JP7548848B2 - Information processing device, information processing method, and program - Google Patents

Description

Embodiments of the present invention relate to an information processing device, an information processing method, and a program that calculate an evaluation value related to a user's situation based on the user's biometric data.

There are known portable health condition data measuring devices that users carry around on a daily basis. Users can manage their own health condition using data such as body temperature and heart rate measured by the devices.

The following technology has been proposed to assist in this type of management: Data measured by the measuring device is sent to a management center. The management center accumulates and analyzes the data. If the management center detects abnormal data in the received data through analysis, it sends an alarm and the abnormal data to the user's mobile phone (see, for example, Patent Document 1).

JP 2003-150718 A

However, with the technology described in Patent Document 1, it is possible that the user may not perceive the alarm as useful. For example, the user may receive an alarm on his/her mobile phone from the management center based on data that the user does not normally perceive as abnormal.

This invention was made in light of the above-mentioned circumstances, and aims to provide a technology that calculates an evaluation value that reflects past judgments that may vary from user to user, based on the user's biometric data.

In order to solve the above problem, an information processing device according to one embodiment of the present invention includes a first acquisition unit that acquires first biometric data of a first user from a first user terminal, a data processing unit that calculates an evaluation value related to the first flag for the first biometric data based on multiple combinations of biometric data and a first flag related to a user's status for at least one user and the first biometric data, and an output unit that outputs data indicating the evaluation value to the first user terminal.

According to one aspect of the present invention, it is possible to provide a technology that calculates an evaluation value that reflects past judgments that may vary depending on the user, based on the user's biometric data.

FIG. 1 shows an example of the configuration of a system including a server device used as an information processing device according to the first embodiment of the present invention. FIG. 2 is a block diagram showing an example of a hardware configuration of a server device used as an information processing device according to the first embodiment of the present invention. FIG. 3 is a block diagram showing an example of the software configuration of a control unit of a server device used as an information processing device according to the first embodiment of the present invention. FIG. 4 is a flowchart showing an example of an operation executed by the server device used as the information processing device according to the first embodiment of the present invention. FIG. 5 is a block diagram showing an example of a software configuration of a control unit of a server device used as an information processing device according to the second embodiment of the present invention. FIG. 6 is a flowchart showing an example of an operation executed by a server device used as an information processing device according to the second embodiment of the present invention.

Below, an embodiment of the present invention will be described with reference to the drawings. Note that it is not essential that each functional block shown in the drawings be distinguished as shown. For example, some functions may be executed by a functional block other than the illustrated functional block. Furthermore, the illustrated functional block may be further divided into smaller functional sub-blocks. Also, the names of each functional block and each component in the following description are for convenience only and do not limit the configuration and operation of each functional block and each component.

[First embodiment]
(Configuration example)
(1) System FIG. 1 shows an example of the configuration of a system SYS including an information processing apparatus according to a first embodiment of the present invention.
The system SYS includes a server device SV, which is a non-limiting example of the information processing device. The system SYS further includes, for example, a plurality of user terminals UT (UT1, UT2, UT3, ...) and a plurality of wearable devices WD (WD1, WD2, WD3, ...) that are associated one-to-one with the plurality of user terminals UT, respectively.

Each wearable device WD is, for example, a wristwatch-type device that can be worn by a user. Each wearable device WD can transmit and receive data to and from the associated user terminal UT. Each wearable device WD can measure at least one of the following: heart rate, electrocardiogram, body temperature (skin temperature), visceral temperature (also called deep body temperature), blood pressure, blood oxygen concentration, estimated oxygen fluctuation, exercise amount, and blood sugar level of the user wearing the wearable device WD. In the following, each wearable device WD is described as measuring a plurality of items among these measurement items, but this embodiment is not limited to this. The measurement is performed, for example, automatically at a certain period and/or repeatedly in response to the user's operation. When the wearable device WD performs the measurement, it transmits data indicating the result of the measurement (hereinafter, for the purpose of simplifying the description, also referred to as "biometric data") to the user terminal UT. In this specification, the term "biometric data" is used to refer to data that indicates the results of a single measurement of each item measured by the wearable device WD.

Each user terminal UT is a smartphone or the like, and is capable of transmitting and receiving data to and from the server device SV via the communication network NW. Each user terminal UT receives biometric data transmitted from the wearable device WD, and transmits a combination of the biometric data and an abnormality flag together with an identifier of the user terminal UT to the server device SV via the communication network NW. Note that each user terminal UT may transmit the biometric data together with the identifier without the abnormality flag to the server device SV. As the communication network NW, for example, a wired LAN (Local Area Network) or a wireless LAN is used, but any other network may be used.

The abnormality flag transmitted to the server device SV together with the biometric data will now be described. The abnormality flag is, for example, 1-bit information. In the following description, the bit value of the abnormality flag is, for example, 1 if the user using the user terminal UT feels that there is something wrong with their health condition, and 0 if they do not, but this embodiment is not limited to this. For example, when the user terminal UT receives the biometric data, the user terminal UT notifies the user with an alarm or the like, thereby urging the user to make an input to the user terminal UT if the user feels that there is something wrong with their health condition. When the user makes the input, the bit value of the abnormality flag is set to 1.

Note that, although the description is given assuming that the combination of biometric data and abnormality flag, and the identifier of the user terminal UT are transmitted to the server device SV in this manner, the present embodiment is not limited to this. The biometric data may be transmitted from the wearable device WD to the server device SV via the communication network NW, without going through the user terminal UT. As long as the identifier of the user terminal UT and the abnormality flag are transmitted to the server device SV so as to be associated with the biometric data, they may be transmitted by either the user terminal UT or the wearable device WD, and may not necessarily be transmitted together with the biometric data. Furthermore, the user terminal UT may have the functions described for the wearable device WD, and the transmission of the above-mentioned data to the server device SV may be performed by the user terminal UT without using a separate wearable device WD.

The server device SV learns an anomaly degree calculation model for each user terminal UT based on the biometric data and anomaly flags transmitted from the user terminals UT (UT1, UT2, UT3, ...). In this specification, the expression "learn a certain model" is intended to include both learning a model based on learning data without relying on a base model, and learning a model obtained by updating the base model based on learning data. The base model is, for example, one that has been learned in advance based on learning data related to multiple users. The server device SV then receives biometric data transmitted from a certain user terminal UT and processes the biometric data using the anomaly degree calculation model learned for that user terminal UT, thereby calculating the degree of anomaly in the health state of the user using that user terminal UT. The server device SV transmits data indicating the degree of anomaly to that user terminal UT via the communication network NW.

(2) Server Device FIG. 2 is a block diagram showing an example of the hardware configuration of the server device SV.
The server device SV includes a control unit 1, a program storage unit 2, a data storage unit 3, an input/output interface (input/output I/F) 4, and a bus 5. Each of the program storage unit 2, the data storage unit 3, and the input/output interface (input/output I/F) 4 is connected to the control unit 1 via the bus 5.

The control unit 1 has a hardware processor such as a central processing unit (CPU).

The program storage unit 2 is a combination of a storage medium, for example, a non-volatile memory such as a hard disk drive (HDD) or a solid state drive (SSD) that can be written to and read from at any time, and a non-volatile memory such as a read only memory (ROM). The program storage unit 2 stores middleware such as an operating system (OS), as well as programs used to execute various control processes according to this embodiment.

The data storage unit 3 is a combination of a non-volatile memory such as a HDD or SSD, which can be written to and read from at any time, and a volatile memory such as a RAM (Random Access Memory), as a storage medium. The data storage unit 3 is used as a working area for the hardware processor of the control unit 1, temporarily holds data, and functions as a buffer and cache.

Under the control of the control unit 1, the input/output interface 4 transmits and receives data to and from the user terminal UT using a communication protocol defined by the communication network NW. The input/output interface 4 is configured, for example, by an interface compatible with a wired LAN or a wireless LAN.

Figure 3 is a block diagram showing an example of the software configuration of the control unit 1 of the server device SV. Figure 3 also shows the configuration related to the transmission and reception of data related to each process performed under the control of the software configuration. The same applies to the following similar drawings.

The control unit 1 includes, for example, a learning data acquisition unit 11, an anomaly calculation model learning unit 12, a model input data acquisition unit 13, an anomaly calculation unit 14, and an anomaly output unit 15. The processing functions of each unit included in the control unit 1 are realized by the control unit 1 causing the hardware processor to execute a program stored in the program storage unit 2. Although the above description assumes that a program stored in the program storage unit 2 is used, the program used may be one provided via the communication network NW.

The input/output interface 4 receives biometric data, the identifier of the user terminal UT, and the abnormality flag transmitted from each user terminal UT via the communication network NW, and inputs the biometric data, the identifier, and the abnormality flag to the control unit 1. Furthermore, the input/output interface 4 receives data output from the control unit 1 according to instructions from the control unit 1, and transmits the data to the target user terminal UT via the communication network NW.

The data storage unit 3 includes, for example, a learning data storage unit 31, an anomaly calculation model storage unit 32, a model input data storage unit 33, and an anomaly storage unit 34.

The learning data storage unit 31 stores biometric data, an identifier of the user terminal UT, and an abnormality flag. The learning data storage unit 31 is described as being included in the server device SV, but the learning data storage unit 31 may be provided, for example, on cloud computing.

The anomaly calculation model storage unit 32 stores the anomaly calculation model.

The model input data storage unit 33 stores the biometric data to be processed by the anomaly degree calculation unit 14.

The abnormality level storage unit 34 stores information indicating the abnormality level calculated by the abnormality level calculation unit 14.

The learning data acquisition unit 11 acquires a combination of biometric data and abnormality flags, and an identifier of the user terminal UT, transmitted from each user terminal UT via the input/output interface 4, and performs a process of storing the combination and the identifier in the learning data storage unit 31. In the storage process, the combination is associated with the identifier. The learning data acquisition unit 11 repeatedly performs the acquisition process and the storage process.

The anomaly degree calculation model learning unit 12 performs a process of reading, from the learning data storage unit 31, multiple combinations of biometric data and anomaly flags associated with the identifier of each user terminal UT.

The anomaly degree calculation model learning unit 12 performs processing to learn an anomaly degree calculation model based on the multiple combinations for each user terminal UT. The anomaly degree calculation model calculates the degree of anomaly in the health state of the user related to the biometric data based on the biometric data. The anomaly degree calculation model learning unit 12 performs processing to store the anomaly degree calculation model in the anomaly degree calculation model storage unit 32.

The learning process of the anomaly degree calculation model will be described.
In the learning process, a machine learning algorithm such as logistic regression analysis is used. In the machine learning algorithm, each combination of the above-mentioned biometric data and abnormality flag is used as learning data. In this way, an abnormality degree calculation model is learned that can output a value indicating the abnormality degree of the user's health condition in the range of 0 to 1 by using the numerical values of the measurement results of each measurement item in the biometric data as explanatory variables. The value indicating the abnormality degree is an evaluation value related to the abnormality flag. As described above, the learning process may be a process in which a base anomaly degree calculation model that has been learned in advance is updated.

The processing functions of each of the model input data acquisition unit 13, the anomaly calculation unit 14, and the anomaly output unit 15 will be explained assuming that an anomaly calculation model for a certain user terminal UT has been learned as described above.

The model input data acquisition unit 13 acquires the biometric data and the identifier of the user terminal UT transmitted from the user terminal UT via the input/output interface 4, and performs processing to store the biometric data and the identifier in the model input data storage unit 33.

The abnormality degree calculation unit 14 reads out the biometric data and the identifier stored in the model input data storage unit 33, and performs a process of reading out the abnormality degree calculation model learned for the user terminal UT from the abnormality degree calculation model storage unit 32 based on the identifier. The abnormality degree calculation unit 14 performs a process of calculating the abnormality degree of the health state of the user who uses the user terminal UT based on the biometric data, using the abnormality degree calculation model. The abnormality degree calculation unit 14 performs a process of storing data indicating the calculated abnormality degree in the abnormality degree storage unit 34.

The abnormality degree output unit 15 reads data indicating the abnormality degree stored in the abnormality degree storage unit 34, and performs a process of transmitting the data to the user terminal UT via the input/output interface 4. When the abnormality degree exceeds a threshold value, the abnormality degree output unit 15 may perform a process of transmitting information to the user terminal UT for the user terminal UT to issue an alert.

(Example of operation)
Next, an example of the operation of the system SYS configured as above will be described.

FIG. 4 is a flow chart showing an example of the operation executed by the control unit 1 of the server device SV among the above operation examples.
The wearable device WD1 measures at least one of the heart rate, electrocardiogram, body temperature (skin temperature), visceral temperature, blood pressure, blood oxygen concentration, estimated oxygen fluctuation, amount of exercise, blood sugar level, etc. of the first user who uses the wearable device WD1. After performing the measurement, the wearable device WD1 transmits biological data indicating the result of the measurement to the user terminal UT1 (shown as the first user terminal in FIG. 4).

The user terminal UT1 receives the biometric data transmitted from the wearable device WD1 and transmits the biometric data and a combination of abnormality flags together with the identifier of the user terminal UT1 to the server device SV. The bit value of the abnormality flag is set to 1 if the user using the user terminal UT1 feels that there is something abnormal about his or her health condition, and is set to 0 otherwise. The operation shown in the flowchart of FIG. 4 is initiated by transmitting the combination of the biometric data and abnormality flags to the server device SV.

Under the control of the learning data acquisition unit 11, the control unit 1 acquires the combination of the biometric data and the abnormality flag and the identifier, and stores them in the learning data storage unit 31 (ST01). In the storage process, the combination is associated with the identifier. The wearable device WD1 automatically performs the above measurement, for example, repeatedly at a fixed interval. Each time the measurement is performed, the combination of the biometric data and the abnormality flag is stored in the learning data storage unit 31 in the same manner as described above (ST01). The storage process is repeated, for example, until a certain period, such as one month, has elapsed since the server device SV received the first combination of biometric data and abnormality flag from the user terminal UT1. Alternatively, the storage process is repeated, for example, until the amount of biometric data and abnormality flag data from the user terminal UT1 stored in the learning data storage unit 31 exceeds a certain amount.

The control unit 1 learns an anomaly degree calculation model for the user terminal UT1 under the control of the anomaly degree calculation model learning unit 12 (ST02). More specifically, the process is as follows. Under the control of the anomaly degree calculation model learning unit 12, the control unit 1 reads out from the learning data storage unit 31 a plurality of combinations of biometric data and anomaly flags associated with the identifier of the user terminal UT1. The plurality of combinations are, for example, all combinations of biometric data and anomaly flags from the user terminal UT1 stored in the learning data storage unit 31 at the time of the learning process. Under the control of the anomaly degree calculation model learning unit 12, the control unit 1 learns an anomaly degree calculation model based on the plurality of combinations. The greater the number of combinations of biometric data and anomaly flags used in the learning process, the higher the reliability of the learned anomaly degree calculation model. Under the control of the anomaly degree calculation model learning unit 12, the control unit 1 stores the anomaly degree calculation model in the anomaly degree calculation model storage unit 32. After the anomaly degree calculation model is learned in this way, the operation described below is performed.

The wearable device WD1 transmits the biometric data to the user terminal UT1. The user terminal UT1 transmits the biometric data together with the identifier of the user terminal UT1 to the server device SV. The control unit 1 acquires the biometric data and the identifier under the control of the model input data acquisition unit 13 (ST03).

Under the control of the abnormality degree calculation unit 14, the control unit 1 reads out an abnormality degree calculation model for the user terminal UT1 from the abnormality degree calculation model storage unit 32 based on the identifier. Under the control of the abnormality degree calculation unit 14, the control unit 1 uses the abnormality degree calculation model to calculate the abnormality degree of the health condition of the user who uses the user terminal UT1 based on the biometric data (ST04).

Under the control of the abnormality level output unit 15, the control unit 1 transmits data indicating the abnormality level to the user terminal UT1 (ST05). This notifies the user of the abnormality level of his or her own health condition.

According to this embodiment, it is possible to provide an information processing device, an information processing method, and a program that calculate an abnormality level reflecting a user's past decisions based on the user's biometric data. That is, the system SYS of this embodiment learns an abnormality level calculation model related to a certain user based on multiple combinations of the user's biometric data and abnormality flags, and uses the abnormality level calculation model to calculate the abnormality level of the user's health condition based on the user's biometric data. The abnormality flag used in this learning indicates whether the user felt an abnormality in their own health condition. This makes it possible to calculate an abnormality level reflecting the user's past decisions based on the user's biometric data.

For example, the control unit 1 of the system SYS, under the control of the abnormality level output unit 15, transmits data indicating the calculated abnormality level to the user terminal UT used by the user. This allows the user to recognize that, for example, even if they do not feel that there is something abnormal about their own health condition, they are in a situation where they would normally feel that there is something abnormal about their health condition.

The control unit 1 of the system SYS, under the control of the abnormality degree calculation model learning unit 12, learns the abnormality degree calculation model using, for example, the numerical values of the measurement results of each of multiple measurement items in the biological data. This makes it possible to process the numerical values of multiple measurement items in a composite manner and calculate the abnormality degree more accurately.

(Modification)
In the above description, the server device SV learns an abnormality degree calculation model and calculates the abnormality degree of the user's health condition using the abnormality degree calculation model, but the present embodiment is not limited to this. Using a technique similar to that disclosed in the present embodiment, the server device SV can also learn the following models.

(1) First Modification The server device SV can learn a model that can output, based on biometric data, a degree of subsequent deterioration of the health condition of a user related to the biometric data in a range from 0 to 1. The model may also calculate the degree of abnormality described above. The server device SV can learn the model as follows.

When each user terminal UT receives biometric data from the associated wearable device WD, it notifies the user using the user terminal, for example, by an alarm. This prompts the user to input into the user terminal UT whether or not their health condition has subsequently deteriorated. The user terminal UT then transmits to the server device SV a combination of the biometric data, a flag indicating whether or not the user's health condition has subsequently deteriorated, along with the identifier of the user terminal UT.

The learning data acquisition unit 11 performs a process of acquiring the combination and the identifier of the user terminal UT in the same manner as described above, and storing the combination and the identifier of the user terminal UT in the learning data storage unit 31. In the storage process, the combination is associated with the identifier of the user terminal UT. This storage process is repeated. The model learning unit 12 described as the abnormality degree calculation model learning unit 12 performs a process of learning a model for each user terminal UT in the same manner as described above. Through this learning process, a model is learned that uses the numerical values of the measurement results of each measurement item in the biometric data as explanatory variables and can output the degree of subsequent deterioration of the health condition of the user related to the biometric data in the range from 0 to 1.

Then, the model input data acquisition unit 13 performs a process of acquiring biometric data transmitted from a certain user terminal UT and an identifier of the user terminal UT. The calculation unit 14 described as the abnormality degree calculation unit 14 performs a process of calculating the degree to which the health condition of the user related to the biometric data will subsequently deteriorate based on the biometric data, using the model learned for the user terminal UT based on the identifier.

(2) Second Modification The server device SV can learn a model that can output the degree to which a certain action improves the health condition of a user related to the biometric data in the range from 0 to 1, based on the biometric data. An example of an action is taking a certain medicine. The model may also calculate the degree of abnormality described above. The server device SV can learn the model as follows.

When each user terminal UT receives biometric data from the associated wearable device WD, it notifies the user using the user terminal, for example, by an alarm. This prompts the user to make an input to the user terminal UT if the user feels that there is something wrong with his/her health condition. If the user feels that there is something wrong with his/her health condition and takes some action, the user makes an input related to the action to the user terminal UT. Furthermore, for example, after taking the action, the user makes an input related to whether or not the action has improved his/her health condition to the user terminal UT. The user terminal UT then transmits a combination of the above biometric data and a flag indicating whether or not the user's health condition has improved, together with the identifier of the user terminal UT and the identifier of the action, to the server device SV.

The learning data acquisition unit 11 performs a process of acquiring the combination, the identifier of the user terminal UT, and the identifier of the action in the same manner as described above, and storing the combination, the identifier of the user terminal UT, and the identifier of the action in the learning data storage unit 31. In the storage process, the combination is associated with the identifier of the user terminal UT and the identifier of the action. This storage process is repeated. The model learning unit 12 described as the abnormality degree calculation model learning unit 12 performs a process of learning a model in the same manner as described above for each combination of a user terminal UT and an action. Through this learning process, a model is learned that uses the numerical values of the measurement results of each measurement item in the biometric data as explanatory variables and can output the degree to which a certain action improves the health condition of a user related to the biometric data in the range of 0 to 1.

Then, the model input data acquisition unit 13 performs a process of acquiring biometric data transmitted from a certain user terminal UT and an identifier of the user terminal UT. The calculation unit 14 described as the abnormality degree calculation unit 14 performs a process of calculating the degree to which each of the multiple actions improves the user's health condition based on the biometric data, using a model for each of the multiple actions learned for the user terminal UT based on the identifier.

As described above, according to this embodiment, by using a combination of biometric data and a certain flag, it is possible to learn a model that calculates an evaluation value related to the flag based on the biometric data. The same applies to the other embodiments described below. Such a flag is not limited to one consisting of one bit as described above, but may be one consisting of multiple bits.

[Second embodiment]
Hereinafter, a server device SVa, which is a non-limiting example of an information processing device according to a second embodiment of the present invention, will be described, focusing on the differences from the first embodiment.

(Configuration example)
The configuration of a system including an information processing apparatus according to the second embodiment is, for example, the same as the configuration of the system SYS described in the first embodiment, except that the server SV is replaced with a server SVa.

Each user terminal UT can transmit information (hereinafter, for the sake of simplicity, also referred to as "learning target information") for identifying data to be used as learning data when learning an anomaly degree calculation model for that user terminal UT to the server device SVa via the communication network NW. The learning target information includes information capable of identifying a group to which a user may belong, such as, for example, body type, age group, and lifestyle pattern, as well as any combination of these. In the following, an example will be described in which the learning target information identifies a group to which multiple users belong, but the learning target information may also identify a single user.

Figure 5 is a block diagram showing an example of the software configuration of the control unit 1a of the server device SVa.

The configuration of the server device SVa is such that in the configuration of the server device SV, the control unit 1 further includes, for example, a learning target information acquisition unit 16, and the program storage unit 2 further stores a program for realizing the processing functions of the learning target information acquisition unit 16. To distinguish it from the server device SV, the control unit and program storage unit of the server device SVa will be described with the reference characters 1a and 2a, respectively.

The learning target information acquisition unit 16 performs processing to acquire learning target information sent from each user terminal UT via the input/output interface 4.

The anomaly calculation model learning unit 12 performs a process of reading, from the learning data storage unit 31, multiple combinations of biometric data and anomaly flags associated with any of the identifiers of each user belonging to the group identified by the learning target information for each user terminal UT.

The anomaly calculation model learning unit 12 performs a process of learning an anomaly calculation model based on the multiple combinations for each user terminal UT, as described in the first embodiment.

(Example of operation)
Next, an example of the operation of the system including the server device SVa configured as above will be described.

FIG. 6 is a flow chart showing an example of the operation executed by the control unit 1a of the server device SVa.
4, combinations of biometric data and abnormality flags transmitted from each of the user terminals UT1, UT2, UT3, ... are stored in the learning data storage unit 31 (ST11). This storage process is repeated, for example, until a certain period, such as one month, has elapsed since the server device SV received the first combination of biometric data and abnormality flags from a certain user terminal UT. Alternatively, this storage process is repeated, for example, until the amount of biometric data and abnormality flags stored in the learning data storage unit 31 exceeds a certain amount.

The user terminal UT1 (shown as the first user terminal in FIG. 6) transmits the learning target information to the server device SVa. The control unit 1a acquires the learning target information under the control of the learning target information acquisition unit 16 (ST12). Note that the timing at which the user terminal UT1 transmits the learning target information to the server device SVa and the timing at which the control unit 1a acquires the learning target information are not limited to those described above.

The control unit 1a learns an anomaly degree calculation model for the user terminal UT1 under the control of the anomaly degree calculation model learning unit 12 (ST13). More specifically, the process is as follows. Under the control of the anomaly degree calculation model learning unit 12, the control unit 1a reads out from the learning data storage unit 31 a plurality of combinations of biometric data and anomaly flags associated with any of the identifiers of the users belonging to the group specified by the learning target information. The plurality of combinations are, for example, all combinations of biometric data and anomaly flags from users belonging to the group stored in the learning data storage unit 31 at the time of the learning process. Under the control of the anomaly degree calculation model learning unit 12, the control unit 1a learns an anomaly degree calculation model based on the plurality of combinations. Under the control of the anomaly degree calculation model learning unit 12, the control unit 1a stores the anomaly degree calculation model in the anomaly degree calculation model storage unit 32. After the anomaly degree calculation model is learned in this way, the operation described below is performed.

Similar to the operation described with ST03 in the explanation of Figure 4, the control unit 1a acquires the biometric data and the identifier of the user terminal UT1 transmitted from the user terminal UT1 under the control of the model input data acquisition unit 13 (ST14).

Similar to the operation described with ST04 in the explanation of Figure 4, the control unit 1a uses an abnormality degree calculation model for the user terminal UT1 to calculate the abnormality degree of the health condition of the user who uses the user terminal UT1 based on the biometric data (ST15).

Similar to the operation described with ST05 in the explanation of FIG. 4, the control unit 1a transmits data indicating the degree of abnormality to the user terminal UT1 under the control of the abnormality degree output unit 15 (ST05). As a result, the user is notified of the degree of abnormality in his or her own health condition.

In the above description, each user terminal UT transmits the learning target information to the server device SVa, but this embodiment is not limited to this. For example, the control unit 1a, under the control of the learning target information acquisition unit 16, may determine the learning target information for each user terminal UT based on pre-stored information about the user who uses the user terminal UT.

According to this embodiment, it is possible to provide an information processing device, an information processing method, and a program that calculate an abnormality level that reflects past decisions made by each user belonging to a certain group based on the user's biometric data. That is, the system of this embodiment learns an abnormality level calculation model for a certain user based on multiple combinations of biometric data and abnormality flags for users belonging to a certain group, and uses the abnormality level calculation model to calculate the abnormality level of the health condition of the user based on the biometric data of the user. This makes it possible to calculate an abnormality level that reflects past decisions made by each user belonging to a certain group based on the user's biometric data.

For example, under the control of the abnormality degree output unit 15, the control unit 1 of the system SYS transmits data indicating the calculated abnormality degree to the user terminal UT used by the user. As a result, even if the user does not feel that there is something wrong with his/her own health condition, he/she can recognize that he/she is in a state where a user belonging to the group specified by the learning target information would feel that there is something wrong with his/her health condition. For example, the user can recognize that he/she is in a state where a user belonging to the group to which he/she belongs would feel that there is something wrong with his/her health condition. Alternatively, the user can recognize that he/she is in a state where a user who he/she often spends a long time with would feel that there is something wrong with his/her health condition. This is useful when the calculated abnormality degree is due to, for example, an infectious disease.

The present invention is not limited to the above-described embodiment, and various modifications can be made in the implementation stage without departing from the gist of the invention. The embodiments may be implemented in appropriate combination, in which case the combined effects can be obtained. Furthermore, the above-described embodiment includes various inventions, and various inventions can be extracted by combinations selected from the multiple constituent elements disclosed. For example, if the problem can be solved and an effect can be obtained even if some constituent elements are deleted from all the constituent elements shown in the embodiment, the configuration from which these constituent elements are deleted can be extracted as an invention.

1, 1a...Control unit 2, 2a...Program memory unit 3...Data memory unit 4...Input/output interface 5...Bus 11...Learning data acquisition unit 12...Anomaly degree calculation model learning unit 13...Model input data acquisition unit 14...Anomaly degree calculation unit 15...Anomaly degree output unit 16...Learning target information acquisition unit 31...Learning data memory unit 32...Anomaly degree calculation model memory unit 33...Model input data memory unit 34...Anomaly degree memory unit SYS...System SV, SVa...Server device NW...Communication network UT...User terminal WD...Wearable device

Claims (9)

A first acquisition unit that acquires first biometric data of a first user from a first user terminal;
a data processing unit that calculates an evaluation value related to the first flag for at least one user's first biometric data based on a plurality of combinations of biometric data and a first flag related to a user's situation and the first biometric data;
an output unit that outputs data indicating the evaluation value to the first user terminal;
The first flag indicates whether or not the user's health condition has deteriorated after receiving the biometric data . The information processing device according to claim 1, wherein the multiple combinations are associated with action identifiers. the data processing unit includes a model learning unit that learns a model for calculating the evaluation value from the first biometric data based on the plurality of combinations of biometric data and first flags for the at least one user;
The evaluation value is calculated based on the first biological data and the model.
The information processing device according to claim 1 . The information processing device according to claim 1, wherein the at least one user is the first user. The information processing device according to claim 1, further comprising a second acquisition unit that acquires information for identifying the at least one user from the first user terminal. The information processing device according to claim 1, wherein the biometric data indicates the results of measurements for a plurality of items. Acquire first biometric data of a first user from a first user terminal;
calculating an evaluation value related to the first flag for at least one user's first biometric data based on a plurality of combinations of biometric data and a first flag related to a user's situation and the first biometric data;
outputting data indicating the evaluation value to the first user terminal;
An information processing method, wherein the first flag indicates whether the user's health condition has deteriorated after receiving the biometric data . The information processing method according to claim 7, wherein the multiple combinations are associated with action identifiers. A program for causing a computer to execute processing by each unit of an information processing device according to any one of claims 1 to 6.