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

Abstract

An information processing device (2) executes processing using a first learning model (7) and a second learning model (8). The information processing device (2) comprises: an acquisition unit (102) that acquires a reflected reception signal strength; a first estimation unit (104) that estimates a user attribute of an estimation target user by inputting the reflected reception signal strength to the first learning model (7); and a second estimation unit (106) that estimates biological information of the estimation target user by inputting the reflected reception signal strength and the user attribute of the estimation target user estimated by the first estimation unit (104) to the second learning model (8).

Description

Information Processing Apparatus, Learning Model, Information Processing Method, and Program

[0001] The present disclosure relates to an information processing apparatus, a learning model, an information processing method, and a program.

[0002] Conventionally, techniques related to the estimation of biological information (vital data) are known. In one example, Patent Document 1 describes a technique for setting a specific region related to a detection target based on an image captured by a camera and estimating vital data based on the reflection from the specific region. In another example, Patent Document 2 describes a technique for generating a Doppler signal corresponding to the state of a living body by receiving a reflected wave of a radio wave transmitted to the living body and outputting biological information based on the Doppler signal.

[0003] Japanese Patent Application Laid-Open No. 2024-24783, Japanese Patent Application Laid-Open No. 2016-59718

[0004] However, with the techniques described in Patent Documents 1 and 2, it is not possible to sufficiently improve the efficiency of estimating biological information. For example, there is room for improvement in the method of estimating biological information.

[0005] The present disclosure provides a technique for improving the efficiency of estimating biological information.

[0006] An information processing device according to one aspect of the present disclosure is an information processing device that performs processing using a first learning model and a second learning model, wherein the first learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning and the user attributes of a target user present indoors and / or outdoors for learning, and the second learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning, the user attributes of a target user for learning, and the biometric information of a target user for learning, and comprises an acquisition unit that acquires the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation where a target user for estimation is present, a first estimation unit that estimates the user attributes of a target user for estimation by inputting the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation into the first learning model, and a second estimation unit that estimates the biometric information of a target user for estimation by inputting the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation, and the user attributes of the target user for estimation estimated by the first estimation unit into the second learning model.

[0007] This disclosure provides a technology that streamlines the estimation of biometric information.

[0008] This is a diagram illustrating an example of the relationship between the user and the wireless communication device according to this embodiment. This is a diagram illustrating an example of the functional configuration of System 1 in this embodiment. This is a flowchart illustrating an example of the operation of the information processing device 2 in this embodiment. This is a block diagram illustrating an example of the operation of the information processing device 2 in the learning phase of this embodiment. This is a block diagram illustrating an example of the operation of the information processing device 2 in the estimation phase of this embodiment. This is a diagram illustrating an example of the hardware configuration of each device in System 1 in this embodiment.

[0009] <1. Overview> Referring to Figure 1, an overview of System 1 according to this embodiment (hereinafter simply referred to as "System 1") will be described.

[0010] In System 1, the wireless communication device emits radio waves indoors where the user is present. The wireless communication device further receives the reflected waves of the emitted radio waves and measures their signal strength (hereinafter referred to as "reflected received signal strength"). System 1 includes a configuration that estimates the user's biometric information based on at least this reflected received signal strength.

[0011] In this embodiment, the "reflected received signal strength" is not limited to, for example, the instantaneous energy of the received signal, but may be the temporal progression of the reflected received signal strength, at least a part of the frequency spectrum of the reflected received signal strength, or a combination thereof. In one embodiment, the reflected received signal strength may be time-series data of RSSI (Received Signal Strength Indicator) over a predetermined period, and / or frequency-series data obtained by Fourier transforming said time-series data.

[0012] In this embodiment, “biometric information” may include measurements indicating the state of at least a part of the user’s body. In one embodiment, the biometric information is at least one of the user’s heart rate, pulse rate, and respiratory rate.

[0013] Reflected signal strength can vary depending on various indoor factors. For example, the reflected signal strength may differ depending on the user's location indoors. Another example is that the reflected signal strength may differ depending on the location and size of furniture installed indoors.

[0014] Furthermore, the reflected received signal strength may vary depending on user attributes. In this embodiment, "user attributes" may be characteristics or elements of the user that may differ from other users. User attributes may include, for example, the user's height, weight, constitution, body shape, and behavioral patterns. For example, since radio waves are generally absorbed by water, if a user is tall or heavy (i.e., if the user has a high water content), the reflected received signal strength may tend to be relatively low. In another example, since the frequency of radio waves that are easily reflected may differ depending on the shape of the object they collide with, there may be a relationship between the user's body shape and the frequency data of the reflected received signal strength. In yet another example, the time-series data of the reflected received signal strength may differ depending on the user's behavioral patterns (for example, the user's tendency to do what, when, where, and indoors). Thus, it is physically clear that the reflected received signal strength may differ depending on user attributes.

[0015] However, techniques that estimate biological information based solely on reflected signal strength may not be able to achieve sufficient accuracy. In contrast, System 1 estimates biological information based not only on reflected signal strength but also on user attributes.

[0016] User attributes can be related to biometric information. For example, taller users tend to have lower heart rates and respiratory rates. Another example is that overweight users tend to have higher heart rates and respiratory rates. Yet another example is that users who move around frequently indoors tend to have higher heart rates and respiratory rates. Furthermore, users' heart rates and respiratory rates are higher when they consume alcohol or experience mental stress. In other words, by further considering user attributes in a technology that estimates biometric information based on reflected received signal strength, it is possible to estimate biometric information with higher accuracy. Below, the configuration and operation of System 1, which realizes such processing, will be described in more detail.

[0017] <2. Functional Configuration> The functional configuration of System 1 will be described with reference to Figure 2. System 1 includes an information processing device 2, a terminal device 3, a wireless communication device 4, a biometric information measuring device 5, a learning target user database 9, a first learning model 7, a second learning model 8, and a communication network NW. The information processing device 2 and the terminal device 3 are configured to communicate via the communication network NW.

[0018] [Terminal Device 3] Terminal device 3 is a communication device used by users of System 1. Users of System 1 may be users whose biometric information is estimated, people who view the estimated biometric information, or administrators of System 1. Terminal device 3 is, for example, a smartphone, a personal computer, a tablet terminal, or a wearable device. Terminal device 3 is equipped with an input interface, an output interface, and a communication interface.

[0019] The input interface is an interface that allows terminal device 3 to receive input from the user. The input interface may be a touch panel, microphone, camera, keyboard, mouse, etc.

[0020] The output interface is an interface for transmitting information to the user through images, sound, etc. The output interface includes a display (which may also function as a touch panel) and speakers.

[0021] A communication interface is an interface for enabling communication with other devices via a communication network (NW). The communication interface may be a wireless communication interface or a wired communication interface.

[0022] Terminal device 3 may access services provided by information processing device 2, for example, via a web browser, or it may access such services by installing dedicated software.

[0023] [Wireless communication device 4] Wireless communication device 4 is a device that emits radio waves indoors where a user is present. In one embodiment, wireless communication device 4 is a commercially available communication device (for example, a Wi-Fi® router and a Bluetooth® communication device, etc.). In one embodiment, wireless communication device 4 is equipped with a function to measure the reflected received signal strength.

[0024] [Biometric Information Measurement Device 5] The biometric information measurement device 5 measures the user's biometric information. In one embodiment, this biometric information is used as part of the training data (correct data) for the second learning model 8, which will be described later. In one embodiment, the biometric information measurement device 5 is a so-called wearable terminal device. The biometric information measurement device 5 is, for example, a smartwatch, a smart ring, or a medical device for measuring biometric information.

[0025] [Training Target User Database 9] The training target user database 9 stores user attributes for each of the multiple users to be trained. In one embodiment, these user attributes are used as part of the training data (ground truth data) for the first training model 7, which will be described later.

[0026] [First Learning Model 7] The first learning model 7 is configured to take learning data relating to the relationship between reflected received signal strength and user attributes as input. In one embodiment, the first learning model 7 is configured to output user attributes estimated according to the reflected received signal strength when reflected received signal strength is input.

[0027] [Second Learning Model 8] The second learning model 8 is configured to take learning data relating the relationship between reflected received signal strength, user attributes, and the user's biometric information as input. In one embodiment, the second learning model 8 is configured to output the user's biometric information estimated according to the combination of reflected received signal strength and user attributes as input.

[0028] In one example, the first learning model 7 and the second learning model 8 may be constructed based on a neural network, a decision tree, and an SVM (Support Vector Machine), respectively. The neural network may be a large-scale deep learning model such as Transformer.

[0029] [Information Processing Device 2] The information processing device 2 estimates the user's biometric information based on the reflected received signal strength and user attributes. In one embodiment, the information processing device 2 is a server when the terminal device 3 is a client device. In one embodiment, the information processing device 2 is a cloud server. The information processing device 2 may be a device that includes, for example, one or more virtual or physical web servers and one or more virtual or physical database servers.

[0030] The information processing device 2 executes processing using the first learning model 7 and the second learning model 8.

[0031] In one embodiment, the information processing device 2 inputs training data to the first learning model 7. In one embodiment, the training data includes (1) training data relating to the reflected received signal intensity corresponding to a wireless signal irradiated in the indoor learning area, and (2) correct data relating to the user attributes of the learning target user present in the indoor learning area.

[0032] In one embodiment, the information processing device 2 inputs training data to the second learning model 8. In one embodiment, the training data includes (1) training data including the reflected received signal intensity corresponding to the wireless signal irradiated indoors for learning, and the user attributes of the user to be learned, and (2) correct data regarding the biometric information of the user to be learned.

[0033] In one embodiment, the information processing device 2 hosts at least one of the first learning model 7 and the second learning model 8 on its own device. In one embodiment, the information processing device 2 communicates with at least one of the other devices hosting the first learning model 7 and the other device hosting the second learning model 8, for example, via an API.

[0034] The information processing device 2 comprises a control unit 10, a storage unit 12, a network interface unit 14, and a bus 16. The control unit 10, the storage unit 12, and the network interface unit 14 are electrically connected via the bus 16.

[0035] (Control Unit 10) The control unit 10 can function as an acquisition unit 102, a first estimation unit 104, a second estimation unit 106, an output unit 108, and an irradiation control unit 110 by executing various programs stored in the storage unit 12, which will be described later.

[0036] —Acquisition Unit 102— The acquisition unit 102 acquires the reflected received signal intensity corresponding to the wireless signal irradiated in the estimated indoor space where the estimated target user is located.

[0037] —First Estimation Unit 104— The first estimation unit 104 estimates the user attributes of the target user by inputting the reflected received signal intensity corresponding to the wireless signal irradiated indoors for estimation into the first learning model 7.

[0038] —Second Estimation Unit 106— The second estimation unit 106 estimates the biometric information of the target user by inputting the reflected received signal intensity corresponding to the wireless signal irradiated indoors for estimation, and the user attributes of the target user estimated by the first estimation unit 104, into the second learning model 8.

[0039] —Output Unit 108— The output unit 108 outputs the biometric information of the estimated target user estimated by the second estimation unit 106. In one embodiment, the output unit 108 transmits the biometric information to the terminal device 3. In one embodiment, the output unit 108 outputs (writes) the biometric information to the storage unit 12.

[0040] —Irradiation control unit 110— The irradiation control unit 110 controls the wireless communication device 4 based on the biometric information of the estimated target user estimated by the second estimation unit 106.

[0041] In one embodiment, the irradiation control unit 110 controls the wireless communication device 4 when the biological information of the estimated target user satisfies a predetermined condition. In one example, the predetermined condition may be a case where it is determined that the biological information of the estimated target user cannot be estimated normally (for example, when the heart rate is abnormally low or high, etc.).

[0042] In one embodiment, the irradiation control unit 110 controls the irradiation method of the wireless signal by the wireless communication device 4 based on the biological information of the estimated target user. In one example, controlling the irradiation method of the wireless signal may be changing the direction (for example, directivity) in which the wireless signal is irradiated. In another example, controlling the irradiation method of the wireless signal may be changing the output power of the wireless signal. (Storage unit 12) The storage unit 12 stores various information for the information processing device 2 to operate. In one embodiment, the storage unit 12 stores the program executed by the control unit 10.

[0043] (Network interface unit 14) The network interface unit 14 realizes communication with other devices via the communication network NW.

[0044] [Communication network NW] The communication network NW realizes communication between the devices of the system 1. In one example, the communication network NW realizes communication between the devices based on the TCP / IP protocol.

[0045] In the present embodiment, acquiring information includes making the information processable by the control unit 10. Acquiring information may be, for example, receiving the information from another device, obtaining the information by a predetermined process, and reading the information from the storage unit 12, etc.

[0046] In the present embodiment, generating information may be at least one of making the information obtained by a predetermined process processable by the control unit 10 and storing the information obtained by a predetermined process in the storage unit 12.

[0047] In this embodiment, determining information may be at least one of selecting at least one from one or more pieces of information and newly generating the information.

[0048] In this embodiment, outputting information may be at least one of transmitting the information to another device and outputting the information by voice or video.

[0049] <3. Operation> Referring to FIGS. 3-5, an operation example of the information processing apparatus 2 will be described. FIG. 3 is a flowchart showing an operation example of the information processing apparatus 2. In this embodiment, the operation of the information processing apparatus 2 will be described by dividing it into a learning phase and an estimation phase.

[0050] [Learning Phase (S100 to S106)] In the learning phase, the information processing apparatus 2 first acquires the reflected received signal strength of the radio signal irradiated indoors for learning and the user attributes of the learning target user existing indoors for learning (S100). At this time, the information processing apparatus 2 can acquire the reflected received signal strength from the wireless communication apparatus 4. Further, the information processing apparatus 2 can acquire the user attributes of the learning target user from the learning target user database 9. Next, the information processing apparatus 2 configures the first learning model 7 by inputting learning data indicating the relationship between the reflected received signal strength and the user attributes into the first learning model 7 (S102).

[0051] The information processing apparatus 2 acquires the reflected received signal strength of the radio signal irradiated indoors for learning, the user attributes of the learning target user, and the biological information of the learning target user (S104). At this time, the information processing apparatus 2 acquires the reflected received signal strength from the wireless communication apparatus 4 and can acquire the user attributes of the learning target user from the learning target user database 9. Further, the information processing apparatus 2 can acquire the biological information from the biological information measurement apparatus 5. Next, the information processing apparatus 2 configures the second learning model 8 by inputting learning data indicating the relationship between the reflected received signal strength and the user attributes and the biological information into the second learning model 8 (S106).

[0052] Figure 4 is a conceptual diagram showing the relationships between the various components of System 1 during the learning phase (S100-S106). The first learning model 7 receives the reflected received signal strength from the wireless communication device 4 as training data, and the user attributes of the target user from the target user database 9 as correct answer data. The second learning model 8 receives the reflected received signal strength from the wireless communication device 4 and the user attributes from the target user database 9 as training data, and biometric information from the biometric information measurement device 5 as correct answer data.

[0053] [Estimation Phase (S108-S112)] In the estimation phase, the information processing device 2 acquires the reflected signal strength of a wireless signal irradiated in the indoor area for estimation where the target user is located (S108). Next, the information processing device 2 estimates the user attributes of the target user by inputting the reflected signal strength of the wireless signal irradiated in the indoor area for estimation into the first learning model 7 (S110). Next, the information processing device 2 estimates the biometric information of the target user by inputting the reflected signal strength of the wireless signal irradiated in the indoor area for estimation and the user attributes of the target user estimated in S110 into the second learning model 8 (S112).

[0054] Figure 5 is a conceptual diagram showing the relationships between the various components of System 1 during the estimation phase (S108-S112). The first learning model 7 receives the reflected signal strength from the wireless communication device 4. In response, the first learning model 7 outputs user attributes estimated according to the reflected signal strength. The second learning model 8 receives the reflected signal strength from the wireless communication device 4 and the user attributes estimated by the first learning model 7. In response, the second learning model 8 estimates biometric information. The biometric information can be output via the terminal device 3.

[0055] System 1 makes it possible to efficiently estimate biometric information. As mentioned above, user attributes can indicate trends in biometric information. The second learning model 8 is configured to estimate biometric information based not only on reflected received signal strength but also on user attributes. Therefore, System 1 can estimate biometric information with higher accuracy. Furthermore, System 1 can sometimes estimate biometric information with less training data compared to using a learning model that has only learned the relationship between reflected received signal strength and biometric information (i.e., a learning model that does not learn user attributes).

[0056] Furthermore, System 1 estimates biometric information based on user attributes, which are estimated by the first learning model 7. In other words, System 1 can estimate the biometric information of a user without separately registering the user attributes of the user to be estimated in System 1.

[0057] <4. Hardware Configuration> Referring to Figure 6, an example of a hardware configuration when the devices included in System 1 described above are implemented by the computer 70 will be explained. Note that the functions of each device can also be implemented by dividing them among multiple devices.

[0058] As shown in Figure 6, the computer 70 includes a processor 700, a storage device 702, an input interface 704, a data interface 706, a communication interface 708, and a display device 710.

[0059] The processor 700 controls various processes in the computer 70 by executing programs stored in the storage device 702. For example, each functional unit of the control unit 10 of the information processing device 2 can be realized by the processor 700 executing programs stored in the storage device 702.

[0060] The storage device 702 is a storage medium such as RAM (Random Access Memory). RAM temporarily stores the program code of the program executed by the processor 700, as well as data required when the program is executed.

[0061] The storage device 702 can also be a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 702 stores the operating system and various programs for realizing the above configurations. The storage medium storing these various programs may be a computer-readable non-temporary storage medium (non-transitor computer-readable medium). In addition, the storage device 702 can also store tables for registering various information and a database (DB) for managing these tables. Such programs and data are loaded into the storage device 702 as needed and accessed by the processor 700.

[0062] The input interface 704 is a device for receiving input from the user. Specific examples of the input interface 704 include cameras, buttons, microphones, keyboards, mice, touch panels, various sensors, and wearable devices. The input interface 704 may be connected to the computer 70 via an interface such as USB (Universal Serial Bus).

[0063] The data interface 706 is a device for inputting data from outside the computer 70. Specific examples of the data interface 706 include drive devices for reading data stored on various storage media. The data interface 706 may also be located outside the computer 70. In that case, the data interface 706 would be connected to the computer 70 via an interface such as USB.

[0064] The communication interface 708 is a device for performing data communication via a communication network NW with an external device of the computer 70, either wired or wirelessly. The communication interface 708 may also be located outside the computer 70. In that case, the communication interface 708 is connected to the computer 70 via an interface such as USB.

[0065] The display device 710 is a device for displaying various types of information. Specific examples of the display device 710 include liquid crystal displays, organic EL (Electro-Luminescence) displays, and displays for wearable devices. The display device 710 may be located outside the computer 70. In that case, the display device 710 is connected to the computer 70 via, for example, a display cable. Furthermore, if a touch panel is used as the input I / F 704, the display device 710 can be configured as an integrated unit with the input I / F 704.

[0066] Furthermore, the components of the device included in the system 1 described above are such that a program stored in the storage device 702 is executed by the processor 700, thereby realizing a defined process in cooperation with other hardware. In other words, these components can be envisioned as software or firmware, or as corresponding hardware, and in both concepts, they can be described and interpreted as "function," "means," "part," "processing circuit," "unit," or "module," etc.

[0067] <5. Modifications> The embodiments described above are provided to facilitate understanding of the Disclosure and are not intended to limit the Disclosure. The configurations that the embodiments may have are not limited to those exemplified and can be modified as appropriate. Furthermore, it is possible to partially substitute or combine configurations shown in different embodiments.

[0068] [Regarding the case of irradiating radio waves outdoors] In the above embodiment, the wireless communication device 4 was described as irradiating a wireless signal indoors, but it is not limited to this. The wireless communication device 4 may irradiate a wireless signal outdoors, and the information processing device 2 may perform various processes based on the reflected received signal strength in that case. In other words, to the extent that no technical inconsistency arises, "indoors" in this embodiment may be read as "outdoors".

[0069] [Regarding the learning of environmental information] In the above embodiment, the first learning model 7 was described as learning the relationship between reflected received signal strength and user attributes, and the second learning model 8 was described as learning the relationship between reflected received signal strength, user attributes and biometric information, but the embodiment is not limited to this. In one embodiment, at least one of the first learning model 7 and the second learning model 8 is configured to further learn environmental information regarding the indoor environment to which the wireless signal is irradiated. In one embodiment, the environmental information includes information regarding at least one of the indoor structure, furniture arrangement, temperature, humidity and wind speed.

[0070] In one example, the first learning model 7 learns the relationship between the reflected received signal strength and environmental information (training data) related to indoor environments for learning, and the user attributes (ground truth data) of the user to be studied. The information processing device 2 can estimate the user attributes of the user to be estimated by inputting the reflected received signal strength and environmental information related to indoor environments for estimation to the first learning model 7.

[0071] In another example, the second learning model 8 learns the relationship between the reflected signal intensity, user attributes, and environmental information (training data) related to indoor environments for learning, and the biometric information (ground truth data) related to the user to be studied. The information processing device 2 can estimate the biometric information of the user to be estimated by inputting the reflected signal intensity, user attributes, and environmental information related to indoor environments for estimation to the second learning model 8.

[0072] Environmental information includes various factors that affect the intensity of reflected received signals. Therefore, by incorporating environmental information into the learning model, it becomes possible to construct a learning model that takes various environmental factors into account.

[0073] [Regarding the learning environment and the estimation environment] In the above embodiment, the learning environment and the estimation environment may be the same or different. That is, in the above embodiment, the "indoor space for learning" may be the same space as the "indoor space for estimation" or it may be a different space. Also, in the above embodiment, the "user to be learned" may be the same person as the "user to be estimated" or it may be a different person.

[0074] When the learning environment and the estimation environment are different, the accuracy of biometric information estimation may decrease compared to when the learning and estimation environments are the same. Therefore, in one embodiment, the first learning model 7 may be configured by further learning the relationship between the reflected received signal intensity corresponding to the wireless signal irradiated indoors for estimation and the user attributes of the user to be estimated. Also, in one embodiment, the second learning model 8 may be configured by further learning the relationship between the reflected received signal intensity corresponding to the wireless signal irradiated indoors for estimation, the user attributes of the user to be estimated, and the biometric information of the user to be estimated. That is, the first learning model 7 and the second learning model 8 can perform learning in the learning environment and also perform additional learning in the estimation environment. With this configuration, it is possible to suppress the decrease in estimation accuracy caused by the difference between the learning environment and the estimation environment.

[0075] [Regarding the case of multiple users] In the above embodiment, an example of performing learning and estimation in a situation where there is typically one user has been described, but it is not limited to this. In one embodiment, the first learning model 7 is configured to learn the relationship between the reflected received signal intensity corresponding to the radio signal irradiated in the indoor learning area and the user attributes of each of the multiple users present in the indoor learning area. The second learning model 8 is configured to learn the relationship between the reflected received signal intensity corresponding to the radio signal irradiated in the indoor learning area, the user attributes of each of the multiple users present in the indoor learning area, and the biometric information of each of the multiple users. Further, other users to be estimated may be present in the indoor and / or outdoor estimation area. The first estimation unit 104 further estimates the user attributes of the other users to be estimated, and the second estimation unit 106 further estimates the biometric information of the other users to be estimated. That is, the information processing device 2 can perform learning in an environment where there are multiple users in the indoor learning area and estimate the biometric information of each of the multiple users when they are in the indoor estimation area. With this configuration, biometric information for each of the multiple users can be estimated.

[0076] <6. Supplementary Information> The wording in this embodiment may be understood as follows, to the extent that it does not cause any contradiction.

[0077] In this embodiment, "executing process B1 based on information A1" may mean executing process B1 based on at least a part of information A1, executing process B1 based on at least information A1, or executing process B1 probabilistically based on information A1. In other words, "executing process B1 based on information A1" is not limited to executing process B1 based solely on information A1.

[0078] In this embodiment, "executing process B2 based on process A2" can mean any of the following: executing process B2 after process A2 has been executed; executing process A2 and process B2 consecutively; executing process B2 based on the information output by process A2; executing process B2 on the condition that process A2 has been executed; or executing process B2 by means of process A2. "Executing process B2 by process A2" can be understood in the same way as "executing process B2 based on process A2".

[0079] In this embodiment, "information A3 includes information B3" means either that at least a part of information A3 is information B3, or that information B3 can be obtained based on information A3.

[0080] In this embodiment, "process A4 includes process B4" may mean either that at least a part of process A4 is process B4 (i.e., process B4 is executed in the process of obtaining the result of process A4), or that one aspect of process A4 is process B4.

[0081] <7. Example Configuration> This disclosure includes the following technologies.

[0082] [Note 1] An information processing device 2 that performs processing using the first learning model 7 and the second learning model 8, wherein the first learning model 7 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning and the user attributes of a learning target user present indoors and / or outdoors for learning, and the second learning model 8 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning, the user attributes of a learning target user and the biometric information of a learning target user, and the estimated indoor and Information processing device 2 comprises: an acquisition unit 102 that acquires the reflected received signal intensity corresponding to a wireless signal irradiated indoors / or outdoors; a first estimation unit 104 that estimates the user attributes of a target user by inputting the reflected received signal intensity corresponding to an estimated indoor and / or outdoor wireless signal into a first learning model 7; and a second estimation unit 106 that estimates the biometric information of a target user by inputting the reflected received signal intensity corresponding to an estimated indoor and / or outdoor wireless signal, and the user attributes of the target user estimated by the first estimation unit 104 into a second learning model 8.

[0083] [Note 2] The information processing device 2 according to Note 1, wherein at least one of the first learning model 7 and the second learning model 8 is configured to further learn environmental information relating to the indoor and / or outdoor environment to which the wireless signal is irradiated.

[0084] [Note 3] The information processing device 2 as described in Note 2, wherein the environmental information includes information relating to at least one of the indoor and / or outdoor structures, furniture arrangement, temperature, humidity, and wind speed.

[0085] [Note 4] The information processing device 2 according to any one of Notes 1 to 3, further comprising: an irradiation control unit 110 that controls a wireless communication device that emits a wireless signal indoors and / or outdoors for estimation purposes based on the biometric information of the estimated target user estimated by the second estimation unit 106.

[0086] [Note 5] The irradiation control unit 110 controls at least one of the output power and irradiation direction of the wireless signal from the wireless communication device, as described in Note 4, for the information processing device 2.

[0087] [Note 6] The user attributes of the user learned by the first learning model 7 and the second learning model 8 include at least one of the user's height, weight, exit time, body shape, and behavioral patterns, as described in any one of Notes 1 to 5, for the information processing device 2.

[0088] [Note 7] The biometric information of the user that the first learning model 7 and the second learning model 8 learn includes at least one of the user's heart rate, pulse rate, and respiratory rate, as described in the information processing device 2 described in any one of Notes 1 to 6.

[0089] [Note 8] The information processing device 2 according to any one of Notes 1 to 7, wherein the first learning model 7 is configured by further learning the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for estimation and the user attributes of the user to be estimated, and the second learning model 8 is configured by further learning the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for estimation, the user attributes of the user to be estimated, and the biometric information of the user to be estimated.

[0090] [Note 9] The information processing device 2 according to any one of Notes 1 to 8, wherein the first learning model 7 is configured to learn the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for learning and the user attributes of each of the multiple users present indoors and / or outdoors for learning, the second learning model 8 is configured to learn the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for learning, the user attributes of each of the multiple users present indoors and / or outdoors for learning and the biometric information of each of the multiple users, and there are further users to be estimated in the indoors and / or outdoors for estimation, the first estimation unit 104 further estimates the user attributes of the other users to be estimated, and the second estimation unit 106 further estimates the biometric information of the other users to be estimated.

[0091] [Note 10] A learning model comprising a first learning model 7 and a second learning model 8, wherein the first learning model 7 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning and the user attributes of a target user present indoors and / or outdoors for learning, and the second learning model 8 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning, the user attributes of a target user for learning, and the biometric information of a target user.

[0092] [Note 11] An information processing method in which a computer 70 performs processing using a first learning model 7 and a second learning model 8, wherein the first learning model 7 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning and the user attributes of a target user for learning that exists indoors and / or outdoors for learning, and the second learning model 8 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning, the user attributes of a target user for learning, and the biometric information of a target user for learning, and the computer 70 performs the following actions: acquire the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation where a target user for estimation exists, input the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation into the first learning model 7 to estimate the user attributes of a target user for estimation, and input the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation, and the estimated user attributes of a target user for estimation into the second learning model 8 to estimate the biometric information of a target user for estimation.

[0093] [Note 12] A program that causes a computer 70 to perform processing using a first learning model 7 and a second learning model 8, wherein the first learning model 7 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning purposes and the user attributes of a target user present indoors and / or outdoors for learning purposes, and the second learning model 8 is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning purposes, the user attributes of a target user for learning purposes, and the biometric information of a target user for learning purposes, and causes the computer 70 to perform the following: obtain the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation purposes where a target user for estimation is present, input the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation purposes into the first learning model 7 to estimate the user attributes of the target user for estimation, and input the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation purposes, and the estimated user attributes of the target user for estimation purposes into the second learning model 8 to estimate the biometric information of the target user for estimation.

[0094] 1...System, 2...Information processing device, 3...Terminal device, 4...Wireless communication device, 5...Biometric information measuring device, 7...First learning model, 8...Second learning model, 9...Target user database, 10...Control unit, 12...Storage unit, 70...Computer, 102...Acquisition unit, 104...First estimation unit, 106...Second estimation unit, 108...Output unit, 110...Irradiation control unit, 700...Processor

Claims

1. An information processing device that performs processing using a first learning model and a second learning model, wherein the first learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a wireless signal irradiated indoors and / or outdoors for learning and the user attributes of a target user present indoors and / or outdoors for learning, the second learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a wireless signal irradiated indoors and / or outdoors for learning, the user attributes of the target user for learning, and the biometric information of the target user, the device comprises: an acquisition unit that acquires the reflected received signal intensity corresponding to a wireless signal irradiated indoors and / or outdoors for estimation where a target user for estimation is present, a first estimation unit that estimates the user attributes of the target user for estimation by inputting the reflected received signal intensity corresponding to the wireless signal irradiated indoors and / or outdoors for estimation into the first learning model, and a second estimation unit that estimates the biometric information of the target user for estimation by inputting the reflected received signal intensity corresponding to the wireless signal irradiated indoors and / or outdoors for estimation and the user attributes of the target user for estimation estimated by the first estimation unit into the second learning model, An information processing device equipped with the following features.

2. The information processing apparatus according to claim 1, wherein at least one of the first learning model and the second learning model is configured to further learn environmental information relating to an indoor and / or outdoor environment to which a wireless signal is irradiated.

3. The information processing apparatus according to claim 2, wherein the environmental information includes information relating to at least one of the structure, furniture arrangement, temperature, humidity, and wind speed, indoors and / or outdoors.

4. The information processing apparatus according to claim 1, further comprising: an irradiation control unit that controls a wireless communication device that emits a wireless signal indoors and / or outdoors for estimation based on the biometric information of the estimated target user estimated by the second estimation unit.

5. The information processing apparatus according to claim 4, wherein the irradiation control unit controls at least one of the output power and irradiation direction of the wireless signal from the wireless communication device.

6. The information processing device according to claim 1, wherein the user attributes of the user learned by the first learning model and the second learning model include at least one of the user's height, weight, constitution, body shape, and behavioral patterns.

7. The information processing device according to claim 1, wherein the biometric information of the user learned by the first learning model and the second learning model includes at least one of the user's heart rate, pulse rate, and respiratory rate.

8. The information processing apparatus according to claim 1, wherein the first learning model is configured to further learn the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for estimation and the user attributes of the estimated target user, and the second learning model is configured to further learn the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for estimation, the user attributes of the estimated target user and the biometric information of the estimated target user.

9. The information processing apparatus according to claim 1, wherein the first learning model is configured by learning the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for learning and the user attributes of each of the multiple users present indoors and / or outdoors for learning; the second learning model is configured by learning the relationship between the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for learning, the user attributes of each of the multiple users present indoors and / or outdoors for learning and the biometric information of each of the multiple users; and there are further users to be estimated in the indoors and / or outdoors for estimation; the first estimation unit further estimates the user attributes of the other users to be estimated; and the second estimation unit further estimates the biometric information of the other users to be estimated.

10. A learning model comprising a first learning model and a second learning model, wherein the first learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning and the user attributes of a target user present indoors and / or outdoors for learning, and the second learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning, the user attributes of the target user for learning, and the biometric information of the target user.

11. An information processing method in which a computer performs processing using a first learning model and a second learning model, wherein the first learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning and the user attributes of a target user present indoors and / or outdoors for learning, the second learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for learning, the user attributes of the target user for learning, and the biometric information of the target user, the computer performs the following: acquire the reflected received signal intensity corresponding to a radio signal irradiated indoors and / or outdoors for estimation where a target user for estimation is present, input the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for estimation into the first learning model to estimate the user attributes of the target user for estimation, and input the reflected received signal intensity corresponding to the radio signal irradiated indoors and / or outdoors for estimation, and the estimated user attributes of the target user for estimation into the second learning model to estimate the biometric information of the target user for estimation.

12. A program that causes a computer to perform a process using a first learning model and a second learning model, wherein the first learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a wireless signal irradiated indoors and / or outdoors for learning purposes and the user attributes of a target user present indoors and / or outdoors for learning purposes, the second learning model is configured to learn the relationship between the reflected received signal intensity corresponding to a wireless signal irradiated indoors and / or outdoors for learning purposes, the user attributes of the target user for learning purposes, and the biometric information of the target user for learning purposes, and causes the computer to perform the following: acquire the reflected received signal intensity corresponding to a wireless signal irradiated indoors and / or outdoors for estimation purposes where a target user for estimation is present, input the reflected received signal intensity corresponding to the wireless signal irradiated indoors and / or outdoors for estimation purposes into the first learning model to estimate the user attributes of the target user for estimation, and input the reflected received signal intensity corresponding to the wireless signal irradiated indoors and / or outdoors for estimation purposes, and the estimated user attributes of the target user for estimation purposes into the second learning model to estimate the biometric information of the target user for estimation.

Images