includes a voice determination unit 118 and a time estimation unit 120.
The sound determination unit 118 determines whether the sound obtained by the sound detection unit 110 is a game sound. Further, the voice determination unit 118 recognizes not only the game sound but also the utterance content of the player. The voice input device 102 converts the uttered voice into character information, and the voice detection unit 110 acquires the character information of the uttered voice from the voice input device 102. At 118, it is determined from the character information indicating the utterance content whether or not an exciting condition described later is satisfied. The time estimation unit 120 estimates the time during which the player is playing the game substantially continuously. Hereinafter, this estimated value is referred to as “cumulative estimated value”.

FIG. 3 is a time chart showing a process of determining the play time of the game.
Game background music has a general feature that the same voice pattern (phrase) is repeatedly executed. Therefore, when a predetermined sound pattern is repeatedly detected, the sound processing device 100 determines that the game background music is playing. In other words, the time during which the repeated voice pattern is detected is determined (estimated) as the game play time.

The audio processing device 100 has two types of modes, a “detection mode” and a “measurement mode”.
The detection mode is a mode for recognizing the beginning of the game background music. The measurement mode is a mode for recognizing the continuation of the game background music and the end timing thereof.
First, the audio processing device 100 is initially set to the detection mode. In the detection mode, when the same voice pattern is repeatedly detected a predetermined number of times or more, for example, three times or more, the voice processing apparatus 100 shifts from the detection mode to the measurement mode. In FIG. 3, the sound pattern P1 of the game G1 has been detected from time t0. At time t1 when the third sound pattern P1 is confirmed, the sound processing device 100 shifts from the detection mode to the measurement mode. A period from time t0 to time t1 corresponding to the detection mode is called a “detection period”.

  The voice pattern P1 is repeatedly detected after time t1, and is interrupted at time t3. At this time, the sound processing device 100 shifts from the measurement mode to the detection mode. A period from time t1 to time t3 corresponding to the measurement mode is called a “measurement period”.

  The time estimating unit 120 calculates a time (n1 × tm1) obtained by multiplying the number of repetitions n1 of the voice pattern P1 in the detection period and the measurement period by one playing time tm1 of the voice pattern P1 as an estimated value of the continuous play time of the game G1. That is, it is calculated as the cumulative estimated value T1. When the cumulative estimated value T1 becomes equal to or more than a predetermined threshold value V1 (first threshold value), the voice processing apparatus 100 prompts the voice input apparatus 102 for a message such as "let's take a break" (hereinafter, "caution message"). (The first message).

  In FIG. 3, no voice pattern is detected from time t3 to time t4. From time t4, a sound pattern P2 of another game G2 is detected. The audio processing device 100 in the detection mode shifts to the measurement mode at time t5 when three consecutive detections of the audio pattern P2 are confirmed.

  The time estimating unit 120 also calculates the cumulative estimated value T2 for the game G2 based on the voice pattern P2. When the cumulative estimated value T2 becomes equal to or more than the threshold value V1, the voice processing device 100 outputs a caution message.

  An interval TX from time t3 to time t4 is a time during which the player is not playing the game. When the interval TX is longer than the threshold value V2 (the second threshold value), in other words, when the player has sufficiently rested after playing the game G1, and then plays the next game G2, the time estimation unit 120 After resetting the total estimated value of G1 once, the total estimated value of the game G2 is calculated. On the other hand, when the interval TX is equal to or less than the threshold value V2, in other words, when the player plays the game G2 continuously after the game G1, the audio processing device 100 sets the cumulative estimated value T1 (game G1) and the cumulative estimated value T2 (game G2). ) Is calculated as the cumulative estimated value of the game play time. In this way, excess play can be detected even in a situation where the player plays the game continuously without taking sufficient rest. Note that the player can arbitrarily set the thresholds V1 and V2.

FIG. 4 is a flowchart showing a processing procedure in the detection mode.
The flowchart shown in FIG. 4 is executed when the voice input device 102 detects a voice pattern in the detection mode. The voice detection unit 110 stores the detected voice pattern. When the same voice pattern is detected twice or more consecutively (Y in S10), the voice determination unit 118 increments the count variable i (S12). If the count variable i is 2 or less (N in S14), or at the time of detecting the first voice pattern (N in S10), no special processing is executed until the next voice pattern is detected.

  If the count variable i is 2 or more (Y in S14), in other words, when the same voice pattern is detected three times in the detection mode consecutively, the voice determination unit 118 shifts from the detection mode to the measurement mode (S16). . Further, the sound determination unit 118 resets the count variable i (S18).

FIG. 5 is a flowchart showing a process in the measurement mode.
The flowchart shown in FIG. 5 is executed when the voice input device 102 detects the same voice pattern as the previous time in the measurement mode. The time estimating unit 120 updates the cumulative estimated value TY by the method described above (S20). When the cumulative estimated value TY is equal to or greater than the threshold value V1 (Y in S22), the notification unit 112 causes the voice input device 102 to output a caution message (S24). After outputting the caution message, the time estimating unit 120 resets the cumulative estimated value TY (S26). On the other hand, when the cumulative estimated value is less than the threshold value V1, the processing after S24 is skipped.

  As described above, when the detection of the voice pattern is interrupted in the measurement mode, the voice determination unit 118 shifts from the measurement mode to the detection mode. In addition, when no voice pattern is detected, that is, when the length of the interval is equal to or greater than the threshold value V2, the time estimating unit 120 resets the cumulative estimated value TY. On the other hand, when a new voice pattern is detected when the length of the interval is less than the threshold value V2, the play time (cumulative estimated value) of the new game is compared with the play time (cumulative estimated value) of the previous game. Add up.

  The voice input device 102 also detects the utterance of the player during the play of the game. When a predetermined utterance is detected from the player during the detection of the game background music, the voice processing device 100 determines that the “exciting condition” is satisfied. The exciting condition is satisfied when an utterance in which excessive excitement of the player is estimated is detected. For example, when an utterance of a violent predetermined word such as “fuck”, “brute”, or “blurred” is detected, the exciting condition may be satisfied. The setting of the excitement condition is optional. For example, it may be determined that the exciting condition is satisfied when a quarrel or cry of a child is detected.

  When the exciting condition is satisfied, the notifying unit 112 causes the voice input device 102 to output a message (hereinafter, referred to as a “sedation message”) for replaying the player (second message). The sedation message may be any message such as, for example, “Come down”, “Donmai”, “Let's take a deep breath”. The notification unit 112 may generate a buzzer sound or the like from the voice input device 102, or may play classical music to calm the player.

As described above, the audio processing device 100 has been described based on the embodiment.
The voice processing device 100 calculates the continuous play time of the game as a cumulative estimated value based on the game sound. Therefore, the actual play time can be measured regardless of the type of the game device 104. Further, there is no need to connect the voice input device 102 and the voice processing device 100 with the game device 104 for communication. Since there is no need to add a special function to the existing game apparatus 104, the system can be easily introduced. In addition, when the interval is short, the sound processing device 100 can reasonably recognize excess play assuming that the player plays the game substantially continuously.

  The performance period of general music is fixed time, and is often completed in about several minutes. Even if there is a repeated phrase, the same phrase is rarely repeated endlessly. On the other hand, the game background music ends when the player interrupts the game, so that the playing time has a variable length. Since the game background music is incomplete music, the same phrase (voice pattern) is often repeated endlessly. For this reason, by using the repetition of the voice pattern as a clue, it can be relatively easily distinguished between game background music and other general music.

  Note that the present invention is not limited to the above embodiments and modified examples, and can be embodied by modifying the constituent elements without departing from the gist. Various inventions may be formed by appropriately combining a plurality of components disclosed in the above embodiments and modifications. In addition, some components may be deleted from all the components shown in the above-described embodiment and the modified examples.

  Although the system has been described as being configured by the voice input device 102 and the voice processing device 100, some of the functions of the voice processing device 100 may be realized by the voice input device 102, or the voice processing device 100 and the voice input device Third devices other than 102 may perform some of the functions of these devices.

[Modification]
In the present embodiment, it has been described that various messages such as a caution message and a sedation message are output from the voice input device 102 by voice. As a modified example, the voice processing device 100 may display a message by text or an image on a built-in monitor or an external monitor. The sound processing device 100 may call attention of the player by turning on a lamp. The message need not be in language, but may be non-verbal audio such as a buzzer.

  The voice processing device 100 may include a communication unit (not shown). The communication unit of the audio processing device 100 may transmit a control signal to the game device 104 when detecting an excessive play, and the game device 104 may stop the game when receiving the control signal. The game device 104 may alert the player by vibrating the vibrator of the controller when receiving the control signal. The communication unit of the voice processing device 100 may transmit a message to a communication terminal of a user other than the player. For example, when the player is a child, a caution message may be transmitted to the mobile terminal of the parent.

  The content of the caution message and the notification method may be changed according to the length of the cumulative estimated value. For example, the notifying unit 112 may output a suggestion-type caution message “Let's rest a little” when the cumulative estimated value exceeds one hour, and may output a caution message such as scolding when the total estimated value exceeds two hours. Good. When the time exceeds three hours, the sound processing device 100 may transmit a control signal for activating the vibrator of the controller, or may output an unpleasant sound such as a high-frequency sound.

  In the present embodiment, it has been described that the game background music is detected based on the repetition of the voice pattern. As a modification, the audio processing device 100 may register a plurality of types of game background music in the data storage unit 116 in advance. When detecting the same game background music as the known game background music, the sound determination unit 118 may determine that the game is being played.

  The sound detection unit 110 may detect a sound effect unique to the game, such as an impact sound or a plosive sound, and the sound determination unit 118 may determine the music that is playing when the sound effect of the game is generated as the game background music. Further, the sound determination unit 118 may register the background music at this time in the data storage unit 116 as game background music. Not only the sound effect of the game but also a typical utterance of the player during the game may be detected, and the music playing at this time may be determined as the game background music. As typical utterances, utterances such as “good”, “shit”, and “mo” can be considered. When such a sound effect or utterance is detected a predetermined number of times or more in a unit time, the background music continuously flowing in the unit time may be registered as the game background music.

  In the present embodiment, it has been described that the cumulative estimated value of the play time is calculated by multiplying the voice pattern by the number of repetitions. As a modification, excess play may be determined based on the number of repetitions of the audio pattern. The time estimating unit 120 may count the number of repetitions of the voice pattern, and when the count value is equal to or greater than a predetermined threshold value, may determine that the excess play has been performed.

  The voice input device 102 may output capture information of the game being played by the player based on the number of repetitions of the voice pattern and the cumulative estimated value of the play time. For example, when the sound detection unit 110 repeatedly detects a sound effect at the time of a game over, the notification unit 112 may cause the sound input device 102 to output game capture information.

  In the present embodiment, the voice processing device 100 is driven when the voice input device 102 detects a voice pattern of game background music. As a modification, the voice processing device 100 may periodically detect game background music. For example, the audio processing device 100 may be driven at a pace of once every five minutes. Then, after driving, 30 seconds is a measurement period. The voice determination unit 118 of the voice processing device 100 increments the count value when a voice pattern is detected during the measurement period, and resets the count value when no voice pattern is detected. That is, as the player continues to play the game, the count value gradually increases. When the count value exceeds a predetermined threshold, the time estimating unit 120 determines that the excess play has been performed. The notification unit 112 may output a warning message from the voice input device 102 by voice when the count value exceeds the threshold.

  In the present embodiment, it has been described that the cumulative estimated value is calculated as the estimated value of the substantial continuous play time of the game. As a modification, the total play time in a predetermined period may be used as the cumulative estimated value instead of the continuous play time. For example, assume that the play time of a game per day is limited to two hours. At this time, the time estimating unit 120 calculates the total value of the game play time per day as a cumulative estimated value, and when the cumulative estimated value exceeds 2 hours, the notifying unit 112 outputs a caution message by voice. You may.

  In the present embodiment, the voice input device 102 has been described as a smart speaker. As a modification, the functions of the audio processing device 100 and the audio input device 102 may be realized by any device including a microphone and a speaker. For example, the function of the voice processing device 100 may be implemented as an application of a smartphone, and the same function may be realized using a microphone and a speaker of the smartphone.

  Reference Signs List 100 voice processing device, 102 voice input device, 104 game device, 110 voice detection unit, 112 notification unit, 114 data processing unit, 116 data storage unit, 118 voice determination unit, 120 time estimation unit

Claims (8)

An audio detection unit that detects external audio,
A sound determination unit that determines whether or not the external sound includes a game sound of a computer game;
A time estimating unit that calculates a cumulative estimated value of the play time of the computer game based on the game sound;
A notification unit that notifies a player of a first message when the total estimated value exceeds a first threshold value ,
The voice processing device according to claim 1, wherein the voice determination unit determines that a game sound is included in the external voice when a predetermined voice pattern is repeatedly detected from the external voice.   The time estimating unit, when a second game sound in the second computer game is detected following the first game sound in the first computer game, the first cumulative estimation based on the first game sound The speech processing device according to claim 1, wherein a total estimated value as a whole play time of the computer game is calculated based on both the value and a second total estimated value based on the second game sound. . The audio processing device according to claim 1 , wherein the time estimation unit calculates a cumulative estimated value by multiplying a length of the audio pattern by the number of times the audio pattern is detected. The time estimating unit resets the cumulative estimated value when the interval from the detection of the game sound to the next detection of the game sound exceeds the second threshold value, and performs the play based on the next game sound. The speech processing device according to claim 1 , wherein a cumulative estimated value of time is recalculated. The sound determination unit further detects an uttered sound by the player together with the game sound from the external sound, and determines whether the uttered sound includes a predetermined word,
The voice processing device according to any one of claims 1 to 4, wherein the notification unit notifies the player of a second message when the predetermined word is uttered . An audio detection unit that detects external audio,
When a predetermined voice pattern is repeatedly detected from the external voice, a voice determination unit that determines that a game sound is included in the external voice,
A notification unit configured to notify a player of a first message when the number of consecutive detections of the voice pattern exceeds a third threshold. The ability to detect external audio,
A function of determining that a game sound is included in the external voice when a predetermined voice pattern is repeatedly detected from the external voice;
A function of calculating a cumulative estimated value of the play time of the computer game based on the game sound;
A sound processing program for causing a computer to perform a function of notifying a player of a first message when the cumulative estimated value exceeds a first threshold value. The ability to detect external audio,
A function of determining that a game sound is included in the external voice when a predetermined voice pattern is repeatedly detected from the external voice;
A sound processing program for causing a computer to perform a function of notifying a player of a first message when the number of times of continuous detection of the sound pattern exceeds a third threshold value.

Images