Information processing device, information processing method, learning model generation method, and program

Abstract

To effectively utilize data in which internal surface information is related to a biosignal acquired by a sensor.SOLUTION: An information processor 10 includes a control part 13. The control part 13 acquires a learning model constructed by learning internal surface information corresponding to a biosignal on the basis of past actual measurement data in which a biosignal of an organism outputted by detecting a biological phenomenon of an organism by a sensor 20 and internal surface information of an organism are related mutually, and generates output information related to the internal surface information on the basis of the acquired learning model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, a learning model generation method, and a program. [Background technology]

[0002] Conventionally, technologies relating to sensors that detect biological phenomena and digitize them as biological signals have been widely known. Sensors include any biological sensors such as electroencephalographs, electromyographs, electrocardiographs, and biological sensors mounted on wearable devices. For example, Patent Document 1 discloses a biological information analyzer that is resistant to variations in brightness and dirt, is non-invasive, compact, and can accurately analyze biological information.

[0003] In addition, it is known that biosignals obtained based on a specific biological phenomenon change depending on internal information such as the emotions of the living body. For example, Non-Patent Document 1 describes that the spectral waveform of a biosignal obtained by detecting the electromagnetic field emitted from the heart based on a human heartbeat changes significantly when the person is feeling grateful or angry. It also describes that the human heartbeat becomes irregular when the person is feeling frustrated, but resumes a regular rhythm when the person is feeling grateful. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-217144 [Non-patent literature]

[0005] [Non-Patent Document 1] Rollin McCraty, Ph.D., “The Energetic Heart: Bioelectromagnetic Interactions Within and Between People”, HeartMath Research Center, Institute of HeartMath, Publication No. 02-035. Boulder Creek, CA, 2002. Summary of the Invention [Problem to be solved by the invention]

[0006] However, in the prior art, when multiple biological signals from a living organism are acquired by a sensor, the acquired multiple biological signals and the internal information associated with each of them are statistically processed as data and effectively utilized, for example, by converting the data into big data and using it for machine learning.

[0007] The present disclosure provides a technology that enables effective use of data that associates internal information with biosignals acquired by sensors. [Means for solving the problem]

[0008] An information processing device according to one embodiment of the present disclosure is an information processing device including a control unit, wherein the control unit acquires a learning model constructed by learning the internal information corresponding to the biological signal based on past measurement data that correlates the biological signal of the organism output by detecting the biological phenomenon of the organism using a sensor with the internal information of the organism, and generates output information related to the internal information based on the acquired learning model.

[0009] An information processing method according to one embodiment of the present disclosure is an information processing method using an information processing device, and includes the steps of: acquiring a learning model constructed by learning the internal information corresponding to the biological signal based on past measurement data that correlates the biological signal of the organism output by detecting the biological phenomenon of the organism using a sensor and the internal information of the organism; and generating output information related to the internal information based on the acquired learning model.

[0010] A method for generating a learning model according to one embodiment of the present disclosure is a method for generating the learning model used in the above-mentioned information processing method, and includes the steps of acquiring the past measured data, and learning the internal information corresponding to the biological signal based on the acquired past measured data to construct the learning model.

[0011] A program according to an embodiment of the present disclosure causes an information processing device to execute the above-described information processing method or learning model generation method. [Effects of the Invention]

[0012] According to an information processing device, an information processing method, a learning model generation method, and a program according to an embodiment of the present disclosure, it is possible to effectively utilize data that associates internal information with biological signals acquired by a sensor. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a configuration diagram illustrating a configuration of an information processing system including an information processing device according to an embodiment of the present disclosure. [Figure 2] 2 is a functional block diagram showing a schematic configuration of each of the information processing device, the sensor, and the terminal device of FIG. 1. FIG. [Figure 3] 2 is a sequence diagram illustrating an example of an information processing method executed by the information processing system of FIG. 1. FIG. [Figure 4] 10 is a flowchart illustrating a first example of an information processing method executed by the information processing device of FIG. [Figure 5] 10 is a flowchart illustrating a second example of an information processing method executed by the information processing device of FIG. [Figure 6] 10 is a flowchart illustrating a third example of an information processing method executed by the information processing device of FIG. [Figure 7] 1. FIG. 4 is a diagram showing a first example of information stored in a storage unit of the information processing device of FIG. [Figure 8] 1. FIG. 4 is a diagram showing a second example of information stored in the storage unit of the information processing device of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0015] 1 is a configuration diagram showing the configuration of an information processing system 1 including an information processing device 10 according to an embodiment of the present disclosure. An overview of the information processing system 1 including the information processing device 10 according to an embodiment of the present disclosure will be mainly described with reference to FIG. 1. The information processing system 1 has a plurality of sets of sensors 20 and terminal devices 30 in addition to the information processing device 10.

[0016] For ease of explanation, only one information processing device 10 is illustrated in Fig. 1, but the information processing system 1 may have two or more information processing devices 10. Although Fig. 1 illustrates a plurality of sensors 20 and a plurality of terminal devices 30, the information processing system 1 may have only one sensor 20 and one terminal device 30. The information processing system 1 may have only one set of sensor 20 and terminal device 30. Each of the information processing device 10, the plurality of sensors 20, and the plurality of terminal devices 30 is communicably connected to a network 40 including a mobile communication network, the Internet, etc.

[0017] The information processing device 10 is one or more server devices that can communicate with each other. The information processing device 10 is not limited to these, and may be any general-purpose electronic device such as a PC (Personal Computer) or a smartphone, or may be another electronic device dedicated to the information processing system 1.

[0018] The sensor 20 is any device that detects a biological phenomenon of a living organism and quantifies it as a biological signal. In this specification, "living organism" includes humans. "Biological phenomenon" includes heartbeat. The sensor 20 includes any electromagnetic field sensor that can detect, for example, an electromagnetic field emitted from inside the body in association with a biological phenomenon of a living organism without contact. In this specification, "electromagnetic field" is a general term for an electric field and a magnetic field. "Electromagnetic field sensor" includes a magnetic sensor, an electric field sensor, etc. The sensor 20 is also carried by a user who uses the information processing system 1.

[0019] The terminal device 30 is a general-purpose electronic device such as a smartphone, a tablet PC, or a PC. The terminal device 30 is an electronic device used by a user who owns the sensor 20. The terminal device 30 is not limited to these, and may be one or more server devices that can communicate with each other and are used by the user who owns the sensor 20, or may be another electronic device dedicated to the information processing system 1.

[0020] In one embodiment, the information processing device 10 acquires a learning model constructed by learning internal information corresponding to a biological signal based on past measurement data that correlates the biological signal output by detecting biological phenomena of the organism using a sensor 20 with the internal information of the organism. In this specification, "internal information" includes any internal information that is not directly apparent on the living organism and cannot be directly detected from the outside by physical means. Internal information includes emotions, psychological states, and mental states.

[0021] The information processing device 10 generates output information related to the internal information based on the acquired learning model. In this specification, the "output information" includes first notification information, second notification information, and simulated biological signals, which will be described later.

[0022] Fig. 2 is a functional block diagram showing a schematic configuration of each of the information processing device 10, the sensor 20, and the terminal device 30 in Fig. 1. For ease of explanation, Fig. 2 shows the configuration of only one pair of the sensor 20 and the terminal device 30 out of the multiple pairs of the sensor 20 and the terminal device 30 in Fig. 1. With reference to Fig. 2, an example of the configuration of each of the information processing device 10, the sensor 20, and the terminal device 30 included in the information processing system 1 will be mainly described.

[0023] As shown in FIG. 2, the information processing device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0024] The communication unit 11 includes a communication module that connects to the network 40. For example, the communication unit 11 includes a communication module that supports mobile communication standards or Internet standards such as 4G (4th Generation) and 5G (5th Generation). In one embodiment, the information processing device 10 is connected to the network 40 via the communication unit 11. The communication unit 11 transmits and receives various information via the network 40.

[0025] The storage unit 12 is, for example, but not limited to, a semiconductor memory, a magnetic memory, or an optical memory. The storage unit 12 functions as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores any information used in the operation of the information processing device 10. The storage unit 12 stores system programs, application programs, and various information received or transmitted by the communication unit 11. The information stored in the storage unit 12 can be updated with information received from the network 40 via the communication unit 11.

[0026] The control unit 13 includes one or more processors. In one embodiment, the "processor" may be, but is not limited to, a general-purpose processor or a dedicated processor specialized for a specific process. The control unit 13 is communicably connected to each component of the information processing device 10 and controls the operation of the information processing device 10 as a whole.

[0027] The following mainly describes the configuration of the sensor 20 included in the information processing system 1. As shown in FIG.

[0028] The communication unit 21 includes a communication module that connects to the network 40. For example, the communication unit 21 includes a communication module that supports mobile communication standards such as 4G and 5G. In one embodiment, the sensor 20 is connected to the network 40 via the communication unit 21. The communication unit 21 transmits and receives various information via the network 40.

[0029] The storage unit 22 is, for example, but not limited to, a semiconductor memory, a magnetic memory, or an optical memory. The storage unit 22 functions as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 22 stores any information used in the operation of the sensor 20. The storage unit 22 stores system programs, application programs, and various types of information received or transmitted by the communication unit 21. The information stored in the storage unit 22 can be updated with information received from the network 40 via the communication unit 21.

[0030] The acquisition unit 23 includes any sensor element capable of detecting a biological phenomenon of a living organism and acquiring the detected biological phenomenon as a biological signal. For example, the acquisition unit 23 includes a magnetic sensor element and an electric field sensor element capable of contactlessly detecting an electromagnetic field emitted from inside the body in association with a biological phenomenon of a living organism.

[0031] The output unit 24 includes any output module capable of outputting an electromagnetic field corresponding to a pseudo biological signal based on the pseudo biological signal generated as output information in the information processing device 10. For example, the output unit 24 includes any oscillation module capable of outputting a pseudo electromagnetic field that imitates an electromagnetic field emitted from inside the body in association with a biological phenomenon of a living organism based on the pseudo biological signal.

[0032] The control unit 25 includes one or more processors. In one embodiment, the "processor" may be, but is not limited to, a general-purpose processor or a dedicated processor specialized for a specific process. The control unit 25 is communicatively connected to each component of the sensor 20 and controls the overall operation of the sensor 20.

[0033] The following mainly describes the configuration of the terminal device 30 included in the information processing system 1. As shown in FIG.

[0034] The communication unit 31 includes a communication module that connects to the network 40. For example, the communication unit 31 includes a communication module that supports mobile communication standards or Internet standards such as 4G and 5G. In one embodiment, the terminal device 30 is connected to the network 40 via the communication unit 31. The communication unit 31 transmits and receives various information via the network 40.

[0035] The storage unit 32 is, for example, but not limited to, a semiconductor memory, a magnetic memory, or an optical memory. The storage unit 32 functions as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 32 stores any information used in the operation of the terminal device 30. The storage unit 32 stores system programs, application programs, and various types of information received or transmitted by the communication unit 31. The information stored in the storage unit 32 can be updated with information received from the network 40 via the communication unit 31.

[0036] The input unit 33 includes one or more input interfaces that detect user input and acquire input information based on the user's operation. For example, the input unit 33 includes physical keys, capacitive keys, a touch screen that is integrated with the display of the output unit 34, and a microphone that accepts voice input.

[0037] The output unit 34 includes one or more output interfaces that output information to notify the user. For example, the output unit 34 includes a display that outputs information as a video, a speaker that outputs information as a sound, and the like.

[0038] The control unit 35 includes one or more processors. In one embodiment, the "processor" may be, but is not limited to, a general-purpose processor or a dedicated processor specialized for a specific process. The control unit 35 is communicably connected to each component of the terminal device 30 and controls the operation of the entire terminal device 30.

[0039] Fig. 3 is a sequence diagram for explaining an example of an information processing method executed by the information processing system 1 of Fig. 1. The example of the information processing method executed by the information processing system 1 of Fig. 1 will be mainly explained with reference to Fig. 3. The sequence diagram shown in Fig. 3 shows a basic processing flow of the information processing method executed by the information processing system 1.

[0040] In step S100, the control unit 13 of the information processing device 10 acquires past measurement data in which the biological signals of the organism output by the sensor 20 detecting the biological phenomenon of the organism are correlated with the internal information of the organism.

[0041] More specifically, when the "living thing" is a human, for example, the control unit 13 acquires from multiple subjects biosignals acquired from the subjects using the sensor 20 and subjective internal information of the subjects at the time the biosignals were acquired, obtained through feedback from the subjects. The subjects may be users themselves who use the information processing system 1, or any person commissioned by the developer of the information processing system 1 to collect actual measurement data during the development stage before the information processing system 1 is provided to users as an information service. The control unit 13 generates past actual measurement data by associating the acquired biosignals with the internal information. The control unit 13 stores the generated past actual measurement data in the storage unit 12, for example, as big data.

[0042] In step S101, the control unit 13 of the information processing device 10 learns internal information corresponding to the biological signal based on the past actual measurement data acquired in step S100, and constructs a learning model. That is, the control unit 13 acquires the learning model by constructing it in the information processing device 10 itself. The control unit 13 stores the constructed learning model in the storage unit 12.

[0043] The learning model is a machine learning model trained based on acquired past measurement data. For example, the learning model is a supervised learning model, which is a mathematical model that uses a biological signal as input data and internal information as training data to learn internal information corresponding to the biological signal. The supervised learning model is, for example, but not limited to, a neural network including an input layer, one or more intermediate layers, and an output layer.

[0044] The supervised learning model is learned by the control unit 13 of the information processing device 10. The supervised learning model may be learned by batch learning or online learning. In this specification, "constructing a learning model" means that batch learning has been completed or online learning has been performed to a certain extent. In the case of online learning, learning may continue even after learning has been performed to a certain extent.

[0045] In step S102, the control unit 25 of the sensor 20 acquires, by the acquisition unit 23, a predetermined biological signal of at least one of the user who owns the sensor 20 and another living thing different from the user that is present around the user.

[0046] In step S103, the control unit 25 of the sensor 20 transmits the predetermined biological signal acquired in step S102 to the information processing device 10 via the communication unit 21 and the network 40. As a result, the control unit 13 of the information processing device 10 acquires the predetermined biological signal from the sensor 20.

[0047] In step S104, the control unit 13 of the information processing device 10 estimates internal surface information corresponding to the predetermined biological signal acquired in step S103 based on the learning model constructed in step S101. For example, when a predetermined biological signal is input to the trained learning model, internal surface information corresponding to the predetermined biological signal is estimated and output.

[0048] When the sensor 20 acquires a predetermined biosignal of the user having the sensor 20 in step S102, the control unit 13 estimates internal information based on the predetermined biosignal of the user as a living organism. In this specification, the "first user" refers to the user who used the sensor 20 to acquire the predetermined biosignal in step S102. On the other hand, when the sensor 20 acquires a predetermined biosignal of another living organism different from the user having the sensor 20 in step S102, the control unit 13 estimates internal information based on the predetermined biosignal of the living organism different from the first user.

[0049] In step S105, the control unit 13 of the information processing device 10 generates output information related to the inner surface information based on the learning model acquired in step S101. More specifically, the control unit 13 generates, as output information, first notification information that notifies one user of the inner surface information estimated in step S104.

[0050] In step S106, the control unit 13 of the information processing device 10 generates output information related to the internal surface information based on the learning model acquired in step S101. More specifically, when the control unit 13 determines that the difference between the waveform of the predetermined biological signal acquired in step S103 and the average waveform exceeds a threshold, the control unit 13 generates, as output information, second notification information that prompts the user to improve the estimated internal surface information in step S104.

[0051] In this specification, the "average waveform" may be calculated by averaging multiple past biosignals of the organism itself that produced a specified biosignal, or may be calculated by averaging multiple past biosignals contained in past actual measurement data, by the control unit 13.

[0052] In step S107, the control unit 13 of the information processing device 10 transmits the first notification information generated in step S105 and the second notification information generated in step S106 to the terminal device 30 of the one user via the communication unit 11 and the network 40. As a result, the control unit 35 of the terminal device 30 of the one user acquires the first notification information and the second notification information from the information processing device 10.

[0053] In step S102, when the sensor 20 acquires a predetermined biosignal of a user having the sensor 20, the control unit 13 notifies the user of the estimated internal surface information as first notification information. Similarly, in step S102, when the sensor 20 acquires a predetermined biosignal of a user having the sensor 20, the control unit 13 prompts the user to improve the estimated internal surface information of the user by using second notification information.

[0054] On the other hand, in step S102, when the sensor 20 acquires a predetermined biological signal of a living organism different from the one user that is present around the one user having the sensor 20, the control unit 13 notifies the one user of the internal surface information estimated for the living organism different from the one user as first notification information. Similarly, in step S102, when the sensor 20 acquires a predetermined biological signal of a living organism different from the one user that is present around the one user having the sensor 20, the control unit 13 prompts the one user to improve the internal surface information estimated for the living organism different from the one user by using second notification information.

[0055] In step S108, the control unit 35 of the terminal device 30 of the one user uses the output unit 34 to execute notification processing based on the first notification information and the second notification information acquired in step S107.

[0056] In step S109, the control unit 13 of the information processing device 10 generates output information related to the internal information based on the learning model acquired in step S101. More specifically, the control unit 13 generates a pseudo bio-signal associated with the predetermined internal information as the output information based on the learning model constructed in step S101. For example, the control unit 13 learns a plurality of bio-signals associated with a predetermined emotion based on past actual measurement data, and reproduces an average bio-signal that can be associated with the predetermined emotion as the pseudo bio-signal.

[0057] In step S110, the control unit 13 of the information processing device 10 transmits the pseudo-biosignal generated in step S109 to the sensor 20 of the one user via the communication unit 11 and the network 40. As a result, the control unit 25 of the sensor 20 of the one user acquires the pseudo-biosignal from the information processing device 10.

[0058] In step S111, the control unit 25 of the sensor 20 of the one user outputs a pseudo electromagnetic field, which imitates an electromagnetic field emitted from inside the body in association with a biological phenomenon of a living organism, based on the pseudo biological signal acquired in step S110, through the output unit 24. The control unit 25 outputs the pseudo electromagnetic field based on the pseudo biological signal using the output unit 24 to at least one of the one user who has the sensor 20 and another living organism different from the one user that is present around the one user.

[0059] Fig. 4 is a flowchart for explaining a first example of an information processing method executed by the information processing device 10 of Fig. 1. The first example of the information processing method executed by the information processing device 10 of Fig. 1 will be described with reference to Fig. 4. The flowchart shown in Fig. 4 mainly relates to the generation process of the first notification information described above with reference to Fig. 3.

[0060] In step S200, the control unit 13 of the information processing device 10 acquires past measurement data in which the biological signals of the organism output by the sensor 20 detecting the biological phenomenon of the organism are correlated with the internal information of the organism.

[0061] In step S201, the control unit 13 constructs a learning model by learning internal information corresponding to a biological signal based on the past actual measurement data acquired in step S200.

[0062] In step S202, the control unit 13 acquires a predetermined biological signal from the sensor 20. More specifically, the control unit 13 receives the predetermined biological signal acquired by the acquisition unit 23 of the sensor 20 from the sensor 20 via the network 40 and the communication unit 11.

[0063] In step S203, the control unit 13 estimates internal surface information corresponding to the predetermined biological signal acquired in step S202 based on the learning model constructed in step S201.

[0064] In step S204, the control unit 13 generates output information related to the inner surface information based on the learning model acquired in step S201. More specifically, the control unit 13 generates, as output information, first notification information that notifies one user of the inner surface information estimated in step S203.

[0065] In step S205, the control unit 13 transmits the first notification information generated in step S204 to the terminal device 30 of one user via the communication unit 11 and the network 40.

[0066] Fig. 5 is a flowchart for explaining a second example of an information processing method executed by the information processing device 10 of Fig. 1. The second example of the information processing method executed by the information processing device 10 of Fig. 1 will be explained with reference to Fig. 5. The flowchart shown in Fig. 5 mainly relates to the generation process of the second notification information described above with reference to Fig. 3.

[0067] In step S300, the control unit 13 of the information processing device 10 acquires past measurement data in which the biological signals of the organism output by the sensor 20 detecting the biological phenomenon of the organism are correlated with the internal information of the organism.

[0068] In step S301, the control unit 13 constructs a learning model by learning internal information corresponding to a biological signal based on the past actual measurement data acquired in step S300.

[0069] In step S302, the control unit 13 acquires a predetermined biological signal from the sensor 20. More specifically, the control unit 13 receives the predetermined biological signal acquired by the acquisition unit 23 of the sensor 20 from the sensor 20 via the network 40 and the communication unit 11.

[0070] In step S303, the control unit 13 estimates internal surface information corresponding to the predetermined biological signal acquired in step S302 based on the learning model constructed in step S301.

[0071] In step S304, the control unit 13 determines whether the difference between the waveform of the predetermined biological signal acquired in step S302 and the average waveform exceeds a threshold. That is, the control unit 13 determines whether the waveform of the predetermined biological signal acquired in step S302 differs significantly from the average waveform beyond an allowable range. If the control unit 13 determines that the difference exceeds the threshold, it executes the process of step S305. If the control unit 13 determines that the difference does not exceed the threshold, it executes the process of step S302 again.

[0072] In step S305, the control unit 13 generates output information related to the inner surface information based on the learning model acquired in step S301. More specifically, when the control unit 13 determines in step S304 that the difference exceeds the threshold, the control unit 13 generates, as output information, second notification information that prompts the user to improve the inner surface information estimated in step S303.

[0073] In step S306, the control unit 13 transmits the second notification information generated in step S305 to the terminal device 30 of the one user via the communication unit 11 and the network 40.

[0074] Fig. 6 is a flowchart for explaining a third example of an information processing method executed by the information processing device 10 of Fig. 1. The third example of the information processing method executed by the information processing device 10 of Fig. 1 will be explained with reference to Fig. 6. The flowchart shown in Fig. 6 mainly relates to the pseudo biological signal generation process described above with reference to Fig. 3.

[0075] In step S400, the control unit 13 of the information processing device 10 acquires past measurement data in which the biological signals of the organism output by the sensor 20 detecting the biological phenomenon of the organism are correlated with the internal information of the organism.

[0076] In step S401, the control unit 13 constructs a learning model by learning internal information corresponding to a biological signal based on the past actual measurement data acquired in step S400.

[0077] In step S402, the control unit 13 generates output information related to the internal surface information based on the learning model acquired in step S401. More specifically, the control unit 13 generates, as output information, a simulated biological signal associated with the predetermined internal surface information based on the learning model constructed in step S401.

[0078] In step S403, the control unit 13 transmits the pseudo biological signal generated in step S402 to the sensor 20 of one user via the communication unit 11 and the network 40.

[0079] Fig. 7 is a diagram showing a first example of information stored in the storage unit 12 of the information processing device 10 in Fig. 1. Fig. 7 relates to past measurement data in which biological signals of an organism output by detecting a biological phenomenon of the organism using the sensor 20 are associated with internal information of the organism. With reference to Fig. 7, the past measurement data stored in the database of the storage unit 12 of the information processing device 10 will be described.

[0080] The database of past measurement data stores not only biosignals and internal information, but also information and attribute information of the organisms from which the information was obtained. The past measurement data is data associated with biosignals, internal information, and attribute information of the organisms.

[0081] The biological information in FIG. 7 indicates which individual the biosignal, internal information, and attribute information are associated with. The biological information corresponds to, for example, identification information that identifies an individual subject. There may be one or more subjects. For example, the biological information is used to identify which subject the biosignal, internal information, and attribute information are associated with, such as subject A, subject B, etc. One set of information may be associated with one subject, or multiple sets of information may be associated with one subject.

[0082] In this specification, "attribute information" includes any information for categorizing living organisms, such as the subject's age, sex, family structure, race, nationality, address, hobbies, preferences, educational status, occupation, industry, job type, position, and qualifications.

[0083] When the subject is the user himself / herself who uses the information processing system 1, the control unit 13 of the information processing device 10 acquires the user's biosignal, acquired by the acquisition unit 23 of the sensor 20 included in the information processing system 1, from the sensor 20 via the network 40 and the communication unit 11. At this time, the control unit 13 acquires the user's own biological information, internal information, and attribute information, input by the user using the input unit 33 of the terminal device 30 used by the user, from the terminal device 30 via the network 40 and the communication unit 11.

[0084] When the subject is any person requested by the developer of the information processing system 1 to collect actual measurement data, the control unit 13 of the information processing device 10 acquires, by any means, the biological signals collected by the developer using the sensor 20. At this time, the control unit 13 similarly acquires, by any means, information about the living organism, internal information, and attribute information collected by the developer as information associated with the biological signals.

[0085] The control unit 13 creates a database of the various pieces of information obtained as described above as past measurement data, and stores the database in the storage unit 12 for centralized management.

[0086] Fig. 8 is a diagram showing a second example of information stored in the storage unit 12 of the information processing device 10 of Fig. 1. Fig. 8 is a diagram showing a summary of information required to use a learning model constructed for the same species of organism and information obtained as a result of using the learning model. With reference to Fig. 8, the information stored in the database of the storage unit 12 of the information processing device 10 will be described.

[0087] 8 stores, in addition to a learning model constructed for an organism of the same species, information about the organism and predetermined biological signals acquired from the organism as information required for using the learning model. In addition, the database stores, as information obtained as a result of using the learning model, internal information estimated according to the acquired predetermined biological signals and output information related to the estimated internal information.

[0088] The organism information in FIG. 8 is intended to indicate which individual a predetermined biosignal is associated with. The organism information corresponds to, for example, identification information for identifying one or more individual users who use the information processing system 1, or for individually identifying one or more organisms different from the users that exist around the users. For example, the organism information is intended to identify which organism a predetermined biosignal is associated with, such as user A and organisms A1, A2, etc. that exist around him, user B and organisms B1, B2, etc. that exist around him. One predetermined biosignal may be associated with one organism, or multiple predetermined biosignals may be associated with one organism.

[0089] The control unit 13 of the information processing device 10 acquires a predetermined biological signal acquired by an acquisition unit 23 of the sensor 20 included in the information processing system 1 from the sensor 20 via the network 40 and the communication unit 11. At this time, the control unit 13 acquires information on the corresponding organism that the user who used the sensor 20 input using the input unit 33 of his or her own terminal device 30 from the terminal device 30 via the network 40 and the communication unit 11.

[0090] The control unit 13 of the information processing device 10 estimates internal state information for each acquired predetermined biological signal based on a learning model. For example, the control unit 13 estimates the emotion of the living thing indicated by the waveform of the predetermined biological signal based on the learning model. The control unit 13 generates output information including first notification information and second notification information related to the estimated internal state information.

[0091] The control unit 13 creates a database of the various information obtained as described above and stores it in the storage unit 12 for centralized management.

[0092] According to the embodiment described above, it is possible to effectively utilize data that associates internal body information with biosignals acquired by the sensor 20. For example, the information processing device 10 learns the internal body information corresponding to the biosignals based on such past actual measurement data, constructs a learning model, and generates output information related to the internal body information based on the acquired learning model. As a result, the information processing device 10 can transmit the output information related to the internal body information to at least one of the user's sensor 20 and the terminal device 30, and provide the user with feedback based on the past actual measurement data.

[0093] The information processing device 10 can more effectively utilize data in which the biosignal acquired by the sensor 20 is associated with the internal information by estimating the internal information according to the acquired predetermined biosignal.

[0094] For example, the information processing device 10 can notify a user of the estimated inner surface information by generating the first notification information as output information. The user can check the notification content based on the first notification information via the output unit 34 of the terminal device 30.

[0095] In this case, if the information processing device 10 estimates the internal information based on a predetermined biosignal of the one user as a living organism, the one user can objectively grasp his / her own internal information as estimated information by measuring his / her own biosignal using the sensor 20. On the other hand, if the information processing device 10 estimates the internal information based on a predetermined biosignal of a living organism different from the one user, the one user can measure the biosignal of a surrounding living organism using the sensor 20 and objectively grasp the internal information of the living organism as estimated information.

[0096] For example, by generating the second notification information as output information, the information processing device 10 can prompt the user to improve the estimated internal body information when it determines that the difference between the waveform of a predetermined biological signal and the average waveform exceeds a threshold. The user can check the notification content based on the second notification information via the output unit 34 of the terminal device 30.

[0097] In this case, if the information processing device 10 estimates the internal information based on a predetermined biosignal of the one user as a living organism, the one user can objectively understand that he or she needs to improve his or her own internal information by measuring his or her own biosignal using the sensor 20. On the other hand, if the information processing device 10 estimates the internal information based on a predetermined biosignal of a living organism different from the one user, the one user can objectively understand that he or she needs to measure the biosignal of a surrounding living organism using the sensor 20 and improve the internal information of the living organism.

[0098] The information processing device 10 can obtain an average waveform specific to a specific organism by averaging a plurality of past biological signals of the organism itself that have produced a predetermined biological signal and calculating the average waveform.

[0099] This allows the information processing device 10 to identify changes in the waveform of a predetermined biological signal based on the average waveform of the user himself / herself, i.e., a waveform that is approximate to the user's waveform in normal times. Therefore, when generating the second notification information to encourage the user to improve the estimated internal information of the user, the information processing device 10 can encourage the user to improve based on a state that is close to the user's normal time.

[0100] Similarly, the information processing device 10 can identify changes in the waveform of a predetermined biological signal based on the average waveform of other living things around the user, i.e., a waveform that approximates the normal waveform of the living thing. Therefore, when the information processing device 10 generates second notification information to prompt the user to improve the estimated internal information of the living thing, it can prompt the user to improve based on a state that is close to the normal state of the living thing.

[0101] The information processing device 10 calculates an average waveform by averaging multiple past biological signals contained in past actual measurement data, thereby making it possible to obtain an overall average waveform across multiple subjects from whom past actual measurement data was collected, rather than an average waveform specific to the organism.

[0102] This allows the information processing device 10 to identify changes in the waveform of a predetermined biological signal for a single user based on an overall average waveform, i.e., a waveform that approximates a normal waveform across multiple subjects. Therefore, when generating second notification information to encourage a single user to improve their estimated internal information, the information processing device 10 can encourage improvement based on the overall average waveform.

[0103] Similarly, the information processing device 10 can identify changes in the waveform of a predetermined biological signal for other living things around a user, based on an overall average waveform, i.e., a waveform that approximates a normal waveform across multiple subjects. Therefore, when generating second notification information to prompt the user to improve the estimated internal information for the living thing, the information processing device 10 can prompt the user to improve the overall average waveform.

[0104] The information processing device 10 generates a pseudo-biological signal as output information based on a learning model, thereby generating a pseudo-biological signal associated with predetermined internal information desired by a user. The user can use the output unit 24 of the sensor 20 to irradiate a pseudo-electromagnetic field based on such a pseudo-biological signal to at least one of the user himself or herself and other living beings different from the user that are present around the user. This allows the user to apply a pseudo-electromagnetic field, which imitates an electromagnetic field emitted from within the body of a living being based on predetermined internal information, to the irradiated target. For example, the user can apply a pseudo-electromagnetic field corresponding to a positive emotion to the irradiated target.

[0105] Since the past measurement data is data that is associated with biological signal and internal information as well as biological attribute information, the information processing device 10 can build a learning model based on more information. Therefore, the information processing device 10 can build a learning model with higher accuracy.

[0106] The present disclosure is applicable to a variety of fields, such as healthcare, medicine, security, education, and childcare.

[0107] Although the present disclosure has been described based on the drawings and examples, it should be noted that those skilled in the art can make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included in the scope of the present disclosure. For example, the functions included in each configuration or step can be rearranged so as not to be logically inconsistent, and multiple configurations or steps can be combined or divided into one.

[0108] For example, at least a part of the processing operations executed in the information processing device 10 in the above-described embodiment may be executed in the sensor 20 or the terminal device 30. For example, instead of the information processing device 10, the sensor 20 or the terminal device 30 itself may execute the above-described series of processing operations related to the information processing device 10. At least a part of the processing operations executed in the sensor 20 or the terminal device 30 may be executed in the information processing device 10.

[0109] For example, a general-purpose electronic device such as a smartphone or a computer can be configured to function as the information processing device 10 according to the above-described embodiment. Specifically, a program describing the processing content for realizing each function of the information processing device 10 according to the embodiment is stored in the memory of the electronic device, and the program is read and executed by a processor of the electronic device. Therefore, the disclosure according to an embodiment can also be realized as a program executable by a processor.

[0110] Alternatively, the disclosure according to an embodiment may be realized as a non-transitory computer-readable medium storing a program executable by one or more processors to cause the information processing device 10 according to the embodiment to execute each function. It should be understood that these are also included within the scope of the present disclosure.

[0111] For example, the information processing device 10 described in the above embodiment may be mounted on the sensor 20. In this case, the information processing device 10 may communicate information directly with the sensor 20 without going through the network 40.

[0112] In the above embodiment, the sensor 20 is described as a separate device from the terminal device 30, but the present invention is not limited to this. The sensor 20 may be mounted on the terminal device 30 and configured integrally with the terminal device 30.

[0113] In the above embodiment, the information processing device 10 is described as estimating internal information corresponding to the acquired predetermined biological signal based on a learning model, but is not limited to this. The information processing device 10 does not have to perform such estimation processing.

[0114] In the above embodiment, the information processing device 10 transmits the first notification information to the terminal device 30 of one user to notify the one user of the estimated internal surface information for at least one of the one user and a living being different from the one user, but this is not limiting. The information processing device 10 may transmit the first notification information to the terminal device 30 of another user to notify the other user of the estimated internal surface information for at least one of the one user and a living being different from the one user.

[0115] In the above embodiment, the information processing device 10 transmits the second notification information to the terminal device 30 of one user to prompt the one user to improve the internal surface information estimated for at least one of the one user and a living being different from the one user, but this is not limited to this. The information processing device 10 may transmit the second notification information to the terminal device 30 of another user to prompt the other user to improve the internal surface information estimated for at least one of the one user and a living being different from the one user.

[0116] In the above embodiment, the information processing device 10 has been described as transmitting a pseudo biological signal to the sensor 20 of one user, but the present invention is not limited to this. The information processing device 10 may transmit a pseudo biological signal to the sensor 20 of another user. In this case, the control unit 25 of the sensor 20 of the other user may use the output unit 24 to output a pseudo electromagnetic field based on the pseudo biological signal to at least one of the other user who has the sensor 20 and a living being different from the other user that is present around the other user.

[0117] In the above embodiment, the information processing device 10 generates the first notification information, the second notification information, and the simulated biological signal as output information, but is not limited to this. The information processing device 10 may generate at least one of the first notification information, the second notification information, and the simulated biological signal as output information, or may generate any other different output information instead of or in addition to these.

[0118] For example, the control unit 13 of the information processing device 10 may estimate, based on a learning model, internal information corresponding to a predetermined biosignal of a user who operates an avatar or the like in an online virtual space such as a game or metaverse. In this case, the information processing device 10 may generate, as output information, display information for changing the facial expression and appearance of the avatar, as well as the appearance of the online virtual space itself, in accordance with the estimated internal information.

[0119] In this way, the information processing device 10 can flexibly change the facial expression and appearance of an avatar, as well as the appearance of the online virtual space itself, based on the internal information estimated for a single user. The information processing device 10 may function as a communication tool in such an online virtual space. In other words, the information processing device 10 can facilitate smooth communication between users in such an online virtual space.

[0120] For example, the control unit 13 of the information processing device 10 may generate, as output information, a pseudo-biosignal corresponding to predetermined internal information related to the facial expression and appearance of an avatar in an online virtual space such as a game or metaverse, and the appearance of the online virtual space itself. The control unit 13 may transmit such a pseudo-biosignal to the sensor 20 of a user who operates an avatar in an online virtual space such as a game or metaverse. At this time, the control unit 25 of the sensor 20 of the user may output, using the output unit 24, a pseudo-electromagnetic field based on the pseudo-biosignal to the user who owns the sensor 20.

[0121] As a result, the information processing device 10 can improve a user's sense of sharing with the facial expressions and appearances of the avatar, as well as the appearance of the online virtual space itself. The information processing device 10 may function as a communication tool in such an online virtual space. That is, the information processing device 10 can facilitate communication between users in such an online virtual space.

[0122] In the above embodiment, the information processing device 10 acquires past actual measurement data by generating the past actual measurement data and storing it in the storage unit 12, but the present invention is not limited to this. The information processing device 10 may acquire past actual measurement data by receiving already constructed past actual measurement data from any other external device via the network 40 and the communication unit 11.

[0123] In the above embodiment, the information processing device 10 has been described as constructing a learning model by itself, but this is not limiting. The information processing device 10 may acquire a learning model by receiving an already constructed learning model from any other external device via the network 40 and the communication unit 11.

[0124] In the above embodiment, it has been described that the database for past actual measurement data stores, in addition to the biosignal and internal information, information and attribute information of the organism from which this information was obtained, but this is not limited to this. In addition to the biosignal and internal information, the past actual measurement data may be associated with only either the organism information or the organism attribute information, or may not include either.

[0125] In the above embodiment, the "living thing" is described as including humans, but is not limited to this. The living thing may also include any other object having life. For example, the living thing may include animals other than humans, plants, microorganisms, fungi, etc.

[0126] The contents of the present disclosure can be applied to various fields, such as healthcare, medicine, breeding, and communication, when the organism is an animal other than a human. The contents of the present disclosure can be applied to various fields, such as cultivation and condition care, when the organism is a plant. The contents of the present disclosure can be applied to various fields, such as quality control of any food or beverage brewed or fermented using the organism, when the organism is a microorganism or fungus. The contents of the present disclosure can also be applied to biotechnology.

[0127] In the above embodiment, the "biological phenomenon" is described as including heartbeat, but is not limited to this. Biological phenomena may also include any other phenomenon that appears in relation to the life activities of a living organism. Biological phenomena may include, for example, pulse, blood flow, brain waves, breathing, and sweating.

[0128] In the above embodiment, the sensor 20 is described as including an electromagnetic field sensor, but is not limited thereto. The sensor 20 may also include any other biosensor, such as an electroencephalograph, an electromyograph, an electrocardiograph, or a biosensor mounted on a wearable device.

[0129] In the above embodiment, the "internal information" is described as including, but not limited to, emotions, psychological states, and mental states. The internal information may also include any other internal information related to the life activities of, for example, plants, microorganisms, and fungi.

[0130] For example, when the "living thing" is something other than a human, the information processing device 10 may acquire from a plurality of subjects biosignals acquired from the subjects using the sensor 20 and internal information of the subjects at the time the biosignals were acquired, which information is indirectly acquired from the subjects using any method. The subjects may be any objects collected by the developer of the information processing system 1 to collect actual measurement data in the development stage before the information processing system 1 is provided to users as an information service.

[0131] In the above embodiment, the acquisition unit 23 has been described as including a magnetic sensor element and an electric field sensor element, but is not limited thereto. The acquisition unit 23 may also include any other sensor element such as an electroencephalograph, an electromyograph, an electrocardiograph, or a biosensor mounted on a wearable device. [Explanation of symbols]

[0132] 1. Information Processing Systems 10. Information processing equipment 11 Communications Department 12 Storage section 13 Control Unit 20 sensors 21 Communications Department 22 Memory section 23 Acquisition Department 24 Output section 25 Control Unit 30 Terminal Equipment 31 Communications Department 32 Storage section 33 Input section 34 Output section 35 Control Unit 40 Network

Claims

1. An information processing system comprising an information processing device and a sensor, The sensor an electromagnetic field sensor that detects electromagnetic fields emitted from inside the body in association with biological phenomena of a living organism without contact and acquires the detected electromagnetic fields as biological signals; an oscillation module that outputs a pseudo electromagnetic field that imitates the electromagnetic field based on a pseudo biological signal generated as output information in the information processing device; and the information processing device has a control unit, The control unit acquiring a learning model constructed by learning the internal information corresponding to the biological signal based on past measurement data in which the biological signal of the organism output by detecting the electromagnetic field with the electromagnetic field sensor and the internal information of the organism are correlated with each other; generating the output information related to the internal information based on the acquired learning model; the output information includes the pseudo biological signal for outputting the pseudo electromagnetic field from the oscillation module; The sensor acquires the pseudo biological signal associated with predetermined internal information desired by a first user having the sensor from the information processing device, and irradiates the pseudo electromagnetic field based on the acquired pseudo biological signal to the first user from the oscillation module. Information processing system.

2. 2. The information processing system according to claim 1, the control unit acquires a predetermined biological signal, and estimates the internal surface information corresponding to the acquired predetermined biological signal based on the learning model. Information processing system.

3. 3. The information processing system according to claim 2, the control unit generates, as the output information, first notification information that notifies the first user of the estimated inner surface information. Information processing system.

4. 4. The information processing system according to claim 2, When the control unit determines that the difference between the waveform of the predetermined biological signal and the average waveform exceeds a threshold, the control unit generates, as the output information, second notification information that prompts the first user to improve the estimated internal surface information. Information processing system.

5. 5. The information processing system according to claim 4, the control unit calculates the average waveform by averaging a plurality of past biological signals of the living organism which have produced the predetermined biological signal. Information processing system.

6. 6. The information processing system according to claim 4 or 5, the control unit calculates the average waveform by averaging the past plurality of biological signals included in the past actual measurement data. Information processing system.

7. 7. The information processing system according to claim 3, The control unit estimates the inner surface information based on the predetermined biological signal of the first user as the living being. Information processing system.

8. 8. The information processing system according to claim 3, the control unit estimates the inner surface information based on the predetermined biological signal of a second user present around the first user. Information processing system.

9. 9. The information processing system according to claim 1, The control unit generates, as the output information, the simulated biological signal associated with predetermined internal surface information based on the learning model. Information processing system.

10. An information processing method using an information processing system including an information processing device and a sensor, a step of detecting an electromagnetic field emitted from inside the body in association with a biological phenomenon of the living organism in a non-contact manner using an electromagnetic field sensor of the sensor and acquiring the detected electromagnetic field as a biological signal; A step of acquiring a learning model constructed by learning the internal information corresponding to the biological signal based on past measurement data in which the biological signal of the organism output by detecting the electromagnetic field with the electromagnetic field sensor and the internal information of the organism are correlated with each other; generating output information related to the internal information based on the acquired learning model; outputting a pseudo electromagnetic field that imitates the electromagnetic field from an oscillation module of the sensor based on the pseudo biological signal generated as the output information; Including, The sensor acquires the pseudo biological signal associated with predetermined internal information desired by a first user having the sensor from the information processing device, and irradiates the pseudo electromagnetic field based on the acquired pseudo biological signal to the first user from the oscillation module. Information processing methods.

11. A method for generating the learning model used in the information processing method according to claim 10, acquiring the past actual measurement data; A step of learning the internal information corresponding to the biological signal based on the acquired past actual measurement data to construct the learning model; Including, How to generate a learning model.

12. The method for generating a learning model according to claim 11, The past measurement data is data associated with attribute information of the organism in addition to the biological signal and the internal information. How to generate a learning model.

13. The method for generating a learning model according to claim 11 or 12, The learning model is a machine learning model learned based on the acquired past actual measurement data. How to generate a learning model.

14. A program that causes the information processing system to execute the information processing method according to claim 10 or the learning model generation method according to any one of claims 11 to 13.

Images