Information processing device, communication terminal, and program

Abstract

The present invention provides an information processing device, a communication terminal, and a program for determining whether or not sleep data has been generated fraudulently. [Solution] In system 10, the information processing device includes a receiving unit that receives user sleep data corresponding to the recorded data from a communication terminal that acquires recorded data of sounds emitted by the user of the communication terminal 200 and sounds emitted by persons other than the user, and a determination unit that determines whether or not the sleep data has been generated fraudulently. The communication terminal includes an acquisition unit that acquires recorded data of sounds emitted by the user of the communication terminal and sounds emitted by persons other than the user, an analysis unit that analyzes the user's sleep state based on the recorded data, a generation unit that generates user sleep data corresponding to the recorded data based on the analysis results obtained by the analysis unit that analyzes the sleep state, and a transmission unit that transmits the sleep data to the information processing device that determines whether or not the sleep data has been generated fraudulently.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, a communication terminal, and a program.

Background Art

[0002] Patent Document 1 describes a program for preventing the unauthorized use of sleep information in a game that progresses based on the sleep information of a user. [Prior Art Document] [Patent Document] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2023-016877

Summary of the Invention

Means for Solving the Problems

[0003] According to an embodiment of the present invention, an information processing apparatus is provided. The information processing apparatus may include a receiving unit that receives sleep data of the user corresponding to the recorded data from the communication terminal that has acquired recorded data obtained by recording sounds emitted by the user of the communication terminal and sounds emitted by others than the user. The information processing apparatus may include a determination unit that determines whether the sleep data has been generated illegally.

[0004] The information processing apparatus may further include a sleep data storage unit that stores past sleep data of the user, and the determination unit determines that the sleep data has not been generated illegally when the similarity between the sleep pattern of the user indicated by the sleep data received by the receiving unit and the past sleep pattern of the user indicated by the past sleep data stored in the sleep data storage unit is lower than a predetermined similarity threshold, and determines that the sleep data has been generated illegally when the similarity is higher than the similarity threshold.

[0005] In any of the above-mentioned information processing devices, the sleep data storage unit may store past sleep data including past sleep patterns encoded by representing REM sleep states with a first value and non-REM sleep states with a second value; the receiving unit may receive the sleep data including sleep patterns encoded by representing REM sleep states with a first value and non-REM sleep states with a second value; and the determination unit may determine the similarity by comparing the encoded sleep pattern with the encoded past sleep patterns.

[0006] In any of the above-mentioned information processing devices, the sleep data storage unit may store past sleep data including past sleep patterns encoded by representing the user being awake with a third value, the user being asleep with a fourth value, the user speaking with a fifth value, and the user not speaking with a sixth value; and the receiving unit may receive the sleep data including the sleep patterns encoded by representing the user being awake with the third value, the user being asleep with the fourth value, the user speaking with the fifth value, and the user not speaking with the sixth value.

[0007] In any of the above-mentioned information processing devices, the sleep data storage unit may store past sleep data including past sleep patterns encoded by representing the communication terminal outputting sound with a seventh value and the communication terminal not outputting sound with an eighth value, and the receiving unit may receive the sleep data including sleep patterns encoded by representing the communication terminal outputting sound with the seventh value and the communication terminal not outputting sound with the eighth value.

[0008] In any of the above-mentioned information processing devices, the receiving unit may further receive metadata of the sleep data, including a recording flag indicating whether or not the communication terminal recorded the sound output by the communication terminal while the user was sleeping, and the determination unit may determine that the sleep data was not fraudulently generated if the recording flag indicates that the communication terminal recorded the sound, and determine that the sleep data was fraudulently generated if the recording flag indicates that the communication terminal did not record the sound.

[0009] In any of the above-mentioned information processing devices, the receiving unit may receive metadata of the sleep data, further including recording start time data indicating the recording start time of the recording data and recording timing data indicating the recording timing at which the communication terminal recorded a sound output by the communication terminal while the user was sleeping. The information processing device may further include a determination unit that determines, based on the recording start time indicated by the recording start time data, the recording timing at which the communication terminal records a sound output by the communication terminal when the sleep data is not fraudulently generated. The determination unit may determine that the sleep data is not fraudulently generated if the recording timing error between the recording timing determined by the determination unit and the recording timing indicated by the recording timing data is smaller than a predetermined tolerance, and determine that the sleep data is fraudulently generated if the recording timing error is larger than the tolerance.

[0010] In any of the above-mentioned information processing devices, the receiving unit may further receive metadata of the sleep data, including a pre-sleep utterance flag indicating whether or not the user uttered a predetermined keyword before starting to sleep, and the determination unit may determine that the sleep data was not generated fraudulently if the pre-sleep utterance flag indicates that the user uttered the keyword, and determine that the sleep data was generated fraudulently if the pre-sleep utterance flag indicates that the user did not utter the keyword.

[0011] If the determination unit determines that the sleep data has not been generated fraudulently, the information processing device may further include a calculation unit that calculates a score for the user's sleep quality based on the sleep data.

[0012] Any of the aforementioned information processing devices may further include a provisioning unit that provides a reward to the user when the score is higher than a predetermined first score threshold, and provides the user with know-how information indicating know-how for improving the user's sleep quality when the score is lower than a predetermined second score threshold which is lower than the first score threshold.

[0013] According to one embodiment of the present invention, a program is provided for an information processing device to execute a receiving procedure for receiving sleep data of the user corresponding to the recorded sound data from a communication terminal that has acquired recorded sound data of sounds emitted by the user of the communication terminal and sounds emitted by persons other than the user, and a determination procedure for determining whether or not the sleep data has been generated fraudulently.

[0014] According to one embodiment of the present invention, a communication terminal is provided. The communication terminal may include an acquisition unit that acquires recording data of sounds emitted by the user of the communication terminal and sounds emitted by persons other than the user. The communication terminal may include an analysis unit that analyzes the user's sleep state based on the recording data. The communication terminal may include a generation unit that generates sleep data of the user corresponding to the recording data based on the analysis results obtained by the analysis unit that analyzes the sleep state. The communication terminal may include a transmission unit that transmits the sleep data to an information processing device that determines whether or not the sleep data has been generated fraudulently.

[0015] The communication terminal may further include an output unit that outputs sound while the user is sleeping, the acquisition unit may acquire the recorded data including the sound output by the output unit, the generation unit may further generate metadata for the sleep data, including recording start time data indicating the recording start time of the recorded data and recording timing data indicating the recording timing when the communication terminal recorded the sound output by the communication terminal while the user was sleeping, and the transmission unit may further transmit the metadata for the sleep data to the information processing device.

[0016] In any of the aforementioned communication terminals, the generation unit may generate the sleep data by encoding the user's sleep pattern, representing the REM sleep state with a first value and the non-REM sleep state with a second value.

[0017] In any of the aforementioned communication terminals, the generation unit may generate the sleep data by encoding the sleep pattern, where a third value indicates that the user is awake, a fourth value indicates that the user is asleep, a fifth value indicates that the user is speaking, and a sixth value indicates that the user is not speaking.

[0018] In any of the aforementioned communication terminals, the generation unit may generate the sleep data by encoding the sleep pattern, where a seventh value indicates that the communication terminal has output sound, and an eighth value indicates that the communication terminal has not output sound.

[0019] According to one embodiment of the present invention, there is provided a program for causing a communication terminal to execute an acquisition procedure for acquiring recording data obtained by recording sounds made by a user of the communication terminal and sounds made by others than the user, an analysis procedure for analyzing a sleep state of the user based on the recording data, a generation procedure for generating sleep data of the user corresponding to the recording data based on an analysis result of the sleep state in the analysis procedure, and a transmission procedure for transmitting the sleep data to an information processing apparatus that determines whether the sleep data is generated illegally.

[0020] Note that the above summary of the invention does not enumerate all the necessary features of the present invention. Also, sub-combinations of these feature groups can also be inventions.

Brief Description of the Drawings

[0021] [Figure 1] An example of the system 10 is schematically shown. [Figure 2] It is an explanatory diagram for explaining an example of the processing flow of the system 10. [Figure 3] It is an explanatory diagram for explaining an example of the processing of the communication terminal 200. [Figure 4] It is an explanatory diagram for explaining the outline of the illegal determination method. [Figure 5] It is an explanatory diagram for explaining an example of the illegal determination method. [Figure 6] It is an explanatory diagram for explaining another example of the illegal determination method. [Figure 7] It is an explanatory diagram for explaining another example of the illegal determination method. [Figure 8] An example of a user 250 in a sleep state is schematically shown. [Figure 9] An example of the functional configuration of the information processing apparatus 100 is schematically shown. [Figure 10] An example of the functional configuration of the communication terminal 200 is schematically shown. [Figure 11] It is an explanatory diagram for explaining an example of the processing flow of the information processing apparatus 100. [Figure 12]A schematic example of the hardware configuration of a computer 1200 that functions as an information processing device 100 or a communication terminal 200 is shown. [Modes for carrying out the invention]

[0022] Driven by the recent rise in health consciousness, the sleep tech market is expanding. Within this market, applications targeting sleep enthusiasts, where users compete based on their sleep quality and quantity, earning rewards such as cryptocurrency for achieving high rankings, are gaining attention. The operators of these applications enhance users' motivation for daily sleep by incorporating a gamified element of rewards for high rankings. Furthermore, these operators collect and analyze sleep data from users, accumulating valuable sleep insights. This allows them to provide users seeking to improve their daily sleep with useful information, such as insights from top-ranked users and product catalogs of sleep-enhancing goods. As a result, these applications can meet a wide range of user needs, giving operators a competitive edge in the sleep tech market. However, given the nature of these applications, where high rankings earn rewards, preventing fraudulent acquisition of rewards is crucial for their operation. In the system according to this embodiment, for example, a communication terminal acquires recording data that includes sounds emitted by the user of the communication terminal, such as breathing sounds or snoring, and sounds emitted by someone other than the user, such as a timestamp emitted by the communication terminal. The system then receives sleep data corresponding to the recording data from the communication terminal and employs a mechanism to determine whether or not the sleep data has been fraudulently generated. Because the sleep data is generated from the recording data that includes not only sounds emitted by the user but also sounds used for fraud detection, the system according to this embodiment can reliably determine whether or not the sleep data has been fraudulently generated.In particular, the system according to this embodiment encodes the user's sleep pattern indicated by sleep data by representing REM sleep and non-REM sleep states with "0" and "1," respectively, and employs a mechanism to determine whether the sleep data has been generated fraudulently by comparing the similarity between the encoded past sleep pattern and the encoded sleep pattern targeted for fraud detection. By encoding the user's sleep pattern and then performing data communication of the sleep data, the system according to this embodiment can reliably determine whether the sleep data, with its reduced data communication volume, has been generated fraudulently while protecting the user's privacy.

[0023] The present invention will be described below through embodiments, but these embodiments are not intended to limit the invention as defined in the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention. In addition, in the drawings, identical or similar parts may be given the same reference numeral to omit redundant descriptions.

[0024] Figure 1 schematically shows an example of system 10. System 10 may include an information processing device 100. System 10 may include a communication terminal 200. System 10 may include a supply device 300.

[0025] System 10 may provide any services related to sleep. For example, System 10 may provide a service for managing sleep. For example, System 10 may provide a service for competing on sleep quality. For example, System 10 may provide a service in which top-ranked individuals in sleep quality scores can receive rewards. For example, System 10 may provide a service for supporting sleep improvement.

[0026] The services provided by System 10 may target a wide range of age groups, from infants to the elderly. Furthermore, the target audience for these services may include healthy individuals, those dissatisfied with their sleep, those with sleep disorders, etc., and is not limited to those with a specific health condition.

[0027] Users of this service may use it for a variety of purposes. Examples of purposes of use include establishing proper sleep habits, improving athletic ability, academic ability, and work vitality, as well as supporting childcare, correcting sleep habits, avoiding overwork and lifestyle-related diseases, coping with hormonal imbalances, and preventing dementia.

[0028] The communication terminal 200 can be any communication terminal capable of wireless communication with the information processing device 100. For example, the communication terminal 200 may be a mobile phone such as a smartphone, a tablet device, or a wearable device. The communication terminal 200 may also be a PC (Personal Computer). Figure 1 shows an example where the communication terminal 200 is a smartphone.

[0029] The communication terminal 200 acquires, for example, recorded sound data of sounds 255 emitted by the user 250 of the communication terminal 200 and sounds emitted by people other than the user. The communication terminal 200 acquires the recorded data, for example, to analyze the sleep state of the user 250.

[0030] Sound 255 includes, for example, the breathing sounds of user 250. Sound 255 includes, for example, the sleep-talking of user 250. Sound 255 includes, for example, snoring. Sound 255 includes, for example, the voice of user 250. Note that "voice" may mean sounds produced by user 250 through their vocal organs at their own will.

[0031] The communication terminal 200 outputs a sound, for example, while user 250 is asleep. The sound output by the communication terminal 200 may be an example of a sound emitted by someone other than user 250.

[0032] The communication terminal 200 analyzes the sleep state of user 250, for example. The communication terminal 200 analyzes the sleep state of user 250 based on recorded data, for example.

[0033] The communication terminal 200 generates sleep data for user 250 corresponding to the recorded data. The communication terminal 200 generates sleep data for user 250 based on the results of an analysis of user 250's sleep state. The communication terminal 200 may also consider the recorded data as user 250's sleep data.

[0034] The communication terminal 200 transmits, for example, the sleep data of user 250. The communication terminal 200 transmits, for example, the sleep data of user 250 via the network 20.

[0035] Network 20 may include a core network provided by a telecommunications carrier. The core network may, for example, conform to a 5G (5th Generation) communication system. The core network may conform to a 6G (6th Generation) or later mobile communication system. The core network may conform to a 3G (3rd Generation) communication system. The core network may conform to an LTE (Long Term Evolution) communication system. Network 20 may include the Internet.

[0036] User 250 may install an application on the communication terminal 200 in order to use the services provided by System 10. User 250 may use the communication terminal 200 to record sound 255 and sounds emitted by persons other than the user by launching the application installed on the communication terminal 200.

[0037] The application may have, for example, a function to acquire recorded data. The application may have, for example, a function to output sound while the application user is sleeping. The application may have, for example, a function to analyze the application user's sleep state based on the recorded data. The application may have, for example, a function to generate sleep data for the application user based on the analysis results of the analysis of the application user's sleep state. The application may have, for example, a function to transmit the application user's sleep data. The application may have, for example, a function to receive the application user's sleep quality score calculated based on the application user's sleep data. The application may have, for example, a function to display the application user's sleep quality score to the application user. The application may have, for example, a function to allow multiple application users to compete for the best sleep quality score. The application may be a free application or a paid application.

[0038] The information processing device 100 performs various information processing tasks. For example, the information processing device 100 performs various information processing tasks so that the system 10 can provide services.

[0039] The information processing device 100 performs a calculation process, for example, to calculate the sleep quality score of user 250. The information processing device 100 performs the calculation process, for example, based on the sleep data of user 250 received from the communication terminal 200. The information processing device 100 receives the sleep data of user 250 from the communication terminal 200 via the network 20.

[0040] The information processing device 100 performs a determination process to determine, for example, whether or not user 250's sleep data has been generated fraudulently. For example, if the information processing device 100 determines that user 250's sleep data has not been generated fraudulently, it performs a calculation process. On the other hand, if the information processing device 100 determines that user 250's sleep data has been generated fraudulently, it does not perform a calculation process. Note that user 250's sleep data that has not been generated fraudulently may be referred to as user 250's legitimately generated sleep data.

[0041] The information processing device 100 notifies, for example, user 250 of score data indicating the sleep quality score. The information processing device 100 notifies user 250 of the score data, for example, via the network 20.

[0042] The information processing device 100 notifies the communication terminal 200 of the score data, for example. The information processing device 100 also notifies the supply device 300 of the score data, for example.

[0043] The supply device 300 supplies various types of information. The supply device 300 supplies various types of information, for example, via the network 20.

[0044] The supply device 300 determines various types of information to supply based, for example, on the score data of the user 250 notified by the information processing device 100. The supply device 300 decides, for example, to supply know-how information showing know-how for improving the user's sleep quality. The supply device 300 decides, for example, to supply a product catalog. Examples of products listed in the product catalog include sleep aids, bedding, furniture, food products, beverages, supplements, medical facilities, and real estate.

[0045] The supply device 300, for example, supplies various information to the information processing device 100. The information processing device 100 may provide the various information supplied by the supply device 300 to the user 250 by transmitting the various information supplied by the supply device 300 to the communication terminal 200. Alternatively, the supply device 300 may supply the various information to the user 250 by directly transmitting the various information to the communication terminal 200.

[0046] Figure 2 is an explanatory diagram illustrating an example of the processing flow of system 10. Here, the starting state is described as the state in which the communication terminal 200 has not yet acquired any recorded data.

[0047] In step 102 (steps may be abbreviated as S), the communication terminal 200 acquires recording data of sounds 255 made by user 250 and sounds made by persons other than user 250. In S104, the communication terminal 200 analyzes user 250's sleep state based on the recording data acquired in S102, and generates user 250's sleep data corresponding to the recording data based on the analysis results of the analysis of user 250's sleep state. In S106, the communication terminal 200 transmits user 250's sleep data generated in S104 to the information processing device 100.

[0048] In S108, the information processing device 100 determines whether the sleep data of user 250 received from the communication terminal 200 in S106 has been generated fraudulently. Here, we will continue the explanation assuming that the information processing device 100 has determined that the sleep data of user 250 has been generated legitimately.

[0049] In S110, the information processing device 100 calculates a sleep quality score for user 250 based on the sleep data of user 250 received from the communication terminal 200 in S106. The information processing device 100 calculates the sleep quality score for user 250 in such a way that, for example, the better the sleep state, the higher the sleep quality score. Note that the sleep quality score may sometimes be referred to as the good sleep score.

[0050] In S112, the information processing device 100 notifies the communication terminal 200 of the score data indicating the sleep quality score of user 250 calculated in S110. In S114, if user 250 is among the top-ranked users in terms of sleep quality score, the information processing device 100 provides a reward to user 250. The reward may be anything that can increase the competitive spirit of application users. The reward may be money, for example. Virtual currency, electronic money, cash, etc. are examples of money. The reward may also be goods, for example. Sleep-enhancing goods, coupon tickets, trophies, etc. are examples of goods. Figure 2 shows an example in which the information processing device 100 provides a reward to user 250 by transmitting virtual currency, which is an example of reward data, to the communication terminal 200.

[0051] In S116, if user 250 wishes to improve sleep quality, the information processing device 100 notifies the supply device 300 of at least one of user 250's score data and user 250's sleep data. In S118, the supply device 300 determines various information to supply to user 250 based on at least one of user 250's score data and user 250's sleep data received from the information processing device 100 in S116, and supplies the determined information to the information processing device 100. In S120, the information processing device 100 provides the information supplied by the supply device 300 to user 250 by transmitting the information supplied by the supply device 300 in S118 to the communication terminal 200.

[0052] Figure 2 shows an example in which the supply device 300 supplies know-how information indicating the sleep techniques of top-ranked users in the sleep quality score ranking. The sleep techniques of top-ranked users in the sleep quality score ranking may be examples of know-how for improving the sleep quality of the 250 users.

[0053] When the supply device 300 supplies sleep know-how from top-ranked individuals in the sleep quality score ranking, it supplies sleep know-how from top-ranked individuals in the sleep quality score ranking who have agreed to disclose their sleep know-how. Agreement to disclose sleep know-how may be included as a condition for receiving compensation.

[0054] As mentioned above, in the sleep tech market, applications that allow users to compete based on their sleep quality and quantity scores, and earn rewards by ranking high in these scores, are currently attracting attention. Due to the nature of these applications, where users can earn rewards by ranking high, preventing fraudulent acquisition of rewards is extremely important for the operation of these applications. To prevent fraudulent acquisition of rewards, it is necessary to be able to reliably determine whether the sleep data used to calculate the sleep quality score has been fraudulently generated. For example, a fraudulent user might try to fraudulently obtain rewards by playing recordings of other users who have achieved high sleep quality scores, or their own past sleep data, and recording them on a communication device, thereby fraudulently generating sleep data that will result in a high sleep quality score. Furthermore, once a fraudulent user succeeds in fraudulently obtaining a reward, they will try to fraudulently obtain rewards multiple times by reusing the fraudulently generated sleep data that they successfully used to fraudulently obtain rewards. However, since the business model using these applications is a new business model, the fraudulent act of fraudulently generating sleep data itself is a newly emerging fraudulent act. Therefore, currently, there is no sufficiently established technology that can reliably determine whether or not sleep data is being generated fraudulently.

[0055] In contrast, according to the system 10 of this embodiment, the communication terminal 200 acquires recording data of sounds 255 emitted by user 250 and sounds emitted by parties other than user 250. For example, the communication terminal 200 acquires recording data of sounds emitted by parties other than user 250, such as sounds emitted by the communication terminal 200, which are used to determine whether user 250's sleep data is fraudulent. Based on the analysis results obtained by analyzing the acquired recording data, the communication terminal 200 generates user 250's sleep data corresponding to the recording data and transmits the generated user 250's sleep data to the information processing device 100. The information processing device 100 determines whether the user 250's sleep data received from the communication terminal 200 has been fraudulently generated. The sleep data of user 250, which is the target of fraud detection by the information processing device 100, corresponds to video data in which not only sounds for analyzing user 250's sleep state but also sounds for determining whether user 250's sleep data has been fraudulently generated. Therefore, the system 10 according to this embodiment can reliably determine whether a user's sleep data has been fraudulently generated. In particular, if the system 10 provides a service in which users with high rankings in sleep quality scores can earn rewards, the system 10 according to this embodiment can reliably determine whether a service user's sleep data has been fraudulently generated, thus preventing fraudulent acquisition of rewards. As a result, the reliability of the sleep quality score ranking is increased, and it is expected that many service users will strive to improve their sleep quality in order to earn rewards. Therefore, the system 10 according to this embodiment can contribute to the promotion of service users' health from the perspective of improving the sleep quality of service users.

[0056] Figure 3 is an explanatory diagram illustrating an example of the processing performed by the communication terminal 200. Here, we will mainly explain an example of the process by which the communication terminal 200 generates sleep data corresponding to the recorded data.

[0057] The communication terminal 200 analyzes the sleep state of user 250, for example. The communication terminal 200 analyzes the sleep state of user 250 based on recorded data of sounds 255 made by user 250 and sounds made by people other than user 250.

[0058] The communication terminal 200 analyzes the sleep state of user 250 at predetermined analysis intervals, for example. Examples of analysis intervals include 1 second, 10 seconds, 30 seconds, 1 minute, 10 minutes, 15 minutes, 30 minutes, 45 minutes, and 1 hour. In Figure 3, the time at which the communication terminal 200 analyzes the sleep state of user 250 is shown as an analysis point.

[0059] The communication terminal 200 analyzes the sleep state of user 250, for example, by analyzing the sleep duration of user 250. The communication terminal 200 also analyzes the sleep duration of user 250, for example, by analyzing the sleep start time when user 250 began sleeping and the sleep end time when user 250 ended sleeping.

[0060] The communication terminal 200 analyzes the sleep state of user 250, for example, by analyzing the sleep state of user 250 while user 250 is asleep. The communication terminal 200 analyzes the sleep state of user 250, for example, by analyzing whether user 250 is in REM sleep or non-REM sleep while user 250 is asleep. The communication terminal 200 analyzes the sleep state of user 250, for example, by analyzing the transition of user 250's sleep state between REM sleep and non-REM sleep. Note that the transition of sleep state may be referred to as a sleep pattern.

[0061] The communication terminal 200 generates sleep data for user 250 corresponding to the recorded data. The communication terminal 200 generates sleep data for user 250 based on the analysis results obtained by analyzing the sleep state of user 250 based on the recorded data.

[0062] The communication terminal 200 generates sleep data for user 250, for example, by encoding the sleep pattern of user 250. The communication terminal 200 encodes the sleep pattern of user 250, for example, by representing REM sleep states with a first value and non-REM sleep states with a second value. The communication terminal 200 may transmit the encoded sleep data of user 250 to the information processing device 100. Figure 3 shows an example in which the communication terminal 200 encodes the sleep pattern of user 250 into 20 binary data "01111011110111101111" by representing REM sleep states with "0" and non-REM sleep states with "1".

[0063] According to the system 10 shown in Figure 3, the communication terminal 200 generates user 250's sleep data by encoding the user 250's sleep pattern and transmits the encoded user 250's sleep data to the information processing device 100. This allows the communication terminal 200 to transmit user 250's sleep data to the information processing device 100 after removing user 250's personal information from the recording data, which may contain sounds that could include user 250's personal information, such as user 250's sleep talking or conversations. Therefore, the system 10 shown in Figure 3 can transmit user sleep data while protecting privacy. Furthermore, by transmitting encoded sleep data, the system 10 shown in Figure 3 can transmit user sleep data with less data transmission compared to transmitting unencoded recording data.

[0064] Figure 4 is an explanatory diagram illustrating the overview of the fraud detection method. Here, we mainly explain the overview of three fraud detection methods used to determine whether or not the sleep data of 250 users targeted for fraud detection has been fraudulently generated.

[0065] "Fraud detection method 1" shown in Figure 4 is a fraud detection method that determines whether or not the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated, based on a sound 255 emitted by user 250. "Fraud detection method 2" shown in Figure 4 is a fraud detection method that determines whether or not the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated, based on a sound 205 output by the communication terminal 200. "Fraud detection method 3" shown in Figure 4 is a fraud detection method that determines whether or not the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated, based on the user 250's past sleep data.

[0066] The information processing device 100 includes, for example, a sleep data storage unit 102. The sleep data storage unit 102 stores, for example, the past sleep data of user 250. The sleep data storage unit 102 stores, for example, legitimately generated past sleep data of user 250.

[0067] The information processing device 100 includes, for example, a fraud detection function 150. The fraud detection function 150 determines, for example, whether or not the sleep data of a user 250 subject to fraud detection has been generated fraudulently.

[0068] The fraud detection function 150, for example, uses "fraud detection method 1" to determine whether or not the sleep data of the user 250 targeted for fraud detection has been generated fraudulently. The fraud detection function 150, for example, uses "fraud detection method 2" to determine whether or not the sleep data of the user 250 targeted for fraud detection has been generated fraudulently. The fraud detection function 150, for example, uses "fraud detection method 3" to determine whether or not the sleep data of the user 250 targeted for fraud detection has been generated fraudulently.

[0069] The fraud detection function 150 uses, for example, one of the fraud detection methods "Fraud Detection Method 1," "Fraud Detection Method 2," and "Fraud Detection Method 3" to determine whether or not the sleep data of the target user 250 has been generated fraudulently. For example, if the fraud detection function 150 determines that the sleep data of the target user 250 has been generated fraudulently using one of the fraud detection methods used, it determines that the sleep data of the target user 250 has been generated fraudulently. On the other hand, if the fraud detection function 150 determines that the sleep data of the target user 250 has not been generated fraudulently using one of the fraud detection methods used, it determines that the sleep data of the target user 250 has not been generated fraudulently.

[0070] The fraud detection function 150 determines whether the sleep data of the target user 250 has been generated fraudulently by using, for example, two or more fraud detection methods from among "fraud detection method 1," "fraud detection method 2," and "fraud detection method 3." For example, if the fraud detection function 150 determines that the sleep data of the target user 250 has been generated fraudulently using any one of the two or more fraud detection methods used, it determines that the sleep data of the target user 250 has been generated fraudulently. On the other hand, if the fraud detection function 150 determines that the sleep data of the target user 250 has not been generated fraudulently using all two or more fraud detection methods used, it determines that the sleep data of the target user 250 has not been generated fraudulently.

[0071] The upper part of Figure 4 schematically shows an example of when user 250's sleep data is generated correctly. The upper part of Figure 4 shows an example where the communication terminal 200 records sounds 255 emitted by user 250 while he is asleep.

[0072] The lower part of Figure 4 schematically shows an example of when user 250's sleep data is fraudulently generated. The lower part of Figure 4 shows an example where the communication terminal 200 records the sound 605, which is a recording of a high-scoring sleep score sound output by speaker 600.

[0073] Figure 5 is an explanatory diagram illustrating an example of a fraud detection method. Here, we will mainly explain "Fraud Detection Method 1".

[0074] The communication terminal 200 generates metadata for user 250's sleep data, for example. The communication terminal 200 may transmit this metadata to the information processing device 100.

[0075] The metadata includes, for example, recording date data indicating the recording date of the recording data corresponding to user 250's sleep data. The metadata also includes, for example, recording time data indicating the recording duration of the recording data. The metadata also includes, for example, recording start time data indicating the recording start time of the recording data. The metadata also includes, for example, recording end time data indicating the recording end time of the recording data. The metadata also includes, for example, a pre-sleep vocalization flag indicating whether user 250 uttered a predetermined keyword before user 250 began to sleep. The metadata also includes, for example, a post-sleep vocalization flag indicating whether user 250 uttered a predetermined keyword after user 250 ended to sleep. The metadata also includes, for example, sleep duration data indicating user 250's sleep duration.

[0076] For example, the fraud detection function 150 determines that the sleep data of user 250 is legitimately generated if the pre-sleep utterance flag indicates that user 250 uttered a predetermined keyword before falling asleep. On the other hand, the fraud detection function 150 determines that the sleep data of user 250 is fraudulently generated if the pre-sleep utterance flag indicates that user 250 did not utter a predetermined keyword before falling asleep. In other words, when the fraud detection function 150 uses "fraud detection method 1" to determine whether the sleep data of user 250 is fraudulently generated, user 250 must utter a predetermined keyword and record it in the recording data in order for the sleep data of user 250 to be determined to be legitimately generated. In Figure 5, "Goodnight" is shown as an example of a predetermined keyword.

[0077] The upper diagram of Figure 5 shows an example of metadata for the sleep data of user 250, when the fraud detection function 150 determines whether the sleep data of user 250, who is subject to fraud detection, is legitimately generated in "Fraud Detection Method 1". The metadata indicates that the recording date of the audio data corresponding to the sleep data is "December 1st to December 2nd", the recording time of the audio data is from "11:15 PM" on December 1st to "5:45 AM" on December 2nd, and the sleep time of user 250 in the sleep data is from "11:30 PM" on December 1st to "5:40 AM" on December 2nd.

[0078] The middle diagram in Figure 5 is an explanatory diagram illustrating an example in which the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, is legitimately generated in "Fraud Detection Method 1". As shown in the middle diagram in Figure 5, user 250 emits sound 255, which is the voice of "goodnight", and records it in the recording data before starting to sleep. Therefore, the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, is legitimately generated because user 250 uttered a predetermined keyword before starting to sleep.

[0079] The lower diagram in Figure 5 is an explanatory diagram illustrating an example in which the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated in "Fraud Detection Method 1". As shown in the lower diagram in Figure 5, user 250 starts to sleep without uttering the voice "goodnight" before falling asleep. Therefore, the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated because user 250 did not utter the predetermined keyword before starting to sleep.

[0080] According to the system 10 shown in Figure 5, simply by having the user 250 utter predetermined keywords such as greetings that are deeply ingrained in daily life, the information processing device 100 can determine whether or not the sleep data of the user 250 being flagged for fraud has been fraudulently generated, without having to examine the sleep data of the user 250 being flagged for fraud itself. Therefore, the system 10 shown in Figure 5 can determine whether or not a service user's sleep data has been fraudulently generated while suppressing a decline in the user experience of the service user.

[0081] Figure 6 is an explanatory diagram illustrating another example of a fraud detection method. Here, we will mainly explain "Fraud Detection Method 2".

[0082] The communication terminal 200 outputs a sound 205, for example, while the user 250 is sleeping. The sound 205 may be a sound used to detect inconsistencies in the user 250's sleep data.

[0083] The communication terminal 200 periodically outputs a sound 205, for example, while the user 250 is asleep. Here, a timestamp is given as an example of a sound 205.

[0084] The communication terminal 200 has, for example, a function to output multiple types of sounds 205. The communication terminal 200 also has, for example, a function to output different types of sounds 205 depending on the output time at which the sounds 205 are output.

[0085] The metadata for user 250's sleep data includes, for example, sound type data indicating the type of sound output by the sound output device during user 250's sleep. This metadata also includes, for example, output timing data indicating the timing of the sound output by the sound output device during user 250's sleep. This metadata also includes, for example, a recording flag indicating whether or not the communication terminal 200 recorded the sound output by the sound output device during user 250's sleep. This metadata also includes, for example, recording timing data indicating the timing at which the communication terminal 200 recorded the sound output by the sound output device during user 250's sleep.

[0086] The sound output device can be any device that can output sound while user 250 is asleep. The sound output device is, for example, a communication terminal 200. The sound output device may also be a device other than the communication terminal 200, such as a speaker. In this case, the sound output device may be synchronized with the time of the communication terminal 200. The sound output by the sound output device may be an example of a sound emitted by someone other than user 250.

[0087] The fraud detection function 150 determines, for example, the recording timing at which the communication terminal 200 records the sound output by the sound output device when the sleep data of the user 250 targeted for fraud detection is legitimately generated. The fraud detection function 150 determines, for example, the recording start time indicated by the recording start time data included in the metadata of the sleep data of the user 250 targeted for fraud detection, when the sleep data of the user 250 targeted for fraud detection is legitimately generated, and the recording timing at which the communication terminal 200 records the sound output by the sound output device.

[0088] For example, the fraud detection function 150 determines that the sleep data of user 250 subject to fraud detection is legitimately generated if the recording timing error between the determined recording timing and the recording timing indicated by the recording timing data is smaller than a predetermined tolerance. On the other hand, the fraud detection function 150 determines that the sleep data of user 250 subject to fraud detection is fraudulently generated if the recording timing error is larger than the tolerance. In other words, when the fraud detection function 150 uses the "fraud detection method 2" to determine whether the sleep data of user 250 subject to fraud detection is fraudulently generated, in order for the sleep data of user 250 subject to fraud detection to be determined to be legitimately generated, user 250 must sleep with the recording timing error smaller than the tolerance. Note that in Figure 6, sound 205 is shown as an example of a sound output by the sound output device. Furthermore, the explanation continues assuming that the tolerance is 60 seconds.

[0089] The upper part of Figure 6 shows an example of metadata for the sleep data of user 250, when the fraud detection function 150 determines whether the sleep data of user 250, who is subject to fraud detection, is legitimately generated in "Fraud Detection Method 2". The metadata indicates that the recording date of the audio data corresponding to the sleep data is "December 1st to December 2nd", the recording time of the audio data is from "11:15 PM" on December 1st to "5:45 AM" on December 2nd, and the sleep time of user 250 in the sleep data is from "11:30 PM" on December 1st to "5:40 AM" on December 2nd.

[0090] Here, we will continue the explanation assuming that the communication terminal 200 output sound 205 a total of six times: at "0:00 AM on December 2nd", "1:00 AM on December 2nd", "2:00 AM on December 2nd", "3:00 AM on December 2nd", "4:00 AM on December 2nd", and "5:00 AM on December 2nd". Furthermore, here we will continue the explanation assuming that the fraud detection function 150 determined that the timing of the recording of sound 205 by the communication terminal 200 when the sleep data of the user 250 subject to fraud detection was legitimately generated was at the time when "00:45:00", "01:45:00", "02:45:00", "03:45:00", "04:45:00", and "05:45:00" elapsed from the recording start time of the recording data corresponding to the sleep data.

[0091] The middle diagram in Figure 6 is an explanatory diagram illustrating an example in which the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, is generated legitimately in "Fraud Detection Method 2". As shown in the middle diagram in Figure 6, the fraud detection function 150 determines that the recording timings indicated by the recording timing data are "00:45:15", "01:45:15", "02:45:15", "03:45:15", "04:45:15", and "05:45:15" from the recording start time of the recording data corresponding to the sleep data. Therefore, the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, is generated legitimately because the recording timing error between each determined recording timing and each recording timing indicated by the recording timing data is 15 seconds, which is less than 60 seconds.

[0092] The lower diagram in Figure 6 is an explanatory diagram illustrating an example in which the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated in "Fraud Detection Method 2". As shown in the lower diagram in Figure 6, the fraud detection function 150 determines that the recording timings indicated by the recording timing data are "00:29:30", "01:29:30", "02:29:30", "03:29:30", "04:29:30", and "05:29:30" from the recording start time of the recording data corresponding to the sleep data. Therefore, the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated because the recording timing error between each determined recording timing and each recording timing indicated by the recording timing data is 930 seconds, which is longer than 60 seconds.

[0093] According to the system 10 shown in Figure 6, the information processing device 100 determines whether the sleep data of the user 250 subject to fraud detection has been fraudulently generated by determining whether the recording timing error is smaller than the allowable error. As a result, the system 10 shown in Figure 6 can determine whether the sleep data of the user subject to fraud detection has been fraudulently generated without examining the sleep data of the user subject to fraud detection itself, even if the user's sleep data has been fraudulently generated by a fraudulent method such as outputting a sound of a high-scoring good sleep score to the speaker. In particular, by having the communication terminal 200 output different types of sounds 205 depending on the output time when the sound 205 is output, or by setting a high output frequency for the communication terminal 200 to output the sound 205, the system 10 shown in Figure 6 can determine with high accuracy whether the sleep data of the user subject to fraud detection has been fraudulently generated without examining the sleep data of the user subject to fraud detection itself. Furthermore, by making the sound 205 output by the communication terminal 200 during the user 250's sleep difficult for the user 250 to hear and still recordable by the communication terminal 200, the system 10 shown in Figure 6 can determine whether or not the service user's sleep data is being generated fraudulently while suppressing a decline in the service user's user experience.

[0094] Figure 7 is an explanatory diagram illustrating another example of a fraud detection method. Here, we will mainly explain "Fraud Detection Method 3".

[0095] The fraud detection function 150 identifies the similarity between two sleep patterns by, for example, comparing the encoded sleep pattern of user 250, indicated by the sleep data of user 250 subject to fraud detection, with the encoded past sleep pattern of user 250, indicated by the past sleep data of user 250 stored in the sleep data storage unit 102. For example, the fraud detection function 150 determines that the sleep data is legitimately generated if the identified similarity is lower than a predetermined similarity threshold. On the other hand, the fraud detection function 150 determines that the sleep data is fraudulently generated if the identified similarity is higher than the similarity threshold. In other words, when the fraud detection function 150 uses the "fraud detection method 3" to determine whether the sleep data of user 250 subject to fraud detection is fraudulently generated, in order for the sleep data of user 250 subject to fraud detection to be determined to be legitimately generated, user 250 must sleep with a sleep pattern whose similarity to user 250's past sleep patterns is lower than the similarity threshold. Here, we will continue the explanation assuming that REM sleep and non-REM sleep are represented by "0" and "1" respectively, and that the similarity threshold is 0.85.

[0096] The upper part of Figure 7 shows an example of metadata for the sleep data of user 250, when the fraud detection function 150 determines whether the sleep data of user 250, who is subject to fraud detection, is legitimately generated in "Fraud Detection Method 3". The metadata indicates that the recording date of the audio data corresponding to the sleep data is "December 1st to December 2nd", the recording time of the audio data is from "11:15 PM" on December 1st to "5:45 AM" on December 2nd, and the sleep time of user 250 in the sleep data is from "11:30 PM" on December 1st to "5:40 AM" on December 2nd.

[0097] The middle diagram in Figure 7 is an explanatory diagram illustrating an example in which the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, is legitimately generated in "Fraud Detection Method 3". As shown in the middle diagram in Figure 7, the sleep pattern of user 250, indicated by the sleep data of user 250, is encoded with 20 binary data "01111011110111101111", and the past sleep pattern of user 250, indicated by the past sleep data of user 250 stored in the sleep data storage unit 102, is encoded with 20 binary data "01110111011111011110". The fraud detection function 150 compares the two sleep patterns and determines that 13 of the 20 binary data match, so the similarity between the two sleep patterns is 13 / 20 = 0.65. Therefore, the fraud detection function 150 determines that the sleep data of the user 250 targeted for fraud detection is legitimate because the similarity of the two sleep patterns in question (0.65) is lower than 0.85.

[0098] The lower diagram of Figure 7 is an explanatory diagram illustrating an example in which the fraud detection function 150 determines that the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated in "Fraud Detection Method 3". As shown in the lower diagram of Figure 7, the sleep pattern of user 250, indicated by the sleep data of user 250, is encoded with 20 binary data "01111011110111101111", and the past sleep pattern of user 250, indicated by the past sleep data of user 250 stored in the sleep data storage unit 102, is encoded with 20 binary data "01111011110111101111". The fraud detection function 150 compares the two sleep patterns and determines that all 20 of the 20 binary data match, so the similarity between the two sleep patterns is 20 / 20 = 1. Therefore, the fraud detection function 150 determines that the sleep data of the user 250 targeted for fraud detection is fraudulently generated because the similarity of the two sleep patterns in question is higher than 0.85.

[0099] According to the system 10 shown in Figure 7, the information processing device 100 determines whether the sleep data of the user 250 targeted for fraud detection has been fraudulently generated by determining whether the similarity between the encoded sleep pattern of the user 250, indicated by the sleep data of the user 250 targeted for fraud detection, and the encoded past sleep pattern of the user 250, indicated by the past sleep data of the user 250 stored in the sleep data storage unit 102, is lower than a similarity threshold. By using the sleep data of the user targeted for fraud detection itself for fraud detection, the system 10 shown in Figure 7 can determine with high accuracy whether the sleep data of the user targeted for fraud detection has been fraudulently generated, even if the user's sleep data was fraudulently generated by a fraudulent method such as outputting a sound recording of a high-scoring sleep score to a speaker. Furthermore, since the system 10 shown in Figure 7 can determine whether the sleep data of the user targeted for fraud detection has been fraudulently generated without causing any special work or burden on the user 250, it can determine whether the sleep data of a service user has been fraudulently generated while suppressing a deterioration in the user experience of the service user.

[0100] Figure 8 schematically shows an example of user 250 in a sleeping state. User 250 is sleeping while wearing a wearable device 400.

[0101] The information processing device 100 may calculate the user 250's sleep quality score not only based on the user 250's sleep data generated from the communication terminal 200 or recorded data, but also based on the user 250's sleep data generated from the user 250's biometric information measured by the wearable terminal 400. The information processing device 100 may also calculate the user 250's sleep quality score based on the user 250's sleep data generated from the user 250's biometric information measured by biosensors mounted on bedding such as beds and pillows.

[0102] At least one of the wearable terminal 400 and the biosensor transmits the user 250's sleep data to the information processing device 100, for example, via the communication terminal 200. For example, at least one of the wearable terminal 400 and the biosensor transmits the user 250's sleep data to the communication terminal 200 by establishing a short-range wireless communication connection such as Wi-Fi®, Bluetooth®, and Zigbee® with the communication terminal 200. The communication terminal 200 transmits the user 250's sleep data received from at least one of the wearable terminal 400 and the biosensor to the information processing device 100. At least one of the wearable terminal 400 and the biosensor may also transmit the user 250's sleep data directly to the information processing device 100 via the network 20.

[0103] Figure 9 schematically shows an example of the functional configuration of the information processing device 100. The information processing device 100 includes a sleep data storage unit 102, a receiving unit 104, a determination unit 106, a decision unit 108, a threshold setting unit 112, a learning data acquisition unit 114, a learning data storage unit 116, a model generation unit 118, a model storage unit 122, a model acquisition unit 124, an input data acquisition unit 125, a calculation unit 126, a notification unit 128, a collection unit 132, a know-how information storage unit 134, and a provision unit 136. However, it is not necessarily required that the information processing device 100 include all of these components.

[0104] The sleep data storage unit 102 stores the past sleep data of user 250. For example, the sleep data storage unit 102 stores the past sleep data of multiple users 250.

[0105] The receiving unit 104 receives various types of information. The receiving unit 104 receives various types of information, for example, via the network 20.

[0106] The receiving unit 104 may receive various information from, for example, the communication terminal 200. The receiving unit 104 may also receive various information from the supply device 300. The receiving unit 104 may also receive various information from any other external device.

[0107] The receiving unit 104 receives, for example, sleep data of user 250. The receiving unit 104 receives, for example, sleep data of user 250 corresponding to recorded data acquired by the communication terminal 200. The receiving unit 104 receives, for example, sleep data of user 250 generated based on the user's biometric information measured by the wearable terminal 400. The receiving unit 104 receives, for example, sleep data of user 250 generated based on the user's biometric information measured by biosensors mounted on bedding such as beds and pillows.

[0108] The receiving unit 104 receives, for example, know-how information. The receiving unit 104 also receives, for example, a product catalog.

[0109] The determination unit 106 determines whether the sleep data of user 250, which is subject to fraud detection and received by the receiving unit 104, has been fraudulently generated. The sleep data of user 250, which is subject to fraud detection, may be the sleep data of user 250 corresponding to the recording data acquired by the communication terminal 200. The fraud detection function 150 may be an example of the determination unit 106.

[0110] The determination unit 106 determines, for example, whether the sleep data of user 250, which is subject to fraud detection, has been fraudulently generated, based on the user's past sleep data stored in the sleep data storage unit 102. For example, the determination unit 106 determines that the sleep data of user 250, which is subject to fraud detection, has not been fraudulently generated if the similarity between the sleep pattern of user 250, as shown by the sleep data of user 250, and the past sleep pattern of user 250, as shown by the past sleep data of user 250 stored in the sleep data storage unit 102, is lower than a predetermined similarity threshold. On the other hand, the determination unit 106 determines that the sleep data of user 250, which is subject to fraud detection, has been fraudulently generated if the similarity is higher than the similarity threshold.

[0111] The determination unit 106 may determine the similarity by, for example, comparing the encoded sleep pattern of user 250, indicated by the sleep data of user 250 subject to fraud detection, with the encoded past sleep pattern of user 250, indicated by the past sleep data of user 250. The determination unit 106 may also determine the similarity by comparing the unencoded sleep pattern of user 250, indicated by the sleep data of user 250 subject to fraud detection, with the unencoded past sleep pattern of user 250, indicated by the past sleep data of user 250.

[0112] The receiving unit 104 receives, for example, metadata of the sleep data of the user 250 that is subject to fraud detection. The determination unit 106 determines, for example, whether or not the sleep data of the user 250 that is subject to fraud detection has been fraudulently generated, based on the metadata of the sleep data of the user 250 that is subject to fraud detection.

[0113] For example, the determination unit 106 determines that the sleep data of user 250, which is subject to fraud detection, has not been fraudulently generated if the recording flag included in the metadata of user 250's sleep data indicates that the communication terminal 200 recorded the sound output by the sound output device while user 250 was sleeping. On the other hand, the determination unit 106 determines that the sleep data of user 250, which is subject to fraud detection, has been fraudulently generated if the recording flag indicates that the communication terminal 200 did not record the sound output by the sound output device while user 250 was sleeping.

[0114] For example, the determination unit 106 determines that the sleep data of user 250 has not been generated fraudulently if the pre-sleep utterance flag included in the metadata of user 250's sleep data indicates that user 250 uttered a predetermined keyword before falling asleep. On the other hand, the determination unit 106 determines that the sleep data of user 250 has been generated fraudulently if the pre-sleep utterance flag indicates that user 250 did not utter a predetermined keyword before falling asleep.

[0115] For example, the determination unit 106 determines that the sleep data of user 250 has not been generated fraudulently if the post-sleep vocalization flag included in the metadata of user 250's sleep data indicates that user 250 uttered a predetermined keyword after ending sleep. On the other hand, the determination unit 106 determines that the sleep data of user 250 has been generated fraudulently if the post-sleep vocalization flag indicates that user 250 did not utter a predetermined keyword after ending sleep.

[0116] For example, the determination unit 106 determines that the sleep data of the user 250 subject to fraud detection has not been generated fraudulently if the pre-sleep vocalization flag included in the metadata of the sleep data of the user 250 subject to fraud detection indicates that the user 250 uttered a predetermined keyword before the user 250 started sleeping, and the post-sleep vocalization flag included in the metadata of the sleep data of the user 250 subject to fraud detection indicates that the user 250 uttered a predetermined keyword after the user 250 ended sleeping. On the other hand, the determination unit 106 determines that the sleep data of user 250 subject to fraud detection has been generated fraudulently if the post-sleep utterance flag indicates that user 250 uttered a predetermined keyword after user 250 finished sleeping, but the pre-sleep utterance flag indicates that user 250 did not utter a predetermined keyword before user 250 started sleeping; if the pre-sleep utterance flag indicates that user 250 uttered a predetermined keyword before user 250 started sleeping, but the post-sleep utterance flag indicates that user 250 did not utter a predetermined keyword after user 250 finished sleeping; or if the pre-sleep utterance flag indicates that user 250 did not utter a predetermined keyword before user 250 started sleeping, and the post-sleep utterance flag indicates that user 250 did not utter a predetermined keyword after user 250 finished sleeping.

[0117] The determination unit 108 determines various timings. For example, the determination unit 108 determines various timings based on various information received by the receiving unit 104.

[0118] The determination unit 108 determines, for example, the output timing that the sound output device will output if the sleep data of the user 250 subject to fraud detection has not been generated fraudulently. The determination unit 108 determines, for example, the output timing that the sound output device will output if the sleep data of the user 250 subject to fraud detection has not been generated fraudulently, based on the recording start time indicated by the recording start time data included in the metadata of the sleep data of the user 250 subject to fraud detection. The determination unit 108 further determines, for example, the output timing that the sound output device will output if the sleep data of the user 250 subject to fraud detection has not been generated fraudulently, based on the type of sound output by the sound output device during the user 250's sleep, indicated by the sound type data included in the metadata.

[0119] The determination unit 108 determines, for example, the recording timing at which the communication terminal 200 will record the sound output by the sound output device when the sleep data of the user 250 subject to fraud detection has not been generated fraudulently. The determination unit 108 determines, for example, the recording start time indicated by the recording start time data included in the metadata of the sleep data of the user 250 subject to fraud detection, and determines the recording timing at which the communication terminal 200 will record the sound output by the sound output device when the sleep data of the user 250 subject to fraud detection has not been generated fraudulently, based on the type of sound output by the sound output device during the user 250's sleep, indicated by the sound type data included in the metadata.

[0120] For example, the determination unit 106 determines that the sleep data of the user 250 subject to fraud detection has not been generated fraudulently if the output timing error between the output timing determined by the decision unit 108 and the output timing indicated by the output timing data included in the metadata of the sleep data of the user 250 subject to fraud detection is smaller than a predetermined tolerance error. On the other hand, the determination unit 106 determines that the sleep data of the user 250 subject to fraud detection has been generated fraudulently if the output timing error is larger than the tolerance error.

[0121] The determination unit 106 determines whether the sleep data of user 250, who is subject to fraud detection, has been generated fraudulently by determining, for example, if the sound output device outputs sound multiple times while user 250 is sleeping, whether the average of the multiple output timing errors is smaller than the allowable error. The determination unit 106 determines whether the sleep data of user 250, who is subject to fraud detection, has been generated fraudulently by determining, for example, if the sound output device outputs sound multiple times while user 250 is sleeping, whether the largest output timing error among the multiple output timing errors is smaller than the allowable error.

[0122] For example, the determination unit 106 determines that the sleep data of the user 250 subject to fraud detection has not been generated fraudulently if the recording timing error between the recording timing determined by the decision unit 108 and the recording timing indicated by the recording timing data included in the metadata of the sleep data of the user 250 subject to fraud detection is smaller than a predetermined tolerance error. On the other hand, the determination unit 106 determines that the sleep data of the user 250 subject to fraud detection has been generated fraudulently if the recording timing error is larger than the tolerance error.

[0123] The determination unit 106 determines whether the sleep data of user 250, who is subject to fraud detection, has been generated fraudulently by determining, for example, if the sound output device outputs sound multiple times while user 250 is sleeping, whether the average of the multiple recording timing errors is smaller than the allowable error. The determination unit 106 determines whether the sleep data of user 250, who is subject to fraud detection, has been generated fraudulently by determining, for example, if the sound output device outputs sound multiple times while user 250 is sleeping, whether the largest of the multiple recording timing errors is smaller than the allowable error.

[0124] For example, if the sound output device outputs sound multiple times while the user 250 is sleeping, and the sound output device outputs multiple different types of sound while the user 250 is sleeping, the determination unit 106 identifies the output timing error between the output timing determined by the determination unit 108 and the output timing indicated by the output timing data included in the metadata of the sleep data of the user 250 subject to fraud detection, for each type of sound output by the sound output device while the user 250 is sleeping.

[0125] The threshold setting unit 112 sets a similarity threshold. The threshold setting unit 112 sets the similarity threshold, for example, by receiving an input for the similarity threshold from an input unit of the information processing device 100. The determination unit 106 may use the similarity threshold set by the threshold setting unit 112 to determine whether or not the sleep data of the user 250 subject to fraud detection has been generated fraudulently.

[0126] The learning data acquisition unit 114 acquires learning data. The learning data includes, for example, user attribute data indicating the attributes of user 250 and similarity data indicating the similarity between two sleep patterns of user 250 previously identified. The learning data acquisition unit 114 may store the acquired learning data in the learning data storage unit 116.

[0127] The model generation unit 118 generates a decision model from input data, including user attribute data indicating the attributes of the user 250, to determine a similarity threshold used to determine whether or not the sleep data of the user 250 subject to fraud detection has been fraudulently generated. The model generation unit 118 generates the decision model by machine learning, for example, using multiple training data stored in the training data storage unit 116 as training data. The model generation unit 118 may store the generated decision model in the model storage unit 122.

[0128] The model acquisition unit 124 acquires a decision model. The model acquisition unit 124 acquires a decision model, for example, from a model generation device. The model acquisition unit 124 may store the acquired decision model in the model storage unit 122. The decision model acquired by the model acquisition unit 124 may be the same as the decision model that the model generation unit 118 can generate.

[0129] The input data acquisition unit 125 acquires input data used to determine the similarity threshold using the decision model stored in the model storage unit 122. The input data includes, for example, user attribute data indicating the attributes of user 250.

[0130] User attribute data may include, for example, gender data indicating the user's sex; age data indicating the user's age; occupation data indicating the user's occupation; family structure data indicating the user's family structure; medical history data indicating the user's medical history; average sleep quality score data indicating the average sleep quality score of the user; average rank data indicating the average rank of the user's sleep quality score; and any other data relating to the user's attributes.

[0131] The threshold setting unit 112 sets a similarity threshold used to determine whether or not the sleep data of a user 250 subject to fraud detection has been fraudulently generated, for example, using a decision model stored in the model storage unit 122. The threshold setting unit 112 determines the similarity threshold from the input data, including the user attribute data of the communication terminal 200, acquired by the input data acquisition unit 125, for example, using the decision model.

[0132] The calculation unit 126 calculates the sleep quality score for user 250. For example, if the determination unit 106 determines that the sleep data of user 250, who is subject to fraud detection, has not been fraudulently generated, the calculation unit 126 calculates the sleep quality score for user 250. On the other hand, if the determination unit 106 determines that the sleep data of user 250, who is subject to fraud detection, has been fraudulently generated, the calculation unit 126 does not calculate the sleep quality score for user 250.

[0133] The calculation unit 126 calculates a sleep quality score for user 250 based on the sleep data of user 250 received by the receiving unit 104, for example. The calculation unit 126 also calculates a sleep quality score for user 250 based on the sleep data of user 250 corresponding to the recorded data acquired by the communication terminal 200, for example.

[0134] The calculation unit 126 calculates a sleep quality score for user 250 based on user 250 sleep data generated based on user 250's biometric information measured by a wearable terminal 400, for example. The calculation unit 126 calculates a sleep quality score for user 250 based on user 250 sleep data generated based on user 250's biometric information measured by a biosensor mounted on bedding such as a bed or pillow, for example.

[0135] The notification unit 128 notifies various types of information. The notification unit 128 notifies various types of information, for example, via the network 20.

[0136] The notification unit 128 notifies, for example, the communication terminal 200 of various information. The notification unit 128 also notifies, for example, the supply device 300 of various information.

[0137] For example, if the determination unit 106 determines that the sleep data of user 250, who is subject to fraud detection, is not generated fraudulently, the notification unit 128 will notify the user 250 of score data showing the sleep quality score calculated by the calculation unit 126. On the other hand, if the determination unit 106 determines that the sleep data of user 250, who is subject to fraud detection, is generated fraudulently, the notification unit 128 will notify the user 250 of an alert indicating that the sleep data of user 250, who is subject to fraud detection, is being generated fraudulently.

[0138] The collection unit 132 collects know-how information of user 250. For example, the collection unit 132 collects know-how information of user 250 based on score data showing the sleep quality score of user 250 calculated by the calculation unit 126. The collection unit 132 may store the collected know-how information of user 250 in the know-how information storage unit 134.

[0139] The provisioning unit 136 provides the user 250 with at least one of either a physical object or information. The physical object may be a tangible object or an intangible object.

[0140] The provisioning unit 136 provides at least one of the goods and information to the user 250, for example, by transmitting at least one of the goods and information to the communication terminal 200 via the network 20. The provisioning unit 136 may also provide at least one of the goods and information to the user 250 by delivering the goods and information to the user 250's residence or the like.

[0141] The provisioning unit 136 provides user 250 with at least one of goods and information, for example, based on the sleep quality score of user 250 calculated by the calculation unit 126. For example, the provisioning unit 136 provides user 250 with a reward if user 250's sleep quality score is higher than a predetermined first score threshold. On the other hand, if user 250's sleep quality score is lower than a predetermined second score threshold that is lower than the first score threshold, the provisioning unit 136 provides user 250 with know-how information that shows know-how for improving user 250's sleep quality. In this case, the know-how information that the provisioning unit 136 provides to user 250 may be know-how information received by the receiving unit 104, or know-how information stored in the know-how information storage unit 134.

[0142] Figure 10 schematically shows an example of the functional configuration of the communication terminal 200. The communication terminal 200 comprises an acquisition unit 202, an analysis unit 204, an output unit 206, a generation unit 208, and a transmission unit 212. However, it is not necessarily required that the communication terminal 200 have all of these components.

[0143] The acquisition unit 202 acquires various types of data. The acquisition unit 202 acquires various types of data, for example, by recording sound. The acquisition unit 202 acquires various types of data, for example, by receiving various types of data. The acquisition unit 202 receives various types of data, for example, via the network 20. The acquisition unit 202 receives various types of data, for example, via a short-range wireless communication connection. The acquisition unit 202 may also acquire various types of data when the input unit of the communication terminal 200 accepts input of various types of data.

[0144] The acquisition unit 202 acquires various data from, for example, the information processing device 100. The acquisition unit 202 acquires various data from the sound output device. The acquisition unit 202 acquires various data from, for example, the supply device 300. The acquisition unit 202 acquires various data from, for example, the wearable terminal 400. The acquisition unit 202 acquires various data from, for example, biosensors mounted on bedding such as beds and pillows.

[0145] The acquisition unit 202 acquires, for example, recorded data. The recorded data includes, for example, sounds emitted by the user 250 of the communication terminal 200 and sounds emitted by persons other than the user 250. The recorded data includes, for example, sounds emitted by the user 250 of the communication terminal 200 and sounds output by the sound output device. The recorded data includes, for example, sounds emitted by the user 250 of the communication terminal 200 and sounds 205 output by the communication terminal 200. The acquisition unit 202 acquires, for example, output timing data indicating the output timing of sounds output by the sound output device while the user 250 is asleep.

[0146] The acquisition unit 202 acquires, for example, score data indicating the sleep quality score of user 250. The acquisition unit 202 also acquires, for example, an alert indicating that user 250's sleep data has been generated fraudulently. The communication terminal 200 may display the score data and alerts acquired by the acquisition unit 202 on a display unit provided in the communication terminal 200.

[0147] The acquisition unit 202 acquires, for example, compensation data. The acquisition unit 202 acquires, for example, know-how information. The acquisition unit 202 acquires, for example, a product catalog.

[0148] The acquisition unit 202 acquires sleep data of user 250, generated based on the user's biometric information measured by a wearable terminal 400, for example. The acquisition unit 202 also acquires sleep data of user 250, generated based on the user's biometric information measured by a biosensor mounted on bedding such as a bed or pillow.

[0149] The analysis unit 204 analyzes the sleep state of user 250. The analysis unit 204 analyzes the sleep state of user 250 based on various data acquired by the acquisition unit 202, for example. The analysis unit 204 analyzes the sleep state of user 250 based on recorded data acquired by the acquisition unit 202, for example.

[0150] The analysis unit 204 analyzes the user 250's sleep state, for example, while the acquisition unit 202 is acquiring the recorded data. The analysis unit 204 may also analyze the user 250's sleep state after the acquisition unit 202 has acquired the recorded data.

[0151] The analysis unit 204, for example, periodically analyzes the sleep state of user 250. The analysis unit 204 analyzes the sleep state of user 250 at predetermined analysis intervals.

[0152] The analysis unit 204 analyzes the sleep state of user 250, for example, by analyzing the sleep onset time when user 250 began to sleep. For example, if user 250 is awake at one of several analysis points and is asleep at the next analysis point, the analysis unit 204 analyzes that user 250's sleep onset time is between the first analysis point and the next analysis point. Note that "awake" may mean that user 250 is awake.

[0153] The analysis unit 204 analyzes the sleep state of user 250, for example, by analyzing the time when user 250 ends sleep. For example, if user 250 is in a sleep state at one of several analysis points and is awake at the next analysis point, the analysis unit 204 analyzes that the time when user 250 ends sleep is between the first analysis point and the next analysis point.

[0154] The analysis unit 204 analyzes the sleep state of user 250 by analyzing user 250's sleep duration. For example, the analysis unit 204 analyzes user 250's sleep duration based on the sleep start time when user 250 began sleeping and the sleep end time when user 250 ended sleeping.

[0155] The analysis unit 204 analyzes the sleep state of user 250, for example, by analyzing the sleep state of user 250 while he is sleeping. The analysis unit 204 analyzes the sleep state of user 250 while he is sleeping, for example, by analyzing whether he is in REM sleep or non-REM sleep.

[0156] The analysis unit 204 analyzes the sleep state of user 250 during sleep, for example, by further analyzing the non-REM sleep state based on the depth of user 250's sleep. The analysis unit 204 further analyzes the non-REM sleep state by classifying it into one of the following: the first non-REM sleep state in which user 250's sleep depth is the deepest, the second non-REM sleep state in which user 250's sleep depth is the second deepest, and the third non-REM sleep state in which user 250's sleep depth is the third deepest.

[0157] The analysis unit 204 analyzes the sleep state of user 250 during sleep, for example, by analyzing user 250's sleep pattern. If the analysis unit 204 classifies user 250's sleep state into either REM sleep or non-REM sleep, for example, it analyzes user 250's sleep pattern by analyzing the transitions between REM sleep and non-REM sleep. If the analysis unit 204 classifies user 250's sleep state into either REM sleep, first non-REM sleep, second non-REM sleep, or third non-REM sleep, it analyzes user 250's sleep pattern by analyzing the transitions between REM sleep and the third non-REM sleep, the transitions between the third non-REM sleep and the second non-REM sleep, and the transitions between the second non-REM sleep and the first non-REM sleep, respectively.

[0158] The output unit 206 outputs sound 205. For example, the output unit 206 outputs sound 205 while the user 250 is sleeping. The acquisition unit 202 may acquire recording data that includes the sound output by the output unit 206.

[0159] The output unit 206 may, for example, output sound 205 once while user 250 is sleeping. The output unit 206 may, for example, output sound 205 multiple times while user 250 is sleeping. The output unit 206 may, for example, output sound 205 periodically while user 250 is sleeping.

[0160] The output unit 206 outputs, for example, one type of sound 205 while the user 250 is sleeping. The output unit 206 outputs, for example, multiple types of sounds 205 while the user 250 is sleeping. In this case, the output unit 206 outputs different types of sounds 205 based on the output time at which the sound 205 is output. For example, if the output unit 206 outputs a sound 205 every "00 minutes", and the output unit 206 outputs three types while the user 250 is sleeping, the output unit 206 outputs a type 1 sound 205 at "0:00 AM", a type 2 sound 205 at "1:00 AM", a type 3 sound 205 at "2:00 AM", a type 1 sound 205 at "3:00 AM", and so on.

[0161] The output unit 206 outputs, for example, a sound 205 that is difficult for the user 250 to hear, within the range of sounds that the acquisition unit 202 can record. The output unit 206 outputs, for example, a sound 205 with a lower volume, within the range of sounds with a volume that the acquisition unit 202 can record. The output unit 206 outputs, for example, a sound 205 in a frequency band that is difficult for the user 250 to hear, within the range of sounds with a frequency band that the acquisition unit 202 can record. The output unit 206 outputs, for example, a sound 205 in a frequency band that is inaudible to the user 250, within the range of sounds with a frequency band that the acquisition unit 202 can record. A sound in a frequency band inaudible to the user 250 is, for example, ultrasound.

[0162] The output unit 206 outputs sound 205 at different output frequencies, for example, based on the remaining battery level of the battery installed in the communication terminal 200. For example, the output unit 206 outputs sound 205 at a first output frequency when the remaining battery level is higher than a predetermined battery level threshold, and outputs sound 205 at a second output frequency, which is lower than the first output frequency, when the remaining battery level is lower than the predetermined battery level threshold. The output unit 206 may also output sound 205 at a higher output frequency as the remaining battery level increases.

[0163] The generation unit 208 generates sleep data for user 250 corresponding to the recorded data acquired by the acquisition unit 202. The generation unit 208 generates sleep data for user 250 based, for example, on the analysis results analyzed by the analysis unit 204.

[0164] The generation unit 208 generates sleep data for user 250, for example, by encoding the sleep pattern of user 250. In this case, the data to be encoded by the generation unit 208 may be the sleep state of user 250.

[0165] The generation unit 208 encodes the sleep state of user 250 by, for example, encoding the sleep state of user 250 with one binary data. The generation unit 208 encodes the sleep state of user 250 by, for example, encoding the sleep state of user 250 with two binary data. The generation unit 208 encodes the sleep state of user 250 by, for example, encoding the sleep state of user 250 with three or more binary data.

[0166] The generation unit 208 encodes the user 250's sleep pattern by, for example, representing the REM sleep state with a first value and the non-REM sleep state with a second value. For example, when the analysis unit 204 classifies the sleep state of the user 250 during sleep into either the REM sleep state or the non-REM sleep state, the generation unit 208 represents the REM sleep state with a value corresponding to the first of two possible value patterns that can be represented by a single binary data (e.g., "0"), and represents the non-REM sleep state with a value corresponding to a second value pattern different from the first of the two possible value patterns (e.g., "1"). For example, when the analysis unit 204 classifies the sleep state of a sleeping user 250 into one of the following states: REM sleep, first non-REM sleep, second non-REM sleep, or third non-REM sleep, the generation unit 208 represents the REM sleep state with a value corresponding to the first of four possible value patterns that can be represented by two binary data (e.g., "00"), the first non-REM sleep state with a value corresponding to the second of the four possible value patterns that is different from the first of the four possible value patterns (e.g., "11"), the second non-REM sleep state with a value corresponding to the third of the four possible value patterns that is different from the first and second of the four possible value patterns (e.g., "10"), and the third non-REM sleep state with a value corresponding to the fourth of the four possible value patterns that is different from the first, second, and third of the four possible value patterns (e.g., "01").

[0167] The generation unit 208 generates sleep data for user 250, for example, by encoding whether or not user 250 is awake. In this case, the data to be encoded by the generation unit 208 may be the user's awake state.

[0168] The generation unit 208 encodes the wakefulness state of user 250 by encoding whether or not user 250 is awake in a single binary data. The generation unit 208 encodes the wakefulness state of user 250 by representing user 250 being awake with a third value and user 250 being asleep with a fourth value. The generation unit 208 represents user 250 being awake with a value corresponding to the first of two possible value patterns that can be represented in a single binary data (e.g., "1"), and represents user 250 being asleep with a value corresponding to a second value pattern different from the first of the two possible value patterns (e.g., "0").

[0169] The generation unit 208 generates sleep data for user 250, for example, by encoding whether or not user 250 is speaking. In this case, the encoding target of the generation unit 208 may be the speaking state of user 250.

[0170] The generation unit 208 encodes the speech state of user 250 by encoding whether or not user 250 is speaking with a single binary data. The generation unit 208 encodes the speech state of user 250 by representing user 250 speaking with a fifth value and user 250 not speaking with a sixth value. The generation unit 208 represents user 250 speaking with a value corresponding to the first of two possible value patterns that can be represented with a single binary data (e.g., "1"), and represents user 250 not speaking with a value corresponding to a second value pattern different from the first of the two possible value patterns (e.g., "0").

[0171] The generation unit 208 generates sleep data for user 250 by, for example, encoding whether or not the sound output device is outputting sound. In this case, the target of encoding by the generation unit 208 may be the sound output status of the sound output device.

[0172] The generation unit 208 encodes the sound output status of a sound output device by encoding, for example, whether or not the sound output device is outputting sound with a single binary data. The generation unit 208 encodes a sleep pattern by, for example, representing the fact that the sound output device has output sound with a seventh value and representing the fact that the sound output device is not outputting sound with an eighth value. The generation unit 208 represents the fact that the sound output device has output sound with a value corresponding to the first value pattern of two possible value patterns that can be represented with a single binary data (e.g., "1"), and represents the fact that the sound output device is not outputting sound with a value corresponding to a second value pattern different from the first value pattern of the two possible value patterns (e.g., "0").

[0173] The generation unit 208 encodes, for example, N types of encoding targets. Here, when encoding N types of encoding targets, including the sleep state and wake state of user 250, the encoding algorithm of the communication terminal 200 may be constructed such that when user 250 is awake, user 250's sleep state is always represented by a predetermined value. For example, when encoding user 250's sleep state and wake state, the encoding algorithm of the communication terminal 200 may be constructed such that when user 250 is awake, user 250's sleep state is always represented by "0". Note that N may be an integer of 2 or more.

[0174] The generation unit 208, for example, encodes N types of encoding targets for each analysis point and generates one dataset using the N types of encoding targets encoded for each analysis point. In this case, when the determination unit 106 of the information processing device 100 calculates the similarity between the encoded sleep data of the user 250 subject to fraud detection and the past sleep patterns of the user 250 indicated by the past encoded sleep data of the user 250 stored in the sleep data storage unit 102 of the information processing device 100, it may calculate the similarity by comparing the encoded sleep data of the user 250 subject to fraud detection with the past encoded sleep data of the user 250 on a dataset basis.

[0175] For example, when the generation unit 208 encodes two types of encoding targets, the combination of the two types of encoding targets may be any of the following combinations: (i) a combination of the user 250's sleep state and the user 250's wake state, (ii) a combination of the user 250's sleep state and the user 250's vocalization state, and (iii) a combination of the user 250's sleep state and the sound output state by the sound output device. For example, when the generation unit 208 encodes three types of encoding targets, the combination of the three types of encoding targets may be any of the following combinations: (i) a combination of the user 250's sleep state, the user 250's wake state, and the user 250's vocalization state, (ii) a combination of the user 250's sleep state, the user 250's wake state, and the sound output state by the sound output device, and (iii) a combination of the user 250's sleep state, the user 250's vocalization state, and the sound output state by the sound output device. For example, when the generation unit 208 encodes four types of encoding targets, the combination of the four types of encoding targets may be a combination of the user 250's sleep state, a combination of the user 250's wake state, a combination of the user 250's vocalization state, and a combination of the sound output state from the sound output device.

[0176] The generation unit 208 generates, for example, metadata for user 250's sleep data. The generation unit 208 generates, for example, metadata for user 250's sleep data based on the recording data acquired by the acquisition unit 202. The generation unit 208 generates, for example, metadata for user 250's sleep data based on the analysis results analyzed by the analysis unit 204.

[0177] The transmitting unit 212 transmits various data, for example. The transmitting unit 212 transmits various data, for example, via the network 20. The transmitting unit 212 transmits various data, for example, via a short-range wireless communication connection.

[0178] The transmitting unit 212 transmits various data to, for example, the information processing device 100. The transmitting unit 212 may also transmit various data to any other external device.

[0179] The transmitting unit 212 transmits, for example, various data acquired by the acquiring unit 202. The transmitting unit 212 transmits, for example, sleep data of user 250 generated based on the user's biometric information measured by the wearable terminal 400. The transmitting unit 212 transmits, for example, sleep data of user 250 generated based on the user's biometric information measured by a biosensor mounted on bedding such as a bed or pillow. The transmitting unit 212 may also transmit recorded audio data.

[0180] The transmitting unit 212 transmits, for example, various data generated by the generation unit 208. The transmitting unit 212 transmits, for example, user 250 sleep data generated by the generation unit 208. The transmitting unit 212 transmits, for example, metadata of user 250 sleep data generated by the generation unit 208.

[0181] Figure 11 is an explanatory diagram illustrating an example of the processing flow of the information processing device 100. Here, the starting state is described as the state in which the information processing device 100 has not yet received sleep data from the user 250 from the communication terminal 200.

[0182] In S202, the receiving unit 104 receives sleep data of user 250 from the communication terminal 200. In S204, the determination unit 106 determines whether or not the sleep data of user 250 received by the receiving unit 104 in S202 has been generated fraudulently. If the determination unit 106 determines that the sleep data of user 250 has been generated fraudulently, the process proceeds to S214. If the determination unit 106 determines that the sleep data of user 250 has not been generated fraudulently, the process proceeds to S206.

[0183] In S206, the calculation unit 126 calculates a sleep quality score for user 250 based on the sleep data of user 250 received by the receiving unit 104 in S202. In S208, the notification unit 128 notifies the communication terminal 200 of the score data indicating the sleep quality score for user 250 calculated by the calculation unit 126 in S210.

[0184] In S210, the supply unit 136 determines whether the sleep quality score of user 250 calculated by the calculation unit 126 in S210 is higher than the first score threshold. If the supply unit 136 determines that the sleep quality score of user 250 is higher than the first score threshold, the process proceeds to S216. If the supply unit 136 determines that the sleep quality score of user 250 is lower than the first score threshold, the process proceeds to S212.

[0185] In S212, the supply unit 136 determines whether the sleep quality score of user 250 calculated by the calculation unit 126 in S210 is lower than the second score threshold. If the supply unit 136 determines that the sleep quality score of user 250 is lower than the second score threshold, the process proceeds to S218. If the supply unit 136 determines that the sleep quality score of user 250 is higher than the second score threshold, the processing by the information processing device 100 ends.

[0186] In S214, the notification unit 128 notifies the communication terminal 200 of an alert indicating that the sleep data of user 250, which the communication terminal 200 sent to the information processing device 100 in S202, has been generated incorrectly. After that, processing by the information processing device 100 is completed.

[0187] In S216, the provision unit 136 provides the reward to the user 250. After that, processing by the information processing device 100 is completed.

[0188] In S218, the provision unit 136 provides user 250 with know-how information that shows know-how for improving the sleep quality of user 250. After that, processing by the information processing device 100 is completed.

[0189] Figure 12 schematically shows an example of the hardware configuration of a computer 1200 that functions as an information processing device 100 or a communication terminal 200. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to this embodiment, or to cause the computer 1200 to execute operations associated with the device according to this embodiment or such one or more "parts", and / or to cause the computer 1200 to execute a process or a stage of such process according to this embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0190] The computer 1200 according to this embodiment includes a CPU 1212, RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0191] The CPU 1212 operates according to the programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires the image data generated by the CPU 1212 and stores it in the frame buffer provided in RAM 1214 or within itself, so that the image data is displayed on the display device 1218.

[0192] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227, etc., and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0193] The ROM 1230 stores boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 upon activation. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0194] The program is provided on a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The program is read from the computer-readable storage medium and installed on a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the operation or processing of information in accordance with the use of the computer 1200.

[0195] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as RAM 1214, storage device 1224, DVD-ROM 1227, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

[0196] Furthermore, the CPU 1212 may read all or necessary parts of files or databases stored on external recording media such as the storage device 1224, DVD drive 1226 (DVD-ROM 1227), or IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording media.

[0197] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the multiple entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies the predetermined condition.

[0198] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0199] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0200] Computer-readable media may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, computer-readable media having instructions stored therein will comprise a product containing instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disc (DVD), Blu-ray® disc, memory stick, integrated circuit card, etc.

[0201] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0202] Computer-readable instructions are provided locally or via a wide area network (WAN) such as a local area network (LAN) or the internet to the processor or programmable circuit of a programmable data processing device such as a computer, and may be executed to create means for performing operations specified in a flowchart or block diagram. Here, the computer may be a PC (personal computer), tablet computer, smartphone, workstation, server computer, general-purpose computer, or special-purpose computer, and may also be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system and is a computer in a broad sense. In a distributed computing system, multiple computers execute a program collectively by having each computer execute a part of the program and passing data during program execution between computers as needed.

[0203] Examples of processors include computer processors, central processing units (CPUs), processing units, microprocessors, digital signal processors, controllers, and microcontrollers. A computer may have one or more processors. In a multiprocessor system with multiple processors, each processor executes a portion of the program, and the processors collectively execute the program by passing program execution data between them as needed. For example, in the execution of multitasking, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which part of a program each processor executes changes dynamically. Which part of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0204] This invention can contribute to promoting user health by improving the quality of sleep, and therefore can contribute to achieving Sustainable Development Goal (SDG) 3, "Ensure good health and well-being for all."

[0205] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0206] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before" or "prior to," and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," and "next," for convenience, this does not mean that it is essential to perform the operations in that order. [Explanation of Symbols]

[0207] 10 System, 20 Network, 100 Information Processing Device, 102 Sleep Data Storage Unit, 104 Receiving Unit, 106 Judgment Unit, 108 Decision Unit, 112 Threshold Setting Unit, 114 Learning Data Acquisition Unit, 116 Learning Data Storage Unit, 118 Model Generation Unit, 122 Model Storage Unit, 124 Model Acquisition Unit, 125 Input Data Acquisition Unit, 126 Calculation Unit, 128 Notification Unit, 132 Collection Unit, 134 Know-how Information Storage Unit, 136 Provision Unit, 150 Fraud Detection Function, 200 Communication Terminal, 202 Acquisition Unit, 204 Analysis Unit, 205 Sound, 206 Output Unit, 208 Generation Unit, 212 Transmission Unit, 250 User, 255 Sound, 300 Supply Device, 400 Wearable Terminal, 600 Speaker, 605 Sound, 1200 Computer, 1210 Host controller, 1212 CPU, 1214 RAM, 1216 Graphics controller, 1218 Display device, 1220 Input / Output controller, 1222 Communication interface, 1224 Storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 Input / Output chip

Claims

1. A receiving unit receives sleep data of the user corresponding to the recording data from the communication terminal, which has acquired recording data of sounds emitted by the user of the communication terminal and sounds emitted by persons other than the user. A determination unit that determines whether or not the aforementioned sleep data has been generated incorrectly. An information processing device equipped with the following features.

2. Sleep data storage unit for storing the user's past sleep data Furthermore, The determination unit determines that the sleep data was not fraudulently generated if the similarity between the user's sleep pattern shown by the sleep data received by the receiving unit and the user's past sleep pattern shown by the past sleep data stored in the sleep data storage unit is lower than a predetermined similarity threshold, and determines that the sleep data was fraudulently generated if the similarity is higher than the similarity threshold. The information processing apparatus according to claim 1.

3. The sleep data storage unit stores past sleep data, including past sleep patterns encoded by representing REM sleep states with a first value and non-REM sleep states with a second value. The receiving unit receives the sleep data, which includes the sleep pattern encoded by representing the REM sleep state with the first value and the non-REM sleep state with the second value. The determination unit determines the similarity by comparing the encoded sleep pattern with the encoded past sleep pattern. The information processing apparatus according to claim 2.

4. The sleep data storage unit stores past sleep data, including past sleep patterns encoded by representing the user being awake with a third value, the user being asleep with a fourth value, the user speaking with a fifth value, and the user not speaking with a sixth value. The receiving unit receives sleep data including the sleep pattern encoded by representing the user being awake with the third value, the user being asleep with the fourth value, the user speaking with the fifth value, and the user not speaking with the sixth value. The information processing apparatus according to claim 3.

5. The sleep data storage unit stores past sleep data, including past sleep patterns encoded by representing the communication terminal outputting sound with a seventh value and the communication terminal not outputting sound with an eighth value. The receiving unit receives the sleep data, which includes the sleep pattern encoded by representing the communication terminal outputting sound with the value of the seventh, and the communication terminal not outputting sound with the value of the eighth. The information processing apparatus according to claim 4.

6. The receiving unit further receives metadata of the sleep data, which includes a recording flag indicating whether or not the communication terminal recorded the sound output by the communication terminal while the user was sleeping. The determination unit determines that the sleep data has not been generated fraudulently if the recording flag indicates that the communication terminal has recorded, and determines that the sleep data has been generated fraudulently if the recording flag indicates that the communication terminal has not recorded. The information processing apparatus according to any one of claims 1 to 5.

7. The receiving unit receives the metadata of the sleep data, which further includes recording start time data indicating the recording start time of the recorded data, and recording timing data indicating the recording timing of the sound output by the communication terminal while the user was sleeping. The aforementioned information processing device is Based on the recording start time indicated by the recording start time data, a determination unit determines the recording timing at which the communication terminal will record the sound output by the communication terminal if the sleep data has not been generated incorrectly. Furthermore, The determination unit determines that the sleep data has not been generated incorrectly if the recording timing error between the recording timing determined by the determination unit and the recording timing indicated by the recording timing data is smaller than a predetermined tolerance, and determines that the sleep data has been generated incorrectly if the recording timing error is larger than the tolerance. The information processing apparatus according to claim 6.

8. The receiving unit further receives metadata of the sleep data, including a pre-sleep vocalization flag indicating whether or not the user uttered a predetermined keyword before the user began to sleep. The determination unit determines that the sleep data has not been generated incorrectly if the pre-sleep vocalization flag indicates that the user has uttered the keyword, and determines that the sleep data has been generated incorrectly if the pre-sleep vocalization flag indicates that the user has not uttered the keyword. The information processing apparatus according to any one of claims 1 to 5.

9. If the determination unit determines that the sleep data has not been generated fraudulently, the calculation unit calculates the user's sleep quality score based on the sleep data. The information processing apparatus according to any one of claims 1 to 5, further comprising the above.

10. A provisioning unit that, when the score is higher than a predetermined first score threshold, provides a reward to the user, and when the score is lower than a predetermined second score threshold that is lower than the first score threshold, provides the user with know-how information showing know-how for improving the user's sleep quality. The information processing apparatus according to claim 9, further comprising:

11. In an information processing device, A receiving procedure for receiving sleep data of the user corresponding to the recording data from a communication terminal that has acquired recording data of sounds emitted by the user of the communication terminal and sounds emitted by persons other than the user, A determination procedure for determining whether the aforementioned sleep data has been generated fraudulently. A program to execute.

12. It is a communication terminal, An acquisition unit that acquires recording data of sounds emitted by the user of the communication terminal and sounds emitted by persons other than the user, An analysis unit analyzes the user's sleep state based on the aforementioned recording data, Based on the analysis results obtained by the analysis unit that analyzes the sleep state, a generation unit generates sleep data of the user corresponding to the recorded data, A transmission unit that transmits the sleep data to an information processing device that determines whether or not the sleep data has been generated incorrectly. A communication terminal equipped with the following features.

13. Output unit that outputs sound while the user is sleeping. Furthermore, The acquisition unit acquires the recording data, including the sound output by the output unit. The generation unit further generates metadata for the sleep data, which includes recording start time data indicating the recording start time of the recorded data, and recording timing data indicating the recording timing of the sound output by the communication terminal while the user was sleeping. The transmission unit further transmits the metadata of the sleep data to the information processing device. The communication terminal according to claim 12.

14. The communication terminal according to claim 12 or 13, wherein the generation unit generates sleep data by encoding the user's sleep pattern, representing REM sleep states with a first value and non-REM sleep states with a second value.

15. The communication terminal according to claim 14, wherein the generation unit generates sleep data by encoding the sleep pattern, where a third value indicates that the user is awake, a fourth value indicates that the user is asleep, a fifth value indicates that the user is speaking, and a sixth value indicates that the user is not speaking.

16. The communication terminal according to claim 15, wherein the generation unit generates sleep data by encoding the sleep pattern, representing the communication terminal outputting sound with a seventh value and the communication terminal not outputting sound with an eighth value.

17. On the communication terminal, A procedure for acquiring recorded data of sounds emitted by the user of the aforementioned communication terminal and sounds emitted by persons other than the user, An analysis procedure for analyzing the user's sleep state based on the aforementioned recording data, A generation procedure for generating user sleep data corresponding to the recorded data, based on the analysis results obtained by analyzing the sleep state in the above analysis procedure, A transmission procedure for transmitting sleep data to an information processing device that determines whether or not the sleep data has been generated incorrectly. A program to execute.

Images